GENERALIZED PATTERN RECOGNITION FOR FAULT DIAGNOSIS IN MACHINE CONDITION MONITORING

• US 20130332773A1
• Filed: 06/12/2012
• Published: 12/12/2013
• Est. Priority Date: 06/12/2012
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG, Siemens Corp. (Siemens AG)
• Inventors: Yuan, Chao, Chakraborty, Amit, Hackstein, Holger, Wiebking, Leif
• Granted Patent: US 8,886,574 B2
• Time in Patent Office: Days
• US Class Current: 714/26
• CPC Class Codes: G05B 23/0205 by means of a monitoring system capable of detecting and responding to faults
• CPC Class Codes: G05B 23/0229 knowledge based, e.g. expert systems; genetic algorithms
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A generalized pattern recognition is used to identify faults in machine condition monitoring. Pattern clusters are identified in operating data. A classifier is trained using the pattern clusters in addition to annotated training data. The operating data is also used to cluster the signals in the operating data into signal clusters. Monitored data samples are then classified by evaluating confidence vectors that include substitutions of signals contained in the training data by signals in the same signal clusters as the signals contained in the training data.

Claims

1. A method of machine condition monitoring, comprising:

receiving, by a computer, historic operating data including data from O signals over time;

extracting I patterns x from data from individual signals in the operating data;

clustering the I patterns into K pattern clusters c_k based on similarities;

clustering the O signals into R signal clusters based on correlations among the O signals;

receiving an annotated training data sample containing data from N signals selected from the O signals and having at least one marked failure time period;

creating a K×

N confidence vector containing K confidence values for each of the N signals, each confidence value representing a confidence that a pattern x extracted from data in the marked failure time period of a signal belongs to one of the K pattern clusters;

training a classifier using the K×

N confidence vector;

receiving, by a computer, a monitored data sample including data from the O signals; and

classifying, by a computer, the monitored data sample as indicating a failure based on at least one of the O signals not among the I signals being in a same signal cluster as one of the I signals and further based on a determination that the at least one of the O signals has confidence values similar to confidence values of the one of the I signals contained in the K×

N confidence vector.

2. A method as in claim 1, wherein extracting I patterns from the individual signals in the operating data comprises using a sliding time window of fixed length.

3. A method as in claim 1, wherein clustering the I patterns into K pattern clusters and clustering the O signals into R signal clusters further comprises:

for each of the I patterns, extracting scalar features describing the pattern; and

using the scalar features to cluster the patterns and the signals.

4. A method as in claim 1, wherein clustering the I patterns into K pattern clusters is performed across all O signals.

5. A method as in claim 1, wherein clustering the I patterns into K pattern clusters is performed across signals in a same signal cluster.

6. A method as in claim 1, wherein clustering the I patterns into K pattern clusters comprises applying K-mean clustering to form the clusters.

7. A method as in claim 1, wherein clustering the O signals into R signal clusters further comprises:

calculating pair-wise signal correlation based on the historic operating data and clustering the signals using hierarchical clustering.

8. A method as in claim 1, wherein each confidence value representing a confidence that pattern x belongs to pattern cluster c_k is defined by:

9. A method as in claim 1, wherein one of the K confidence values for a particular signal equals 1, and the remaining of the K confidence values equal zero.

10. A method as in claim 1, wherein, for each of the N signals, a sum of the K confidence values equals 1.

11. A method as in claim 1, wherein classifying the monitored data sample comprises:

evaluating confidence vectors for sub-combinations of the monitored data sample signals O in which each of the annotated data training signals N is either included in the sub-combination or is represented in the sub-combination by a monitored data sample signal in the same signal cluster c_k as the represented annotated data training signal.

12. A method as in claim 11, wherein classifying the monitored data sample further comprises:

applying a greedy algorithm to identify a dominant confidence vector; and

determining whether an evaluation function value for the dominant confidence vector exceeds a threshold.

13. A non-transitory computer-usable medium having computer readable instructions stored thereon for execution by a processor to perform a method of machine condition monitoring, the method comprising:

receiving historic operating data including data from O signals over time;

extracting I patterns x from data from individual signals in the operating data;

clustering the I patterns into K pattern clusters c_k based on similarities;

clustering the O signals into R signal clusters based on correlations among the O signals;

receiving an annotated training data sample containing data from N signals selected from the O signals and having at least one marked failure time period;

creating a K×

N confidence vector containing K confidence values for each of the N signals, each confidence value representing a confidence that a pattern x extracted from data in the marked failure time period of a signal belongs to one of the K pattern clusters;

training a classifier using the K×

N confidence vector;

receiving a monitored data sample including data from the O signals; and

classifying the monitored data sample as indicating a failure based on at least one of the O signals not among the I signals being in a same signal cluster as one of the I signals and further based on a determination that the at least one of the O signals has confidence values similar to confidence values of the one of the I signals contained in the K×

N confidence vector.

14. A non-transitory computer-usable medium as in claim 13, wherein extracting I patterns from the individual signals in the operating data comprises using a sliding time window of fixed length.

15. A non-transitory computer-usable medium as in claim 13, wherein clustering the I patterns into K pattern clusters and clustering the O signals into R signal clusters further comprises:

for each of the I patterns, extracting scalar features describing the pattern; and

using the scalar features to cluster the patterns and the signals.

16. A non-transitory computer-usable medium as in claim 13, wherein clustering the I patterns into K pattern clusters is performed across all O signals.

17. A non-transitory computer-usable medium as in claim 13, wherein clustering the I patterns into K pattern clusters is performed across signals in a same signal cluster.

18. A non-transitory computer-usable medium as in claim 13, wherein clustering the I patterns into K pattern clusters comprises applying K-mean clustering to form the clusters.

19. A non-transitory computer-usable medium as in claim 13, wherein clustering the O signals into R signal clusters further comprises:

calculating pair-wise signal correlation based on the historic operating data; and

clustering the signals using hierarchical clustering.

20. A non-transitory computer-usable medium as in claim 13, wherein each confidence value representing a confidence that pattern x belongs to pattern cluster c_k is defined by:

21. A non-transitory computer-usable medium as in claim 13, wherein one of the K confidence values for a particular signal equals 1, and the remaining of the K confidence values equal zero.

22. A non-transitory computer-usable medium as in claim 13, wherein, for each of the N signals, a sum of the K confidence values equals 1.

23. A non-transitory computer-usable medium as in claim 13, wherein classifying the monitored data sample comprises:

evaluating confidence vectors for sub-combinations of the monitored data sample signals O in which each of the annotated data training signals N is either included in the sub-combination or is represented in the sub-combination by a monitored data sample signal in the same signal cluster c_k as the represented annotated data training signal.

24. A non-transitory computer-usable medium as in claim 23, wherein classifying the monitored data sample further comprises:

applying a greedy algorithm to identify a dominant confidence vector; and

determining whether an evaluation function value for the dominant confidence vector exceeds a threshold.