JPH07295821A - Fault diagnosis device - Google Patents

Abstract

(57) [Abstract] [Purpose] To inform the user that the inquiry regarding the user has been completed in the process of verifying the inference result, and prevent the user from wasting time. [Structure] Narrow down the interview candidates generated in the inference process,
By displaying the narrowed-down contents of the inquiry on the touch screen 1a and obtaining an answer, the reasoning result of this time is verified and used as information for generating a new hypothesis. At that time, when the inquiry regarding the user is completed, the end of the inquiry regarding the user is displayed, and the user is immediately opened to prevent waste of time.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a failure diagnosis apparatus which uses a so-called expert system to search for a cause of a failure leading to a defective phenomenon of a vehicle, an aircraft or the like.

[0002]

2. Description of the Related Art In recent years, an expert system has been adopted in various fields such as medicine, architecture, and chemistry to utilize a computer as a clue for problem solving. This expert system is a system in which the knowledge of a specialist in a certain specific field is input to a computer and it is possible to solve a complicated problem at a level equivalent to that of a specialist.

Conventionally, this expert system has been adopted for vehicle failure diagnosis, for example, as disclosed in JP-A-62-62.
As disclosed in Japanese Patent No. 6846, a defect phenomenon is input, and a fundamental failure cause (fault location) causing the phenomenon is represented by a set of rules as knowledge data or past cases. It is known to make inferences using stored knowledge data.

In this case, in order to obtain a highly accurate inference result, it is necessary to make an inquiry about the occurrence state of the trouble phenomenon and the inspection instruction. If this inquiry is not carried out smoothly, the efficiency of the diagnosis work will decrease. JP-A-3-185251
Japanese Patent Publication discloses a technique of holding a question that the user cannot answer, putting it in a question holding stack, holding confirmation of success or failure of an event by the question, and asking the next question.

[0005]

By the way, there are two types of questioning that occur in the process of verifying the inference result: those relating to the user who first detected the malfunction, and those relating to the maintenance personnel who disassemble the equipment. Conventionally, these interviews have been performed in the order on the inference route or the order in which the inference reliability is high.

[0006] Therefore, there is a possibility that the user may be restrained despite the end of the inquiry regarding the user because the outside may not know when the inquiry for the user is completed.

The present invention has been made in view of the above circumstances, and provides a failure diagnosis apparatus capable of notifying the user that the inquiry regarding the user is completed in the process of verifying the inference result and preventing the user from wasting time. It is intended to be provided.

[0008]

In order to achieve the above object, a failure diagnosis apparatus according to the present invention uses a knowledge base unit for storing knowledge data necessary for failure diagnosis, and a defect input by using this knowledge data. In a failure diagnosis device, which comprises an inference mechanism section for investigating a cause of failure corresponding to a phenomenon by inference, and which displays input / output information in a process of investigating a cause of failure by the reasoning mechanism section on a display section, In the process of displaying an inquiry from the reasoning section on the display section to obtain an answer, the reasoning section that generates an inquiry to verify the hypothesis generated by investigating the cause of failure by inference and the answer is completed When this is done, an inference control unit for displaying the end of the inquiry to the user on the display unit is provided.

[0009]

[Operation] In the failure diagnosis device according to the present invention, for the input failure phenomenon, the knowledge data stored in the knowledge base section is used to search the cause of the failure by inference to generate a hypothesis and answer the inquiry. When the hypothesis is obtained and the hypothesis is verified, when the inquiry regarding the user is completed, it is displayed that the inquiry regarding the user is completed.

[0010]

Embodiments of the present invention will be described below with reference to the drawings.

In the present embodiment, description will be given while describing a defective phenomenon of a fuel system of an aircraft as an example of a failure diagnosis target.

As shown in FIG. 8, the failure diagnosis apparatus A according to this embodiment comprises an apparatus body 1 and an input pen 2, and information is input to the apparatus body 1 using the input pen 2. The touch screen 1a is provided.

The failure diagnosis device A is installed in an airport maintenance department or the like, and when a trouble phenomenon is input to the touch screen 1a by using the input pen 2, the built-in computer causes the trouble phenomenon or the location of the trouble. To support the maintenance staff by displaying necessary information such as the search result and the inspection procedure on the touch screen 1a.

As shown in FIG. 1, the computer incorporated in the apparatus main body 1 has a window processing section 12, a system control section 13, an inference mechanism section 14, a technical information collecting section 15, and a knowledge as a function for executing a failure diagnosis. A base section 16 and an operation record data section 17 are configured. The touch screen 1a includes an input unit 11a and a display unit 11b.

The window processing section 12 is provided with a character recognition section 12a and an operation input section 12b as preprocessing, and a display control section 12c as postprocessing.

In the character recognition unit 12a, handwritten characters such as a trouble phenomenon input by the maintenance staff with the input pen 2 in the pen input window (see FIG. 11) displayed on the touch screen 1a are converted into character codes, The commands are output to the system control unit 13. When the graphics or menu displayed on the touch screen 1a is selected by the input pen 2 in the operation input unit 12b, commands corresponding to the graphics or menu are output to the system control unit 13. Further, the display control unit 12c causes the display unit 11b to display characters, graphics and the like based on the signal output from the system control unit 13.

The system control unit 13 includes a man-machine interface control unit 13a, an operation mode control unit 13b, and a system management unit 13c.
The man-machine interface control section 13a performs execution processing according to the commands from the window processing section 12. Alternatively, it outputs character data, graphics data, etc. to the display control unit 12c. The operation mode control unit 13b controls the operation mode of the entire device including peripheral devices such as interruption / restart of diagnostic processing, printing of maintenance records, and data transfer of the order management system according to the use mode selected by the maintenance personnel. To do. The system management unit 13c manages the entire system such as the operating state of the system and data management.

Further, the inference mechanism section 14 is provided with a character string retrieval section 14a, a rule-based inference section 14b, a case-based inference section 14c, and an inference control section 14d.

In the character string search unit 14a, the character string representing the trouble phenomenon input by the maintenance personnel is decomposed using the separation characters ("."",""Ga""wa" etc.) registered in advance, Using this decomposed character string, a character string that is the same as or similar to the above character string is extracted from the knowledge data stored in each of the knowledge data storage units 16a to 16c of the knowledge base unit 16 described later as a character string unit, The search is performed in word units or character units, and the knowledge data stored in each of the knowledge data storage units 16a to 16c is totaled.

The rule-based reasoning unit 14b and the case-based reasoning unit 14c use knowledge data to infer the cause of failure or the place of failure by inference, generate a hypothesis, and conduct an inquiry to verify the generated hypothesis. Generate candidates (details will be described later in the flowchart).

The hypothesis in the rule-based reasoning unit 14b is
Failure tree analysis (fault tree analysis, hereinafter abbreviated as “FTA”) type knowledge data storage section 16b provided in the knowledge base section 16 and failure mode influence analysis (certainty matrix) ;Less than,
"FMECA") type knowledge data storage unit 16c
It is generated by investigating the cause or location of the failure by inference using the knowledge data stored in the.

Further, the hypothesis in the case-based reasoning unit 14c is based on the defect phenomenon retrieved by the character string retrieval unit 14a.
It is generated by searching the knowledge data stored in the diagnostic case type knowledge data storage unit 16a of the knowledge base unit 16 for a phenomenon having the same or similar phenomenon.

Then, the inference control section 14d judges the consistency of the hypotheses generated by the inference sections 14b and 14c. If the hypotheses are consistent, this hypothesis is output as a conclusion hypothesis, and an inspection item If yes, narrow down the content of the interview and verify the conclusion hypothesis.

The technical information collector 15 is a data collector 15
a, the case registration unit 15b. The data collection unit 15a collects data input during maintenance work, such as defective items, inspection points, and measurement values, which the maintenance personnel input to the device during failure investigation. The case registration unit 15b registers the results (both success cases and failure cases) searched for in the failure diagnosis as diagnosis cases in the knowledge data of the diagnosis case type knowledge data storage unit 16a described later.

The knowledge base unit 16 includes a diagnostic case type knowledge data storage unit 16a for storing diagnostic case type knowledge data, an FTA type knowledge data storage unit 16b for storing FTA type knowledge data, and an FMEC for storing FMECA type knowledge data.
It is composed of an A-type knowledge data storage unit 16c and an electronic manual data storage unit 16d that stores electronic manual data.

The above-mentioned diagnostic case type knowledge data is a data base that summarizes the search results of past failure causes as examples,
As shown in FIG. 12, a failure phenomenon (or a location where the failure has occurred), a failure cause of the failure and its remedy, a defective component, a type of knowledge source, and the like are stored for each diagnostic case. In addition, as a knowledge source of this diagnostic case data,
There are defect record sheets, maintenance record sheets, interviews with maintenance staff, etc.

As shown in FIG. 10, the defect recording form 21 is provided with a column for recording the "defects and inspection points" found by the occupant and a column for recording the "procedures" performed by the maintenance personnel. ing. The maintenance record sheet records "defective phenomena" that occurred at the time of inspection, as well as "defective parts" and "fault status" entered in the department that performed the work.

In the interview, know-how such as non-textualized maintenance procedures and trouble investigations conducted for the maintenance personnel are collected and reflected in the diagnosis case.

The FTA-type knowledge data stored in the FTA-type knowledge data storage unit 16b is designed to analyze design materials and experience of experienced maintenance personnel, and to logically identify failure phenomena and failure causes for each component system. 15 and is expressed as a set of rules. As shown in FIG. 15, each component is classified into rules (rules 1 to 6 in the figure), and each rule is connected in a chain through an intermediate hypothesis. Has been. For example, rule 2 indicates a conclusion hypothesis (fuel leakage, etc.) when “booster / pump abnormality” is used as an intermediate hypothesis, and rule 4
Indicates the conclusion hypothesis (improper tightening, internal pump failure, etc.) when "fuel leakage" is used as the intermediate hypothesis.

On the other hand, the FMECA type knowledge data is expressed in a matrix form, and the experience of skilled maintenance personnel and the reliability information of parts or systems are analyzed, and as shown in FIG. In the tabular form of so-called FMECA table, which classifies the cause and the failure cause for each part or system, the failure mode column describes the failure mode of the part or system, the effect of the failure, and the method of detecting the failure. Has been done. In addition, the certainty factor is specified inside each grid. This certainty factor is set in consideration of MTBF (mean time between failures) of parts or systems, the number of possible causes of failure for the same failure phenomenon, or the number of times failures have actually occurred. The degree indicates the depth of the causal relationship between the failure phenomenon and the cause of failure.

Further, the computerized manual data is data for inquiry such as trouble occurrence status, inspection items of component parts and the like, and text and graphics data representing replacement or assembling procedures of the component parts. As shown in FIG. 26, on the touch screen 1a of the apparatus body 1, data such as the graphic of the booster pump and the inspection procedure of the booster pump is read from the electronic manual data and displayed in the window.

The operation record data section 17 includes a maintenance record data storage section 17a and a work progress temporary storage section 17b.
And the maintenance record data storage section 17a.
Then, the maintenance result such as the measures against the failure phenomenon, the inspection result, and the condition of the trial run is stored for each case. Further, in the work progress temporary storage unit 17b, for example, in the case of interruption for arranging replacement parts during maintenance and then restarting the failure diagnosis, it is possible to continue from the interrupted maintenance work. In order to achieve the above, the progress of the maintenance performed by the maintenance staff or the maintenance status is sequentially stored.

Next, the fault diagnosis procedure will be described with reference to FIGS.
It will be described in accordance with the flowchart of. In the present embodiment, the malfunction of the fuel system of the aircraft will be described as an example.

This failure diagnosis is executed in accordance with the inference processing routine shown in FIGS.

When the power switch of the failure diagnosing device A is turned on, a use mode selection screen is displayed on the touch screen 1a of the device main body 1 as shown in FIG. When "Start" is selected (pointed) by the input pen 2, a window for inputting a defect phenomenon and a pen input window for inputting this defect phenomenon in text representation are displayed and inferred, as shown in FIG. The process is started.

In step S1, necessary items such as the movable state of the system of the aircraft obtained by referring to the handed defect recording form 21 (see FIG. 10) and the like, the occupant (user).
The problem phenomenon (symptom) transmitted from the etc., or the answer to the inquiry displayed in step S14 described later,
The maintenance staff uses the input pen 2 to touch the touch screen 1a.
To enter.

After the maintenance staff completes the inspection, maintenance record data such as the treatment and the trial run status can be written in the action column of the trouble recording slip 21 shown in FIG. 10 (see FIG. 30). .

On the other hand, in step S2, symptoms such as measured values obtained by the tester connection are directly input according to the inspection instruction based on the inquiry displayed in step S14 described later.

Then, when the necessary items have been entered in the fields such as the trouble phenomenon input window on the touch screen 1a, and the "end input" button displayed on the screen is pointed by the input pen 2, the entered information is entered. (date,
(Mission, contents, etc.) is stored in the memory in step S3 as input data.

Next, in step S4, the degree of similarity between the trouble phenomenon input in step S1 and stored in step S3 and the knowledge data stored in each of the knowledge data storage units 16a to 16c is calculated.

The calculation of the similarity is performed by the character string search unit 14a.
Is performed by the following procedure.

(1) First, each of the above knowledge data storage units 16a
Character strings (sentences) whose similarity is to be calculated are taken out from the respective knowledge data of 16c. Each character string is provided with an ID (self-certification) number for associating with the knowledge data stored in the knowledge data storage units 16a to 16c.

(2) Next, the character string to which the ID number is given is decomposed into each unit of string, word and character, and stored in the working memory for each knowledge data. The "disassembled character string" stored in each working memory has the same ID number as that before disassembly.

Here, the "string" refers to the character string itself, and the "word" is a blank character or a pre-registered separating character (".", ",", "Ga", " ”
Etc.), for example, the string "engine does not start"
Is disassembled into "engine" and "without starting".

The character means that a character string is decomposed into a predetermined number of characters. For example, the character string "engine does not start", "engine""starts""does not move", or """"Njin""starts""without", or
Disassemble every 3 characters such as "En", "Jin ga", "Start", "Zu", etc.

(3) Then, the "ignored word (" but "," iwa ", etc.) registered in advance is deleted from the" decomposed character string "stored in the working memory.

(4) After that, the "decomposed character string" is replaced by using the "synonymous phrase (" abnormal "" is regarded as "fault" etc.) registered in advance ".

(5) On the other hand, the character string of the trouble phenomenon (symptom) input by the maintenance worker is decomposed into each unit of string, word and character, as in the above (1) to (4).

(6) Then, the "decomposed character string" stored in the working memory is searched using the decomposed character string of the trouble phenomenon.

For example, the similarity between the character string extracted from the knowledge data stored in each of the knowledge data storage units 16a to 16c and "The engine does not start" input by the maintenance worker is as follows. Become.

[0051]

(7) Next, data that completely matches in each unit of string, word, or character is totaled for each ID number, and the totaled result is output to the corresponding inference units 14b, 14c as the similarity. . When totaling, the weighting coefficient is used for each string, word, or character.

As a result, the similarities between the input failure phenomena "fuel depletion""left tank not consumed but consumed only from the right" and the knowledge data stored in the knowledge data storage units 16a to 16c are as follows. become.

Among the knowledge data stored in the diagnostic case type knowledge data storage unit 16a, the diagnostic cases for which similarity is calculated are as shown in FIG. 12, and the similarity of each diagnostic case is The value becomes 13. In this, case-1048
“Cruising at 3000 ft” “Left tank does not consume fuel”
Is the highest similarity, that is, the case where the input failure phenomenon and symptom are the closest.

Further, in the knowledge data stored in the FTA type knowledge data storage unit 16b, the tree for which the similarity is calculated has the "fuel system malfunction" as the top event, as shown in FIG. It is a tree composed of a chain of rules, and the similarity of each hypothesis is as follows.

1) Rule 5 "Internal defect in the pump itself" →
3, 2) "Fuel leakage", which is an intermediate hypothesis between rules 2 and 4 →
40, 3) Rule 3 "fuel leak" → 40, 4) Intermediate hypothesis between rule 1 and rule 2 "Booster pump abnormality" → 3, 5) Intermediate transfer hypothesis between rule 1 and rule 3 "Transfer・ Pump error "→ 3, 6) Rule 1 i)" Fuel shut off valve error "→ 35, ii)" Fuel sub-tank error "→ 36, iii)" Fuel indicating system indication error "→ 38 ,.

On the other hand, the FMECA type knowledge data storage unit 16
In the knowledge data stored in c, the phenomenon for which the similarity is calculated is as shown in FIG. 18, and the similarity is most “fuel piece reduction” as shown in FIG. It shows a high value.

The knowledge data stored in each of the knowledge data storage units 16a to 16c in step S4,
When the similarity with the failure phenomenon is calculated, the process of searching the cause of failure by inference to generate a hypothesis based on the knowledge data stored in the respective knowledge data storage units 16a to 16c is the next step S5. , S6, S7 are executed in parallel.

That is, in step S5, the knowledge data stored in the diagnostic case type knowledge data storage section 16a is used to search the cause of failure by case-based reasoning and generate a hypothesis. In step S6, the knowledge base stored in the FTA-type knowledge data storage unit 16b is used to search the cause of failure by rule-based reasoning and generate a hypothesis. Further, in step S7, the cause of failure is searched for by rule-based reasoning using the knowledge base stored in the FMECA type knowledge data storage unit 16c, and a hypothesis is generated.

First, generation of a hypothesis by the diagnosis case inference in step S5 will be described. This diagnostic case inference is executed by the case-based inference unit 14c, and is specifically executed according to the hypothesis generation routine by the diagnostic case inference shown in FIG.

In step S31, hypotheses are narrowed down based on the similarity of each case of the knowledge data stored in the diagnostic case type knowledge data storage unit 16a calculated in step S4 of the inference processing routine. The narrowing down of this hypothesis is judged by whether the similarity is equal to or more than a preset "threshold value". For example, if the "threshold value" is 10,
2. As shown in FIG. 13, “case-1048” is a hypothesis generated by diagnostic case inference. Incidentally, FIG. 12 and FIG.
In the knowledge data shown in FIG. 3, only one case exceeds the “threshold value”. However, if there are multiple cases having a similarity higher than this “threshold value”, they are all diagnostic cases. It is a hypothesis based on inference.

After that, in step S32, the reliability of the hypothesis narrowed down in step S31 is calculated, and the inquiry candidates necessary for verifying this hypothesis are generated. The above reliability is based on other inference (FTA inference or FM
It serves as a reference when resolving the conflict with the hypothesis obtained by ECA inference), and is calculated by multiplying the similarity calculated in step S4 of the above inference processing routine by a coefficient. In addition, the above-mentioned interviews include those related to the passenger (user) who first detected the failure and those related to maintenance personnel who disassemble the equipment. For example, the narrowed down hypothesis is "Case-1048". Then, a plurality of candidates for grasping the inspection location for identifying the abnormality of the booster / pump and the abnormality occurrence state are designated as the inquiry candidate.

In this embodiment, as shown in FIG.
The coefficient used when calculating the reliability is 1.

Then, the cases narrowed down in step S31 are output to the inference control section 14d as "hypotheses by diagnosis case inference", and the process returns to the inference processing routine.

Next, generation of a hypothesis by FTA inference in step S6 will be described. This FTA inference is executed by the rule-based inference unit 14b, and is specifically executed according to the hypothesis generation routine by FTA inference shown in FIG.

First, in step S41, a rule having "fuel system malfunction" as a top event in the knowledge data stored in the FTA type knowledge data storage unit 16b calculated in step S4 of the inference processing routine is used. Hypotheses are narrowed down by selecting a hypothesis having a similarity equal to or higher than a preset “threshold” based on the similarity of each hypothesis of a tree formed by a chain.

For example, when the "threshold value" is set to 15,
In the FTA type knowledge data of FIG. 15, the above-mentioned a) “fuel leakage”, which is an intermediate hypothesis between rules 2 and 4, b) “fuel leakage” in rule c) i) in rule 1, i) “fuel shut off. "Valve abnormality" ii) "Fuel sub-tank abnormality" iii) "Faulty indication of fuel indicating system" is narrowed down.

Then, in step S42, a route connecting the hypotheses narrowed down in step S41 is searched. In FIG. 15, the “fuel system failure”, which is the top event, is the “failure phenomenon” of this time, and the root extending from the failure phenomenon to the left in the figure has a causal relationship with this phenomenon, that is, It is a "hypothesis". As shown in FIG. 16, the routes connecting the hypothesis selected in step S41 and the above-mentioned trouble phenomenon are 5 of routes 1 to 5.
Get on the street.

Then, in step S43, the completeness of the route searched in step S42 is calculated. The higher the degree of perfection, the stronger the connection (causal relationship) between the failure phenomenon and the cause of failure, the higher the value. The completeness of the route searched in FIG. 16 is as follows. 1) Route 1 → 50 2) Route 2 → 50 3) Route 3 → 50 4) Route 4 → 30 5) Route 5 → 30

Then, in step S44, the hypotheses are narrowed down based on the completeness based on whether or not the completeness is equal to or more than a preset "threshold value". For example, when the "threshold value" is set to 20, all of the routes 1 to 5 are targeted.

Next, in step S45, the reliability of each of the hypotheses narrowed down in step S44 is calculated and an inquiry candidate for hypothesis verification is generated. The reliability is set by multiplying the completeness by a coefficient. For example, when the "threshold" is 20 and the coefficient is 1, as shown in FIG. The “hypothesis” covers all routes 1 to 5. In addition, as for the generation of the inquiry candidate, for example, as shown in FIG.
In the case of [fuel leakage], which is linked to the “booster / pump abnormality”, which is the intermediate hypothesis of [1] by a rule, when the conclusion hypothesis of rule 4 is chained, it is performed by designating a portion that identifies the booster / pump abnormality.

Then, each of these hypotheses is output to the inference control section 14d as a "hypothesis by FTA inference", and the process returns to the inference processing routine.

Next, step S of the above inference processing routine.
Generation of a hypothesis by FMECA inference performed in 7 will be described. This FMECA inference is executed by the rule-based inference unit 14b similarly to the FTA inference, and specifically, it is performed according to a hypothesis generation routine by FMECA inference shown in FIG.

First, in step S51, the phenomena to be diagnosed this time are narrowed down from each phenomenon of the knowledge data stored in the FMECA type knowledge data storage unit 16c. This phenomenon is narrowed down by selecting a phenomenon whose similarity is equal to or more than a preset "threshold" based on the similarity calculated in step S4 of the above inference processing routine for the phenomenon corresponding to the defective phenomenon. To do. For example, when the “threshold” is set to 10, the so-called FM shown in FIG.
The phenomena displayed in the ECA table are narrowed down to "fuel reduction", "fuel depletion", and "fuel tank remaining amount cannot be corrected" (see FIG. 19).

Then, in step S52, the certainty factor corresponding to the phenomenon narrowed down in step S51 is set to the FM.
Obtained from the ECA table. For example, in the so-called FMECA table shown in FIG. 18, the certainty factor corresponding to “fuel reduction” is 1
6,21,63, the certainty factor corresponding to "fuel depletion" is 5
0, 31, 46, and the certainty factors corresponding to "fuel tank remaining amount cannot be corrected" are 40, 60.

Then, in step S53, a certainty factor equal to or higher than a preset "threshold value" is selected from the above certainty factors to narrow down the hypotheses. For example, the above "threshold"
18 is set to 20, as shown in FIG. 18, the certainty factor surrounded by a thick frame is targeted, and in step S54, the component and the cause corresponding to this certainty factor are selected.

Next, in step S55, the reliability of the part or cause selected in step S54 is calculated, and the inquiry candidates are generated, and the reliability and hypothesis are set as "hypothesis by FMECA inference", for example, as shown in FIG.
The data shown in the above is output to the inference control unit 14d,
Return to the above inference processing routine.

In the present embodiment, the reliability is calculated by multiplying the sum of the values obtained by multiplying the similarity and the certainty factor by the coefficient, which is shown in the table below.

[0079]

When the hypotheses are generated in steps S5, S6 and S7, the process proceeds to step S8 of the inference processing routine shown in FIG. 2 to judge whether the generated hypotheses conflict with each other. Is resolved according to a preset standard. This hypothesis conflict resolution is executed by the inference control unit 14d shown in FIG. 1, and is specifically performed according to the hypothesis conflict resolution routine of FIG.

First, in step S61, the hypotheses generated in steps S5, S6, and S7 are collected.
The hypotheses generated in steps S5, S6, and S7 described above are aggregated for each inference, for example, as shown in the table in FIG.
Ranking is performed according to the calculated reliability.

Then, in step S62, the consistency of the hypotheses generated in steps S5, S6, and S7 is obtained from the defect target, the attribute, and the like. For example, in FIG. 21, the rank 1 of the hypothesis based on the diagnostic case inference and the rank 1 of the hypothesis based on the FMECA inference are consistent in that the defective component is the “booster pump”, but the rank of the hypothesis based on the diagnosis case inference is consistent. 1 and the hypothetical rank 1 based on FTA inference are common in that the defective phenomenon is "a malfunction of the fuel system", but the defective parts compete with each other. Similarly, in order 1 of the above-mentioned hypothesis based on FTA inference and the hypothesis based on FMECA inference, defective parts are in conflict.

Next, in step S63, the consistency of the hypotheses calculated in step S62 is collated with a preset "standard of judgment of consistency" to determine whether or not there is consistency. In this embodiment, the "matching criterion" is defined as "all defects having the highest reliability of the hypothesis in each inference match", and the matching is judged according to this definition.

As a result, for example, as shown in FIG.
If all the hypotheses of rank 1 generated by each inference do not match, it is determined in step S64 that there is no consistency, the process proceeds from step S64 to step S65, the inference frequency measurement count value C is incremented, and step S66 is performed. Go to.

In step S66, the inference count measuring count value C is compared with the set value N. If C≤N,
It is determined that "inference is not completed", and the process proceeds to step S67. In step S67, data for re-inference is created from the hypotheses collected in step S61 according to a certain standard. When this criterion is defined as, for example, “selecting the one with the highest reliability of each hypothesis”, the re-inference data is created based on the rank 1 hypothesis by FMECA inference in the summary table of FIG. (See FIG. 22), this data is output together with the information of "inference incomplete", and the routine is exited.

On the other hand, when it is determined that C> N in the above step S66, that is, when the hypotheses do not match even after the re-inference is repeated a set number of times, the process proceeds to step S68.
The conflict is resolved according to a preset priority criterion.

In the priority order in this embodiment, the hypothesis based on the most logically constructed FTA type knowledge data is given the highest priority, and when the FTA type knowledge data does not generate a hypothesis, the FMECA type knowledge data is used. The hypothesis based on the diagnostic case type knowledge data is adopted when the hypothesis is not generated in either of the knowledge data. Then, in accordance with this priority, the hypothesis in which the conflict is resolved is output as the search result together with the information of "end of inference", and the routine is exited.

If the cause of the failure cannot be found in any of the knowledge data, step S68.
At, the information of "hypothesis not established" and "end of inference" is output, and the routine is exited.

On the other hand, in step S64, when the hypotheses generated in steps S5, S6, and S7 match, this hypothesis is used as a search result, and the process branches to step S69 to calculate the inference frequency count value C. After clearing
Output the above inquiry result together with the information of "end reasoning",
Exit the routine.

Then, step S9 of the inference processing routine.
Returning to step S10, it is determined whether "inference is completed" based on the information created in step S8. If "inference is completed", the process proceeds to step S10. If "inference is not completed", the process is completed. Return to S4.

When it is judged in step S9 that "inference is not completed" and the process returns to step S4, the trouble phenomenon stored in the memory in step S3 and the input data such as a predetermined measurement value and the step S8 ( Step S6
The similarity between the character string combining the “re-inference data” created in 7) and the knowledge data stored in each of the knowledge data storage units 16a to 16c is calculated again.

In the data for re-inference of FIG. 22, "fuel depletion", "left tank not reduced", "only consumed from right", "booster pump", and "improper operation of own" are given as character strings. , The character strings and the knowledge data storage unit 16 described above.
defect phenomenon of knowledge data stored in a to 16c,
Comparing defective parts, causes of failure, etc., the degree of similarity is calculated by logical operation or the like.

Then, according to the degree of similarity for each piece of knowledge data, the cause of the failure is sought by re-inference in steps S5, S6 and S7.

As a result, in the diagnostic case inference in step S5, the hypothesis generated based on the diagnostic case type knowledge data is not changed even at the time of re-inference, so the same inference result as the previous time is output.

On the other hand, in the FTA inference executed in step S6, as shown in FIG. 15, from the character string obtained by the similarity calculation, "fuel system failure" and "booster / pump abnormality" are "phenomenon". The causal relationship between the hypothesis that is the cause of the failure and the phenomenon is the strongest in the route 5 shown in FIG. 16. Therefore, as shown in FIG. 23, the reliability of the route 5 is as high as 80, and the FTA is high. Inference hypothesis ranking 1
become.

On the other hand, in the FMECA inference in step S7, as shown in FIG. 18, there is a character string that coincides with "fuel depletion", the hypothesis remains unchanged, and the same result is output.

As a result, in step S64 of the hypothesis conflict resolution routine of FIG. 7, which is executed in step S8, as shown in the table of FIG. The predefined "matching criterion" is satisfied, it is determined in step S64 that there is consistency, and the process branches to step S69 to clear the inference frequency measurement count value C, and then the search result. Is output together with the information of "end of inference", and the routine exits.

After that, if it is determined in step S9 that "inference is completed", the process proceeds to step S10, it is determined whether there is another inspection item, and if there is an inspection item, step S11 is performed.
It branches to and checks whether the inquiry to the user is completed.

If the inquiry to the user is not completed, the process jumps to step S13 to narrow down the contents of the inquiry, and if the inquiry to the user is completed, in step S12, for example, as shown in FIG. As described above, when the inquiry about the user is completed and the user may be released on the touch screen 1a, and the "OK" button displayed on the screen is pointed by the input pen 2, the step S1 is performed.
Go to 3 and narrow down the interview details.

The narrowing down of the contents of the inquiry in step S13 is performed by, for example, the trouble occurrence status, the booster / pump inspection, the fuel shut /
From the interview candidates such as off-valve inspection, select the one that is related to the "booster / pump abnormality" that is the conclusion hypothesis of this time, verify the conclusion hypothesis of this time, and information when creating a new hypothesis And

Then, in step S14, the contents of the inquiry narrowed down in step S13 are displayed on the touch screen 1a of the apparatus main body 1. This display is displayed as shown in FIG. 24 when the inquiry is about the user. For example, if the occurrence situation of the trouble is "high altitude", the response from the user is received. Use the input pen 2 to point to the item to be input, and input.

If the inquiry is about maintenance personnel, the contents of work such as related inspection procedures and necessary information are displayed as shown in FIG. 26, and step S1,
It returns to S2 and waits for the input of the inspection result from the maintenance staff.

Next, the maintenance person touches the touch screen 1
When the inspection result is input to the a from the input pen 2 or the tester, this data is stored in step S3, and in step S4, the input character string, the character string of "input data" up to the previous time, and the measurement result are stored. Based on this, the degree of similarity with each piece of knowledge data is recalculated, and in steps S5, S6, and S7 and below, inference is performed again based on each piece of knowledge data to investigate the cause of the failure.

When the inference is completed and the process proceeds from step S9 to step S10 and there is no inspection item for verifying the inference, the process directly proceeds to step S15 and it is determined whether the cause of the failure can be searched.

When the cause of failure can be sought, step S
16, the reasoning result and the reasoning are displayed on the touch screen 1a, for example, as shown in FIG.
After confirming this content and pointing the "OK" button displayed on the screen with the input pen 2, in step S17,
Display necessary procedures such as the procedure for replacing parts corresponding to the hypothesis. Next, in step S18, the maintenance staff waits for the input of the result of the treatment, that is, the result of whether or not the malfunction is resolved. Then, when this treatment result is input, the process proceeds to step S19, and the inquiry result is confirmed.

On the other hand, if it is determined in step S15 that the cause of the failure cannot be found by inference, then steps S16 to S18 are skipped and step S1 is executed.
Proceed to 9.

In step S19, a search result confirmation screen is displayed on the touch screen 1a. This inquiry result confirmation screen is displayed by displaying the history of inquiry, as shown in FIG. 28, for example. Incidentally, if the maintenance staff does not obtain a satisfactory result even if the parts are replaced in accordance with the inquiry result, the maintenance worker inputs the fact in step S18, and in step S19, the inquiry is made on the touch screen 1a. Displays a confirmation screen indicating that is failed. Also, in the dialog box, for example, Then, the confirmation contents for obtaining the consent from the maintenance staff are displayed.

When the maintenance staff has accepted the registration of the case, first, in step S20, the phenomenon and the cause or the part selected in the present exploration of the knowledge data stored in the FMECA type knowledge data storage unit 16c are selected. The certainty factor (see FIG. 18) connecting with is updated according to the failure investigation result of this time. That is, if this inquiry is successful, the confidence is relatively high, and if it is unsuccessful,
Make the confidence relatively low.

Next, in step S21, the diagnostic case type knowledge data storage unit 16a is set with the result of the current inquiry as a diagnostic case.
29 is added to the knowledge data stored in FIG. 29, for example, “Case-5721”. In addition, when the result of the inquiry is unsuccessful, the content thereof is described in the “cause and action” column, and in the “special note” column, “inquiry failure” is described.

Next, the process proceeds to step S22, and the history of this investigation is recorded along with supplementary information such as the date of diagnosis, the name of the person who made the diagnosis, and the like.
Memory is stored in the maintenance record data storage unit 17a, and the failure diagnosis ends.

The data stored in the maintenance record data storage section 17a can be taken out through an external printing machine or the like. For example, as shown in FIG. You can

As described above, when verifying the inference result by the inquiry, the inquiry about the user and the inquiry about the maintenance staff are performed in the order of the inference process, and the user may be released immediately when the inquiry about the user is completed. Since it is displayed, it is possible to avoid a situation in which the user is restrained despite the end of the inquiry regarding the user, and it is possible to prevent time waste.

The present invention is not limited to the above-described embodiment. For example, the knowledge base unit 16 may be used as the diagnostic case type knowledge data storage unit 16a and the FTA type knowledge data storage unit 16b, or the diagnostic case type knowledge data storage unit. Section 16a and FMEC
A type knowledge data storage unit 16c, or FTA type knowledge data storage unit 16b and FMECA type knowledge data storage unit 1
6c, or may be composed of a single piece of knowledge data.

The target equipment for failure diagnosis is not limited to an aircraft, but may be an automobile, a vehicle such as a railroad, or a ship.

[0115]

As described above, according to the present invention,
When investigating the cause of failure by inference using the knowledge data stored in the knowledge base to generate a hypothesis and obtaining a response to the inquiry and verifying the hypothesis, when the inquiry regarding the user is completed, the inquiry regarding the user is completed. Is displayed, it is possible to avoid the situation in which the user is restrained despite the end of the inquiry regarding the user, and it is possible to immediately open the user and prevent waste of time. The effect is obtained.

[Brief description of drawings]

FIG. 1 is a functional block diagram of a failure diagnosis device.

FIG. 2 is a flowchart showing an inference processing routine.

FIG. 3 is a flowchart showing an inference processing routine (continued)

FIG. 4 is a flowchart showing a hypothesis generation routine by diagnostic case inference.

FIG. 5 is a flowchart showing a hypothesis generation routine by FTA type knowledge base inference.

FIG. 6 is a flowchart showing a hypothesis generation routine by FMECA type knowledge base inference.

FIG. 7 is a flowchart showing a hypothesis conflict resolution routine.

FIG. 8 is an external view of the failure diagnosis device

FIG. 9 is an explanatory diagram showing a usage mode selection screen.

FIG. 10 is an explanatory diagram showing a defect recording form.

FIG. 11 is an explanatory diagram showing an input screen of a defect phenomenon.

FIG. 12 is an explanatory diagram showing diagnosis case type knowledge data.

FIG. 13 is an explanatory diagram showing the calculation result of the similarity in the diagnosis case type knowledge base inference.

FIG. 14 is an explanatory diagram showing a result of hypothesis generation by diagnostic case type knowledge base inference.

FIG. 15 is an explanatory diagram showing FTA type knowledge data.

FIG. 16 is an explanatory diagram of a route search result in FTA type knowledge base inference.

FIG. 17 is an explanatory diagram showing a result of hypothesis generation by FTA type knowledge base inference.

FIG. 18 is an explanatory diagram of FMECA type knowledge data.

FIG. 19 is an explanatory diagram of a calculation result of similarity by FMECA type knowledge base inference.

FIG. 20 is an explanatory diagram showing a result of hypothesis generation by FMECA type knowledge base inference.

FIG. 21 is an explanatory diagram showing aggregation of hypotheses obtained by each inference.

FIG. 22 is an explanatory diagram of data for re-inference.

FIG. 23 is an explanatory diagram showing aggregation of hypotheses obtained by re-inference.

FIG. 24 is an explanatory diagram showing an inquiry screen for users.

FIG. 25 is an explanatory diagram of a display screen showing the end of the inquiry for users.

FIG. 26 is an explanatory diagram showing an inquiry screen for maintenance personnel.

FIG. 27 is an explanatory diagram showing a display screen of inference results and reasoning.

FIG. 28 is an explanatory diagram showing a display screen for confirming the inquiry result.

FIG. 29 is an explanatory diagram of diagnosis case type knowledge data in which a new case is registered.

FIG. 30 is an explanatory diagram showing a defect recording form in which details of measures are described.

[Explanation of symbols]

 A failure diagnosis device 11b display unit 14 inference mechanism unit 14b, 14c inference unit 14d inference control unit 16 knowledge base unit

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI Technical display location G01M 19/00 Z (72) Inventor Yasuo Kagei 1-7-2 Nishishinjuku, Shinjuku-ku, Tokyo Fuji In heavy industry Co., Ltd. (72) Inventor Masaaki Furuyama 1-2-7 Nishi-Shinjuku, Shinjuku-ku, Tokyo Fuji Heavy Industry Co., Ltd. (72) In-house Kunihiro Abe 1-2-7 Nishi-Shinjuku, Shinjuku-ku, Tokyo Fuji Heavy Industries Ltd. In the company

Claims (1)

[Claims] 1. A knowledge base section (16) for storing knowledge data required for failure diagnosis, and an inference mechanism section (inference section) for inferring a failure cause corresponding to an input failure phenomenon by using this knowledge data. 14), and a failure diagnosis device that displays input / output information in the display part (11b) in the process of investigating the cause of failure by the inference mechanism part (14), at least the cause of failure in the inference mechanism part (14). The reasoning unit (14b, 14c) that generates an inquiry to verify the hypothesis generated by investigating When the inquiry regarding the user is completed in the process of obtaining the
A fault diagnosis apparatus comprising: an inference control section (14d) to be displayed on (11b).