JP3455276B2 - Fault diagnosis device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [0001] [Industrial applications] [0002] The present invention relates to a so-called expert system.
Failures that lead to malfunctions in vehicles, aircraft, etc.
The present invention relates to a failure diagnosis device that searches for the cause.
Reasoning when it can be determinedResults and inspection results and their causesMaintain
The present invention relates to a failure diagnosis device presented to a member or the like. Conventionally, this expert system has been used in vehicles.
For example, Japanese Patent Application Laid-Open No.
As disclosed in US Pat.
The root cause of the failure that is causing the phenomenon
(Failure location) using knowledge data expressed as a set of rules.
To explore or to remember past cases
There is known an object to be explored using knowledge data or the like. [0004] In such a failure diagnosis device, by inference,
When the cause of the failure can be investigated, maintenance personnel, etc.
Therefore, parts are replaced or necessary measures are taken. Soshi
When the problem is resolved,
The result of the inquiry is success. [0005] SUMMARY OF THE INVENTION However, experts
In failure diagnosis using the system, even beginner maintenance staff etc.
Investigate the cause of failure with the same maintenance capability as a skilled maintenance person.
Although it has the convenience of being able to
Simply replacing it will eliminate the problem
The basis for linking the failure phenomenon to the cause of the failure
To improve the maintenance capacity of maintenance staff etc.
The disadvantage of not being able to be achieved is likely to occur. The present invention has been made in view of such circumstances.
Logically link the failure phenomenon to the inference result.
To improve the maintenance capacity of maintenance staff etc.
With the aim of providing a fault diagnosis device
are doing. [0007] [MEANS FOR SOLVING THE PROBLEMS] To achieve the above object
In the present invention, the cause of the failure is
A knowledge base unit for storing the described knowledge data;
From the similarity between the extracted character string and the character string of the knowledge data.
A fault having an inference mechanism for searching for the cause of the fault by inference
In the diagnostic apparatus, the knowledge base unit further includes an inference
Parts assembly procedures and inspection procedures to verify the results of
Data is stored, and the inference
Output the results and terminate the inference, identify the cause of the failure.
Judge the necessity of the inspection, and when the inspection is necessary,
Inspection procedures for locations that identify product abnormalities
And the inspection result according to the above inspection procedure is input.
Then, in the character string and the inference of the inspection result, the inference mechanism section
EnterEmpoweredOf the previous input dataCharacter string
Input to the logic unit to perform inference again to find the cause of the failure
When this is possible, the inquiry results,
The cause of the inspection result is displayed. [0008] [0009] In the failure diagnosis apparatus according to the present invention, maintenance personnel and the like are not
When the character string corresponding to the condition phenomenon is input, the inference mechanism
Is stored in the knowledge base based on the input character string.
The cause of the failure is displayed in a character string corresponding to the failure phenomenon.
By using the described knowledge data,
Inference based on similarity with character strings described in knowledge data
Investigate the cause of failure more. The inference mechanism concludes
When the output is output and the inference ends, the cause of the failure is identified.
Judgment of the necessity of inspection, and if inspection is necessary,
Parts required to verify the location to identify abnormalities
Outputs the assembly procedure and inspection procedures from the knowledge base unit and performs inspection
When the inspection result according to the procedure is input, the inspection result
Inference mechanism part in character strings and inferenceEnterEmpoweredUntil last time
Input dataEnter the character string into the inference mechanism
Inference is performed, and when the cause of the failure is
The results of the inspection, the inspection results, and the causes of the inspection results are displayed.
Let me show you. [0010] [0011] Embodiments of the present invention will be described below with reference to the drawings.
I do. In this embodiment, the fuel system of the aircraft is
A description is given while describing the failure phenomenon as an example of a failure diagnosis target.
I will tell. As shown in FIG. 8, a failure diagnosis according to this embodiment is performed.
The cutting device A is composed of an apparatus main body 1 and an input pen 2.
The information is input to the main body 1 using the input pen 2.
A touch screen 1a for inputting is provided. [0014] The above-mentioned failure diagnosis apparatus A is used in an airport maintenance department or the like.
The touch panel using the input pen 2
When a malfunction is input to the screen 1a, the built-in
Computer seeks cause or location of failure
Necessary information, such as the results of the investigation and
The information is displayed on the screen 1a to assist the maintenance staff. Figure
As shown in FIG.
Is a window processing unit
12, system control unit 13, inference mechanism unit 14, technical information
Collection unit 15, knowledge base unit 16, and operation record data unit
17 are constituted. Also, the touch screen 1a
Is composed of an input unit 11a and a display unit 11b. The window processing unit 12 includes pre-processing and
Character recognition unit 12a and operation input unit 12b
And a display control unit 12c is provided as post-processing.
Have been killed. In the character recognition unit 12a, the touch screen
Window for pen input displayed on the screen 1a (see FIG. 11).
The trouble phenomenon entered by the maintenance staff using the input pen 2
Convert handwritten characters such as
Are output to the system control unit 13. Operation input
In the unit 12b, the group displayed on the touch screen 1a is displayed.
Select a prefix or menu with input pen 2
Command, the corresponding commands are controlled by the above system control.
Output to the unit 13. In the display control unit 12c,
Based on the signal output from the system control unit 13,
The display unit 11b displays characters, graphics, and the like. The system control unit 13 includes a man machine
Interface control unit 13a and operation mode control unit
13b and a system management unit 13c are provided.
In the man-machine interface control unit 13a,
Execution processing according to commands from window processing unit 12
Work. Alternatively, the character data is sent to the display control unit 12c.
And graphics data. action mode
In the control unit 13b, according to the use mode selected by the maintenance staff or the like.
Suspension / resumption of diagnostic processing and printing / ordering of maintenance records
Equipment including peripheral equipment such as data transmission of the management system
Controls the overall operating mode. In the system management unit 13c
Is the entire system, including the operating status of the system, data management, etc.
Manage. The inference mechanism 14 has a character string search function.
Unit 14a, rule-based inference unit 14b, and case base
Inference unit 14c, inference control unit 14d, and inference report generation unit
14e. In the character string search section 14a, maintenance personnel and the like enter
The character string that represents the malfunction that occurred
Decomposition using characters (“.”, “,”, “Ga”, “wa”, etc.)
Then, using this decomposed character string, a knowledge base
Each of the knowledge data storage units 16a to 16c of the unit 16 respectively
From the stored knowledge data, it is the same as the above character string
Or similar character strings,
The search is performed in units of characters or in units of characters.
Aggregation is performed for each piece of knowledge data stored in 16c. The rule-based inference unit 14 b
Fault tree analysis (fault tree provided in the knowledge base unit 16)
Analysis; hereinafter abbreviated as "FTA") type knowledge data
The knowledge data stored in the storage unit 16b and the failure mode
Impact analysis (matrix with confidence; hereinafter referred to as “FMEC
A) is stored in the type knowledge data storage unit 16c.
The cause or location of the failure using the knowledge data
Explore by inference and generate hypotheses (for more information,
This will be described later with reference to a flowchart). In the case base inference unit 14c, the character string
Same or similar to the defect phenomenon searched by the search unit 14a
Similar events are stored in the diagnosis case type knowledge
Search from knowledge data stored in data storage unit 16a
Then, a hypothesis of a failure cause or a failure location is generated. Then, the inference control unit 14d sets each of the above
Determine consistency of hypotheses generated by inference units 14b and 14c
And if the hypotheses are consistent, this hypothesis is considered the conclusion hypothesis.
And output. In the inference report generator 14e,
The inference controller 14d determines that the cause of the failure has been investigated.
When inferredThe resultFor example, the inference of FIG.resultWi
Display in window title bar. at the same time,This conclusion
In addition to the results, the inspection results and the causes of the phenomena observed during the inspectionTo
The above inferenceresultDisplay in a window. Also this inferenceConclusion
Displayed in the result windowIs the second and third failure sources
Is also generated for the cause, and the input pen 2
By selecting the “next candidate” window,
Reasoning forResults, inspection results and phenomena observed during inspection
the cause ofCan be displayed. Note that this inferenceConclusion
Results, inspection results, and causes of phenomena observed during inspectionTo generate
This will be described in steps S14 to S14 in a flowchart described later.
Details will be described in S16. The technical information collecting unit 15 includes a data collecting unit 15
a and a case registration unit 15b. Data collection
In the section 15a, the maintenance staff etc.
Items and inspection items entered from the touch screen 1a
Collect data entered during maintenance work, such as
You. In the case registration unit 15b, the inquiry result by inference (success
Cases and failure cases) as diagnostic cases
Register in the knowledge data of the disconnected case type knowledge data storage unit 16a.
You. The above-mentioned knowledge base unit 16 stores diagnosis case type knowledge.
Diagnostic case type knowledge data storage unit 16a for storing data;
FTA type knowledge data storage for storing FTA type knowledge data
Unit 16b and FMEC storing FMECA type knowledge data
A-type knowledge data storage unit 16c and digitized manual data
And an electronic manual data storage unit 16d for storing the
Has been established. The above-mentioned diagnosis case type knowledge data is obtained from a past failure source.
A database that summarizes the results of exploring factors as examples,
As shown in FIG. 12, a failure phenomenon (A
Or the location of the failure), the cause of the failure and
The stored contents, defective parts, and the type of knowledge source are stored.
ing. Note that this diagnosis case type knowledge data
Trouble report, maintenance record, maintenance personnel, etc.
Interview etc. Interviews with maintenance staff
Undocumented maintenance personnel procedures, investigation of causes, etc.
The know-how was collected and reflected in the diagnosis cases. [0027] As shown in FIG.
A column to record “defects and inspection points” discovered by the crew
And a column to record the “treatment” performed by the maintenance staff, etc.
Have been. The maintenance record sheet contains the "defects"
Phenomenon "and" Incorrect "written by the department that performed the work
The “condition part”, the “failure situation” and the like are recorded. Recorded in the FTA type knowledge data storage section 16b
The remembered FTA type knowledge data is
Analyze the experience etc. of the maintenance staff etc. and find out the trouble phenomenon and the cause of the trouble.
Analyze logically for each component system and display it as a set of rules
As shown in FIG. 15, rules for each component
(Rules 1 to 6 in the figure)
They are linked in a chain via hypotheses. For example, le
Rule 2 assumes that "booster / pump malfunction" is an intermediate hypothesis.
The conclusion hypothesis (fuel leakage etc.) is shown, and Rule 4
Conclusion hypothesis when “fuel leakage” is used as an intermediate hypothesis (not tightened)
Good, bad inside the pump, etc.). On the other hand, FMECA type knowledge data is
It is displayed in the form of a table in the form of a box.
And analyze the reliability information of the parts or the system.
As described above, the failure phenomenon and the cause of failure are
Classified, expressed in tabular form as a so-called FMECA table
In the column of failure phenomena, the failure mode of parts or
The failure, the effects of the failure, and how to detect the failure.
You. In addition, certainty is clearly indicated inside each grid.
You. This confidence is based on the MTBF (mean failure
Interval) or for the same malfunction
Consider the number of failure causes or the actual number of failure occurrences, etc.
The degree of certainty can be set as
The depth of the causal relationship with the cause of failure is shown. Further, the digitized manual data includes component parts.
Inspection, replacement or assembly procedure, and the above inferenceresult
Text and graphs showing parts names, locations, etc. corresponding to
Data, for example, as shown in FIG.
And a booth on the touch screen 1a of the device body 1.
Pump graphic and booster pump
Inspection procedures and other data from the above electronic manual data
It is read and displayed in the window. The operation record data section 17 stores a maintenance record.
Recording data storage section 17a and work progress temporary storage section 17b.
And is stored in the maintenance record data storage section 17a.
Of the measures, inspection results, and test runs
The maintenance result such as the situation is stored for each case. Also, the above work
The temporary storage section 17b includes, for example, an exchange section during maintenance.
Suspend to arrange the product and then resume fault diagnosis
In case of maintenance, continue from the interrupted maintenance work
To be able to perform
The maintenance progress or maintenance status is sequentially stored. Next, a failure diagnosis procedure will be described with reference to FIGS.
Follow the flowchart in
A description will be given while exemplifying the case. This failure diagnosis is performed according to the inference processing routine shown in FIG.
Therefore, it is executed. First, the power switch of the apparatus main body 1 is turned on.
Then, on the touch screen 1a, as shown in FIG.
The selection screen for the application mode (menu) is displayed. Soshi
And maintenance personnel touch the device main body 1 of the failure diagnosis device A.
From the menu displayed on the screen 1a, select
When "Start" is selected by the input pen 2, as shown in FIG.
Window for inputting the error phenomenon
A pen input window for inputting
The window is displayed and the inference process is started. The mechanic or the like was handed over in step S1.
Referring to a form such as the defect record form 21 (see FIG. 10),
Necessary items such as the operational state of the aircraft system
Input pen 2 to input the trouble phenomenon (symptom) reported from the staff etc.
And input to the touch screen 1a. The processing of the defect record slip 21 shown in FIG.
After the maintenance is completed by the maintenance staff,
And maintenance record data such as test operation status can be written.
(See FIG. 28). On the other hand, in step S2, a later-described step is performed.
Is obtained by a tester connection according to the medical inquiry displayed in step S12.
Enter symptoms such as measured values directly. Then, an error on the touch screen 1a is detected.
Complete the necessary items in the condition phenomena input window, etc.
And select the “End of input” window with input pen 2
Then, the entered information (date, mission, contents, etc.) is entered.
The data is stored in the memory in step S3 as force data. Next, at step S4, at step S1
Failure phenomena entered and stored in step S3
Knowledge stored in knowledge data storage units 16a to 16c
Calculate the degree of similarity between the data and the event. The calculation of the similarity is performed by the character string search unit 14a.
This is performed, for example, in the following procedure. (1) First, each of the above knowledge data storage units 16a
From which the similarity is calculated from each of the knowledge data
Extract each character string (sentence). Note that each of these strings
Are stored in the knowledge data storage units 16a to 16c.
ID (self) to associate with the knowledge data
Certificate) number. (2) Next, a sentence to which this ID number is assigned
String, string, word, and character units
For each piece of knowledge data and store it in the working memory for each piece of knowledge data.
To pay. Note that the data stored in each working memory is
The “decomposition character string” has the same ID number as the one before decomposition.
Has been granted. Here, the "string" is a character string
"Word" is a blank character, registered in advance
Separating characters (“.”, “,”, “Ga”, “ha”
)), For example, the string "Engine does not start"
Is disassembled into "engine" and "not started". [0044] A character is a character string that is divided into a predetermined number of characters.
Refers to disassembly, for example, the string "
"No", "Eng", "N-start", "No movement", or
Are "E", "Engine", "Start", "No", or "E"
Every three characters, such as "N", "Jinga", "Start", "Zu", etc.
Decompose. (3) Next, the data is stored in the working memory.
"Ignored word" registered in advance from the "decomposed character string"
Phrase ("but", "I am", etc.) ". (4) After that, the "synonyms" registered in advance
("Failure" is regarded as "Failure").
Replace "Understood String". (5) On the other hand, a malfunction phenomenon entered by a maintenance person or the like
Strings of (symptoms) can be changed to string
For each word, word, and character. (6) Then, the character of the broken down phenomenon
"Decomposed" stored in the working memory using
Character string ". For example, when an engine is
Not start ", the above-described knowledge data storage units 16a to 16c
With the character string extracted from the knowledge data stored in
The similarity is as follows. [0050] (7) Next, a string, word, or character
Total data that matches perfectly in each unit of is counted for each ID number
The aggregation results are used as similarities and the corresponding
Output to the logic units 14b and 14c. When calculating
Is the weight for each string, word, or character
This is performed using the assignment coefficient. As a result, the defect phenomena “fuel depletion” “left”
"Consumption only from the right without reducing the tank"
Kinds of events stored in knowledge data of 6a to 16c
The similarity is as follows. Stored in the diagnosis case type knowledge data storage unit 16a
Subject to similarity calculation in the knowledge data
Excerpts of the diagnosis examples are shown in FIG.
As a result of calculating the similarity of the disconnected cases according to the above criteria,
As shown in FIG. Among them, “-3” in Case 1048
Cruising at 2,000 ft "and" No fuel consumption on left tank "
High similarity, that is, the most
This is an approximate case. The FTA type knowledge data storage unit 16b stores
Among the stored knowledge data, the similarity
As shown in FIG. 15, the tree shown in FIG.
Tree consisting of a chain of rules with
The similarity of each hypothesis is as follows. 1) Rule 5 “Internal failure of pump itself” →
3, 2) The intermediate hypothesis between Rule 2 and Rule 4 is "fuel leakage" →
40, 3) Rule 3 "fuel leak" → 40, 4) An intermediate hypothesis between Rule 1 and Rule 2
Abnormal "→ 3, 5) "Transf is an intermediate hypothesis between Rule 1 and Rule 3.
Pump failure "→ 3 6) Rule 1 i) “Fuel shut-off valve error” → 35, ii) “Fuel sub tank abnormality” → 36, iii) "Incorrect indication of fuel indicating system" → 38, It is. On the other hand, the FMECA type knowledge data storage 16
c in the knowledge data stored in c.
Elephant phenomena are as shown in FIG.
Is the highest value of “fuel loss” as shown in FIG.
Is shown. In step S4, each knowledge data storage unit 1
6a to 16c and the fault data
When the similarity with the elephant is calculated, the next steps S5, S5
6 and S7 are executed in parallel (concurrent processing).
In steps S5, S6, and S7, the respective knowledge data storage units
Based on knowledge data stored in 16a to 16c
Then, the cause of the failure is investigated by inference to generate a hypothesis. That is, in step S5, the diagnosis
Knowledge data stored in the example-type knowledge data storage unit 16a
Search for the cause of failure by case-based reasoning
Generate a theory. In step S6, the FTA type knowledge data
Using the knowledge base stored in the data storage unit 16b
Investigate failure causes and generate hypotheses by rule-based reasoning
I do. Further, in step S7, the FMECA type knowledge data
Using the knowledge base stored in the data storage unit 16c.
Search for failure causes and generate hypotheses by rule-based inference
You. First, the diagnosis case inference in step S5 is performed.
Generation of a hypothesis will be described. This diagnosis case inference
This is executed by the example-based inference unit 14c.
Is a hypothesis generation routine based on the diagnosis case inference shown in FIG.
It is performed according to. In step S31, the above inference processing routine
Diagnosis case type knowledge data storage unit calculated in step S4
The similarity for each case of the knowledge data stored in 16a
A hypothesis is narrowed based on the hypothesis. Refine this hypothesis
Is determined based on whether or not the similarity is equal to or greater than a preset threshold.
Refuse. For example, if the "threshold value" is set to 10, FIG.
2. As shown in FIG. 13, “Case-1048” is a diagnosis case
It is a hypothesis generated by inference. 12 and FIG.
In the case of the knowledge data shown in Fig. 13, the case where the threshold is exceeded
There was only one, but a class higher than this "threshold"
If there are multiple cases with similarity,
This is a hypothesis based on inconsistent case reasoning. Thereafter, in step S32, the above steps
The reliability of the hypothesis narrowed down in S31 is calculated. This message
The reliability is based on other inferences (FTA inference or FMECA inference).
Criteria for resolving conflicts with the hypotheses obtained by
In step S4 of the above inference processing routine,
It is calculated by multiplying the calculated similarity by a coefficient. In addition,
In the present embodiment, the reliability is calculated as shown in FIG.
In this case, the coefficient is set to 1. Then, in the step S31, the narrowing down is performed.
Inference control unit
14d, and outputs to step S8 of the above inference processing routine.
Return to Next, a provisional calculation based on the FTA inference in step S6 is performed.
Generation of the theory will be described. This FTA inference is based on the rules
-This is executed by the base inference unit 14d.
Is a hypothesis generation routine based on FTA inference shown in FIG.
This is done accordingly. First, in step S41, the above inference processing
Of FTA type knowledge data calculated in step S4 of the routine
"Fuel" in the knowledge data stored in the storage unit 16b
Consists of a chain of rules with "system failure" as the top event
Based on the similarity of each hypothesis in the tree
Select a hypothesis that is equal to or greater than a preset "threshold"
Perform refinement. For example, if the “threshold value” is 15,
In the FTA type knowledge data of FIG. 15, as described above, a) Intermediate hypothesis between rule 2 and rule 4 "fuel leakage" b) Rule 3 “Fuel leakage” c) of rule 1 i) `` Fuel shut-off valve error '' ii) "Fuel sub tank error" iii) `` Incorrect indication of fuel indication system '' Is narrowed down. Then, in step S42, the above steps
Search for a route linking each hypothesis narrowed in S41
I do. In FIG. 15, the top event, “Failure in fuel system,
"" Is the "fault phenomenon" this time.
The root extending to the left of the figure has a causal relationship to this phenomenon.
, That is, a “hypothesis”. Above
Link the hypothesis selected in step S41 with the above-mentioned problem
As shown in FIG.
It becomes street. Then, in step S43, the above steps
The completeness of the route searched in S42 is calculated. This complete
The degree is the connection (causality) between the failure phenomenon and the cause of the failure.
The higher the value, the higher the value. Of the route searched in FIG.
The completeness is as follows. 1) Route 1 → 50 2) Route 2 → 50 3) Route 3 → 50 4) Route 4 → 30 5) Route 5 → 30 Next, in step S44, based on the degree of completeness,
Hypothesis narrowing based on whether all degrees are equal to or greater than a preset "threshold"
Perform the insertion. For example, when "threshold" is set to 20,
, All of the above routes 1 to 5 are targeted. Next, in step S45, the above steps
The reliability of each hypothesis narrowed down in S44 is calculated,
Each of these hypotheses is referred to above as "hypothesis by FTA inference".
Output to the control unit 14d, and execute the inference processing routine.
Return to step S8. The reliability is obtained by multiplying the perfection by a coefficient.
For example, the above “threshold value” is set to 20,
When the coefficient is 1, as shown in FIG.
A hypothesis based on A inference ”covers all routes 1 to 5
You. Next, step S of the inference processing routine is performed.
The generation of hypotheses by FMECA inference performed at 7
explain. This FMECA inference is the same as the above FTA inference.
As described above, the rule-based inference unit 14b executes
Specifically, generation of a hypothesis by FMECA inference shown in FIG.
It is performed according to a routine. First, in step S51, the FMECA type
Of the knowledge data stored in the knowledge data storage unit 16c.
From the phenomena, narrow down the phenomena to be diagnosed this time.
U. The narrowing down of this phenomenon is the phenomenon corresponding to the malfunction phenomenon.
Is calculated in step S4 of the above inference processing routine.
Based on the degree, the degree of similarity is determined by a preset “threshold
This is done by selecting phenomena equal to or greater than the value For example, "Shiki
Assuming that the “value” is 10, as shown in FIGS.
In the phenomenon displayed in any FMECA table, the message "Fuel reduction
"Low", "Fuel depletion" and "Unable to correct fuel tank remaining"
Narrowed down to Next, in step S52, the above steps
The certainty factor corresponding to the phenomenon narrowed down in S51 is calculated using the FM
Determined from the ECA table. For example, the so-called
The FMECA table shows that the confidence level corresponding to “fuel reduction” is 1
6,21,63, confidence level corresponding to "fuel depletion" is 5
0, 31, 46, "Unable to correct fuel tank remaining amount"
Is 40,60. Then, in step S53, the above-mentioned certainty factors
Select a certainty factor that is equal to or greater than the preset "threshold value"
Then, hypotheses are narrowed down. For example, the above "threshold"
Is set to 20, as shown in FIG.
In step S54, this confidence
Select the parts and causes corresponding to the degrees. Next, in step S55, the above steps
Calculate the reliability of the parts or causes selected in S54
Then, the reliability and the hypothesis are referred to as “provisional by FMECA inference”.
For example, as shown in FIG.
Output to the inference control unit 14d, and executes the inference processing routine.
It returns to step S8. Note that, in this embodiment, the above-mentioned reliability
Is obtained by multiplying the sum of values obtained by multiplying
It is as shown in the table below. [0076] Then, the process proceeds to step S8 of the inference processing routine shown in FIG.
Returning, the hypotheses generated in steps S5, S6, and S7 are
Judge whether there is a conflict, and if there is a conflict, set in advance
Eliminate according to standards. This hypothesis conflict resolution is shown in Figure 1.
This is executed by the inference control unit 14d shown in FIG.
Is performed according to the hypothesis conflict resolution routine of FIG. First, in step S61, each of the above steps
The hypotheses generated in S5, S6, and S7 are collected.
The temporary data generated in each of the above steps S5, S6 and S7
Theories are aggregated for each inference, for example, as shown in the table shown in FIG.
And are ranked according to the calculated reliability. Then, in step S62, each of the above steps is performed.
Check the consistency of the hypotheses generated in steps S5, S6, and S7.
From attributes, attributes, etc. For example, in FIG.
Rank 1 of hypothesis by case inference and provisional by FMECA inference
The first rank of the theory is that the faulty part is "Booster pump"
Consistent in some respects, but the order of hypotheses based on diagnostic case inference
Rank 1 and rank 1 of the hypothesis based on FTA inference
Are common in terms of "fuel system failure"
However, defective parts are competing. Similarly, FTA inference
And the hypothesis based on FMECA inference
Defective parts are competing. Next, when the operation proceeds to step S63, the step
The consistency of the hypothesis calculated in step S62 is
To determine whether there is consistency.
Perform settings. In the present embodiment, the "consistency determination criteria"
All the defects with the highest reliability of the hypothesis in the inference match
To comply with this definition.
Judge. As a result, for example, as shown in FIG.
If all the hypotheses of rank 1 generated by each inference do not match
In step S64, it is determined that there is no consistency.
Proceeding from S64 to step S65, the inference count measuring cow
Increments the count value C and proceeds to step S66.
No. In step S66, the above inference frequency measurement
The count value C is compared with the set value N, and when C ≦ N,
It is determined that "inference has not been completed", and the flow advances to step S67. Stay
In step S67, the hypothesis collected in step S61
Create data for re-inference according to certain criteria. This
The criterion is, for example, “The reliability of each hypothesis is the highest
If you define as "select one," in the summary table of FIG.
Is re-estimated based on the hypothesis of rank 1 by FMECA inference.
Rational data is created (see FIG. 22), and this data is
Step S:
Return to 9. On the other hand, at step S66, it is determined that C> N.
Rejection, that is, re-inference
If the hypotheses do not match, the process proceeds to step S68,
Resolve conflicts according to preset priority criteria
You. The priority in this embodiment is the most logically
Best hypothesis based on FTA-type knowledge data
No hypothesis is generated with this FTA type knowledge data
In case, adopt hypothesis based on FMECA type knowledge data
In addition, a hypothesis arises in both of these knowledge data.
If not, hypotheses based on diagnosis case type knowledge data
Is adopted. And resolve conflicts according to this priority
As a result of exploring the hypothesized hypothesis, information
Also saves the memory and exits the routine. Note that this knowledge
If the cause of failure cannot be investigated in any of the data
In step S68, "hypothesis not established" and "
The information of "End of theory" is stored, and the process returns to step S9. On the other hand, in step S64, each of the above steps is performed.
When the hypotheses generated in steps S5, S6, and S7 match
Makes this hypothesis a search result and branches to step S69.
After clearing the count value C for measuring the number of inference times,
Store the results of the above inquiry together with the information
Then, the process returns to step S9. Then, step S9 of the inference processing routine
Returning to, whether "inference is completed" is created in step S8 above.
Judgment is made based on the information obtained, and if
Proceed to step S10, and if "inference not completed",
It returns to step S4. Then, in the above step S9, "inference not completed"
If the process returns to step S4 after determining "
Failure phenomena stored in memory in S3 and predetermined measurement values
And the like, and the above-mentioned step S8 (step S6
Characters combined with "Re-inference data" created in 7)
Column, and stored in each of the knowledge data storage units 16a to 16c.
The similarity with the existing knowledge data is calculated again. In the data for re-inference shown in FIG.
"Fuel depletion", "Left tank not reduced", "Only from right
Consumption, booster pump, own malfunctioning
The respective character strings and the respective knowledge data storage units 16
defect phenomena of knowledge data stored in a to 16c,
Comparing defective parts, failure causes, etc., and performing logical operations, etc.
Calculate the similarity. Then, according to the similarity of each knowledge data,
In steps S5, S6, and S7, the
Investigate the cause of the obstacle. As a result, the diagnosis case inference in step S5
Then, even at the time of re-inference, based on the diagnosis case type knowledge data,
Since the hypothesis generated is not changed, the same
The inference result is output. On the other hand, the FTA estimation executed in step S6
In theory, as shown in FIG.
From the character string, “Failure in fuel system” and “Booster
Pump abnormality) becomes a phenomena,
The causal relationship with the phenomenon is the strongest in route 5 shown in FIG.
Therefore, as shown in FIG.
Is a high value of 80, and rank 1 of the hypothesis by FTA inference
become. On the other hand, the FMECA inference in step S7
Is a sentence corresponding to "fuel depletion" as shown in FIG.
There is a string, the hypothesis has not changed, and a similar result is output.
It is. As a result, FIG.
In step S63 of the hypothesis conflict resolution routine of FIG.
As shown in Table 23, rank 1 of the hypothesis by each inference
Since the parts match, the predefined
Is satisfied, and in step S64, it is determined that there is consistency.
When it is determined, the process branches to step S69, and the number of inferences is calculated.
After clearing the count value C for measurement,
Step S9 stores the information together with the information of "end of inference".
Return to Then, in the above-mentioned step S9, "the inference
If it is determined that the check has been completed, the process proceeds to step S10, and other check items
Judge whether there is an eye, and if there is an inspection item,
The process branches to S11, and is performed for the maintenance staff or the user.
Narrow down the content of the interview. With this interview, the conclusion
Information for testing hypotheses and generating new hypotheses
And That is, for example, in the FTA type knowledge base,
As shown in FIG. 16, the intermediate hypothesis of Rule 2
[Fuel leak] linked to the "star pump abnormality" by the rule
Is linked to the conclusion hypothesis of Rule 4. Therefore,
Specify the location to identify the abnormality of the pump
By inspecting this location, the failure location can be further narrowed down.
Can be. Then, in step S12, the above steps
The contents of the medical inquiry narrowed down in S11 are
Display on the clean 1a, and at the same time,
The work contents and necessary information are, for example, as shown in FIG.
indicate. Then, returning to steps S1 and S2, the maintenance staff
Wait for the input of the inspection result from etc. A maintenance person enters the touch screen 1a.
When the inspection result is input from the force pen 2 or the tester,
This data is stored in step S3, and step S4
In the input character string and the previous "input data"
Based on the character strings and measurement results,
The similarity is calculated again, and in steps S5, S6, S7 and below,
Based on each piece of knowledge data, make inferences again and determine the cause of the failure.
Investigate. Then, the inference is completed, and from step S9
Proceed to step S10 to check the hypothesis
If not, the process proceeds directly to step S13, and
Determine if the cause could be explored. If the cause of the failure can be found, step S
Go to 14 and make inferences when investigating the cause of the failureresultRaw
And investigate the cause in step S15.Inspection results
Of the phenomenon observed in the inspection and inspectionGenerate The above inferenceresultWhich part or where
Inferred about the location, that is, indicates the target
In the above-mentioned electronic manual data storage section 16d,
Read stored data such as component names and fault locations
Generate. [0099] Then, in a step S16, as shown in FIG.
In the dialogue on the touch screen 1a,
In the boxes S14 and S15,
Generated inferenceResults, inspection results and phenomena observed during inspection
the cause ofInferresultDisplay in the window and rationale for the diagnosis results
Is presented. The maintenance staff and the like are shown in the above inference result window.
Was doneInquiryResults, inspection results and the phenomena observed
Knowing the cause allows you to know which part or where
What was the cause of the investigation and the questionnaire inspection?
To understand what was necessary for the project. The result
As a result, maintenance personnel are linked
Can be understood logically and maintenance capacity can be improved.
Educational effect such as Then, the maintenance staff etc.
Check the content displayed on the
Select the "OK" window of the user box with the input pen 2.
Then, the process proceeds to step S17, where the touch screen 1a is
Contains the parts corresponding to the cause of failure obtained by inference.
Necessary measures such as replacement procedure of (for example, booster / pump)
The information of the point is stored in the above-mentioned electronic manual data storage section 16d.
Search and display from the data stored in
In step S18, the operator inputs a treatment result of a maintenance person or the like. The maintenance staff is presented in step S17.
Replacement of parts in accordance with the
The result of the transfer or the like is input to the apparatus main body 1. Then, on
In the main body 1, it is determined whether or not the test operation is good.
Depending on whether the failure phenomenon has been resolved,
It is determined whether or not the search was successful.
Confirmation is made, for example, as shown in FIG.
It is displayed on the lean 1a. Note that parts are replaced according to the results of the inquiry.
If you are not satisfied with the results,
However, if the user inputs that fact in step S18,
In step S19, the current time is displayed on the touch screen 1a.
A confirmation screen is displayed to the effect that the search has failed. Also die
In the dialog box, for example, And the confirmation contents for obtaining the consent of the maintenance staff are displayed. Then, the maintenance staff understands the registration of the case.
In step S20, first, the FMECA type knowledge data
Of the knowledge data stored in the data storage unit 16c
Phenomena selected by the search
The degree of confidence (see Fig. 18) according to the results of this investigation.
Update. In other words, if this search was successful,
Increases confidence and, in the case of failure,
Make the confidence relatively low. Then, in a step S21, the result of this inquiry
The result is used as a diagnosis case, and the diagnosis case type knowledge data storage unit 16 is used.
a, for example, as shown in FIG.
(Case- 5721). In addition, this search
If the result is unsuccessful, the content is "cause and action"
In the column of "Special Notes", "Inquiry lost"
Loss ". Next, when the operation proceeds to step S22, the current
The history of the inquiry is shared with supplementary information such as the date of the diagnosis and the name of the diagnostician.
The maintenance record data storage unit 17a stores the
End the disconnection. The maintenance record data is stored in the maintenance record data storage section 17a.
Data can be retrieved via an external printer, etc.
For example, as shown in FIG.
It can be described and tabulated. On the other hand, in step S13, the cause of the failure is
If you are unable to search,
Jump from S14 to S18 and proceed to step S19,
In this inference, it was confirmed that the cause of failure could not be investigated
Display the screen. And the maintenance staff understand the contents.
The reasoning could not be investigated with this inference,
In steps S20 and S21, the update of the certainty factor and the inquiry
Is not added, and in step S22, the maintenance record data
The maintenance result is stored in the storage unit 17a in the same manner as described above.
And terminate the failure diagnosis. As described above, in this embodiment, the cause of the failure is detected.
When it can be inferred, its inferenceResults, inspection results and inspection
Cause of the observed phenomenonIs displayed.
By knowing this content, employees and other
Can be understood logically and educational effects
Is big. Note that the present invention is not limited to the above embodiment.
For example, the target of failure diagnosis is not limited to aircraft,
It may be a vehicle such as a car, a railway, or a ship. [0112] As described above, according to the present invention,
Make inferences based on the inspection results entered according to the inspection guidelines.
As a result, if the cause of the failure could be investigated,
Display the cause of the phenomenon observed in the results and inspection, Maintenance
The maintenance staff and others were informed
Logically understand the connection between the elephant and the inference result.
Not only has a large educational effect, but also
You can aim up.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a functional block diagram of a failure diagnosis apparatus. 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 hypothesis based on diagnosis case inference. FIG. 5 is a flowchart showing a hypothesis generation routine based on FTA type knowledge base inference. FIG. 6 is a flowchart showing a hypothesis generation routine based on FMECA type knowledge base inference. FIG. 7 is a hypothesis conflict resolution routine. FIG. 8 is an external view of the failure diagnosis device. FIG. 9 is an explanatory diagram showing a use mode selection screen. FIG. 10 is an explanatory diagram showing a defect record slip. FIG. 11 is an explanatory diagram showing a defect phenomenon input screen. FIG. 12 is an explanatory diagram showing diagnosis case type knowledge data. FIG. 13 shows similarity calculation results in diagnosis case type knowledge base inference. FIG. 14 is an explanatory diagram showing a hypothesis based on diagnosis case type knowledge base inference by reliability. FIG. 15 is an explanatory diagram showing FTA type knowledge data. FIG. 16 is an explanation of a route search result in FTA type knowledge base inference. FIG. 17 is an explanatory diagram showing the result of hypothesis generation in FTA-type knowledge base inference. FIG. 18 is an explanatory diagram of FMECA-type knowledge data. FIG. 19 is an explanatory diagram of similarity calculated by FMECA-type knowledge base inference. 20: Explanatory diagram showing the result of hypothesis generation by FMECA-type knowledge base inference [FIG. 21] Explanatory diagram showing aggregation of hypotheses obtained by each inference [FIG. 22] Explanatory diagram of data for re-inference [FIG. 23] FIG. 24 is an explanatory diagram showing the aggregation of the obtained hypotheses. FIG. 24 is an explanatory diagram showing a display screen at the time of a medical inquiry. FIG. 25 is an explanatory diagram showing a display screen when a cause of failure can be investigated. Explanatory diagram showing a result confirmation display screen [Fig. 27] Explanatory diagram of diagnosis case type knowledge data in which a new case is registered [Fig. 28] Explanatory diagram showing a failure record form describing the contents of treatment [Explanation of reference numerals] 14 Inference mechanism 16 Knowledge base

──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Yasuo Kagei 1-7-2 Nishi-Shinjuku, Shinjuku-ku, Tokyo Inside Shimizu Tomi Heavy Industries Co., Ltd. (72) Inventor Masaaki Koyama 1-7-1, Nishishinjuku, Shinjuku-ku, Tokyo No. Tomi Shige Kogyo Co., Ltd. (72) Inventor Kunihiro Abe 1-7-2 Nishi-Shinjuku, Shinjuku-ku, Tokyo Inside Fushi Shige Kogyo Co., Ltd. (56) References Masami Kato, 6 other authors, “Turbine & Electric Machine Online “Monitoring and Diagnosis Expert System”, IEEJ Transactions B, The Institute of Electrical Engineers of Japan, October 20, 1991, Vol. 111, No. 10, p. 1112-1120. (58) Field surveyed (Int. Cl. ⁷ , DB name) G06N 5/00 JICST file (JOIS)

Claims (1)

(57) [Claims] [Claim 1] A knowledge base unit for storing knowledge data in which a failure cause is described in a character string corresponding to a failure phenomenon, and an input character string and the character string of the knowledge data An inference mechanism for inferring the cause of the failure by inference from the degree of similarity to the fault diagnosis device having the knowledge base unit, wherein the knowledge base unit further includes data including an assembly procedure of parts and an inspection procedure in order to further verify the result of the inference. When the inference mechanism outputs the inference result and terminates the inference, it is determined whether or not an inspection for identifying the cause of the failure is necessary, and when the inspection is necessary, the abnormality of the failed component is identified. outputs iNSPECTION locations from said knowledge base section, input data up to the previous, which is entered in the inference mechanism when the inspection inspection results according to the manner is input in the inference the string of the inspection result
And inputting the character string of the data into the inference mechanism and inferring it again. When the cause of the failure can be found, the search result, the object to be searched, the check result, and the cause of the check result are displayed. Fault diagnosis device.