JPH11120001A - Instance base inference system wherein design history is taken into consideration - Google Patents

Abstract

PROBLEM TO BE SOLVED: To widen a design application range and to shorten a design period by accumulating and reusing a design history for instance inference. SOLUTION: A design instance data base 1 stores analysis and design instances of product knowledge, various design knowledge (design designing knowledge, structure designing knowledge, etc.), analytic knowledge, design history knowledge, etc., on an object-oriented basis. A general knowledge base 2 stores an instance correction rule 21, a countermeasure rule 22, and a procedure 23 for generating, designing, and correction shapes. The general knowledge base 2 applies general knowledge common to knowledge and an instance obtained from an instance inference agent 3. A simultaneous cooperation design part 4 is a block which makes design evaluations cooperatively at the same time. When a new instance is designed by using a design system, the instance inference agent 3 extract effective knowledge of an instance which is similar in state from analysis and design instances accumulated in the past according to the similarity calculated by an individual knowledge similarity calculation part 37 and a history knowledge similarity calculation part 38.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a case-based inference system for extracting effective knowledge of cases having similar situations from analysis and design cases accumulated in the past. It is applied to a CAE expert system that uses the information processing and knowledge processing.

[0002]

2. Description of the Related Art Conventionally, various systems using case inference have been proposed as design systems for products and processes.

For example, a design specification to be applied to a required design specification is determined in consideration of design constraints and interference relationships between specification items, and a past design having the same design specification is determined from a design case base. Search cases as similar design cases,
There is a similar design case search device (Japanese Patent Laid-Open No. 7-219899) which outputs the search result. However, this similar design case search apparatus can only apply knowledge of similar parts, and cannot completely acquire all knowledge including dissimilar parts.

Therefore, a case-based reasoning system has been proposed in which, when knowledge cannot be completely acquired, a case is modified and applied (JP-A-6-19714). When solving a problem, the case-based inference system searches for a case that is most similar to the problem to be solved from a plurality of cases stored in advance in the storage unit, and determines a part different from the searched case and the problem. The case is corrected based on the above rule, and the corrected case is additionally stored in the storage unit.

[0005] In addition, attributes are sectioned as a structure of a case to be handled (Japanese Patent Laid-Open No. Hei 6-19714), and search performance is improved by adding a first index (Japanese Patent Laid-Open No. Hei 6-176072). A case-based inference system has been proposed in which a successful case is patterned (JP-A-6-92237).

[0006]

However, none of the above case-based inference systems can handle a design history. In addition, a device having a history storage function in manual correction of a case (Japanese Patent Laid-Open No. Hei 4-29013)
No. 1) has been proposed, but this saves the trouble of correcting the case, and does not have a history in the case structure.

In other words, there has not been a case-based inference system that can directly handle the design history of a target in which a design result is evaluated in a design case and a countermeasure is repeatedly performed when there is a defect.

The present invention has been devised to solve such a problem. The purpose of the present invention is to accumulate design histories and reuse them at the time of case inference to increase the range of design application and increase the design period. It is an object of the present invention to provide a case-based reasoning system that takes into account a design history that enables a reduction in the design time.

[0009]

In order to solve the above-mentioned problems, a case-based reasoning system according to the first aspect of the present invention, which considers a design history, comprises a product knowledge, various design knowledges, an analysis knowledge, a design history knowledge, and the like. Analysis, design case database that stores design cases in an object-oriented manner, and individual knowledge similarity that calculates similarity based on individual knowledge such as product knowledge, various design knowledge, and analysis knowledge stored in the design case database A degree knowledge calculating unit and a history knowledge similarity calculating unit that calculates the similarity of the design history based on the design history knowledge stored in the design case database. The individual knowledge similarity calculating unit and the history knowledge similarity calculating A case inference agent that extracts effective knowledge of similar cases from analysis and design cases accumulated in the past according to the similarity calculated by the department A structure with a door.

According to a second aspect of the present invention, there is provided a case-based inference system in which a design history is taken into consideration, wherein the design case database includes an evaluation for a design result and an implementation based on the evaluation. The measures taken and the effects obtained as a result of implementing these measures are taken as one case structure, and the analysis and design histories performed in the past are organized,
This is accumulated as the design history knowledge.

According to a third aspect of the present invention, in the case-based inference system in consideration of the design history, in the second aspect, the case inference agent includes the same measure history as the currently implemented measure. Cases are extracted from the design history knowledge of the design case database, and a case with the closest countermeasure history is analogized among the extracted cases.

[0012]

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

FIG. 1 is an explanatory diagram showing the overall configuration of a design system using a case-based reasoning system in consideration of the design history of the present invention.

A design system using this case-based reasoning system is roughly composed of a design case database 1, a general-purpose knowledge base 2, a case reasoning agent 3, and a simultaneous cooperative design unit 4.

The design case database 1 stores product knowledge, various design knowledge (design design knowledge, structural design knowledge, etc.), analysis knowledge, design history knowledge, etc., and design cases in an object-oriented manner.

The general-purpose knowledge base 2 has a case modification rule 2
1. The countermeasure rule 22 and the procedure 23 for shape creation, design, and correction are stored. The general-purpose knowledge base 2 applies general-purpose knowledge common to the case and the knowledge obtained from the case inference agent 3.

The case inference agent 3 includes a case base editor 31 for constructing only necessary knowledge in the design case database 1 as a case, a case list creating unit 32 for developing actual case data in a space, and this case list creating. Part 32
A similar case search unit 33 for estimating the case most similar to the current design from the cases developed in the above, a result display unit 34 for displaying finally usable cases, and a correlation / weight definition unit 3
5. Similarity calculation formula definition unit 36, design case database 1
Based on individual knowledge such as product knowledge, various design knowledge, and analysis knowledge stored in the design knowledge database 37, and the design history knowledge stored in the design case database 1. It is configured by a history knowledge similarity calculation unit 38 that calculates the similarity of the design history.

The simultaneous cooperative design unit 4 is a block for simultaneously and cooperatively performing a plurality of design evaluations. A request input unit 41 for inputting data such as required functions and qualities. Condition creation unit 4 for setting
2. A tool execution unit (design simulation, functional simulation, CAE (structure, molding), design based on rules, etc.) 43 for evaluating an evaluation item, a result evaluation unit 44 for evaluating an execution result, and a result evaluation unit 44 A measure solution extractor 45 that extracts a measure from the general-purpose knowledge base 2 based on the evaluation result, a measure implementer 46 that implements the extracted measure, and a design solution display that displays the evaluation result (design solution) of the result evaluator 44. It comprises a unit 47 and a case storage unit 48.

Next, using the design system having the above configuration,
The overall operation when actually designing a new case will be described with reference to the flowchart shown in FIG.

The data of the requested function, quality, and the like input to the request input unit 41 are input to the case inference agent 3 (step S1). The case inference agent 3 creates a list of cases based on the input data of required functions, quality, and the like (step S2), and infers past cases satisfying the required functions, quality, and the like from the design case database 1 (step S2). Step S3), and display the result on the result display unit 34 (Step S4).

Thereafter, in order to realize all the obtained knowledge, procedural rules are obtained from the general-purpose knowledge base 2 and input to the simultaneous cooperative design unit 4 (step S5). The simultaneous cooperative design unit 4 performs an initial design based on the rules obtained here (step S6), and evaluates the initial design (steps S7 to S10). The evaluation here is an evaluation using CG and VR such as design simulation and functional simulation (step S8), an evaluation using CAE such as structural analysis and formability simulation (step S9),
A plurality of evaluations, such as an evaluation using an empirical formula (step S10), are performed simultaneously.

If a defect is found in the evaluation result, a measure is extracted from the general-purpose knowledge base 2 (steps S11 and S12). Here, when there is no countermeasure rule in the countermeasure rule 22 of the general-purpose knowledge base 2, a request is made to the case inference agent 3 to extract a case where the same countermeasure has been performed in the past. At this time, if the design history is to be handled, a part of the case structure is replaced with a structure corresponding to the history, the history knowledge similarity is calculated only for that part, and the similarity of the history knowledge is calculated as the overall similarity. Is added to obtain the overall similarity.

The calculation of the history knowledge similarity will be described later, but will be described in more detail here. That is, when the next design countermeasure is extracted in the state where the countermeasure has already been performed a plurality of times in the design process, the design history up to this point which does not correspond to the standard in the problem part can be described. Then, by comparing the design histories of the past cases, those which have taken the same countermeasure histories so far are extracted. By adding such a history knowledge similarity calculation, not only the similarity of the product knowledge in the problem part but also the similarity of the design history executed at that time can be handled.

The countermeasures thus obtained are implemented (step S13), and the evaluation is performed again (step S7). This work (step S7 to step S13) is repeated,
When the design solution is optimized, the optimized design solution is displayed on the design solution display unit 47 (step S14).

Finally, these series of operations are stored as cases in the design case database 1 (step S15).

The overall processing flow has been described above. Specific processing procedures in the case inference agent 3 and the simultaneous cooperative design unit 4 will be individually described below.

(1) The processing in the case inference agent 3 will be described with reference to the flowchart shown in FIG.

When the case inference agent 3 receives the obtained required function and quality, and product knowledge such as shape characteristics and material information, it expands the design case database 1 and sets them in the problem area (step S21, step S21). S22).
In the problem part, for example, “product group”, “product name”, “volume”, “surface area”, “boundary condition”, and the like are set. Thereafter, the number of cases M in which the same item is set in the problem part is calculated while comparing with the problem part of the past case stored in the design case database 1 (step S).
23) Then, the number N of problem parts in each case is calculated (step S24), and the inter-case distance is calculated for each case (step S25).

That is, one case is extracted from the calculated cases (step S26), and the distance between the problem part An and the problem part Bn of the extracted case is calculated. In this case, when the item set in the problem part is a numerical value X, and the numerical value X indicates an error, An and Bn are calculated using the distance calculation formula 1.
Is calculated (steps S27, S28, S2).
9, S30).

[0030]

[Equation 1] y = 1.0 (where −αX <x <αX) On the other hand, the item set in the problem part is a numerical value X, and the distance calculation formula is represented by distance calculation formula 2. If it is set, the distance y between An and Bn is calculated using the distance calculation formula 2 (steps S27, S28, S29, S3).
1).

[0031]

[Equation 2] y = 0.0 (where x <−αX) y = (1 / αX) · x + 1 / (− α) (where −αX <x <X) y = 1 (However, x = X) y = (1 / −αX) · x + 1 / α (however, X <x <αX) y = 0.0 (where αX <x) On the other hand, if the item set in the problem part is If it is a character, the distance y between An and Bn is calculated using the distance calculation method 3 (steps S27, S28, S29, S32). The distance calculation method 3 here is, for example, a perfect matching method. That is, the character (name) of the problem part An is, for example, “flange”.
When the character (name) of the problem part Bn is “flange”, y = 1.0, the character (name) of the problem part An is “flange”, for example, and the character (name) of the problem part Bn is set. Is “flange”, y = 0.0. In addition, a distance calculation method based on an ontology using a thesaurus is possible.

The entire distance between An and Bn calculated in this way is stored as the distance Y (n) of the case (step S33). Such processing is performed in step S2.
After repeating the process up to the number of problem copies N calculated in Step 4 (Step S34), the inter-case distance obtained by comprehensively evaluating the extracted cases as a whole is calculated (Step S35). At this time, in addition to numerical values and text,
Natural languages, semantic distances, images, shapes, etc. may also be handled.

That is, in the calculation of the inter-case distance, if the individual knowledge is not weighted, the inter-case distance is calculated using the inter-case distance calculation method 1 (step S36,
S37).

[0034]

(Equation 3)

In the calculation of the inter-case distance, if the individual knowledge is weighted, the inter-case distance is calculated using the inter-case distance calculation method 2 (steps S36 and S3).
8, S39). That is, the weight changes in each region even when calculating the entire inter-case distance.

[0036]

(Equation 4)

The distance L between the cases calculated as described above
(M) is stored (step S40).

Such steps S26 to S4
0 is repeatedly performed up to the number M of cases calculated in step S23 (step S41), and the calculation result is
The cases are displayed in ascending order of the inter-case distance (step S42), the applied knowledge is displayed (step S43), and the process in the case inference agent 3 ends.

(2) Next, the processing in the simultaneous cooperative design unit 4 will be described with reference to the flowchart shown in FIG.

In the simultaneous cooperative design unit 4, first, an evaluation item and a criterion are set in order to simultaneously perform a plurality of evaluations (step S71). Then, select a tool that can evaluate those evaluation items (for example, CG software for evaluating designability, structural analysis software for evaluating structure, etc.),
Information that satisfies these analysis conditions is set from the application knowledge of the case inference agent 3 (steps S73 to S7).
6). Then, these tools are simultaneously executed according to the set analysis conditions.

That is, a design simulation (step S77) and a function simulation (step S7)
8), structural analysis (step S79), and molding simulation (step S80) are simultaneously executed, and the evaluation results are output individually for each (steps S81 to S8).
4). Then, the result evaluation unit 43 aggregates the individual evaluation results, extracts and executes a measure until the total evaluation result satisfies the required quality (steps S86, S87, S8).
8). The extraction and execution of such a measure are repeated, and when the total evaluation result satisfies the required quality, the result is displayed (step S89).

Here, the item structure used in the initial case inference will be described. As shown in FIG.
Analysis and design cases are set as problematic parts as product knowledge (required quality, function, shape characteristics, material information, etc.), and various design knowledge used at the time of design (design knowledge, structural design knowledge, formability design knowledge, workability) Design knowledge, usability design knowledge, etc., analysis knowledge (shape creation knowledge, mesh creation knowledge, boundary condition setting knowledge, result evaluation knowledge, etc.), design history knowledge (evaluation values, countermeasure plans, countermeasure effects, etc.) as the answer part You have set.

The design history information is stored in the design case database 1 together with other information. FIG. 6 shows an example of a design history storage method.

In this design history, the “graphic” of the design solution is stored in the upper part, and “evaluation (“ stress ”and“ volume ”in this embodiment)”, “effect (judgment)”, and “measures” are stored in the lower part.
Are stored in association with each other. That is, in the initial design solution, the stress is 52 kg / mm ² and the volume is 190 c.
m ³ , and the stress was determined to be “out of tolerance”, which is out of tolerance. As a result, the design solution was obtained again by taking the measure of “addition of ribs”, and as a result, the stress was 54 kg / mm ² and the volume was 195 cm ³ , and it was determined that this measure had no effect and “no effect”. As a result, the design solution was determined again by taking measures against “increase in height”, and as a result, the stress was 30 kg / mm ² and the volume was 230 cm ³ , and although the stress was within the allowable range, the volume increased. It is determined that "the stress increases, the volume increases". As a result, a design solution was again obtained by taking measures against “foot shape correction”, and as a result, the stress was 38 kg / mm ² and the volume was 195 cm ³
It is determined that the stress is within the allowable range and the volume is equal to the initial value. In other words, in this design history, looking at the countermeasures, as a result of taking three countermeasures in this order of “addition of ribs” — “increase height” — “correction of foot shape”, the initial design solution is required. It shows that the design solution has satisfied the quality.

FIG. 7 shows a specific structure of the countermeasure rule 22 stored in the general-purpose knowledge base 2, and each defect is associated with each countermeasure in a weighted manner. The weights change from time to time, and new items and new countermeasures for defects also increase from time to time. From the contents of the countermeasure rule 22, for example, when it is desired to reduce the stress concentration at the corner without increasing the volume, it is effective to execute the countermeasure 1 (large R). In addition, when it is desired to suppress the deflection without increasing the volume, it is effective to execute the measures 1 (large R) and the measure 5.

In addition, the general-purpose knowledge base 2
If the countermeasure rule 22 has no countermeasure, the case inference agent 3 is inquired again to infer the past countermeasure.

Here, in the case currently being implemented, two countermeasures have already been taken, and the history is shown in FIG.
It is assumed that the state is as shown in FIG. In this example,
The item of “evaluation” is “deflection amount”, and two measures are “addition of rib” and “increase height”.

That is, in the initial design solution, the deflection amount is 0.9 mm, and it is determined that the deflection amount is too large (×). As a result, the design solution was determined again by taking measures against "addition of ribs". As a result, the deflection amount was 0.8 mm, and the deflection amount was reduced by 11% (0.1 ÷ 0.9 × 100). But it is judged that there is too much (x). Therefore, as a result of taking a measure of “increase the height” and finding a design solution again, the deflection amount becomes 0.6 mm, and the deflection amount is reduced by 25% (0.2 ÷ 0.8 × 100). However, this is judged to be too much (×).

If the countermeasure rule 22 stored in the general-purpose knowledge base 2 is used, the following countermeasures such as countermeasure 1 (large R) will be implemented. In the case where the countermeasure cannot be executed in a restricted manner, the present invention implements the next executable and most effective countermeasure by inference in consideration of the design history.

Next, the process of calculating the similarity in consideration of the design history by the history knowledge similarity calculator 38 will be described with reference to the flowchart shown in FIG.

That is, in this case, two evaluations, countermeasures, and effects are assembled as a case structure (see FIG. 8B), and this is added to the conventional problem part.
Therefore, the history knowledge similarity calculation unit 38 of the case inference agent 3 calculates all cases including the same countermeasure history as the currently implemented countermeasures (ie, “add rib” and “increase height”) in the design case database. 1 (step S91), the case structures of all cases are changed (step S92), and the similarity of each case is calculated (step S93).

That is, the points are scored in descending order of the number of the same countermeasures implemented (step S94), the points are scored in the order of the countermeasures in the same order (step S95), and the points are scored in the order of the effect (step S96). Points are scored in ascending order of countermeasures (step S97), points are scored in order of easier countermeasures (step S98), and cases are displayed in descending order of similarity in accordance with the total points of these points (step S97).
99).

FIG. 10 shows a case in which cases are displayed in descending order of similarity by such similarity calculation.
In FIG. 10, what is displayed in the upper column is the two measures currently being implemented, and what is displayed in the lower column is the case inference result displayed in descending order of similarity.

The one with the highest similarity (1) is the same two times as the countermeasure that is currently being implemented, and the contents are exactly the same "addition of ribs" and "increase of height". ,
This case cannot be used. That is, the measure (1) does not include the following measure (third measure).

For this reason, here, the countermeasure for the item having the second highest similarity (2) will be implemented. That is, (2)
The first and second countermeasures are the same as the ones currently being implemented. As the third countermeasure, the "leg change" countermeasure was implemented, and the design solution met the required quality. It is shown that. Therefore, even in the current case, if you implement “leg change” as the next measure,
It is presumed that a good effect can be obtained.

If the leg cannot be changed due to the structure of the design solution or constraints, the countermeasure (3) having the next highest similarity, that is, the "thickness increase" countermeasure will be taken.

However, actually, not only the similarity calculation result by the history knowledge similarity calculation unit 38 but also the normal (conventionally performed) similarity calculation result by the individual knowledge similarity calculation unit 37 (ie, The following countermeasures are executed based on the total similarity in consideration of the similarity of the product knowledge portion). As a result, more effective and appropriate measures can be taken.

[0058]

According to the present invention, the case-based reasoning system in consideration of the design history is an individual knowledge for calculating similarity based on individual knowledge such as product knowledge, various design knowledge, and analysis knowledge stored in a design case database. A similarity calculator and a history knowledge similarity calculator for calculating similarity of the design history based on the design history knowledge stored in the design case database; these individual knowledge similarity calculator and history knowledge similarity calculator According to the degree of similarity calculated by the section, effective knowledge of a case having a similar situation is extracted from analysis and design cases accumulated in the past. In other words, since the design history can be directly handled in case inference,
The next countermeasure can be selected more effectively and appropriately.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing an overall configuration of a design system using a case-based reasoning system in consideration of a design history according to the present invention.

FIG. 2 is a flowchart for explaining an overall operation when a new case is actually designed using a design system using a case-based reasoning system in consideration of a design history of the present invention.

FIG. 3 is a flowchart for explaining a processing operation in a case inference agent.

FIG. 4 is a flowchart illustrating a processing operation in a simultaneous cooperative design unit.

FIG. 5 is a diagram showing a case structure used at the time of initial case inference.

FIG. 6 is a chart showing an example of a design history storage method.

FIG. 7 is a table showing a specific structure of a countermeasure rule stored in a general-purpose knowledge base.

FIG. 8A is a table showing an example of a currently stored design history storage, and FIG. 8B is a diagram showing a case in which this is structured.

FIG. 9 is a flowchart illustrating a similarity calculation process performed by a history knowledge similarity calculation unit in consideration of a design history.

FIG. 10 is a table showing case inference results.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Design case database 2 General-purpose knowledge base 3 Case inference agent 4 Simultaneous cooperative design part 21 Case modification rule 22 Countermeasure rule 23 Procedure data 31 Case base editor 32 Case list creation part 33 Similar case search part 34 Result display part 35 Correlation / weight definition Unit 36 similarity calculation expression definition unit 37 individual knowledge similarity calculation unit 38 history knowledge similarity calculation unit 41 request input unit 42 condition creation unit 43 tool execution unit 44 result evaluation unit 45 countermeasure plan extraction unit 46 countermeasure execution unit 47 design solution Display unit 48 Case storage unit

Claims (3)

[Claims] An analysis of product knowledge, various design knowledge, analysis knowledge, design history knowledge, and the like, a design case database for storing design cases in an object-oriented manner, product knowledge stored in the design case database,
An individual knowledge similarity calculator that calculates similarity based on individual knowledge such as various design knowledge and analysis knowledge, and history knowledge that calculates similarity of design history based on design history knowledge stored in the design case database Having a similarity calculation unit,
A case inference agent that extracts effective knowledge of cases having similar situations from analysis and design cases accumulated in the past in accordance with the similarities calculated by the individual knowledge similarity calculation unit and the history knowledge similarity calculation unit. Case-based reasoning system that takes into account design history. 2. The design example database includes an evaluation of a design result, a measure implemented based on the evaluation,
2. The design according to claim 1, wherein an effect obtained as a result of implementing this measure is taken as one case structure, a history of analysis and design performed in the past is arranged, and accumulated as the design history knowledge. Case-based reasoning system considering history. 3. The case inference agent extracts, from the design history knowledge of the design case database, a case that includes the same measure history as the currently implemented measure, and selects the case with the closest measure history among the extracted cases. 3. The case-based reasoning system according to claim 2, wherein the design history is considered.