JPH1077893A - Vehicle driving direction estimation device and vehicle driving force control device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a driving direction estimating device to estimate a driving direction precisely reflected by the drive will of a driver. SOLUTION: In a drive direction estimating means 100, based on a drive- associated variable, the drive directions DL of a vehicle are estimated, in order, and in a standard drive direction estimating means 102, based on a past drive direction DL estimated by an operation direction estimating means 100, a standard drive direction SDL for a vehicle to indicate the average drive direction or the standard drive direction of a given driver is estimated. By an output filter means 104, by applying filter processing on the drive direction DL based on a filter constant KDL2 being the function of the standard drive direction SDL, a driving direction FDL high-precisely reflected by the will of the driver is provided.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a driving direction estimating device for estimating a driving direction of a driver in a vehicle, and a driving force control device for controlling a driving force of the vehicle based on the estimated driving direction. It is.

[0002]

2. Description of the Related Art Generally, a shift control device for controlling a speed ratio or a gear of an automatic transmission based on an actual engine load and a vehicle speed from a preset shift diagram, and an actual accelerator pedal based on a preset relationship. 2. Description of the Related Art In a vehicle including a throttle valve opening control device that controls a throttle valve opening based on an operation amount, it is desired that the vehicle be driven with a driving force that reflects a driver's driving direction in order to enhance drivability.
In addition, vehicles equipped with control devices such as a steering force control device that controls the steering force of the vehicle power steering and a suspension control device that controls the damping force and spring characteristics of the shock absorber of the vehicle suspension device are also driven by the driving direction. Thus, it is desired that the steering force of the steering, the damping force of the shock absorber or the spring characteristics be switched.

On the other hand, for example, Japanese Patent Application Laid-Open No. 6-221
No. 420 discloses a neural network in which a driver learns in advance whether the driver is in an acceleration direction with an emphasis on power performance or in a fuel efficiency direction with a focus on fuel efficiency based on sensor signals detected by each sensor of the vehicle. A shift control technique has been proposed in which a determination is made by using an automatic transmission and the shift diagram of the automatic transmission is switched. Further, for example, Japanese Patent Laid-Open No. 3-20
Japanese Patent No. 4468 discloses a technique for determining a control pattern of a continuously variable transmission based on a change rate of a value corresponding to a driver's will and an average value of the change rate, and a value corresponding to a driver's will. A technique for performing fuzzy inference based on a difference between a maximum throttle valve opening change rate and an average throttle opening change rate and a throttle valve opening degree has been proposed. Further, for example,
Japanese Patent Application Laid-Open No. 7-167272 discloses that in order to enhance the response of estimation, a larger value of an engine load and a tire load is obtained, and the larger value is determined according to the degree of acceleration / deceleration of the accelerator operation and the increase / decrease of the acceleration directivity. There has been proposed a method of estimating the driver's acceleration direction through a filter that changes the filter constant.

[0004]

However, the above-mentioned prior art does not consider the tendency of change between the past driving orientation and the current driving orientation, and does not consider the driving orientation of the driver in various driving situations and road environments. It was hard to say with high precision.
That is, since the above-described conventional technique estimates the current driving orientation, the actual driver's operation may be the same even if the driving orientation is different depending on the driving situation or the road environment. In such a situation, erroneous estimation can be sufficiently suppressed only by changing the filter variable by changing the degree of acceleration / deceleration of the accelerator operation and increasing / decreasing the acceleration directivity. There was no.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a vehicle driving direction estimating apparatus for estimating a driving direction reflecting a driver's driving intention with high accuracy, and It is an object of the present invention to provide a driving force control device for a vehicle that controls a driving force by reflecting a driving intention of a driver with high accuracy.

[0006]

The present inventors have conducted various studies in an attempt to solve the above-mentioned problems, and as a result, have found that the driving orientation estimated based on the driving operation-related variables that are sequentially calculated or the driving orientation estimated therefrom. By modifying the driving operation-related variables used for estimation based on past driving directions, it was found that the driving directions of the driver can be accurately reflected in various driving situations and road environments. The present invention has been made based on such findings.

That is, the gist of the first invention is a driving direction estimating device for estimating the driving direction of a vehicle, and (a) determining the driving direction of the vehicle based on variables related to the driving operation of the vehicle. Driving direction estimating means for successively estimating, (b) standard driving direction estimating means for estimating a standard driving direction of the vehicle based on past driving directions estimated by the driving direction estimating means, and (c) Output filter means for filtering the driving direction estimated by the driving direction estimating means based on a filter constant which is a function of the standard driving direction estimating means estimated by the standard driving direction estimating means.

[0008]

According to the first aspect of the present invention, the driving direction estimating means sequentially estimates the driving direction of the vehicle based on the driving operation related variables.
Based on the past driving directions estimated by the driving direction estimating means, the standard driving direction of the vehicle indicating the average driving direction or the standard driving direction of the predetermined driver is estimated. Then, based on the filter constant, which is a function of the standard driving direction estimated by the standard driving direction estimating means, the output filter means performs a filtering process on the driving direction estimated by the driving direction estimating means. Thereby, the driving direction estimated by the driving direction estimating means is filtered by the output filter means having a filter constant reflecting the standard driving direction of the vehicle, so that the driving intention of the driver is increased after the filtering processing. It is possible to obtain a driving orientation reflected in the accuracy.

[0009]

According to a second aspect of the present invention, there is provided a driving orientation estimating apparatus for estimating a driving orientation of a vehicle, comprising: Driving direction estimating means for sequentially estimating the driving direction of the vehicle based on the first driving operation-related variable generated in advance and the second driving operation-related variable periodically generated every predetermined period; (b) Standard driving direction estimating means for estimating a standard driving direction of the vehicle based on past driving directions estimated by the driving direction estimating means; and (c) standard driving direction estimated by the standard driving direction estimating means. Input filter means for performing a filtering process on the second driving operation related variable input to the driving direction estimating means based on a filter constant which is a function of directivity.

[0010]

According to this configuration, the driving direction estimating means allows the driving direction estimating means to generate the first driving signal generated in association with the driving operation of the vehicle.
Based on the driving operation-related variable and the second driving operation-related variable that is periodically generated every predetermined period, the driving direction of the vehicle is sequentially estimated. Based on the estimated past driving orientation, the standard driving orientation of the vehicle indicating the average driving orientation or the standard driving orientation of the predetermined driver is estimated. Then, based on the filter constant which is a function of the standard driving direction estimated by the standard driving direction estimating means, the input filter means performs filtering on the second driving operation related variable input to the driving direction estimating means. Will be applied. Accordingly, the driving direction estimated by the driving direction estimating unit is estimated based on the second driving operation related variable filtered by the input filter unit having the filter constant reflecting the standard driving direction of the vehicle. It is possible to obtain a driving orientation that reflects the driver's driving intention with high accuracy.

[0011]

A third aspect of the present invention is a driving force control device for a vehicle for controlling a driving force based on an estimated value of a driving direction of the vehicle,
(a) driving direction estimating means for sequentially estimating the driving direction of the vehicle based on the driving operation related variables of the vehicle, and (b) based on past driving directions estimated by the driving direction estimating means,
Standard driving direction estimating means for estimating the standard driving direction of the vehicle, (c) based on the driving direction estimated by the driving direction estimating means and the standard driving direction estimated by the standard driving direction estimating means. Driving force selecting means for selecting the actual driving force of the vehicle.

[0012]

According to the third aspect of the invention, based on the driving orientation estimated by the driving orientation estimating means and the standard driving orientation estimated by the standard driving orientation estimating means, the actual driving force of the vehicle is determined by the driving force selecting means. Is selected, the erroneous estimation of the driving orientation is prevented, and a driving force that reflects the driver's driving intention with high accuracy is obtained.

[0013]

In another aspect of the present invention, preferably, the output filter means detects a portion of the value indicating the driving direction which is successively estimated by the driving direction estimating portion and which is changed to the fuel consumption direction side. A filter process is performed on the driving direction estimated by the driving direction estimating means. With this configuration, when the driving direction changes to the acceleration direction side, for example, when the accelerator pedal is suddenly depressed and a driving force is required, no filtering process is performed. Can be rapidly changed to the acceleration-oriented side, and the responsiveness is enhanced.On the contrary, when the driving orientation changes to the fuel-efficiency-oriented side, there is a possibility that unavoidable erroneous estimation may be necessary depending on the driving situation or road environment. In addition, there is an advantage that the response of the driving orientation estimation is reduced by the filtering process.

Preferably, the output filter means increases the filter constant when the standard operation direction is the acceleration direction as compared with the case where the standard operation direction is the fuel efficiency direction, thereby enhancing the filtering effect. . This allows
Even if the driving direction changes to the fuel consumption direction side, if the standard driving direction having a high driving direction component before that is a value on the acceleration direction side, the filter constant is increased and the response of the driving direction estimation by filtering is increased. Is reduced, erroneous estimation of driving orientation is reduced. Conversely, even if the driving orientation changes to the acceleration orientation side, if the standard operation orientation having a high component of the previous driving orientation is a value on the fuel economy orientation side, the filter constant is reduced and the driving orientation is reduced by filtering. By increasing the response of the estimation of the driving direction, it is possible to estimate the driving orientation close to the intention of the actual driver.

Preferably, the vehicle further includes a driving force selection unit for selecting an actual driving force of the vehicle based on the driving direction estimated by the driving direction estimation unit and filtered by the output filter unit. . With this configuration, the driving force selection unit selects a shift diagram as a basis for a shift determination or a relationship as a basis for controlling the throttle valve opening based on the filtered driving direction, Since the driving force of the vehicle is switched,
Sufficient acceleration or fuel efficiency that matches the driver's will is obtained.

Preferably, the input filter means is input to the driving direction estimating means when the value indicating the driving direction successively estimated by the driving direction estimating means has changed to the fuel consumption directing side. The second driving operation related variable is subjected to a filtering process. With this configuration, when the driving direction changes to the acceleration direction side, for example, when the accelerator pedal is suddenly depressed and the driving force is required, the filtering process is not performed on the second driving operation related variable. Therefore, the value indicating the driving direction can be rapidly changed to the acceleration direction side, and the response is improved.On the contrary, when the driving direction changes to the fuel efficiency side, erroneous estimation is unavoidable due to driving conditions and road environment. Therefore, there is an advantage that the responsiveness of the driving-oriented estimation is reduced by the filtering process.

[0017] Preferably, the input filter means increases the filter constant when the standard driving direction is the acceleration direction as compared with the case where the standard driving direction is the fuel consumption direction, thereby enhancing the filtering effect. . This allows
Even if the driving direction changes to the fuel consumption direction side, if the standard driving direction having a high driving direction component before that is a value on the acceleration direction side, the filter constant is increased and the response of the driving direction estimation by filtering is increased. Is reduced, erroneous estimation of driving orientation is reduced. Conversely, even if the driving orientation changes to the acceleration orientation side, if the standard operation orientation having a high component of the previous driving orientation is a value on the fuel economy orientation side, the filter constant is reduced and the driving orientation is reduced by filtering. By increasing the response of the estimation of the driving direction, it is possible to estimate the driving orientation close to the intention of the actual driver.

Preferably, the actual driving force of the vehicle is selected by the driving direction estimating means based on the driving direction estimated based on the second driving operation related variable filtered by the input filter means. Driving force selection means is further included. With this configuration, the driving force estimated by the driving force selecting means on the basis of the filtered second driving operation-related variable controls the shift diagram or the throttle valve opening that serves as the basis for the shift determination. Is selected, the driving force of the vehicle is switched, so that acceleration or fuel efficiency suitable for the driving direction of the driver can be obtained.

Preferably, the driving force selecting means includes:
Based on the standard driving direction estimated by the standard driving direction estimating unit, a criterion value determining unit for determining a criterion value for selecting a driving force, the driving direction estimated by the driving direction estimating unit, and the like. A comparison determination unit that selects a driving force by switching a shift diagram used in the shift control unit by comparing with a determination reference value. In this way, the shift diagram is switched using the criterion value determined based on the standard driving orientation, so that acceleration or fuel efficiency suitable for the driver's driving orientation can be obtained.

Preferably, the standard driving direction estimating means performs a smoothing process or a weighted average value process in a predetermined moving section on the value indicating the driving direction sequentially estimated by the driving direction estimating means. Thus, the standard driving direction is estimated.

Preferably, the vehicle includes automatic shift control means for outputting a shift based on an engine load and a vehicle speed from a shift diagram set in advance, and the driving force selecting means includes an automatic shift control unit. A shift diagram used for shifting control of the means is selected from a plurality of types of shift diagrams stored in advance. Alternatively, the vehicle includes throttle valve opening control means for controlling a throttle valve opening based on an actual accelerator pedal operation amount from a preset relationship, and the driving force selecting means includes a throttle valve opening control. One of the relationships used for the throttle valve opening control of the means is selected from a plurality of types of relationships stored in advance.

Preferably, the driving direction estimating means includes a neural network to which the driving operation related variables are input, and estimates the driving direction based on the output of the neural network.

Preferably, the vehicle control apparatus further includes driving operation related variable calculating means for calculating the first driving operation related variable and the second driving operation related variable, and the driving operation related variable calculating means includes the first driving operation related variable. As the related variables, the output manipulated variable at the time of starting the vehicle, the maximum change rate of the output manipulated variable, the maximum deceleration at the time of the braking operation of the vehicle, the coasting travel time of the vehicle, and the vehicle speed constant travel time are calculated, and any one of them is calculated. Is calculated, the input value is input to the neural network, and the input signal section maximum value and the maximum vehicle speed are calculated at predetermined intervals as the second driving operation related variables, and each time any one of them is calculated. , To the neural network.

Preferably, in the driving direction estimating device for a vehicle, the driving direction estimating means includes an output operation amount at the time of starting the vehicle, a maximum change rate of the output operation amount, Each time one of the maximum deceleration at the time of the braking operation, the coasting travel time of the vehicle, and the constant vehicle speed travel time is calculated, the driving direction of the vehicle is estimated based on the output of the neural network. In this way, every time a driving operation-related variable is calculated, a driving orientation estimation result is obtained, so that there is an advantage that the responsiveness of the driving orientation estimation is improved.

Preferably, the driving operation related variable calculating means is provided with an input signal variance value calculating means for calculating a value indicating a variance of the input signal within a predetermined section, and the input signal variance value calculating means is provided. The value indicating the variance of the input signal in the predetermined section calculated by the above is input to the driving direction estimating means. With this configuration, when the engine speed or the vehicle speed increases during highway driving, the variance tends to be small in fuel economy orientation, so that it is preferably prevented from being estimated as acceleration orientation.

[0026]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below in detail with reference to the drawings.

FIG. 1 shows an automatic transmission and a shift control device of a vehicle. In FIG. 1, power output from an engine 10 of a vehicle is transmitted to drive wheels (not shown) via a torque converter 12, an automatic transmission 14, a differential gear device and an axle (not shown).

The torque converter 12 includes a pump wheel 18 connected to a crankshaft 16 and a pump wheel 18 connected to an input shaft 20 of the automatic transmission 14 and through a fluid.
Impeller, to which power is transmitted from, a fixed impeller 28 fixed to a position-fixed housing 26 via a one-way clutch 24, and a pump impeller 18 and a turbine impeller 22 directly connected via a damper 30. And a lock-up clutch 32. This lock-up clutch 32
Is controlled by the pressure difference between the release-side oil chamber 33 and the engagement-side oil chamber 35.

The automatic transmission 14 is, for example, a forward four-speed
Alternatively, a planetary gear type multi-stage transmission in which a fifth gear is achieved
Machine. The automatic transmission 14 in the case of the fourth forward speed is
Three sets of single pinion type planetary gear units arranged on a shaft
, 34, 36, 38, the input shaft 20,
Output gear 39 that rotates with the ring gear of
A counter shaft (output) that transmits power to and from the differential gear unit
(Force axis) 40. These planetary gear units 34,
Some of the components 36 and 38 are integrally connected to each other.
As well as three clutches C₀ , C₁ , C_Two By
Are selectively connected to each other. The above planetary gear
Some of the components of the devices 34, 36, 38
B₀ , B₁ , B_Two , B_Three To the housing 26
Selectively linked, plus some of the components
Means three one-way clutches F₀ , F ₁ , F_Two By that
Engaged with each other or with housing 26 depending on the direction of rotation
Is to be made.

The clutches C ₀ , C ₁ , C ₂ and the brakes B ₀ , B ₁ , B ₂ , B ₃ include, for example, a multi-plate clutch or one band or two bands whose winding directions are opposite to each other. It is constituted by a band brake or the like, and each is operated by a hydraulic actuator (not shown). The operation of each of the hydraulic actuators is controlled by a hydraulic control circuit 44 that operates according to a command from an electronic control unit 42, which will be described later, so that the gear ratio γ (= the input shaft 20) as shown in FIG. Thus, four forward speed stages and one reverse speed stage having different rotation speeds / rotation speeds of the counter shaft 40 are obtained. In FIG. 2, "1st",
“2nd”, “3rd”, and “O / D (overdrive)” represent the first gear, second gear, third gear, and fourth gear on the forward side, respectively. The gear ratio gradually decreases from the first gear to the fourth gear. In addition, since the torque converter 12 and the automatic transmission 14 are configured symmetrically with respect to the axis, the lower side of the rotation axis of the input shaft 20 and the upper side of the rotation axis of the counter shaft 40 in FIG. It is abbreviated.

The hydraulic control circuit 44 includes the automatic transmission 1
A shift control hydraulic control circuit for controlling the fourth gear and an engagement control hydraulic control circuit for controlling the engagement of the lock-up clutch 32 are provided. The shift control hydraulic control circuit consists of solenoid No. 1 and solenoid N
First solenoid valve 4 that is driven on and off by o.2
6 and a second solenoid valve 48, the clutch and the brake are selectively operated as shown in FIG. 1 by a combination of the operations of the first solenoid valve 46 and the second solenoid valve 48, and One of the gears to the fourth gear is established.

Further, the engagement control hydraulic control circuit is provided with a clutch switching valve (not shown) for switching between a release side position where the lock-up clutch 32 is released and an engagement side position where the lock-up clutch 32 is engaged. A third solenoid valve 50 for generating a switching signal pressure for turning on and off the valve and adjusting the pressure difference ΔP between the engagement side oil chamber 35 and the release side oil chamber 33 to control the slip amount of the lock-up clutch 32 (not shown). A linear solenoid valve 54 for generating a slip control signal pressure for operating the slip control valve in accordance with a drive current from the electronic control unit 42.

The electronic control unit 42 includes a CPU 60, R
The microcomputer is a so-called microcomputer including an AM 62, a ROM 64, an input / output interface (not shown), and includes a throttle sensor 7 for detecting an opening degree TA of a throttle valve 68 provided in an intake pipe 66 of the engine 10.
0, an engine rotation speed sensor 72 for detecting the rotation speed of the engine 10, an input shaft rotation speed sensor 74 for detecting the rotation speed of the input shaft 20 of the automatic transmission 14, and a counter of the automatic transmission 14 for detecting the vehicle speed V. A vehicle speed sensor 76 that detects the rotation speed of the shaft 40, an operation position of the shift lever 78, that is, an operation position sensor 80 that detects one of the L, S, D, N, R, and P ranges, and an operation of the brake pedal 82 are detected. A signal indicating the throttle valve opening TA, a signal indicating the engine rotation speed _NE , a signal indicating the input shaft rotation speed N _IN , a signal indicating the rotation speed N _OUT of the output shaft (counter shaft 40), Shift lever 7
Signal representing the operating position P _S 8, the signal S _BK representing the operation of the brake pedal 82 is adapted to be supplied. The throttle valve 68 is controlled by the throttle actuator 86 based on the operation amount Acc of the accelerator pedal 58 corresponding to the output operation member by the electronic control device 42 from the relationship shown in FIG. 24, for example. .

The CPU 60 in the electronic control unit 42
The input signal is processed in accordance with the program stored in the OM 64 to execute, for example, driving orientation estimation control, shift control, lock-up clutch control, throttle opening control, and the like. Therefore, in the present embodiment, the electronic control unit 42 functions as a driving orientation estimating device and a shift control device.

In the driving direction estimation control of the electronic control unit 42, predetermined driving operation related variables are calculated from an input signal,
The driving direction is estimated based on the output of the neural network NN to which the driving operation related variables are input. Further, in the shift control and the lock-up clutch control of the electronic control unit 42, a plurality of types of shift diagrams previously stored in the ROM 64, that is, an acceleration-oriented shift diagram of FIG. 3, and an intermediate-oriented (normal) shift line of FIG. A shift diagram corresponding to the driving orientation is selected from the fuel efficiency oriented shift diagram of FIG. 5 and FIG. 5, and from the selected shift diagram, a predetermined gear position is determined based on the actual vehicle speed V and the throttle valve opening TA. Or the lock-up on / off determination is made. For example, when a point indicating the actual vehicle speed V and the throttle valve opening TA in the normal shift diagram of FIG. 4 intersects with the upshift line or the downshift line, an upshift determination or a downshift determination is performed. Then, the first solenoid valve 46 and the second solenoid valve 48 shown in FIG. 1 are driven so as to establish the gear position for which the shift determination has been performed, or the third solenoid valve 46 is controlled for engagement of the lock-up clutch 32. The solenoid valve 50 and the linear solenoid valve 54 are driven.

In FIGS. 3, 4 and 5, a solid line indicates an upshift line, a broken line indicates a downshift line,
An alternate long and short dash line indicates an engagement line of the lock-up clutch, and an alternate long and short dash line indicates an open line of the lock-up clutch. In the acceleration-oriented shift diagram of FIG. 3, the shift line is set such that the shift is executed at a higher vehicle speed (high engine rotation speed) than in FIG. Further, in the fuel consumption-oriented shift diagram of FIG. 5, the shift line is set such that the shift is executed at a lower engine rotation speed as compared with FIG.

FIG. 6 is a functional block diagram for explaining the control function of the electronic control unit 42. In the figure, the (electronic) throttle control means 88 controls the throttle valve opening TA by driving the throttle actuator 86 based on the actual accelerator pedal operation amount Acc based on the relationship shown in FIG. The speed change control means 90 includes a ROM 64
From the shift diagram selected by the driving force selecting means 92 from a plurality of types of shift diagrams stored in advance, the vehicle speed sensor 76
Is determined based on the actual vehicle speed V detected by the ECU and the actual throttle valve opening TA detected by the throttle sensor 70, and the gear determined by the shift determination is achieved. Solenoid valve 4 for
The automatic transmission 1 performs a shift output for 6, 48, and 50.
The fourth gear is switched and controlled.

The driving force selecting means 92 calculates the driving direction value DL or the value DL indicating the driving direction estimated by the driving direction estimating section 94 from a plurality of types of shift diagrams shown in FIGS. 3, 4 and 5 stored in the ROM 64 in advance. A shift diagram is selected based on the FDL. For example, in the driving force selecting means 92, for example, FIG.
When the value DL or FDL, which is indicated by a solid line of 0 and indicates the driving direction output from the driving direction estimating unit 94, exceeds a preset acceleration direction determination reference value PSL, the acceleration-directional shift line of FIG. Although the figure is selected, if the fuel efficiency is lower than the fuel efficiency direction determination reference value ESL, the fuel efficiency direction shift diagram in FIG. 5 is selected, and the speed change diagram between the acceleration direction determination reference value PSL and the fuel efficiency direction determination reference value ESL is obtained. In some cases, the intermediately-oriented shift diagram of FIG. 4 having an intermediate characteristic between the acceleration-oriented shift diagram and the fuel consumption-oriented shift diagram is selected.

The driving orientation estimating section 94 includes a neural network NN for inputting the driving operation-related variable and starting an estimation operation each time one of a plurality of types of driving operation-related variables is calculated, and the neural network NN.
The driving direction of the vehicle is estimated based on the output of the vehicle, and a value DL or FDL indicating the driving direction is output. The value DL or FDL indicating the driving direction is, for example, a continuous value from “0” to “1”.

For example, as shown in FIG. 7, the driving direction estimating section 94 includes the sensors 70, 72, 74, 76,
A signal reading means 96 for reading a detection signal from the sensor 84 or the like at a relatively short predetermined cycle, and a plurality of types of driving closely related to driving operation reflecting driving direction from signals sequentially read by the signal reading means 96. Operation-related variables, that is, the amount of output operation when the vehicle starts (accelerator pedal operation amount)
That is, the throttle valve opening TA _ST when the vehicle _starts , the maximum change rate of the output manipulated variable during acceleration operation, that is, the maximum change rate A _CCMAX of the throttle valve opening, the maximum deceleration G _NMAX during the braking operation of the vehicle, and the coasting of the vehicle. Driving operation-related variable calculating means for calculating a running time T _COAST , a constant vehicle speed running time T _VCONST , a section maximum value of a signal input from each sensor in a predetermined section, a maximum vehicle speed V _max after the start of driving, etc. Means 98 and a neural network NN for permitting the driving operation-related variable every time the driving operation-related variable is calculated by the preprocessing means 98 and performing a driving orientation estimation calculation.
A driving direction estimating means 100 for outputting a driving direction estimation value which is an output of N, and a standard driving direction estimating a standard driving direction SDL of the vehicle based on past driving directions estimated by the driving direction estimating means 100. Based on the estimating means 102 and the filter constant K _DL2 which is a function of the standard driving direction estimated by the standard driving direction estimating means 102,
Driving direction DL estimated by driving direction estimating means 100
And an output filter means 104 for performing a filtering process on the output signal NN _OUT to supply a value DL or FDL indicating the driving direction based on the output signal NN _OUT of the neural network NN to the driving force selecting means 92, and to provide the driving force selection means 92 with the driving force. To other control devices that need to change the control in relation to

As the other control device, for example, a steering force control device for controlling the steering force of the power steering of the vehicle based on the driving direction estimated by the driving direction estimating unit 94, The suspension control device controls the damping force or the spring characteristic of the shock absorber of the vehicle suspension device based on the estimated driving direction DL or FDL. The driving direction estimating means 100 includes a throttle valve opening TA _ST at the time of vehicle start, a maximum rate of change A _{CC MAX} of the throttle valve opening at the time of acceleration operation, a maximum deceleration G _NMAX at the time of braking operation of the vehicle, coasting of the vehicle. Since the driving direction of the vehicle is estimated based on the output of the neural network calculated each time the driving time T _COAST and the constant vehicle speed driving time T _VCONST are input, the driving direction can be estimated more accurately. Without having to estimate
The responsiveness of the driving orientation result to the driver's operation is sufficiently obtained.

The pre-processing means 98 shown in FIG.
Output manipulated variable, that is, the throttle valve opening when the vehicle starts
TA_STStart output manipulated variable calculating means 98a for calculating
The maximum rate of change of the output manipulated variable during high-speed operation,
Maximum change rate A of the throttle valve opening _CCMAXAcceleration operation to calculate
Hour output manipulated variable maximum change rate calculating means 98b, vehicle braking operation
Maximum deceleration G during operation_NMAXCalculation of maximum deceleration during braking
Output means 98c, coasting travel time T of the vehicle_COASTCalculate
Coasting traveling time calculating means 98d, constant vehicle traveling time T
_VCONSTThe vehicle speed constant traveling time calculating means 98e for calculating
For example, input from each sensor within a predetermined section of about 3 seconds
Force signal (throttle valve opening TA, vehicle speed V, engine rotation
Speed N_E, The maximum value of the longitudinal acceleration NOGBW) periodically
Input signal section maximum value calculating means 98f to calculate the
Maximum vehicle speed V since the beginning_maxFor about 3 seconds
Maximum vehicle speed calculating means 9 for periodically calculating in a fixed section
8 g each.

The input signal section maximum value calculating means 98f
Value of the input signal in the predetermined section calculated in
Is the throttle valve opening TA_maxt, Vehicle speed V_maxt, D
Engine rotation speed N_Emaxt, Longitudinal acceleration NOGBW_maxt (Decrease
Negative value for speed) or deceleration G_NMAXt(Absolute value)
Used. NOGBW longitudinal acceleration_maxt Or deceleration G
_NMAXtIs, for example, the vehicle speed V (N_OUT) From the rate of change
Can be

The driving orientation estimating means 100 shown in FIG.
Throttle valve opening TA at start of vehicle _STDuring acceleration operation
Change rate A of throttle valve opening_CCMAX, Vehicle control
Maximum deceleration G during dynamic operation_NMAX, The coasting time T of the vehicle
_COAST, Constant vehicle speed T_{VC ONST}Driving operation
A first driving operation-related variable generated in succession;
The maximum value of the input signals from the sensor
Maximum vehicle speed V_maxThe second which is generated periodically
Driving operation related variables are input. Driving direction estimation means 1
00 uses the neural network NN to
From the first driving operation related variable and the second driving operation related signal.
Based on them per input, eg at least every 3 seconds
The value indicating the degree of driving orientation, that is, the driving orientation DL
Output.

The news provided in the driving orientation estimating means 100
Neural network NN is a computer program
By software or from the coupling of electronic components
Modeling of neural cells in living organisms
For example, the driving-oriented
Is configured as exemplified in the block of the
You. In FIG. 7, the neural network NN is represented by r
Individual neuron elements (neurons) X_i(X₁ ~ X_r) Or
Input layer composed of s neuron elements Y _j(Y₁ 
~ Y_s) And t neuronal elements
Z_k(Z₁ ~ Z _t) Composed of the output layer and
It has a three-layer structure. And from the above input layer
To transmit the state of neuron elements toward the output layer
The coupling coefficient (weight) W_XijAnd the r neural networks
Cell element X_iAnd s neuron elements Y _jAnd join each
Transmission element D_XijAnd the coupling coefficient (weight) W_YjkHas
S neuron elements Y_jAnd t neuron elements Z_kWhen
Transfer elements D that couple_YjkIs provided.

[0046] The neural network NN is its coupling coefficient (weight) W _Xij, pattern associative system that is made to learn the coupling coefficient (weight) W _Yjk called backpropagation learning algorithm. Since the learning has been completed in advance by a driving experiment in which the values of the driving operation-related variables and driving directions are made to correspond to each other, at the time of vehicle assembly, the coupling coefficient (weight) W _Xij and the coupling coefficient (weight) are set.
W _Yjk is given a fixed value. In the learning described above, fuel-efficient, acceleration-oriented, and intermediate (normal) -oriented driving of a plurality of drivers is performed on various roads such as highways, suburban roads, mountain roads, and city roads. Then, the driving direction at that time is used as a teacher signal, and n indicators (input signals) obtained by preprocessing the teacher signal and the sensor signal are input to the neural network NN. The teacher signal is converted into a numerical value for the driving direction to a value from 0 to 1, for example, 0 for fuel consumption direction, 0.5 for intermediate direction, and 1 for acceleration direction. The input signal is used after being normalized to a value between -1 and +1 or between 0 and 1.

The standard driving direction estimating means 102 calculates a value indicating the degree of the standard driving direction of the vehicle based on the past driving directions among the values DL indicating the driving directions successively estimated by the driving direction estimating means 100. That is, the standard driving direction S
DL is estimated. That is, the driving direction estimating means 1
00 to a value DL _n representing the driving orientation which is successively estimated,
By performing the smoothing process or the weighted average value process in a predetermined moving section, the standard driving direction SDL having a component indicating the average driving direction or the standard driving direction of the driver from the start of driving is estimated. Is done. Equation 1 is
An example of the smoothing process is shown. In Equation 1,
n is an integer indicating the sampling number, and K _DL1 is a _smoothing filter constant indicating the characteristics of the _smoothing process, and is set to, for example, about “10”. As the filter constant increases, the past components in the standard operation-oriented SDL increase.

[0048]

SDL _{n + 1} = [DL _{n + 1} + K _DL1 · SDL _n ]
/ (1 + K _DL1 )

The output filter means 104 calculates a filter constant K _DL2 based from Equation 2 above normal operation directed SDL, using a filter processing equation Equation 3 with the filter constant K _DL2, driver's intention estimating means Filter processing is performed on a part of the driving direction DL output from 100 that is decreasing, that is, a part that changes to the fuel consumption direction side. That is, the output filter means 104 outputs the standard driving direction S estimated by the standard driving direction estimating means 102.
Based on the filter constant K _DL2, which is a function of the DL, that is, the filter characteristic, filter processing such as delay processing or smoothing processing is performed on the driving-oriented DL. In Equation 2, CK _DL is a reference filter constant, and K _SDLO is, for example, a constant of about “6”. Further, in Expression 3, n is an integer indicating a sampling number, and FDL is a value indicating the driving direction after filtering.

[0050]

[ _Equation 2] K _DL2 = CK _DL + K _SDLO · SDL

[0051]

## EQU3 ## FDL _{n + 1} = [DL _{n + 1} + K _DL2 · FDL _n ]
/ (1 + K _DL2 )

FIGS. 8 and 9 are flow charts for explaining a main part of the control operation of the electronic control unit 42, that is, a driving direction estimation operation and a driving force selection operation. In step SM1 in FIG. 8 (hereinafter, step is omitted), the initial processing is executed to clear various storage areas or registers provided in the RAM 62, counters and timers for counting or timing, and the like. together with the contents of the estimation permission flag X _NNCAL the contents of cleared and stop flag X _STOP to "0" is set to "1". Next, SM2 corresponding to the signal reading means 96
Then, an input signal from each sensor is read.

Next, in SM3 corresponding to the pre-processing means (driving operation related variable calculating means) 98, the occurrence timing and the amount of events related to each driving operation, that is, the driving operation related variables are calculated. That is, the throttle valve opening TA _ST when the vehicle starts, the maximum change rate A _CCMAX of the throttle valve opening after the start of operation, the maximum deceleration G _NMAX during the braking operation of the vehicle, the coasting time T _{COAST of} the vehicle, and the constant vehicle speed. The travel time T _VCONST , a section maximum value of input signals from each sensor in a predetermined section, for example, a throttle opening degree TA _maxt , a vehicle speed V _maxt , an engine rotation speed N _Emaxt ,
A plurality of types of driving operation related variables such as longitudinal acceleration NOGBW (G _NMAXt ) are calculated based on input signals from each sensor. When the P and R ranges are selected by the shift lever 78, the driving orientation is not estimated.

Next, in SM4, it is determined whether or not the content of the estimation permission flag _XNNCAL is set to "1". _If the content of the estimation permission flag X _NNCAL is not set to “1”, the determination of SM4 is denied, and the above SM 2 and _subsequent steps are repeated, but the content of the estimation permission flag X _NNCAL is set to “1”. If it is set, the determination of SM4 is affirmed, and the driving orientation estimating calculation is executed in SM5 corresponding to the driving orientation estimating means 100. The estimation permission flag X _NNCAL is set for each calculation of the driving operation related variable or for the coasting travel time T.
During measurement of _COAST , measurement of constant vehicle speed T _VCONST ,
Alternatively, when the maximum deceleration G _NMAX during braking is being measured, its content is set to “1” at every predetermined time of about 3 seconds, and the SM4 is set every time the estimation permission flag X _NNCAL is set. The operation orientation estimation calculation of SM5 is permitted.

In the above SM5, the driving direction estimating means 1
As described at 00, the throttle valve opening TA _ST when the vehicle starts, the maximum change rate A _CCMAX of the throttle valve opening after the start of operation, the maximum deceleration G _NMAX during the braking operation of the vehicle, the coasting time of the vehicle T _COAST , constant vehicle speed T _VCONST , the maximum value of the input signal from each sensor in a predetermined interval, that is, the throttle opening T
A neural network NN to which a plurality of types of driving operation related variables such as A _maxt , vehicle speed V _maxt , engine speed N _Emaxt , longitudinal acceleration NOGBW _maxt (G _NMAXt ) is input is used, and based on an output signal of the neural network NN. Thus, a value DL indicating the driving direction is output. The value DL indicating the driving orientation sequentially indicates fuel economy orientation, intermediate orientation, and acceleration orientation as the value increases.

Next, the standard driving direction calculating means 102
In SM6 corresponding to the above, the smoothing process shown in Expression 1 is performed on the value DL _n representing the driving orientation successively estimated in SM5, so that the average driving orientation of the driver from the start of driving or the standard A standard driving direction SDL having a component indicating a typical driving direction is estimated. In SM7 corresponding to the output filter means 104, the filter constant K _DL2
Is calculated, and a filtering process is performed on a part of the driving direction DL calculated in the above SM5 that has a tendency to decrease, using the filtering processing formula of Expression 3 including the filter constant K _DL2 , The driving direction FDL after the filtering process is output.

After the driving direction FDL after the filtering process is estimated as described above, the content of the estimation permission flag _XNNCAL is cleared to "0" in SM8, and thereafter, the above SM2 and subsequent steps are repeatedly executed. You.

FIG. 9 shows a shift diagram switching routine corresponding to the driving force selecting means 92. In FIG.
In SH1, the driving direction FDL output from the output filter means 104 is set to a predetermined acceleration direction determination reference value PS.
It is determined whether or not L is greater than or equal to L. If the determination of SH1 is affirmed, the acceleration-directed shift diagram shown in FIG. 3, for example, is selected in SH2, but if the determination is denied, the drive-directed FDL output from the output filter means 104 is output in SH3. Is determined to be greater than or equal to a preset fuel efficiency direction determination reference value ESL. This SH3
If the determination is affirmative, then in SH4, for example, the middle-directional shift diagram of FIG. 4 is selected, but if the determination is negative, in SH5, for example, the fuel-efficient shift diagram of FIG. 5 is selected. . As a result, the driving force of the running vehicle is increased as the shift diagram becomes more acceleration-oriented, so that the driving force of the vehicle is selected by the shift diagram switching routine.

As described above, according to the present embodiment, the driving direction estimating means 100 (SM5) sequentially estimates the driving direction DL of the vehicle based on the driving operation related variables, and the standard driving direction estimating means 102 (SM5). In (SM6), the standard driving direction SDL of the vehicle indicating the average driving direction or the standard driving direction of the predetermined driver is estimated based on the past driving directions estimated by the driving direction estimating means 100. You. Then, the output filter means 104 (SM7)
, The filter constant K which is a function of the standard driving direction SDL estimated by the standard driving direction estimating means 102
Based on _DL2 , the driving direction DL estimated by the driving direction estimating means 100 is filtered. As a result, the driving direction DL estimated by the driving direction estimating means 100 is changed to the output filter means 10 having the filter constant K _DL2 reflecting the standard driving direction SDL of the vehicle.
4, the driving direction F that reflects the driver's driving intention with high accuracy after the filtering process.
DL can be obtained.

Incidentally, the broken line in FIG. 10 indicates the driving direction DL which is not subjected to the filtering process by the output filtering means 104.
Is shown. According to the driving direction DL, the accelerator pedal 5 is compared with the filtered driving direction FDL.
8 is significantly affected by the return operation of FIG.
₁ it is determined that fuel efficiency oriented in the section shown in t _2, the driving force is switched to the fuel consumption-oriented shift line map shown in FIG. 5 is low. For this reason, the driver cannot avoid a driving period with a driving force that does not fit his or her intention, despite the fact that the driver is oriented to acceleration.

Further, as shown in FIG. 11, a filter having a filter constant K _{DL 2} reflecting the standard driving direction SDL of the vehicle when the advanced driver travels on a 4 km test course with the intention of accelerating direction as shown in FIG. Processed driving orientation (hereinafter paragraph

FIGS. 12 and 14 show the FDL and the filter constant K _DL2, which are referred to as the former driving orientation, and show the acceleration / deceleration degree and acceleration directivity of the accelerator operation for a period used in the prior art (Japanese Patent Laid-Open No. Hei 7-167272). The filtered driving direction that changes the filter constant K _DL2 based on the increase or decrease of

The DL and filter constant K _DL2 are referred to in FIGS. 13 and 15. At this time, assuming that the acceleration directivity determination reference value PSL is set to “0.5”, the portion of the former driving directivity FDL that is equal to or higher than the acceleration directivity determination reference value PSL is 94.98%, while the latter is not. The portion of the pointing DL that is equal to or greater than the acceleration pointing determination reference value PSL is 79.94, and the accuracy of the former driving pointing FDL of the present embodiment is higher than that of the latter by 15%.
% Or more. Also, at this time, comparing the two figures with the erroneously determined portion indicated by the black portion, it can be seen that in the former driving orientation FDL, the acceleration orientation determination is maintained, but in the latter driving orientation DL, Is in a state where the determination of the acceleration orientation cannot be maintained.

Further, according to the present embodiment, the output filter processing means 104 (SM7) includes the driving direction estimating means 100.
When the driving direction DL is changed to the acceleration direction, the filtering process is applied to the driving direction DL only when the driving direction DL output from the vehicle is on the changing tendency toward the fuel efficiency side, that is, when the driving direction DL is decreasing. When the accelerator pedal 58 is suddenly depressed and a driving force is required, no filter processing is performed. Therefore, the value FDL indicating the driving direction can be rapidly changed to the acceleration direction, and the response is improved. Conversely, when the driving-oriented DL changes to the fuel-efficiency-oriented side, there is a possibility that the erroneous estimation may be unavoidable due to the driving situation or the road environment. There is. In the meantime, the erroneously determined portion shown by the black portion in FIG.
Comparing FIG. 13 with FIG. 13, in the case of the former driving-oriented FDL, since the filtering process is applied only to the part where the driving-oriented DL is decreasing, the response to the increase of the former driving-oriented FDL is high, and the erroneous estimation is performed. After that, the return is quicker than before, and the driving force corresponding to the increase in the driving orientation can be obtained with good responsiveness. However, in the case of the latter driving orientation DL, the filter processing is performed even when the driving orientation DL increases. Is performed, the responsiveness corresponding to the increase in the driving orientation DL is suppressed, and the return after erroneous estimation is delayed.

In this embodiment, the output filter means 1
04 (SM7), when the standard driving tendencies SDL is accelerated oriented, because compared to the case where fuel efficiency oriented those to enhance the filtering effect by increasing the filter constant K _{DL 2,} the driver's intention DL Standard driving direction S with high driving direction component even before it changes to fuel efficiency direction
When DL is a value on the acceleration directing side, the above filter constant K
_DL is largely driving tendency by filtering FDL
Of the driving-oriented FD
The erroneous estimation of L is further reduced. Conversely, even if the driving direction DL changes to the acceleration direction side, if the standard driving direction SDL having a high driving direction component before that is the value on the fuel consumption direction side, the filter constant K _DL is reduced and the filter processing is performed. As a result, the responsiveness of the estimation of the driving orientation FDL is increased, so that the estimation of the driving orientation close to the intention of the actual driver can be performed.

In this embodiment, the driving direction estimating means 1
A driving force selection unit 92 (SH1 to SH5) for selecting an actual driving force of the vehicle based on the driving direction FDL estimated by the driving filter unit 00 and filtered by the output filter unit 104 is provided. Means 92
As a result, the driving force of the vehicle is switched by selecting the shift diagram that is the basis of the shift determination based on the filtered driving orientation FDL, so that the vehicle has sufficient acceleration or Fuel economy is obtained. That is, as shown by the solid line in FIG. 10, the shift diagram is switched by the driving force selecting means 92 based on the driving direction FDL, so that the driver's operation and the behavior of the vehicle are the same as those of the fuel efficiency direction depending on the driving conditions and road environment. Even if the driving direction is changed, the output driving direction FDL includes the standard driving direction SDL by the output filter processing 104, so that a driving force or an acceleration force suitable for the driving direction of the driver can be obtained, and there is no uncomfortable feeling. Traveling becomes possible.

Next, another embodiment of the present invention will be described. In the following description, the same parts as those in the above-described embodiment are denoted by the same reference numerals, and description thereof will be omitted.

FIGS. 16 and 17 are a functional block diagram illustrating a main part of a control function of an electronic control unit 42 according to another embodiment of the present invention, and a flowchart illustrating a main part of a control operation.

FIG. 16 is a diagram corresponding to FIG. 6, showing another example of the configuration of the driving orientation estimating unit 94. In FIG. In the figure, similarly to the above-described embodiment, the driving direction estimating means 100 includes a throttle valve opening TA _ST at the time of starting the vehicle, a maximum change rate A _CCMAX of the throttle valve opening at the time of acceleration operation, and a braking operation of the vehicle at the time of braking operation. The maximum deceleration G _{NMAX of} the vehicle, the coasting time T _{COAST of} the vehicle,
A first driving operation related variables such as the vehicle speed constant running time T _VCONST, maximum value, a second operation is brought up to speed V _max etc. periodically generated in operation since the beginning of the predetermined interval of the input signals from the sensors The operation-related variables are stored in the preprocessing unit 98.
The driving direction estimating means 100 supplies the driving direction of the vehicle based on the first driving operation-related variable and the second driving operation-related variable every time the first driving operation-related variable is supplied or at predetermined intervals. DL is estimated sequentially. Then, based on the filter constant K _DL3 , which is a function of the standard driving direction estimating means 102 and estimated by the standard driving direction estimating means 102, an input for performing a filtering process on the second driving operation related variable input to the driving direction estimating means 100 is input. Filter means 1
10 is provided in place of the output filter means 104.

The input filter means 110 calculates a filter constant K _DL3 based on the standard operation-oriented SDL from the equation 4 similar to the equation 2, and calculates an equation 5 similar to the equation 3 having the filter constant K _DL3 . The driving direction D output from the driving direction estimating means 100 using the filter processing equation
During a period in which L is decreasing, that is, a period in which the value L is changing to the fuel consumption direction side, a filter process is performed on the second driving operation related variable. In Equation 4, CK _DL3 is a reference filter constant, and K _SDLO3 is, for example, a constant of about “6”. In Equation 5, n is an integer indicating a sampling number, OP _n and OP _{n + 1} are values indicating a second operation-related variable before filtering, and FOP _{n + 1} is a second variable after filtering. It is a value indicating a driving operation related variable.

[0071]

[ _Equation 4] K _DL3 = CK _DL3 + K _SDLO3 · SDL

[0072]

FOP _{n + 1} = [OP _{n + 1} + K _DL3 · FOP _n ]
/ (1 + K _DL3 )

FIG. 17 is a flowchart for explaining a main part of the control operation of the electronic control unit 42 of the present embodiment, that is, a driving direction estimation operation, and is a diagram corresponding to FIG. The flowchart of FIG. 17 is different from the flowchart of FIG. 8 in that the input filter processing of SM9 is provided between SM4 and SM5 instead of removing the output filter processing of SM7 in FIG. Hereinafter, the difference will be mainly described.

S corresponding to the input filter means 110
In M9, the filter constant K _DL3 is determined from Equation 4 based on the actual standard driving direction SDL, and changes to a period in which the driving direction DL output from the driving direction estimating means 100 is decreasing, that is, toward the fuel consumption side. in the period, of the input signal inputted to the driver's intention estimating means 100, first be predetermined interval maximum value in the causes maximum vehicle speed V _max etc. periodically generated in operation since the beginning of the input signals from the sensors 2 The filtering process shown in Expression 5 is performed on the driving operation related variables.

According to this embodiment, the driving orientation estimating means 10
0 (SM5), the driving direction DL of the vehicle is determined based on the first driving operation-related variable generated in connection with the driving operation of the vehicle and the second driving operation-related variable periodically generated every predetermined period. Are sequentially estimated, and the standard driving direction estimating means 102 (SM6), based on the past driving direction DL estimated by the driving direction estimating means 100, calculates the average driving direction of the predetermined driver or the standard driving direction. The standard driving direction SDL of the vehicle exhibiting the proper driving direction is estimated.
Then, based on the filter constant K _DL3 which is a function of the standard driving direction SDL estimated by the standard driving direction estimating means 102 by the input filter means 110 (SM9), the second input to the driving direction estimating means 100 is made. The driving operation related variables are filtered. Thus, the driving direction DL estimated by the driving direction estimating means 100
Is estimated based on the second driving operation related variable filtered by the input filter means 110 having the filter constant K _{DL 3} reflecting the standard driving orientation SDL of the vehicle, so that the driving intention of the driver can be determined with high accuracy. It is possible to obtain the driving orientation reflected in

Further, according to the present embodiment, the input filter means 110 (SM9) determines whether the value DL indicating the driving direction, which is successively estimated by the driving direction estimating means 100, is changing to the fuel consumption direction side. Since filter processing is performed on the second driving operation related variable input to the driving direction estimating means 100, when the driving direction DL changes to the acceleration direction side, for example, the accelerator pedal is suddenly depressed and the driving force is reduced. When the request is made, the second driving operation related variable is not filtered, so that the value DL indicating the driving direction can be rapidly changed to the acceleration direction side, and the responsiveness is enhanced. When the driving-oriented DL changes to the fuel-consumption-oriented side, there is a possibility that unavoidable erroneous estimation may occur due to driving conditions or road environment. There is an advantage that is low.

Further, according to the present embodiment, the input filter means 110 (SM9) increases the filter constant K _DL3 when the standard operation-oriented SDL is acceleration-oriented, as compared with the case of fuel-efficient orientation. Therefore, even if the driving direction DL changes to the fuel consumption direction side, if the standard driving direction SDL having a high driving direction component before that is the value on the acceleration direction side, the filter constant K _DL3 is enlarged and the second
By reducing the responsiveness of the driving operation-related variables, that is, the responsiveness of the driving orientation estimation, erroneous estimation of the driving orientation is reduced. Conversely, even if the driving direction DL changes to the acceleration direction side, if the standard driving direction SDL having a high driving direction component before that is the value on the fuel consumption direction side, the filter constant K _DL3 is reduced and the filter processing is performed. As a result, the responsiveness of the second driving operation-related variable, that is, the responsiveness of the estimation of the driving orientation is increased, so that the estimation of the driving orientation close to the actual driver's intention becomes possible.

Further, according to the present embodiment, the actual driving force of the vehicle is obtained by the driving direction estimating means 100 based on the driving direction DL estimated based on the second driving operation related variable filtered by the input filter means 110. Is further included, and the driving direction DL estimated by the driving force selecting unit 92 based on the filtered second driving operation-related variable includes
Since the shift diagram as the basis for the shift determination is selected and the driving force of the vehicle is switched, sufficient acceleration or fuel efficiency suitable for the driver's driving orientation can be obtained.

FIG. 18 is a functional block diagram for explaining a main part of a control function according to another embodiment of the present invention.
FIG. 9 and FIG. 20 are flowcharts for explaining the main part of the control operation in another embodiment of the present invention. In this embodiment, the driving direction estimating unit 94 includes the standard driving direction estimating means 10.
2 is provided, and the driving force selecting means 92 determines the actual driving force of the vehicle based on the driving direction DL estimated by the driving direction estimating means 100 and the standard driving direction SDL estimated by the standard driving direction estimating means 102. Is selected.

In FIG. 18, the driving force selection means 92
A criterion value determining means 114 for determining criterion values CPSL and CESL for selecting a driving force based on the standard driving directional SDL estimated by the standard driving directional estimating means 102, and a driving directional estimating means 100 A comparison determination unit 116 that compares the driving orientation DL estimated by the above with the reference values CPSL and CESL and switches the shift diagram used in the shift control unit 90 to select the driving force.

The criterion value determining means 114 calculates
From the value SDL indicating the standard driving orientation and "0.8" in advance
Acceleration pointing determination reference value CPSL set to a constant value of degree
The acceleration reference value PSL to be actually used is calculated on the basis of
Based on L and a fuel efficiency orientation reference value CESL preset to a constant value of about "0.2", a fuel efficiency orientation reference value ESL to be actually used is calculated. In Equations 6 and 7, K _PSL and K _ESL are, for example, “0.
It is a constant set to a constant value of about 2 ”
Is a constant set near the middle between the acceleration directivity determination reference value CPSL and the fuel efficiency directivity determination reference value CESL, and is set to a constant value of, for example, about “0.5”.

[0082]

PSL _n = CPSL + K _PSL (CNDL−SDL _n )

[0083]

ESL _n = CESL + K _ESL (CNDL−SDL _n )

When the driving direction DL estimated by the driving direction estimating means 100 is equal to or larger than the acceleration direction determination reference value CPSL, the comparison determining means 116 selects, for example, a shift diagram for acceleration direction shown in FIG. If the driving direction DL is lower than the acceleration direction determination reference value CPSL but is equal to or higher than the fuel efficiency direction determination reference value CESL, for example, FIG.
When the driving direction DL is lower than the fuel efficiency directivity determination reference value CESL, for example, a fuel efficiency directing speed diagram shown in FIG. 5 is selected.

In the driving orientation estimation control routine of FIG.
In SM5 corresponding to the driving direction estimating means 100, the driving direction DL is calculated in the same manner as described above, and in SM6 corresponding to the standard driving direction estimating means 102, the standard driving direction SDL is calculated in the same manner as described above.

In the shift diagram switching routine of FIG. 20, the shift diagram switching routine of FIG. 9 is added with SH6 for previously calculating the acceleration-based determination reference value CPSL and the fuel-efficiency-based determination reference value CESL. They differ in points. In FIG. 20, first, SH6 corresponding to the criterion value determination means 114 is executed. In this SH6, the expression 6
Based on the value SDL indicating the standard driving direction and the preset acceleration direction criterion value CPSL set in advance, the acceleration direction criterion value PSL actually used is calculated. Based on the set fuel efficiency directivity determination reference value CESL, a fuel efficiency directivity determination reference value ESL to be actually used is calculated. Next, by executing SH1 to SH5 including SH1 and SH3 corresponding to the comparison determination means 116 in the same manner as described above, the shift diagram is switched to the shift diagram suitable for the actual driving orientation, and the driving force is selected.

According to this embodiment, the driving direction estimating means 10
0 (SM5) and the standard driving direction SDL estimated by the standard driving direction estimating means 102 (SM6).
H6, SH1 to SH5) select the actual driving force of the vehicle, so that erroneous estimation of driving orientation is prevented, and a driving force that reflects the driver's driving intention with high accuracy is obtained.

That is, the criterion value determining means 114 (S
H6), acceleration acceleration based on standard driving orientation SDL
Determination reference value CPSL and fuel consumption direction determination reference value CESL
Is determined, and is sent to the comparison determination means 116 (SH1, SH3).
The driving finger estimated by the driving orientation estimating means 100
Direction DL, their reference values CPSL and fuel efficiency
Is compared with the pointing determination reference value CESL, and based on the comparison result.
The shift diagram used in the shift control means 90 is
As shown in FIG.
Of the accelerator pedal 58 was performed while the vehicle was running
In connection with this, the value DL indicative of the driving orientation sharply decreased
In this case, it is possible to prevent erroneous estimation that the vehicle is fuel-efficient. Cause
In addition, the value set in advance to a constant value shown by the broken line in FIG.
Speed pointing determination reference value CPSL and fuel efficiency direction determination reference value C
If ESL is used, t ₁From time t_TwoAt the time
As shown in the range, a misconception that fuel economy is
By switching to the fuel consumption direction shift diagram,
Driving with a driving force that does not match the driving orientation of the diver
It was.

FIG. 22 and FIG. 23 are functional block diagrams illustrating the main part of the control function of the electronic control unit 42 in another embodiment of the present invention, and the main part of the control operation of the electronic control unit 42. It is a flowchart. The present embodiment is characterized in that a value indicating the variance of the input signal within a predetermined period is input to the neural network NN of the driving direction estimating means 94.

In FIG. 22, the pre-processing means 9 of this embodiment
8, the calculation means 98a, 98b, 98c, 98
In addition to d, 98e, 98f, and 98g, an input signal variance value calculating unit 98h for calculating a value indicating the variance of the input signal in a predetermined section is provided, and the input signal variance value calculating unit 98h calculates the value. input signal within a predetermined interval, for example, the throttle valve opening TA, the engine rotational speed N _E, vehicle speed V, the adapted variance values such as the longitudinal acceleration is input to the neuro network NN driving manner estimation means 94. The value indicating the variance of the input signal is not only a so-called standard deviation value σ or a variance value σ ^{2 of} the input signal value, but also a value indicating a variation of the input signal value, such as a difference between a highest value and a lowest value. Good.

FIG. 23 shows an input signal variance value calculation routine SM3h included in the preprocessing routine SM3 of FIG. The input signal variance calculation routine SM3h is for corresponding to the input signal variance value calculating means 98h, for example, the throttle valve opening TA, the engine rotational speed N _E, vehicle speed V, the variance of the input signal, such as the longitudinal acceleration Is calculated.

According to the present embodiment, for example, the variance values of input signals such as the throttle valve opening TA, the engine rotation speed N _E , the vehicle speed V, and the longitudinal acceleration are input to the neural network NN of the driving direction estimating means 94. Therefore, when the vehicle speed V and the engine rotation speed _NE are high, as in the case of traveling on a highway, the variance value is small in the fuel consumption orientation, so that it is avoided to erroneously estimate the acceleration orientation. Therefore, the driving direction D corresponding to the driving direction of the driver
L is output with high accuracy and the driving force selecting means 92
As a result, the driving force is selected based on the driving direction DL, so that drivability in accordance with the driver's will is obtained.

Although the above has been described with reference to the drawings showing an embodiment of the present invention, the present invention can be applied to other embodiments.

For example, the driving force selecting means 92 in the above-described embodiment switches between a plurality of types of shift diagrams stored in advance based on the driving direction DL or FDL. The stored relationship between the accelerator pedal operation amount Acc and the throttle valve opening TA may be switched. FIG. 24 illustrates a relationship for acceleration pointing indicated by a one-dot chain line, a relationship for intermediate pointing indicated by a solid line, and a relationship for fuel economy indicated by a two-dot chain line. Throttle control means 8 for driving and controlling actuator 86
8. Switch the relationship used in 8.

The above-mentioned standard driving direction estimating means 102
Has been estimated using Equation 1 similar to the delay process or the smoothing process, but the average value of the driving direction DL estimated by the driving direction estimating means 100 within the period since the ignition switch was turned on is a predetermined value. The moving average value of the driving direction DL in the section or a weighted average value thereof may be used.

The signal reading means 96 described above may read signals such as wheel speed, lateral acceleration, and steering angle.

In addition, FIG. 7, FIG. 16, FIG. 18, FIG.
In each of the embodiments shown in FIG. 2, the case where the present invention is carried out independently has been described. However, the embodiments may be carried out in combination with each other.

In the above-described embodiment, the neural network NN of the driving orientation estimating means 100 includes the throttle valve opening TA _ST at the time of starting, the maximum throttle valve opening change rate A _CCMAX at the time of depressing the accelerator, and the maximum at the time of braking. Deceleration G
_NMAX , coasting running time T _COAST , constant vehicle speed running time T
_{Although VCONST} is input, even if any one of them or any one or more of them is input, a tentative and reliable estimation is possible.

In the above-described embodiment, the driving orientation is estimated from the output of the neural network NN in three stages: acceleration orientation, intermediate orientation, and fuel economy orientation, but is estimated in two stages of acceleration orientation and fuel economy orientation. May be done. Further, the estimation between the acceleration orientation and the fuel economy orientation may be continuously performed. In such a case, the orientation between the acceleration orientation and the fuel economy orientation is estimated by the complementary function of the neural network NN.

Further, the driving orientation estimating means 1 of the above-described embodiment is used.
The neural network NN of 00 has a three-layer structure including an input layer, an intermediate layer, and an output layer. However, the neural network NN may have a hierarchical structure of four or more layers. It can be a type.

In the above-described embodiment, the throttle valve opening TA and the maximum throttle valve opening change rate A _CCMAX are used. However, in a vehicle such as a diesel engine-equipped vehicle, the throttle valve 68 is not provided. In this case, the accelerator pedal operation amount and accelerator pedal depression speed may be used instead of the throttle valve opening TA and the maximum throttle valve opening change rate A _CCMAX .

The above is merely an example of the present invention, and the present invention can be variously modified without departing from the gist thereof.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a shift control device of an automatic transmission for a vehicle having a driving direction estimation function according to an embodiment of the present invention.

FIG. 2 is a table showing combinations of gears in the automatic transmission of FIG. 1 and operating states of a solenoid valve or a friction engagement device for establishing the gears.

3 is a shift diagram used in the shift control device of FIG. 1, and is a shift diagram selected when the driving is estimated to be acceleration (sports) -oriented. FIG.

FIG. 4 is a shift diagram used in the shift control device of FIG. 1 and is a shift diagram selected when the operation is estimated to be in an intermediate (normal) direction.

5 is a shift diagram used in the shift control device of FIG. 1, and is a shift diagram selected when the driving is estimated to be fuel-efficient (economy) -oriented.

FIG. 6 is a functional block diagram for explaining a main part of a control function of the electronic control device of FIG. 1;

FIG. 7 is a functional block diagram for explaining in detail a control function of a driving orientation estimating unit in FIG. 6;

FIG. 8 is a flowchart illustrating a main part of a control operation of the electronic control device of FIG. 1, that is, a driving direction estimation operation.

9 is a flowchart illustrating a main part of a control operation of the electronic control device of FIG. 1, that is, a driving force selection operation.

10 is a diagram illustrating the driving force selection operation of FIG. 9, and is a time chart illustrating a relationship between a change in a value FDL indicating the driving direction and a shift diagram to be selected.

[11] As a test run of a predetermined distance, the throttle valve opening TA when performing the operation of the acceleration-oriented, the vehicle speed V, and is a time chart showing the engine rotational speed N _E.

12 is a time chart showing changes in the driving direction FDL estimated by the control operation in FIG. 8 and subjected to the filtering process in the acceleration directional running in FIG. 11;

13 is a time chart showing a change in driving direction DL in which the filtering process in FIG. 8 is not performed in the acceleration-directed running in FIG. 11;

FIG. 14 is a time chart showing changes in filter constants used for the filter processing determined by the control operation of FIG. 8 in the acceleration-oriented running of FIG. 11;

15 is a time chart showing a change in a filter constant that is not determined as in the control operation of FIG. 8 in the acceleration-oriented running of FIG. 11;

FIG. 16 is a functional block diagram illustrating a main part of a control function of an electronic control unit according to another embodiment of the present invention.
FIG. 8 is a diagram corresponding to FIG. 7.

17 is a flowchart illustrating a main part of a control operation of the electronic control device of FIG. 16, that is, a driving direction estimation operation, and is a diagram corresponding to FIG.

FIG. 18 is a functional block diagram illustrating a main part of a control function of an electronic control unit according to another embodiment of the present invention,
FIG. 8 is a diagram corresponding to FIG. 7.

19 is a flowchart illustrating a main part of a control operation of the electronic control device in FIG. 18, that is, a driving direction estimation operation, and is a diagram corresponding to FIG.

20 is a flowchart illustrating a main part of a control operation of the electronic control device in FIG. 18, that is, a driving force selection operation, and is a diagram corresponding to FIG. 9;

21 is a time chart for explaining a control operation of the electronic control device of FIG. 18, and is a diagram corresponding to FIG.

FIG. 22 is a functional block diagram illustrating a main part of a control function of an electronic control device according to another embodiment of the present invention;
FIG. 8 is a diagram corresponding to FIG. 7.

23 is a flowchart illustrating a main part of a control operation of the electronic control device of FIG. 22, that is, an operation of calculating a variance of an input signal in a predetermined section.

FIG. 24 is a diagram showing a relationship between an accelerator pedal operation amount Acc and a throttle valve opening TA used in a throttle control unit according to another embodiment of the present invention.

[Explanation of symbols]

 14: Automatic transmission 90: Shift control means 92: Driving force selection means 94: Driving direction estimating unit 98: Pre-processing means (driving operation related variable calculating means) 100: Driving direction estimating means 102: Standard driving direction estimating means 104: Output filter means 110: Input filter means NN: Neural network

 ──────────────────────────────────────────────────続 き Continued on the front page (72) Inventor Yasuya Nakamura 1 Toyota Town, Toyota City, Aichi Prefecture Inside Toyota Motor Corporation (72) Inventor Keihan Fukumura 1 Toyota Town, Toyota City, Aichi Prefecture Toyota Motor Corporation (72) Inventor Hideo Tomomatsu 1 Toyota Town, Toyota City, Aichi Prefecture Inside Toyota Motor Corporation (72) Inventor Koji 1 Toyota Town, Toyota City, Aichi Prefecture Inside Toyota Motor Corporation (72) Inventor Kisaburo Hayakawa 41 Toyota Chuo Research Institute, Nagakute-machi, Aichi-gun, Aichi-gun, Toyota-Chuo Research Institute, Inc. (72) Inventor Masataka Osawa 41 Toyota Chuo-Laboratory, Aichi-gun, Nagakute-cho, Aichi-gun 72) Inventor Masuji Oshima 41-cho, Yokomichi, Nagakute-cho, Aichi-gun, Aichi Pref. (72) inventor Hiroyuki Yoshida Aichi Prefecture Aichi-gun Nagakute Oaza Nagakute-shaped side street No. 41 land of 1 Co., Ltd. Toyota Central Research Institute in

Claims (3)

[Claims] 1. A driving direction estimating device for estimating a driving direction of a vehicle, the driving direction estimating means for sequentially estimating the driving direction of the vehicle based on a driving operation related variable of the vehicle, and the driving direction estimating means. A standard driving direction estimating means for estimating the standard driving direction of the vehicle based on the past driving direction estimated by the following; and a filter constant which is a function of the standard driving direction estimated by the standard driving direction estimating means. An output filter means for performing a filtering process on the driving direction estimated by the driving direction estimating means on the basis of the driving direction estimating means. 2. A driving direction estimating device for estimating a driving direction of a vehicle, the driving direction estimating device comprising: a first driving operation related variable generated in connection with a driving operation of the vehicle; Driving direction estimating means for sequentially estimating the driving direction of the vehicle based on the second driving operation related variable; and estimating a standard driving direction of the vehicle based on past driving directions estimated by the driving direction estimating means. Based on a standard driving direction estimating means and a filter constant which is a function of the standard driving direction estimated by the standard driving direction estimating means, filter processing is performed on the second driving operation related variable input to the driving direction estimating means. A driving direction estimating device for a vehicle. 3. A driving force control apparatus for a vehicle for controlling a driving force based on an estimated value of a driving direction of a vehicle, wherein the driving direction estimation for sequentially estimating the driving direction of the vehicle based on a driving operation related variable of the vehicle. Means, a standard driving direction estimating means for estimating a standard driving direction of the vehicle based on the past driving directions estimated by the driving direction estimating means, and a driving direction estimated by the driving direction estimating means; A driving force selection unit for selecting an actual driving force of the vehicle based on the standard driving direction estimated by the standard driving direction estimation unit.