AGGREGATED INFORMATION FUSION FOR ENHANCED DIAGNOSTICS, PROGNOSTICS AND MAINTENANCE PRACTICES OF VEHICLES

• US 20100228423A1
• Filed: 03/05/2009
• Published: 09/09/2010
• Est. Priority Date: 03/05/2009
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations Incorporated (Motors Liquidation Co. GUC Trust)
• Inventors: ZHANG, YILU, ZHANG, XIAODONG, DE, SOUMEN, PATNAIK, DEBPRAKASH, HOWELL, MARK N., MURTY, BALARAMA V., DEBOUK, RAMI I., CHIN, YUEN-KWOK, BHATTACHARYA, SABYASACHI, HOLLAND, STEVEN W., BANDYOPADHYAY, PULAK, SALMAN, MUTASIM A., TANG, XIDONG, MONTGOMERY, GEORGE PAUL JR., ALRABADY, ANSAF I.
• Granted Patent: US 8,095,261 B2
• Time in Patent Office: Days
• US Class Current: 701/29
• CPC Class Codes: G05B 19/0428 Safety, monitoring G05B19/0423 takes precedence
• CPC Class Codes: G05B 2219/24069 Diagnostic
• CPC Class Codes: G05B 2219/24216 Supervision of system
• CPC Class Codes: G05B 2219/2637 Vehicle, car, auto, wheelchair
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

A system and method for enhancing vehicle diagnostic and prognostic algorithms and improving vehicle maintenance practices. The method includes collecting data from vehicle components, sub-systems and systems, and storing the collected data in a database. The collected and stored data can be from multiple sources for similar vehicles or similar components and can include various types of trouble codes and labor codes as well as other information, such as operational data and physics of failure data, which are fused together. The method generates classes for different vehicle components, sub-systems and systems, and builds feature extractors for each class using data mining techniques of the data stored in the database. The method also generates classifiers that classify the features for each class. The feature extractors and feature classifiers are used to determine when a fault condition has occurred for a vehicle component, sub-system or system.

Claims

1. A method for providing vehicle diagnostics and prognostics evaluations, said method comprising:

collecting data from multiple vehicle components, sub-systems and systems and multiple vehicle sources including components, sub-systems and system for different vehicles;

storing the collected data in one or more databases;

generating classes for different types of collected data;

fusing the collected data from the vehicle components, sub-systems and systems and multiple vehicle sources; and

analyzing the fused data to identify fault conditions in vehicle components, sub-systems and systems.

2. The method according to claim 1 wherein fusing the collected data from multiple data sources includes building feature extractors for each class using data mining techniques of the data stored in the databases, generating feature classifiers that classify the features for each class, and using the feature extractors and feature classifiers to determine when a fault condition has occurred for a vehicle component, sub-system or system.

3. The method according to claim 2 further comprising combining the outputs from multiple feature classifiers to increase the robustness for determining when a fault condition occurs.

4. The method according to claim 2 further comprising using the features extractors and feature classifiers to update previous feature classifiers.

5. The method according to claim 1 further comprising using the fused data to improve vehicle maintenance procedures.

6. The method according to claim 1 wherein collecting data includes collecting data from the vehicle components, sub-systems and systems for both fault and non-fault conditions.

7. The method according to claim 1 further comprising transmitting the collected data telematically from the vehicle to a remote data center.

8. The method according to claim 7 wherein storing the collected data in a database includes storing the collected data in one or both of a database on the vehicle and a database at the remote data center.

9. The method according to claim 1 wherein collecting data includes collecting data that does not include trouble codes.

10. The method according to claim 9 wherein collecting data that does not include trouble codes includes collecting data related to physics of failure and operational data.

11. A method for providing vehicle diagnostics and prognostics evaluations, said method comprising:

collecting data from vehicle components, sub-systems and systems on vehicles;

storing the collected data in a database either onboard the vehicles or off-board the vehicles;

telematically transmitting the collected data from the vehicles to a remote data center;

generating classes for different types of the collected data at the remote data center;

building feature extractors for each class using data mining techniques of the data stored in the database at the remote data center;

generating feature classifiers that classify the features for each class at the remote data center;

using the feature extractors and feature classifiers to determine when a fault condition has occurred for a vehicle component, sub-system or system;

combining outputs for multiple feature classifiers to increase the robustness for determining when a fault condition occurs; and

transmitting the results of the fault condition analysis back to the vehicles.

12. The method according to claim 11 wherein collecting data includes collecting data from multiple vehicle components, sub-systems and systems including components, sub-systems and systems for different vehicles and multiple vehicle sources.

13. The method according to claim 11 further comprising using the feature extractors and feature classifiers to determine when a fault condition has occurred to improve vehicle maintenance procedures.

14. The method according to claim 11 wherein collecting data includes collecting data from the vehicle components, sub-systems and systems for both fault and non-fault conditions.

15. The method according to claim 11 further comprising using the features extractors and feature classifiers to update previous feature classifiers.

16. The method according to claim 11 wherein collecting data includes collecting data relating to physics of failure and operational data.

17. A system for providing vehicle diagnostics and prognostics evaluations, said system comprising:

means for collecting data from vehicle components, sub-systems and systems on a vehicle;

means for storing the collected data in a database on the vehicle;

means for transmitting the collected data telematically to a remote data center;

means for generating classes for different types of collected data at the remote data center;

means for building feature extractors for each class using data mining techniques of the data stored in a database on the remote data center;

means for generating feature classifiers that classify the features for each class; and

means for using the feature extractors and feature classifiers to determine when a fault condition has occurred for a vehicle component, sub-system or system.

18. The system according to claim 17 wherein the means for collecting data includes the means for collecting data from multiple vehicles and multiple vehicle sources.

19. The system according to claim 17 further comprising means for combining the outputs from multiple feature classifiers to increase the robustness for determining when a fault condition occurs.

20. The system according to claim 17 further comprising means for using the feature extractors and feature classifiers to determine when a fault condition has occurred to improve vehicle maintenance procedures.