Intelligent model-based diagnostics for system monitoring, diagnosis and maintenance

• US 7,260,501 B2
• Filed: 04/21/2005
• Issued: 08/21/2007
• Est. Priority Date: 04/21/2004
• Status: Expired due to Fees

• Current Assignee: University of Connecticut (State of Connecticut), Toyota Technical Center USA, Inc. (Toyota Motor Corporation)
• Original Assignee: University of Connecticut (State of Connecticut), Toyota Technical Center USA, Inc. (Toyota Motor Corporation)
• Inventors: Luo, Jianhui, Chigusa, Shunsuke, Qiao, Liu, Pattipatti, Krishna R.
• Primary Examiner(s): Hoff; Marc S.
• Assistant Examiner(s): SUAREZ, FELIX E
• Application Number:
  US11/111,071
• Publication Number:
  US 20060064291A1
• Time in Patent Office: 852 Days
• Field of Search: 702/81, 702/109, 702/118, 702/127, 702/183, 702/186, 702/182, 702/196, 702/188, 324/427, 700/21, 700/28, 714/37, 703/2, 703/8, 703/22, 706/59
• US Class Current: 702/183
• CPC Class Codes: G05B 23/0243 model based detection method, e.g. first-principles knowledge model
• CPC Class Codes: G05B 23/0251 Abstraction hierarchy, e.g. "complex systems", i.e. system is divided in subsystems, subsystems are monitored and results are combined to decide on status of whole system
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06

Abstract

Systems and methods are provided for monitoring, diagnosis and condition-based maintenance of mechanical systems. The disclosed systems and methods employ intelligent model-based diagnostic methodologies to effectuate such monitoring, diagnosis and maintenance. According to exemplary embodiments of the present disclosure, the intelligent model-based diagnostic methodologies combine or integrate quantitative (analytical) models and graph-based dependency models to enhance diagnostic performance. The disclosed systems and methods may be employed a wide variety of applications, including automotive, aircraft, power systems, manufacturing systems, chemical processes and systems, transportation systems, and industrial machines/equipment.

Claims

1. A diagnostic method for implementing at least one performance limit on a system, comprising:

(a) generating a hybrid quantitative and graphical dependency model that captures at least one fault-to-error characteristic for the system,

(b) establishing at least one fault condition associated with the system;

(c) running at least one test design on the hybrid quantitative and graphical dependency model for the system;

(d) evaluating performance of the at least one test design with respect to the at least one fault condition using the hybrid quantitative and graphical dependency model to refine the hybrid quantitative and graphical dependency model for the system;

(e) implementing the refined hybrid quantitative and graphical dependency model in connection with at least one of diagnosis of a fault in system performance and monitoring of system performance; and

(f) outputting at least one error code based on implementation of the refined hybrid quantitative and graphical dependency model.

2. A diagnostic method according to claim 1, further comprising validating the hybrid system model.

3. A diagnostic method according to claim 1, further comprising running at least one simulation on said hybrid system model to extract a relationship between a failure cause and an observable effect for the system.

4. A diagnostic method according to claim 1, further comprising generating a design matrix based on a plurality of test designs for a plurality of system faults.

5. A diagnostic method according to claim 4, wherein a subsystem-resident local agent functions as an electronic control unit for the system.

6. A diagnostic method according to claim 4, wherein said design matrix is accessed by a subsystem-resident local agent and wherein said subsystem-resident local agent is adapted to make local diagnostic or prognostic decisions with respect to said system based, at least in part, on said design matrix.

7. A diagnostic method according to claim 6, wherein said subsystem-resident local agent communicates with a system-level agent, and wherein said system-level agent is adapted to combine local decisions into a system-level diagnosis.

8. A diagnostic method according to claim 7, wherein said system-level agent is adapted to communicate diagnostic results to a central facility.

9. A diagnostic method according to claim 1, wherein information associated with said system model is stored in a database.

10. A diagnostic method according to claim 9, wherein said information is selected from the group consisting of model parameters, test specifications, simulation data and combinations thereof.

11. A diagnostic method according to claim 1, further comprising generating a directed graph model of the system based on the performance evaluation.

12. A diagnostic method according to claim 11, wherein at least one test is input to an electronic control unit associated with the system.

13. A diagnostic method according to claim 12, wherein said at least one test is adapted to respond to a fault in the system.

14. A diagnostic method according to claim 13, wherein said at least one test is adapted for online detection of a system fault.

15. A diagnostic method according to claim 1, wherein said system is selected from the group consisting of an automotive system, an aircraft system, a power system, a manufacturing system, a chemical system, a chemical process system, a transportation system, a machine system, and an equipment system.

16. A diagnostic method according to claim 1, wherein said system is an automotive system.

17. A diagnostic system for providing diagnostics with respect to a system, comprising:

(a) a plurality of subsystem-resident local agents in communication with said system, each of the subsystem-resident local agents being adapted to;

(i) make diagnostic determinations with respect to said system based, at least in part, on a design matrix; and

(ii) implement at least one action with respect to the system based on said diagnostic determinations,

(b) a system-level agent in communication with said plurality of subsystem-resident local agents, said system-level agent being adapted to combine diagnostic determinations by said plurality of subsystem-resident local agents;

wherein said design matrix is established by;

(i) generating a hybrid quantitative and graphical dependency model that captures at least one fault-to-error characteristic for the system,

(ii) establishing at least one fault condition associated with the system,

(iii) running at least one test design on the hybrid quantitative and graphical dependency model,

(iv) evaluating performance of the at least one test design with respect to the at least one fault condition using the hybrid quantitative and graphical dependency model to refine the hybrid quantitative and graphical dependency model,

(v) establishing the design matrix based on the refined hybrid quantitative and graphical dependency model; and

(vi) outputting at least one error code based on implementation of the refined hybrid quantitative and graphical dependency model.

18. A diagnostic system according to claim 17, wherein the system-level agent is adapted to communicate diagnostic results to a central facility.

19. A diagnostic system according to claim 17, wherein said system is selected from the group consisting of an automotive system, an aircraft system , a power system, a manufacturing system, a chemical system, a chemical process system, a transportation system, a machine system, and an equipment system.