Diagnosis of equipment failures using an integrated approach of case based reasoning and reliability analysis

• US 20050060323A1
• Filed: 09/17/2003
• Published: 03/17/2005
• Est. Priority Date: 09/17/2003
• Status: Active Grant

• Current Assignee: GlobalFoundries, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Parija, Gyana Ranjan, Leung, Ying Tat, Sharma, Samir
• Granted Patent: US 7,313,573 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G05B 23/0275 Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

Equipment failures are diagnosed using an integrated approach of case-based reasoning (CBR) and statistical reliability analysis. The method outputs a single list of suggested failed components, ranked by an overall probability of failure, and their associated past solutions from the case base. The overall probability of failure is calculated using the combined logic of case based reasoning and statistical reliability analysis. The method is typically used in a real-time decision support system to aid equipment diagnosis by a maintenance technician working in the field.

Claims

1. A method to diagnose equipment failures using an integrated approach of case-based reasoning and reliability analysis, comprising the steps of:

maintaining a case base database for the equipment;

receiving an equipment problem description from a user;

for each component in the equipment, calculating failure probability based on historical failure and published data, using reliability theory;

for each component, calculating probability of matching problem description assuming that a component fails, using case based reasoning;

for each component, combining the calculated probabilities to compute the overall failure probability given the historical behavior and published data and problem description; and

composing a list of component recommendations by ranking components by their overall failure probabilities and retrieving corresponding past solutions from the case base.

2. The method of claim 1, further comprising the step of producing a single list of suggested failed components based on published failure data, historical failure behavior as observed by the equipment user, and the problem description specified by the user.

3. The method of claim 1, further comprising the step of producing a list of probabilities of failure corresponding to the list of suggested failed components, with the probabilities estimated from published failure data, historical failure behavior as observed by the equipment user, and the problem description specified by the user.

4. The method of claim 1, wherein the step of combining probabilities to compute overall failure probability uses an equipment hierarchy such that component failure probabilities are estimated in a hierarchical manner, calculated from data for the equipment at hand, if there is adequate data, otherwise, from data from an equipment group one level up in the hierarchy, and repeating the process until adequate data is found.

5. The method of claim 1, wherein the step of combining probabilities to compute overall failure probability uses an equipment hierarchy such that historical cases are retrieved in a hierarchical manner, from data for the equipment at hand, if there is adequate data, otherwise, from data from an equipment group one level up in the hierarchy, and repeating the process until adequate data is found.

6. A decision support system to diagnose equipment failures using an integrated approach of case-based reasoning and reliability analysis, comprising:

a case base maintenance management system database for the equipment;

a decision support system database;

a decision support system client for receiving an equipment problem description from a user;

a decision support system server receiving input from the decision support system client and accessing said maintenance management system database and said decision support system database, said decision support system server including

a real-time decision support system engine for calculating failure probability for each component in the equipment, based on historical failure and published data, using reliability theory, and for calculating probability of matching problem description for each component, assuming that a component fails, using case based reasoning, and for each component, combining the calculated the calculated probabilities to compute the overall failure probability given the historical behavior and published data and problem description and composing a list of component recommendations by ranking components by their overall failure probabilities and retrieving corresponding past solutions from the case base; and

a case base update processor for copying closed failure transaction records from the maintenance management systems database, and extracting the information these transaction records to the attributes required by said decision support system engine, and indexing each transaction record by the failed component identification and the number of occurrence of failure of that particular component.

7. The decision support system of claim 6, wherein the decision support system server produces a single list of suggested failed components based on published failure data, historical failure behavior as observed by the equipment user, and the problem description specified by the user.

8. The decision support system of claim 6, wherein the decision support system server produces a list of probabilities of failure corresponding to the list of suggested failed components, with the probabilities estimated from published failure data, historical failure behavior as observed by the equipment user, and the problem description specified by the user.

9. The decision support system of claim 6, wherein the decision support system server combines probabilities to compute overall failure probability uses an equipment hierarchy such that component failure probabilities are estimated in a hierarchical manner, calculated from data for the equipment at hand, if there is adequate data, otherwise, from data from an equipment group one level up in the hierarchy, and repeats the process until adequate data is found.

10. The decision support system of claim 6, wherein the decision support system server combines probabilities to compute overall failure probability uses an equipment hierarchy such that historical cases are retrieved in a hierarchical manner, from data for the equipment at hand, if there is adequate data, otherwise, from data from an equipment group one level up in the hierarchy, and repeats the process until adequate data is found.