Power Plant System Fault Diagnosis by Learning Historical System Failure Signatures

• US 20180299877A1
• Filed: 01/26/2018
• Published: 10/18/2018
• Est. Priority Date: 04/18/2017
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Laboratories America Inc (NEC Corporation)
• Inventors: Cheng, Wei, Chen, Haifeng, Yoshihira, Kenji
• Granted Patent: US 10,496,085 B2
• Time in Patent Office: Days
• CPC Class Codes: G01D 5/00 Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable G01D3/00 takes precedence; specially adapted for apparatus giving results other than momentary value of variable G01D1/00
• CPC Class Codes: G05B 23/0275 Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
• CPC Class Codes: G05B 23/0286 Modifications to the monitored process, e.g. stopping operation or adapting control
• CPC Class Codes: G06F 11/0736 in functional embedded systems, i.e. in a data processing system designed as a combination of hardware and software dedicated to performing a certain function testing or monitoring of automated control systems G05B23/02
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 41/0654 using network fault recovery ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437
• CPC Class Codes: H04L 41/142 using statistical or mathematical methods
• CPC Class Codes: Y04S 10/52 Outage or fault management, e.g. fault detection or location
• CPC Class Codes: Y04S 40/00 Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them

Abstract

A method, computer program product, and a system is provided for power plant system fault diagnosis. The method includes detecting, using an invariant model, a fault event based on a broken pair-wise correlation. The method also includes constructing a fault signature based on the fault event. The method further includes generating a feature vector in a feature subspace for the fault signature, wherein said feature vector includes at least one status of at least one system component during the fault event. The method additionally includes determining a corrective action correlated to the fault signature, from among a plurality of candidate corrective actions associated with the one or more historical representative signature, based on a Jaccard similarity using the feature vector in the feature subspace. The method also includes initiating the corrective action on a hardware device to mitigate expected harm.

Claims

1. A computer-implemented method for power plant system fault diagnosis, the method comprising:

detecting, by a processor using an invariant model, a fault event based on a broken pair-wise correlation;

constructing, by the processor, a fault signature based on the fault event;

generating, by the processor, a feature vector in a feature subspace for the fault signature, wherein said feature vector includes at least one status of at least one system component during the fault event;

determining, by the processor, a corrective action correlated to the fault signature, from among a plurality of candidate corrective actions associated with the one or more historical representative signature, based on a Jaccard similarity using the feature vector in the feature subspace; and

initiating, by the processor, the corrective action on a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

2. The computer-implemented method of claim 1, wherein the invariant model learns continuous pair-wise correlations between one or more system components over time.

3. The computer-implemented method of claim 2, wherein the invariant model computes a normalized residual between a measurement for one of the pair-wise correlations and an estimate for the one of the pair-wise correlations, wherein the normalized residual exceeding a predetermined threshold signals the one of the pair-wise correlations is broken.

4. The computer-implemented method of claim 1, wherein the invariant model includes an autoregressive model.

5. The computer-implemented method of claim 1, further comprising generating the feature subspace using one or more binary vectors representing each of one or more pair-wise correlations in the invariant model.

6. The computer-implemented method of claim 5, wherein the one or more binary vectors has a value of 1 if the represented one or more pair-wise correlations is broken and 0 otherwise.

7. The computer-implemented method of claim 5, wherein the generating the feature subspace includes a chi-square feature selection method using one or more categories of historical signatures with one or more fault labels.

8. The computer-implemented method of claim 1, wherein the generating the feature vector includes generating fault signatures feature vectors from the fault signature and one or more historical representative signature feature vectors from the one or more historical representative signature.

9. The computer-implemented method of claim 8, wherein the generating the feature vector further includes mapping the fault signature feature vectors and the one or more historical representative signature feature vectors in the feature subspace based on informative broken evidence.

10. The computer-implemented method of claim 4, wherein the autoregressive model is an autoregressive exogeneous model.

11. A computer program product for power plant system fault diagnosis, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

detecting, using an invariant model, a fault event based on a broken pair-wise correlation;

constructing a fault signature based on the fault event;

generating a feature vector in a feature subspace for the fault signature, wherein said feature vector includes at least one status of at least one system component during the fault event;

determining a corrective action correlated to the fault signature, from among a plurality of candidate corrective actions associated with the one or more historical representative signature, based on a Jaccard similarity using the feature vector in the feature subspace; and

initiating the corrective action on a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

12. A power plant fault diagnosis system, comprising:

a detection network coupled to a processor, the processor configured to;

detect, using an invariant model, a fault event based on a broken pair-wise correlation;

construct a fault signature based on the fault event;

generate a feature vector in a feature subspace for the fault signature, wherein said feature vector includes at least one status of at least one system component during the fault event;

determine a corrective action correlated to the fault signature, from among a plurality of candidate corrective actions associated with the one or more historical representative signature, based on a Jaccard similarity using the feature vector in the feature subspace; and

initiate the corrective action on a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.

13. The power plant fault diagnosis system of claim 12, wherein the invariant model learns continuous pair-wise correlations between one or more system components over time.

14. The power plant fault diagnosis system of claim 13, wherein the invariant model computes a normalized residual between a measurement for one of the pair-wise correlations and an estimate for the one of the pair-wise correlations, wherein the normalized residual exceeding a predetermined threshold signals the one of the pair-wise correlations is broken.

15. The power plant fault diagnosis system of claim 12, wherein the invariant model includes an autoregressive exogeneous model.

16. The power plant fault diagnosis system of claim 12, further comprising generating the feature subspace using one or more binary vectors representing each of one or more pair-wise correlations in the invariant model.

17. The power plant fault diagnosis system of claim 16, wherein the one or more binary vectors has a value of 1 if the represented one or more pair-wise correlations is broken and 0 otherwise.

18. The power plant fault diagnosis system of claim 16, wherein the generating the feature subspace includes a chi-square feature selection method using one or more categories of historical signatures with one or more fault labels.

19. The power plant fault diagnosis system of claim 12, wherein the generating the feature vector includes generating fault signatures feature vectors from the fault signature and one or more historical representative signature feature vectors from the one or more historical representative signature.

20. The power plant fault diagnosis system of claim 19, wherein the generating the feature vector further includes mapping the fault signature feature vectors and the one or more historical representative signature feature vectors in the feature subspace based on informative broken evidence.