JPH0424744A - Learning method for prewire neuro of rule part - Google Patents

Abstract

PURPOSE:To efficiently adjust the weight of an antecedent membership function realization part and a consequent membership function realization part while using the weight of a rule part efficiently by simultaneously learning the weight of both the antecedent membership function realization part and the consequent membership function realization after the initial setting of the weight value. CONSTITUTION:After setting the weight initial value with preliminarily held knowledge introduced for the antecedent membership function realization part 10, a rule part 12 and the consequent membership function realization part 14, it is constituted using the learning data to learn the weight of the antecedent membership function realization part 10 and the consequent membership function realization part 14 simultaneously. Further, the initial setting of the weight value of the antecedent membership function realization part 10 and the consequent membership function realization part 14 can be executed using a random number, or it can be a combination of the preliminary held knowledge. Thus, the efficient weight adjustment of the antecedent membership function realization part 10 and the consequent membership function realization part 14 can be executed while effectively using the weight of the rule part 12.

Description

[Detailed Description of the Invention] [Summary] A control output corresponding to an input is generated according to a hierarchical network structure that realizes a fuzzy control rule, which is composed of an antecedent membership function implementation unit, a rule unit, and a consequent membership function implementation unit. Regarding the learning method of the rule part pre-wired neuro, we have developed an antecedent membership function realization part, a rule part and a consequent part membership function realization part, with the aim of efficiently learning to perform control suitable for the target system. After setting initial weight values that introduce pre-existing knowledge for each, the weights of the antecedent membership function realization part and the consequent membership function realization part are simultaneously learned using the training data. Configure. Note that the initial setting of the weight values of the antecedent membership function realization unit and the consequent membership function realization unit may be performed using random numbers, or may be performed in combination with pre-existing knowledge and random numbers. .

[Industrial Application Field] The present invention relates to a learning method for a rule section prewired neuron that combines fuzzy control and neural network.

In information processing using neurons, learning data consisting of a set of input patterns of the target system and desired output patterns for that input pattern is used in a hierarchical format.
It is presented to the physical network to learn and perform adaptive processing. In particular, a processing method called pack propagation method is attracting attention due to its high practicality in this learning process.

On the other hand, fuzzy theory was proposed by Zadeh in 1960, and is a theory that models the process of thinking and judgment based on ambiguity that humans make, such as whether the temperature is "low" or "high." This fuzzy theory is mathematically based on fuzzy set theory, which introduces membership functions to represent ambiguity.

As an application of fuzzy theory, in 1974 Maqmda
Various types of fuzzy control have been used since it was first used to control steam engines.

Since the system that performs this fuzzy control handles uncertain things, it is necessary to have a configuration that can adaptively respond to adjustments and changes in the control algorithm.

[Prior Art] Generally, the following procedure is taken to construct a fuzzy control system.

■Obtain ambiguous control rules such as ``If the temperature is high, reduce the fire'' held by experienced operators.

■ Quantify the meaning of the words (propositions) in the control rules in the form of membership functions, and convert the control rules into rlF-THEN~
” Described using a type rule expression.

■Conduct inspections through simulations and on-site tests.

■Evaluate inspection results and improve membership functions and rules.

To explain in more detail, the fuzzy control rules are, for example, rif I, is big and x2i
It is described as s small then Yl eyes bigJ. Here, the IF section is called an antecedent section, and is a section that describes conditions regarding control state quantities (control inputs) such as temperature. Further, the THEN section is called a consequent section, and is a section that describes the conditions regarding the control operation amount (control output) of the operating terminal, etc.

Fuzzy control manages multiple fuzzy control rules prepared as the control logic of the target system, and also manages the meaning of ambiguous linguistic expressions such as "large" or "small" written in each fuzzy control rule. Quantify and manage it as a ship function.

The control procedure of the completed fuzzy control system is as follows.

■When a controlled state quantity such as temperature is input from the controlled object, the truth value is calculated according to the membership function of the antecedent part that has been set.

(2) Next, in accordance with the antecedent computation such as selecting the minimum value, a process is executed to determine the value to be applied to the consequent in each fuzzy control rule. For example, r XI is b
Truth value of igJ = 0.8 "!2is smallJ
When the truth value of = 0.5, the truth value = 0.5 is output as the applied value to the consequent part of the fuzzy control rule according to the antecedent part operation that selects the minimum value. Process.

(2) Next, a process is executed to determine an output application value from the input value (applied value) from the antecedent part to the membership function of the consequent part, which has the same amount of control operation.

For example, with two fuzzy control rules, [ma, i
Applied value of s bigJ=0.5r r1+s bigJ
When the applied value=0.6 is obtained, the applied value=0.6 is selected and determined according to the consequent operation that selects the maximum value.

■Subsequently, the membership function of the control operation amount is reduced (or expanded) according to the determined applied value, and the center of gravity of the figure of the function part of the membership function for the same control operation amount is calculated. The control operation amount, which is a fuzzy inference value, is calculated and output.

By the way, fuzzy control rules are planned to be generated according to the knowledge possessed by a skilled operator, and it is difficult to establish fuzzy control rules that can realize optimal control from the beginning. Therefore, it is necessary to improve the generated fuzzy control rules through trial and error while evaluating them through simulations and field tests.

Therefore, the inventors of the present application developed a hierarchical network structure that realizes fuzzy control rules by applying neurology.
That is, we have proposed an adaptive fuzzy control system using prewired neuro in the rule section (Patent Application No. 2-602).
(See No. 56, “Hierarchical Network Configuration Data Processing Device and Data Processing System”). That is, the rule part prewire neuro has a hierarchical network configuration that realizes a fuzzy control rule consisting of an antecedent part membership function realization part, a rule part, and a consequent part membership function.

Considering the automatic extraction of fuzzy control rules by the pre-wired neuron of the rule section, the following procedure may be taken.

■Set the membership function of the rule section prewire neuro.

■The rule section prewire neuro is presented with the input pattern of the target system and a set of desirable output patterns for that input pattern, and is made to learn.

■Extract the optimal fuzzy control rule for the target system by analyzing the weights of connections in the rule section.

[Problems to be Solved by the Invention] However, the learning performed for extracting fuzzy control rules for the rule section pre-wired neuron is
The learning method for learning, including the weights of the antecedent membership function part, rule part, and consequent part membership function realization part, has not been determined, and the performance of the roll part prewire neuron has not yet been determined. There is a need to develop efficient learning methods that can bring out the best in students.

The present invention has been made in view of the above situation, and an object of the present invention is to provide a learning method for a rule section pre-wired neuron that can efficiently perform learning for controlling a target system. .

[Means to solve the problem] FIG. 1 is a diagram explaining the principle of the present invention.

First, the present invention provides antecedent membership function realization unit 10.1
Or, it has a hierarchical network structure that realizes a fuzzy control rule consisting of a multi-layered rule section 12 and a consequent membership function realization section 14, where the rule section 12 is an antecedent membership function realization section 10 in the preceding stage and/or a subsequent stage. The consequent membership function realization unit 14 does not internally connect all the units, but internally connects some of them according to the control rule, and input control state quantities (X+, X2,...Xo
) The rule section pre-wire neuro 100 that outputs one or more control operation amounts (Y) corresponding to ) is targeted.

In the present invention, as a learning method for such a rule part prewire neuron 100, [each of the first step antecedent membership function realization unit 10, rule part 12, and consequent membership function realization unit 14] Initialize weight values; [Second process] The antecedent membership function realization unit 10 and the consequent membership function realization unit 1 use the learning data prepared in advance.
A learning method is constructed that includes a processing process in which four weights are learned simultaneously.

Here, the initial setting of the weight value in the first process is based on the knowledge (in the figure, " Initialize the weight values created based on "a priori knowledge").

In addition, as another initial setting of the weight values in the first process, weight values created using random numbers are initialized in the antecedent membership function realization unit 10 and the consequent membership function realization unit 14, and the rules The unit 12 is initially set with weight values created based on knowledge held in advance.

Furthermore, in the first process, the antecedent membership function realization part (
10) and another method of setting the initial weight values of the consequent membership function realization unit (14) is to initialize the weights that can be set based on prior knowledge, and use random numbers for the other weights. It may be initialized.

On the other hand, at the start of learning in the second process, the antecedent membership function realization unit 10 and the consequent membership function realization unit 1
While turning on the learning flag provided for each connection of 4,
The learning flag provided for each connection in the rule unit 12 is turned off, and only the weight values of the connections having the learning flag in the on state are optimized through learning processing.

[Operations] According to the learning method of the rule section pre-wired neuron of the present invention having such a configuration, the following operations can be obtained.

First, initial setting of weight values based on prior knowledge or initial setting of weight values using random numbers for the antecedent membership function realization part and the consequent membership function realization part of the rule part prewire neuro. and initial setting of weight values for the rule section based on knowledge held in advance.

Next, the learning process is started, the input pattern for learning is presented to the rule section pre-wired neuron, and the output pattern from the rule section pre-wired neuron is a learned output pattern (the teacher The weights of the antecedent membership function realization unit and the consequent membership function realization unit are simultaneously learned by, for example, the pack propagation method.

In this way, by simultaneously learning the weights of the antecedent membership function realization part and the consequent membership function realization part of the rule part prewire neuro, pre-existing knowledge can be introduced and initial settings can be performed. It becomes possible to adjust the weights of the antecedent membership function realization section and the consequent membership function realization section while effectively utilizing the weights of the rule section.

Further, by initializing the weights of the antecedent membership function realization section, the rule section, and the consequent membership function realization section into which knowledge held in advance is introduced, learning can be facilitated and learning efficiency can be increased.

Further, by initializing the weights of the antecedent membership function realization unit and the consequent membership function realization unit using random numbers, it is possible to maximize the neuro-based learning function.

[Example 2] FIG. 2 is a learning operation flowchart showing a processing procedure as an example of the learning method of the rule section pre-wired neuron according to the present invention.

The rule section prewire neuron that is the target of the learning method according to the procedure of FIG. 2 is, for example, the antecedent section membership function realization section 101 shown in FIG. It has a hierarchical network structure for realizing fuzzy control rules, which is composed of a rule section 12 and a consequent membership function realization section 14 (including a centroid calculation realization section 18).

Here, the rule section pre-wire neuro means the rule section 12.
has a network structure in which all units are not internally connected with the antecedent membership function realizing unit 10 in the previous stage and/or the consequent membership function realizing unit 14 in the subsequent stage, but some are internally connected according to the control rule. , is compared to a rule-part fully connected neuron that internally connects everything between hierarchical units.

In the learning process shown in FIG. 2, the following steps 81 to S6 are performed.

[Step Sl] Weight Cab of the antecedent membership function realization unit 10.

Cbc is initialized based on the introduction of prior knowledge to realize a given membership function.

Note that Cab and Cbc are connection group numbers of connections for which weights are set, as will be described later.

[Step S2: Initialize the weights Ccd and Cde of the co-rule unit 12 based on the introduction of pre-existing knowledge so as to realize the given fuzzy rule.

[Step S3] The weight Cef of the consequent membership function realization unit 14 is initialized based on the introduction of knowledge held in advance so as to realize the given membership function.

[Step S4] The weight C1g of the center of gravity calculation implementation unit 18 is initialized so as to realize the center of gravity calculation.

[Step S5] A phase/group correspondence table indicating neuron groups for each phase in which learning processing is performed and a group/connection correspondence table indicating connection groups belonging to each two-neelon group are set. In the present invention, since the weights of the antecedent membership function realization unit 10 and the consequent membership function realization unit 14 are learned simultaneously after the initial setting of the weight values, the phase group correspondence table contains the phase 1 In this step, only the neuron groups belonging to the antecedent membership function realization unit 10 and the consequent membership function realization unit 14 to be learned are set.

[Step S6] Start the learning scheduler and perform learning processing using the pack propagation method. In the present invention, the weights of the antecedent membership function realization unit 10 and the consequent membership function realization unit 14 are learned simultaneously in one phase.

Below, step 81 shown in the learning operation flow diagram of FIG.
- S6 will be explained in detail separately.

[Configuration of the rule section prewire neuron] The rule section prewire neuron to which the present invention is applied has a hierarchical network structure capable of realizing the fuzzy control rule shown in FIG. 3, for example.

In FIG. 3, each node shown in each part represents one basic unit, and two types of basic units are used: a sigmoid function unit shown by a black circle, and a linear function unit shown by a white circle.

FIG. 4 shows the configuration of the basic unit shown in FIG. 3.

In FIG. 4, the basic unit 20 constitutes a multi-power single output system, and includes a multiplication section 22 that multiplies a plurality of inputs by the weight value of each internal connection, and a multiplication section 22 that adds all the multiplication results of the multiplication section 22. It is composed of an adding section 24 and a threshold processing section 26 that performs threshold processing on the output of the adding section 24.

Here, if the first layer is the h layer and the second layer is the i layer, the multiplier 22
The addition unit 24 executes the calculation of equation (1) below, and the threshold processing unit 26 executes the calculation of equation (2) below.

x, l=ΣV, hw l h
(1) 3' pr= 1 / (1+ e-""-"
' ) (2) However, h: Unit number of the h layer i: Unit number of the i layer p: Input signal pattern number θ,: Threshold value of the first unit of the i layer VLh: Weight of internal coupling between h and i layers Value x, I: Product sum of inputs from each unit of the h layer to the 1st unit of the i layer 3'ph: Output y1 from the h unit of the h layer in response to the input signal of the I)th pattern: pth pattern The output from the first unit of the i-layer with respect to the input signal of the equation (2) is known as a sigmoid function, and is the threshold value processing of the basic unit indicated by the black circle shown in FIG.

In contrast, the threshold processing unit 26 ypl=x.

The linear function unit set as follows becomes the white circle linear function unit in FIG. However, the input section, which is the first unit of the antecedent membership function realization section 10, does not necessarily have to be a linear function unit.

The hardware of the basic unit shown in Fig. 4 is a patent application filed in 1983.
It is shown in "Network configuration data processing device" of No.-21fi865.

Referring again to FIG. 3, the configuration of each part of the rule section pre-wire neuro will be explained.

First, the antecedent membership function realization unit 10 processes each input variable X1, X2 . ...Xn is input, input variable X,
Output the grade value of the membership function of ~Xn. In the figure, each membership function is a one-variable function for simplicity, but it may be a multi-variable function. In other words, it may be a membership function of XI &X2 (SA) with variables X and x2 as inputs.

The rule section 12 includes an antecedent section rule section 12-1 and a consequent section rule section 12-2. The antecedent part rule part 12-1 is
Membership function X + (S
A) The grade values of ~X n (LA) are input, and the grade values of each rule are output.

Further, the consequent part rule part 12-2 contains the grade value L of the rule.
H3-1 to LH3-n are input, and grade values of membership functions y(SA) to y(LA) of output variables are output.

Further, the consequent membership function realization unit 14 (including the centroid calculation realization unit 16) calculates the membership function y (
Input the grade values of SA) to y (LA) and output the value of the output variable Y.

Here, the antecedent part rule part 12-1 and the consequent part rule part 12
Since both the input and output of the rule unit 12 including -2 are the grade values of the membership function, these can be cascaded and multi-stage inference is possible.

Further, the neurons connecting each module 10.12-1.12-2.14 can be shared. For example, the output neuron of the antecedent membership function implementation unit 10 and the input neuron of the antecedent rule unit 12-1 may actually be the same.

Further, in FIG. 3, each unit is described as one neuron, but if the function of the unit can be specified, it may be used as a gate circuit, an arithmetic unit, etc. that realizes the unit function instead of a neuron.

FIG. 5A shows a specific embodiment of the rule section pre-wired neuron of the present invention, taking as an example a case where two inputs, X1 and X2, are given to obtain a control output Y.
The configuration of each part will be explained in detail with reference to the drawings as follows.

The input section 16 is composed of separation units 28-1 and 28-2, which divides the inputs XI and X2 into two and supplies them to the antecedent membership function realization section 10. The antecedent membership function realization unit 10 includes four sigmoid function units 30-1 to 30.
-4 and the same four linear function units) 32-1 to 32
-4.

The rule section 12 includes, for example, sigmoid function units 34-1 to 348 that realize eight fuzzy rules, and the antecedent membership function realization section 10 connects each fuzzy rule according to the descriptions 1 to L8. ing. The outputs of the sigmoid function units 34-1 to 34-8 are connected according to fuzzy rules to two linear function units 36-1 and 36-2 which perform consequent operations according to fuzzy rules.

The consequent membership function realization unit 14 is composed of, for example, nine linear function units 38-1 to 38-9, and determines membership based on two unit output values (grade values) output from the rule unit 12. The function is reduced (or enlarged) and the function sum of the two reduced (or enlarged) membership functions is calculated.

Furthermore, the center of gravity calculation implementation unit 18 is composed of a center of gravity determining element output device 40 and a center of gravity calculation device 42. The linear function units 40-1 and 40-2 of the center-of-gravity determining element output device 40 calculate the weighting of the unit outputs from the consequent membership function realization unit 14 by calculating the sum and calculating the two center-of-gravity calculation elements Y1. Y 2
Finally, the centroid calculation device 42 calculates the two centroid calculation elements Y1. A center of gravity is calculated from Y2 to generate a control output Y as a fuzzy inference value.

FIG. 5B shows neuron groups and connection groups used in initial setting of weight values and weight learning for implementing the learning method according to the present invention for the rule section pre-wired neuron in FIG. 5A.

In FIG. 5B, there are seven neuron groups, Ga-Gg, among which neuron group G in the input section
a and the two knee long loops Gg of the center of gravity calculation realization unit 18
As for the first one, it is excluded from the weight learning target by the pack propagation method because it merely performs separation and addition/synthesis. Therefore, there are five neuron groups that are subject to weight learning by the pack propagation method: Gb, Gc, Gd, Ge, and Gf.

On the other hand, there are six connection groups, Cab-CfH, representing the input connections of each two-neelon group, and the weight values of the input connections located in the previous stage of the neuron group to be learned are learned by the pack propagation method.

Regarding the learning operation flow shown in Fig. 2, which targets the rule section pre-wired neuron having the structure shown in Figs. 5A and 5B,
First, the initial setting of weight values for each part will be explained as follows.

[Initial setting of the antecedent membership function realizing unit] The initial setting of the weight value for the antecedent membership function realizing unit 10 is to set the weight of each connection included in the connection groups Cab and Cbc to the given membership function. Initial settings are made to achieve this.

FIG. 6 shows the antecedent membership function realization unit 10 of FIG. 5A.
The control human power X, side is taken out and shown. In FIG. 6, the output value y output from the sigmoid function unit 30-1.30-2 is y=i/(1+e-"""'
) (3).

In the initial setting of the weight value for the antecedent membership function realization unit 10 of the present invention, based on the knowledge that is available in advance, for example, as the weight value W of the input connection of the sigmoid function unit 30-1, W= −20 is set, and θ=−10 is set as the threshold value θ in the sigmoid function unit 30-1.

Further, the weight value W of the input connection of the other sigmoid function unit 30-2 is set to W=20, and at the same time, the threshold value θ of the sigmoid function unit 30-2 is set to θ=10. In addition, linear function unit) 32-1. 32-
The weight value of the input connection No. 2 is set to the initial weight value=1.

In this way, in the sigmoid function unit 30-1, W〈0
When the weight value and threshold value are initially set such that θ×O, the unit output value x, (SS) for the control output X shown in the characteristic curve 44 in FIG. It is possible to set a truth value calculation function for a membership function having a function shape such that X and (SS) become small.

Also, in the sigmoid function unit 30-2, W>0
By initially setting the weight value and threshold value such that θ〉0, the unit output value X1 (LA) for the control human power X1 shown in the characteristic curve 46 in FIG. It is possible to realize a function that calculates the truth value of a membership function with a function shape that is thick.

Sigmoid function unit 30-1.3 shown in FIG.
The initial setting of the weight value and threshold for 0-2 is such that the desired antecedent membership function is also realized for the remaining sigmoid function units 30-3 and 30-4 in the antecedent membership function realization unit 10. Initial settings are made based on prior knowledge.

[Initial Setting of Rule Section] The initial setting of the weight value for the rule section 12 in FIG. 5A is as follows.
The weight values of the connections belonging to the connection groups Ccd and Cde shown in FIG. 5B are initialized by introducing knowledge held in advance so as to realize a given fuzzy rule.

FIG. 8 is an explanatory diagram showing a specific example of initial setting of weight values for the rule section 12 together with fuzzy rules.

In Figure 8, eight sigmoid function units) 34-
1 to 34-8 correspond to fuzzy rules 1 to L8 shown on the right side, respectively. For each of the sigmoid function units 34-1 to 34-8, the fuzzy rules are calculated from the antecedent membership function realization unit 100 and the linear function units 32-1 to 32-4 located at the previous stage.
Input connections are made in accordance with ~L8. Furthermore, fuzzy rules are applied to the two linear function units 36-1 and 36-2 provided following the eight sigmoid function units 34-1 to 34-8, and the consequent parts of 1 to L8 (T HE
Connections are made in accordance with N).

Here, the function shape of the fuzzy logic operation based on the weight values initially set for the input connections of the sigmoid function units 34-1 to 34-8 in the rule section 12 of FIG. 8 and the threshold values set for the units themselves will be explained as follows. become.

FIG. 9 shows one sigmoid function unit 34 of the rule section 12, in which truth value

X2 is input, and output value y is generated by product-sum calculation and threshold processing.

The output value y output from the sigmoid function unit 34 in FIG. 9 is: 5=Wx1・X+ +Wx+@X2−θ (4)
y=1/ (1+e-s) (5)
It is calculated as The unit output value y given by the above equation (5) can have an appropriate function shape by arbitrarily setting the weight value WXI+WX□ of the input connection and the threshold value θ.

Specifically, the sigmoid function units 34-1 to 34-1 in FIG.
The numerical value shown in the input connection of 34-8 is set as the initial weight value, and the sigmoid function unit) 34-1 to 34-8
The numerical value shown below indicates the threshold value θ.

For example, in the sigmoid function unit 34-1 that realizes the fuzzy rule Ll, the following is set, and by setting these initial values, the sigmoid function unit 34-1 that realizes the fuzzy rule L1
will perform threshold processing of the function shape shown by the three-dimensional coordinates in FIG.

Hereinafter, similarly, sigmoid function units 34-2 to 34-
By initializing the weight values and threshold values for each of the 8 fuzzy rules 2 to L8, the function shapes shown in FIGS. 11 to 17 can be obtained.

Note that the linear function unit 36 provided at the output stage in FIG.
The weight value of the connection for -1.36-2 is initially set to 1, and since the threshold value processing is a linear function, θ=0 is set.

[Initial Setting of Consequent Part Membership Function Realization Unit] Initial setting of weight values for the consequent part membership function realization unit 14 in FIG. 5A is as follows: Initial setting of weight values for the consequent part membership function realization unit 14 shown in FIG. Initial settings are made to realize the given membership function based on the knowledge of the given membership function.

FIG. 18 is an explanatory diagram specifically showing the initial setting of weight values for the consequent membership function realization unit 14.

In FIG. 18, the consequent membership function realization unit 14
Nine linear function units 38-1 to 38- provided in
9, a connection input is performed from the linear function unit 36-1, 36-2 of the rule section 12 at the previous stage as shown in the figure. These nine units are 38-1 to 38-9
correspond to points in the range of 0 to 1 on the training line of the control output y at equal intervals.

The initial setting of the weight values of the input connections for the linear function units 38-1 to 38-9 is performed by the unit 3 of the rule section 12.
Regarding the weight value of the connection of the output y (SS) from the unit 38-1, the weight value of the connection of the output y (SS) from the unit 38-1 is determined according to the characteristic curve 46 shown on the right side of the graph in which the horizontal axis is the control output Y1 and the vertical axis is the unit output value.
Weight values from the side to the unit 38-9 side, 1, 1. 1.0.75.0.5, 0.25. 0
．． 0. Initialize 0.

Regarding the weight values of the input connections from the unit output y (LA) of the rule section 12, the weight values are as follows from the unit 38-1 side to the unit 389 side according to the characteristic curve 48: 0, O, 0, 0, 25, 0,5,0,75,1,1
, 1 are initialized.

Furthermore, the threshold value θ of the linear function units 38-1 to 38-9 is θ
=0.

Due to the initial setting of the weight values in the consequent membership function realization unit 14, the unit output values y (SS) and y (LA) output from the linear function unit 36-1.36-2 of the rule unit 12 are are reduced by multiplication by initial weight values, added, and output to the next center-of-gravity calculation implementation unit 18.

In FIG. 18, a weight value of 1 or less is initially set so as to reduce the unit output, but it is also possible to set a weight value of 1 or more to enlarge it.

[Initial Setting of Center of Gravity Calculation Implementation Section] The initial settings of weight values for the center of gravity calculation implementation section 18 shown in FIG. 5A are initialized so as to realize center of gravity calculation for the connection group C1g of FIG. 5B.

FIG. 19 shows a specific example of initial setting of weight values for realizing the center of gravity calculation performed on the center of gravity determining element output device 40 of the center of gravity calculation implementation unit 18.

For the two linear function units 40-1 and 40-2 provided in the centroid determining element output device 40, the nine linear function units 38-1 provided in the consequent membership function realization unit 14 of the preceding stage ~38-9 are connected. Then, as shown in the figure, weight values for calculating two gravity center derived values Y1 and Y2 used in the gravity center calculation are set for this input connection.

In fuzzy control, a method is generally adopted in which the control output Y, which is a fuzzy inference value, is calculated by finding the center of gravity of a figure consisting of the sum of functions of reduced membership functions for the same control output position according to the following formula: do.

Y= f grade (y) ydy / f g+a+
Ie(T)d! (6) In order to realize this formula (6), the linear function units 40-
As the connection weight value for 1, the minimum value Y of the control output Y
Starting from O, weight values are assigned that increase from 0 at equal intervals up to the maximum value Y=1. On the other hand, the linear function unit 40
-2 input connection, maximum value of control output Y = 1
From 0 to the minimum value Y=0, weight values that decrease from 0 to -1, for example, are assigned at the same equal intervals as above.

With such weighting of the input connections to the linear function unit 40-1 and 40-2, if the unit output values of the linear function units 38-1 to 38-9 in the previous stage are C1 to C9, the linear function unit 40-1 becomes , Yl"IC+ +0.875 C2+0.75C3+0
．． 625 C4+Q, 5 C5+0.375 C6+0
．． 25C, +0.125 C, +OC9 (7), and the linear function unit 40-2 outputs Y1=OCt
[1,125C20,25Ci-0,375C4-0,
5C5-0,625C6-0,75C7-0,875C
Outputs 8+IC9 (8).

The centroid derived values Y1 and Y2 outputted from the linear function unit 40-1. A control output Y, which is an inferred value, is calculated.

By substituting the above equations (7) and (8) into the above equation (9), it can be seen that Y in the above equation (9) matches Y in the above equation (6).

With the above processing, the initial setting of the weight value for the rule section prewire neuron shown in steps 81 to S4 in FIG. 2 is completed, and the process proceeds to step S5.

[Setting of learning schedule] In step S5 of FIG. 2, following the completion of the initial settings, a learning plan, ie, a learning schedule, for causing the rule section pre-wired neuro to perform learning processing is set. This learning schedule is set by two steps: setting the phase/group correspondence table shown in FIG. 20 (Ca') and setting the group/connection correspondence table shown in FIG. 20(b).

First, the phase-group correspondence table specifies the neuron groups to be learned in each phase as the learning phase progresses. In the present invention, after the initial setting of the weight values, the weight learning of the antecedent membership function realization unit 10 and the consequent membership function realization unit 14 is performed at the same time, so that as shown in FIG. 20(a), In phase 1, three neuron groups Gb, Gc, and Gf shown in FIG. 5B belonging to the antecedent membership function realization unit 10 and the consequent membership function realization unit 14 are set as learning target groups.

On the other hand, the group/connection correspondence table sets the correspondence between each neuron group Ga to Gg in the rule section prewire neuron and the input connection group Cab to ClH as shown in FIG. 20(b) based on FIG. 5B.

When the setting of the phase/group correspondence table and the group/connection correspondence table is completed, the process proceeds to step S6 in Fig. 2, starts the learning scheduler, and actually gives the learning data to the rule section pre-wire neuron to set the pack properties. The weight learning of the antecedent membership function realization unit 10 and the consequent membership function realization unit 14 is performed simultaneously using the gation method.

[Processing and Configuration of Learning Scheduler] FIG. 21 shows a flowchart of the learning process of the rule section pre-wire neuro of the present invention. This processing flow diagram is, for example, the 22nd
First, the device configuration for learning processing that can be realized by the device configuration shown in the figure will be explained.
In the figure, a learning instruction unit 50 and a learning unit 70 are provided for the rule section pre-wired neuron 100.

The learning instruction unit 50 has a learning scheduler 52,
For the learning scheduler 52, there is a learning signal storage unit 54 that stores learning signals consisting of pairs of control inputs and desired control outputs for the control inputs, and a phase group storage unit 54 that stores the phase group correspondence table shown in FIG. A correspondence tape 56, a group/connection correspondence table 58 storing a group/connection correspondence table, and a learning convergence determination section 60 are provided.

On the other hand, the learning unit 70 is provided with a learning instruction reading section 72, a learning flag setting section 74, and a weight changing section 76 that changes weight values using the pack propagation method.

Furthermore, a feature of the device configuration in FIG. 22 is that a learning adjuster 80 is provided in the connection connecting each unit in the rule section prewire neuron 100.

The learning adjuster 80 has the configuration shown in FIG.

Note that the weight change unit 76 is shown together with the learning adjuster 80.

The learning adjuster 80 is provided with a flag storage section 82 , a weight change information reading section 84 , and a weight change amount adjustment section 86 .

On the other hand, the weight change unit 76 includes a weight calculation unit 88 that performs weight calculation based on the pack propagation method, and a weight storage unit 9.
0 and a weight change amount storage section 92 are provided.

In this way, by providing the learning adjuster 80 for each connection of the rule section pre-wire neuro 100, it is possible to determine whether or not the learning scheduler 52 of the learning instruction unit 50 changes the weight value of the connection for the rule section pre-wire neuro 100. It is possible to set a learning flag that determines the weight, and it is possible to perform weight learning only for connections for which the learning flag is valid, that is, the flag is turned on.

Furthermore, the flag set for the learning coordinator 80 sets the antecedent membership that can execute fuzzy rules for a general hierarchical network that does not have a network structure that can implement fuzzy rules as shown in FIG. It is also used when specifying a hierarchical network structure consisting of a function realization section, a rule section, and a consequent membership function realization section.

When a hierarchical network conforming to fuzzy rules is configured, the weight values are adjusted as follows when actually learning is performed by the pack propagation method.

In FIG. 23, the weight change information reading unit 84 of the learning adjuster 80 monitors whether the weight change amount has been written by the weight calculation unit 88 to the weight change amount storage unit 92 of the weight change unit 76. There is. When the weight change information reading unit 84 detects that the weight has changed, it notifies the weight change amount adjustment unit 86 of the fact. The weight change amount adjustment unit 86 checks the learning flag in the flag storage unit 82, and does nothing if the learning flag is on. That is, writing to the weight change amount storage section 92 is made valid. On the other hand, if the learning flag is off, the weight change amount adjustment section 86 changes the weight change amount storage section 9 of the weight change section 76.
2 is set to zero to disable the weight change.

The hardware of this learning scheduler is patent application No. 63-2.
No. 27825, “Learning method for network configuration data processing device”.

Next, with reference to the learning processing flow in FIG. 21, Section 22.
The learning process of the rule section pre-wire neuron according to the device configuration shown in FIG. 23 will be explained.

First, when the learning scheduler 52 of the learning instruction unit 50 is activated, the first step (hereinafter "step" is omitted) is to
In SL, set the phase counter i that indicates the progress of the learning phase to i=l, proceed to S2, and refer to the phase/group correspondence table 56 to find the neuron group numbers Gb, Gc, and Gf corresponding to the learning phase i=1. read out.

Next, proceed to S3, and set neuron group numbers Gb and Gc.
, Gf.

Cbc, Cef group/connection correspondence table 58
Refer to and read.

Next, proceed to S4, and set the connection group numbers Cab, Cb.
c, Output Cef and connect connection group number Cab,
Cbc.

The learning flag of the learning adjuster 8o provided in the connection belonging to Cef is turned on.

Specifically, the learning scheduler 52 of the learning instruction unit 50 outputs a connection group number to the learning instruction reading section 72 of the learning unit 7o and causes it to read it. The learning flag setting unit 74 that receives the reading result from the learning instruction reading unit 72 instructs the flag storage unit 82 of the learning adjuster 80 provided in the connection belonging to the connection group number for which the learning instruction has been received to turn on the flag. and set the learning flag.

Next, the process proceeds to S5, where the learning scheduler 52 issues a learning execution command to start the learning process. This learning process reads out the control human power X prepared in the learning signal storage section 54 and the teacher signal d that is a desirable control output for the control human power X, and converts the control human power X into the rule section prewire neuro 10
0, and the teacher signal d is given to the weight changing unit 76 and the learning convergence determining unit 60. Then, the control output Y output from the rule section prewire neuro 100 that receives the learning human power X
is taken into the weight change unit 76 and learning convergence determination unit 60,
The weight changing unit 76 changes the weight values according to the pack propagation method, and the learning convergence determining unit 60 determines the end of learning when the error of the control output Y with respect to the teacher signal d becomes equal to or less than a specified value. Finish the process.

When the learning process ends based on the learning execution command in S5,
S6 increments the phase counter i by one, and
Check the end of the learning phase at 7. Since the learning process of the present invention ends at phase 1, the series of processes ends as is.

[Principle of learning by pack propagation method 3 Next, the principle of weight learning by the pack propagation method of the present invention will be explained together with the hierarchical network.

FIG. 24 shows a general hierarchical neural network, which is composed of a type of node called a unit and internal connections with weights.

In Figure 24, the h layer is the input device, and the i layer is the intermediate layer.
layer, and the j layer as the output layer.

Of course, there is only one i-layer as the intermediate layer, but the same is true even if there are a plurality of intermediate layers. Each unit has the configuration shown in FIG. 4, and the calculations performed in the unit are as shown in equations (1) and (2) above for the basic unit 20. In the pack propagation method, the weight value Wi of the hierarchical network
b and the threshold θi are adaptively and automatically adjusted and learned by error feedback. As is clear from the above equations (1) and (2), it is necessary to adjust the weight value W i h and the threshold value θi at the same time, but this work is a difficult work that interferes with each other. Therefore, in addition to the normal unit, the applicant has provided a unit whose output value is always 1 in the h layer on the input side, and uses a threshold value θi as a weight value for the input connection from this unit with an output value of 1. By assigning
A pack propagation method has been proposed in which the threshold value θi is incorporated into the weight value Wih and the threshold value θi can be treated as the weight value (Japanese Patent Application No. 333484/1984).

By doing this, the above equations (1) and (2) become x, 1=
ΣyphW+h (II)rey1, = 1/ (1+eXp(x,+))
(12), and the threshold value θi does not appear.

By expanding from equations (1, 1) and (12) above, we get the following (1
3) Equation (14) is obtained.

xpI:Σ5'ptWz (1
3) y1, = 1/ (1+exp(XDI))
(14) However, j: unit number W1 of the j layer,: weight value of internal connection between the i-j layers The output from the first unit of the j layer for the pattern input signal The weight change unit 76 in FIG.
When receiving the teacher pattern apl, which is the signal to be taken by the output cover turn ypI and the output cover turn 'lp+ output from the output layer j when is presented, the difference value (d++-xpI) between the two is calculated, and then δ1 , = y l (1y□) (dp+-Yp+)
(15) is calculated. Subsequently, ΔW++(+)=εΣδp r V p ++ζΔw+
1 (+-1) where ε: Learning constant ζ: Momentum t: Update amount ΔW of weight values between the i layer and the j layer according to the number of learning times.

Calculate (1). Here, the reason for adding the weight value update amount determined in the previous update cycle in the second term on the right side of equation (16) is to speed up learning.

Subsequently, the weight value changing unit 76 uses Δδ1 calculated by the equation (15) to calculate δpl=Vl (I Yp+) transcription δ−W++(+−1
) (17), then ΔWlh(1)=εΣδp+3'++h×ζΔW+h(
+-1), update amount Δw+h of weight values of h layer and i layer
Calculate (+).

Subsequently, the weight change unit 76 determines the weight value for the next update cycle according to the update amounts calculated by the equations (16) and (18). To update the above weight values, the output pattern ypI for the input pattern for learning is the teacher pattern ap.
The learning process is repeated so that a weight value matching l is obtained.

On the other hand, if the units constituting the hierarchical network in FIG. 24 are linear function units, the above equation (14) becomes Y 1,=
20). The above equations (15) and (17) in this linear function unit are δ1, = d p+ V p+
(21) δ, quantity = 4. δ, IWth (t-1)
It appears as (22).

[Weight Learning Process of the Present Invention] FIG. 25 is a processing flow diagram of weight learning performed by the pack propagation method for the rule section pre-wire neuron of the present invention shown in FIG. 5A.

The parameters of each part in this learning process flow are the 26th
It is defined as shown in the figure.

FIG. 26 schematically shows the hierarchical structure of the rule section pre-wire neuron in FIG. 5A. As shown, it has a six-layer structure from the first layer to the sixth layer.
The layer is made up of sigmoid function units, and the rest are made up of linear function units.

In the present invention, in order to simultaneously learn the weights of the antecedent membership function realization unit 10 and the consequent membership function realization unit 14, that is, to learn the weights in the same phase, the first layer, the second layer and Each of the fifth layers is set as a learning target. Specifically, learning flags provided at the connections of the first layer, second layer, and fifth layer are set to on. In contrast, the third and fourth layers of the rule section 12 that do not perform weight learning
Regarding the sixth layer of the layer and center of gravity calculation implementation section 18, the learning flag of the learning adjuster 80 provided in the connection is reset to OFF.

Here, the fuzzy inference value, that is, the control output value, output by the realization of the fuzzy rule by the pre-wired neuron in the rule section is y6, and the learning process in one learning phase is performed from the 6th layer to the 5th layer, the 4th layer, and the 4th layer. 3rd layer, 2nd layer, 1st layer
Do this sequentially, layer by layer. The progress of learning for each layer is indicated by an i counter. That is, in the initial state, the i counter is i
It is set on layer 6.

To further simplify the explanation, W1,1 and ΔWlto1 represent a matrix whose size is (the number of neurons in the i-th layer) x (the number of neurons in the i-1th layer). Furthermore, δi and yi represent vectors whose size is the same as the number of neurons in the i-th layer.

The weight learning process of the present invention shown in FIG. 25 will be explained as follows based on the parameters of each part shown in FIG. 26.

First, a counter i for setting a learning target layer is initialized using Sl. Specifically, since it has a six-layer structure as shown in FIG. 26, the counter i is initially set in the i-layer 6. With this initial setting, the unit in the sixth layer is designated as a learning target.

Next, the process advances to 82 to determine whether it is a sigmoid function unit. Since the 6th layer is a linear function unit, the process proceeds to 814, where it is determined whether or not it is the final layer.Since the 6th layer is the final layer, the process proceeds to 815, where the teacher signal d obtained at that time is determined.
Using the control output y and the difference value δ6, the difference value δ6 is determined according to a formula similar to the formula (21).

Next, the process proceeds to 86, where it is determined whether the weight is a learning unit or not.

At this time, since the sixth layer is excluded from the learning target, the process proceeds to S8, where the weight update amount ΔW65=O, and the process proceeds to S9, where the weight value W6. update is disabled.

Next, the process proceeds to 812, and it is determined whether the value of the counter i is E=1, which indicates the first layer as the final learning layer in phase 1. At this time, since i=6, the process proceeds to 313, where the counter i is incremented. Decrement by one, set i to 5, and return to S2 to start learning the next fifth layer.

Since the fifth layer is also a linear function unit, 82
The process proceeds to 814, but since it is not the final stage layer, the process proceeds to 316.
Then, the difference value δ5 is calculated according to a formula similar to the formula (22) above.
Calculate.

Next, proceed to 86 to determine whether it is a learning target,
Since the fifth layer is the consequent membership function realization unit 14, it is the learning target in the present invention, and therefore S
Proceed to step 7. In S7, the weight update amount ΔW54 is calculated using the difference value δ5 obtained in 816 according to equations similar to equations (16) and (18). Next, the process proceeds to S9, where the weight values W and 4 are updated according to a formula similar to the formula (19).

Thereafter, the same process is repeated until the final unit of the fifth layer, and when the process of the fifth layer is completed, the process proceeds to the fourth layer.

Since the fourth layer is a linear function unit, it is 82°S14
The process proceeds to step S16 to calculate the difference value δ4, but since it belongs to the rule section 12, it is not a learning target.
Therefore, proceeding from 86 to 88, the weight update amount ΔW4'3=O
Then, the update of the weight W43 in S9 is invalidated. When the above processing is performed up to the final unit of the fourth layer, the processing proceeds to the third layer.

Since the third layer is a sigmoid function unit, the process proceeds from S2 to S3, and since it is not the final stage, the process proceeds to 85, where a difference value δ3 unique to the sigmoid function is obtained using an arithmetic expression similar to equation (17). However, the third layer is the rule part 1
Since it belongs to class 2, it is not a learning target, and the process proceeds from S6 to 88, where the weight update amount ΔW3□=0, and the update of the weight W32 at S9 is invalidated. When the third layer processing is completed, the process proceeds to the second layer.

The second layer is a linear function unit and belongs to the antecedent membership function realization unit 10, so it is a learning target. Therefore, the process proceeds from 82 to S16 via S14 to calculate the difference value δ2. Next, the process proceeds from S6 to S7 to calculate the weight update amount ΔW2+, and in S9 the weight value W2. Update. When the above process is repeated up to the final unit of the second layer, the process proceeds to the first layer.

The first layer is a sigmoid function unit and belongs to the antecedent membership function realization unit 10, so it is a learning target. Therefore, the process proceeds from S2 to S5 via 83 to calculate the difference value δ1, the process proceeds from S6 to 87 to calculate the weight update amount ΔW,o, and the weight value W1o is updated in S9.

This process is repeated until the final unit of the first layer, and when the process of the final unit is completed and the process proceeds from S10 to 812, the counter i becomes a value that matches i=1 and learning end layer E==1. Therefore, it is determined that the learning of all the layers in Phase 1 has been completed, and the series of processing is completed.

``Initial Setting of Weights Using Random Numbers'' Next, another embodiment of the learning method of the present invention will be described with reference to the learning operation flow diagram of FIG.

In the learning process shown in FIG. 27, the antecedent membership function realizing unit 10 and the consequent membership function realizing unit 1 of the rule unit pre-wired neuron are executed in steps S1 and S3.
As the initial setting of the weight value for 4, the weight value is randomly initialized using random numbers. on the other hand,
Regarding the initial setting of weight values for the rule section 12 in step S2, the weight values are initialized based on the introduction of knowledge held in advance, similar to the first embodiment shown in FIG.

Other steps S4. The processing in S5 and S86 is the same as in the first embodiment shown in FIG.

By randomly initializing weight values using random numbers in the antecedent membership function implementation unit 10 and the consequent membership function implementation unit 14 that perform weight learning in this way, the performance of the neuron network can be maximized. We can expect efficient weight learning that brings out the best possible results.

In the initial setting of weight values using random numbers, if there is some knowledge that is previously held, the setting may be performed based on this knowledge.

[Other Notes: The above embodiment takes as an example the rule section pre-wired neuron that realizes fuzzy rules targeting two control human forces X1 and X2 as shown in FIG. 5A. Of course, the number of inputs may be 1 or 3 or more as appropriate.

Further, in the above embodiment, y=1/(1+e-wx'') (23
) was taken as an example of the membership function, but
Two sigmoid function units 9 as shown in FIG.
The unit output of 4-1.94-2 may be applied to the subtraction unit 96 to realize the function shape shown in FIG. The unit output y in this case is y = 1/(1-e -w1x'') -1/(1-
e−w2x″12).

Furthermore, in the embodiment shown in FIG. 5A, the rule unit 12 is constructed of a neuron network, but in the present invention, the rule unit 12 only initializes the weight values and does not perform weight learning. Therefore, it is not necessarily necessary to use a neuron network, and it may be configured using hardware. This point also applies to the center of gravity determining element output device 40 of the center of gravity calculation implementation unit 18.

[Effects of the Invention] As described above, according to the present invention, by simultaneously learning the weights of the antecedent membership function realization unit and the consequent membership function realization unit after initial setting of the weight values,
It is possible to efficiently adjust the weights of the antecedent membership function realization part and the consequent membership function realization part while making effective use of the weights of the rule part that have been initialized by introducing knowledge that is previously held. , when realizing an arbitrary control system using fuzzy rules, more efficient connection weight analysis can be realized.

In addition, weight learning can be easily performed by initializing the weight values by introducing prior knowledge of the antecedent membership function realization unit and the consequent membership function realization unit.

Furthermore, neuron network learning is possible by initializing weight values using random numbers for the antecedent membership function realization unit and consequent membership function realization unit, or by initializing weight values using a combination of prior knowledge and random numbers. You can learn efficiently by maximizing your functions.

[Brief Description of the Drawings] Fig. 1 is a diagram explaining the principle of the present invention; Fig. 2 is a learning operation flow diagram of the present invention; Fig. 3 is a configuration diagram of an embodiment of the rule section pre-wired neuron of the present invention; The figure is an explanatory diagram of the basic unit; Figure 5A is a configuration diagram of a specific example of the rule section pre-wired neuron of the present invention; Figure 5B is an explanatory diagram of the neuron group and connection group in Figure 5A; Figure 6 is a diagram of the main unit. An explanatory diagram of the initial settings of the antecedent part membership function realization part of the invention; FIG. 7 is an explanatory diagram of the membership function of the antecedent part; FIG. 8 is an explanatory diagram of the initial settings of the rule part of the invention; 10 is an explanatory diagram of the fuzzy rule L1 of FIG. 9; FIG. 11 is an explanatory diagram of the fuzzy rule L2 of FIG. 9
Explanatory diagram: Fig. 12 is an explanatory diagram of fuzzy rule L3 in Fig. 9; Fig. 13 is an explanatory diagram of fuzzy rule upper 4 in Fig. 9.
The figure is the top 5 explanatory diagram of the fuzzy rule in Figure 9. Figure 15 is the 9th
Fig. 16 is an explanatory diagram of the fuzzy rule L6 in Fig. 9. Fig. 17 is an explanatory diagram of the fuzzy rule upper 8 in Fig. 9. Fig. 18 is an explanatory diagram of the fuzzy rule L6 in Fig. 9. An explanatory diagram of initial settings; Fig. 19 is an explanatory diagram of the initial settings of the center of gravity calculation implementation unit of the present invention; Fig. 20 is an explanatory diagram of the settings of the phase/group correspondence table and group/connection correspondence table of the present invention; A flowchart of the learning process according to the invention; FIG. 22 is a configuration diagram of a device for learning processing according to the invention; FIG. 23 is a configuration diagram of a learning regulator provided for each connection in FIG. 22; FIG. 24 is a diagram of a general hierarchical neuron Network explanatory diagram; Fig. 25 is a weight learning processing flow diagram of the present invention; Fig. 26 is a parameter explanatory diagram of each part of Fig. 25; Fig. 27 is an operation flow diagram showing another embodiment of the present invention; FIG. 28 is an explanatory diagram of another membership function used in the present invention. In the figure, 10: Antecedent part membership function realization part 12: Rule part 14: Consequent part membership function realization part 16 Two-man power part 18: Center of gravity calculation realization part 20: Basic unit 22: Multiplication part 24: Addition part 26 :Threshold processing unit 2g-1, 28-2, 32-1 to 32-4.38-1
~38-9.40-1.40-2: Linear function unit 30-1~30-2.34-1~34-1t, 94-
194-2: Sigmoid function unit 40: Center of gravity determining element output device 42: Center of gravity calculation device 50: Learning instruction unit 52: Learning scheduler 54: Learning signal storage unit 56: Phase-group correspondence table 58, group-phase correspondence table 60: Learning convergence determination section 70: Learning unit 72: Learning instruction reading section 74: Learning flag setting section 76 Duplex change section 80: Learning adjuster 82: Flag storage section 84: Weight change information reading section 86: Weight change amount adjustment section 88 : Weight calculation section 90: Weight storage section 92: Weight change amount storage section 96: Subtraction unit 100: Rule section Lower doto simple span, also light day H figure unit output value reduction 1,770 lower Z7 Benz 7 sekiru lt light decoy figure 7 figure 9 (a) 214-day H)re fuzzy rule Ll :rF:ff5S) O[SS) T) Positive N'/
(SS) L2:IF Xl(SS) ANDX2SS
) THEN '/(LA)L3:IFXl(LA)
ANDY2(SS) THEN y(ss)L4:I
FYl(LA) ORX2SS) T)IEN Y(L
A) L5: IFXl (SS) o=(LA) T HE
N y (ss) L6: IF Xl (s S) AND
22 (LA) THEN y (LA)L7:IF)
(j Mountain A) Station Han) THENY (SS) L8:nFXl
(LA) OR Me 2 (LA) THENY (LA) (b) -1 and 11 Pre-7'l Fight Nu F Garden 1 Sun Moon Figure 8 "C0 111-Y---No゛- --- to 111' (0 111) -m-J αfu' cy c'y ako111) -1-no z' C Ri N's 11 II II (-1- Y----) Between 0f and misfire! 11. ；R″r Tatsumi Shatama υ's Kito Scream ■ Stain Removal Problem Figure 19 (a) (b) Figure 20

Claims (5)

[Claims] (1) It has a hierarchical network consisting of an antecedent part membership function realization part (10), a rule part (12) consisting of one or more layers, and a consequent part membership function realization part (14), and the rule part (12) does not internally connect all units with the antecedent membership function realization unit (10) in the previous stage and/or the consequent membership function realization unit (14) in the subsequent stage, but only some parts according to the control rule. In a learning method of a rule section pre-wired neuro that is internally coupled and outputs one or more control operation quantities (Y) corresponding to input control state quantities (X_1, X_2,...X_n), Subject membership function realization unit (10), rule unit (12), and consequent membership function realization unit (14)
a first step of initially setting weight values for each of; the antecedent membership function realization unit (10) using learning data;
and a second step of simultaneously learning the weights of the consequent membership function realization unit (14). (2) Initial setting of the weight values in the first process is performed by using the weight values created based on knowledge held in advance by the antecedent membership function realization unit (10), the rule unit (12), and the 2. A learning method for a rule part prewired neuron according to claim 1, characterized in that initial settings are made in each of the subject membership function realization units (14). (3) The initial setting of the weight value in the first process is a weight initial value created using random numbers in the antecedent membership function realization unit (10) and the consequent membership function realization unit (14). 2. A learning method for a rule section pre-wired neuron according to claim 1, characterized in that said rule section (12) is initially set with a weight value created based on knowledge held in advance. (4) Antecedent membership function realization unit (10) and consequent membership function realization unit (14) in the first process.
), the weights that can be set based on knowledge held in advance are initialized using this knowledge, and the other weights are initialized using random numbers. How to learn neuro. (5) At the start of learning in the second process, turning on a learning flag provided for each connection of the antecedent membership function realization unit (10) and the consequent membership function realization unit (14), The rule according to claim 1, characterized in that a learning flag provided for each connection in the rule section (12) is turned off, and only the weight value of a connection having a learning flag in an on state is optimized by a learning process. How to learn part prewire neuro.