METHOD AND SYSTEM FOR PREDICTING REMAINING LIFE FOR MOTORS FEATURING ON-LINE INSULATION CONDITION MONITOR

• US 20060259271A1
• Filed: 05/12/2005
• Published: 11/16/2006
• Est. Priority Date: 05/12/2005
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Flickinger, Greg, House, Michael, Chmiel, Gary
• Granted Patent: US 7,254,514 B2
• Time in Patent Office: Days
• US Class Current: 702/181
• CPC Class Codes: G01R 31/343 in operation
• CPC Class Codes: G05B 23/0248 Causal models, e.g. fault tree; digraphs; qualitative physics
• 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

A method for determining reliability and a remaining time before failure with statistical confidence for a motor system includes acquiring historical motor data in a computer system, obtaining operational parameter data, uploading the operational parameter data to the computer system, performing failure analysis, developing a causal network, and performing an integrated causal network and reliability analysis of the motor system. The historical motor data corresponds to the motor system. The operational parameter data is obtained from sensors at the motor system. The sensors include a tan delta sensor. The failure analysis is performed based on a composite of reliability probability distributions corresponding to predetermined sub-populations of historical motor system failure causes. The causal network is developed for modeling reliability of one or more motor system components and assessing motor system component condition based on the causal network. Results from the performing failure analysis are integrated with results from the assessing motor system component condition based on the causal network to compute a quantitative value for a time remaining before failure with an ascertained statistical confidence.

Claims

1. A method for determining reliability and a remaining time before failure with statistical confidence for a motor system, the method comprising:

acquiring historical motor data corresponding to the motor system in a computer system;

obtaining operational parameter data from sensors at the motor system, the sensors including a tan delta sensor;

uploading the operational parameter data to the computer system;

performing failure analysis based on a composite of reliability probability distributions corresponding to predetermined sub-populations of historical motor system failure causes;

developing a causal network for modeling reliability of one or more motor system components and assessing motor system component condition based on the causal network; and

performing an integrated causal network and reliability analysis of the motor system, wherein results from the performing failure analysis are integrated with results from the assessing motor system component condition based on the causal network to compute a quantitative value for a time remaining before failure with an ascertained statistical confidence.

2. The method of claim 1, wherein the developing a causal network includes developing a Bayesian Belief Network.

3. The method of claim 1, wherein the performing failure analysis comprises modeling a failure rate of a system component using a Weibull probability distribution function.

4. The method of claim 1, wherein the obtaining operational parameter data comprises obtaining leakage current data.

5. The method of claim 4, wherein the obtaining leakage current data comprises at least one of:

obtaining leakage current phase data; and

obtaining leakage current amplitude data.

6. The method of claim 4, wherein the obtaining leakage current data further comprises obtaining leakage current data using the tan delta sensor.

7. The method of claim 4, further comprising predicting insulation degradation responsive to the leakage current data.

8. The method of claim 1, further comprising providing a graphical user interface that displays remaining time before failure and/or predicted motor life as a moving bar-graph.

9. The method of claim 1, further comprising transmitting the operational parameter data from sensors to the computer system via a wireless network.

10. The method of claim 1, wherein the performing failure analysis further comprises predicting insulation degradation of a motor system component responsive to leakage current data measured at the motor system.

11. A method for assessing reliability and determining, with a statistical degree of confidence, a quantitative value for time remaining before failure for an electric motor system, the method comprising:

storing motor system component failure data in a computer data base, the motor system component failure data including leakage current data;

performing a motor system fault-tree analysis based on the motor system component failure data, the fault-tree analysis including insulation degradation based on the leakage current data;

developing a motor system component fault model based on the motor system fault-tree analysis;

modeling historical failure data of motor system components using a probability distribution function;

developing a directed causal inference model and selecting system variables used for collecting data based on the causal inference model;

developing a conditional probability matrix comprising failure probability corresponding to possible failure events for the motor system;

developing an overall motor system reliability model based on the causal interference model and the conditional probability matrix; and

computing a statistical assessment of reliability of the motor system and a qualitative value for time remaining before failure using the overall motor system reliability model.

12. The method of claim 11, wherein the computing the statistical assessment includes identifying a particular motor system component as a most probable candidate for needing at least one of service and replacement.

13. The method of claim 11, wherein the modeling historical failure data of motor system components comprises using a Weibull probability distribution function to model historical failure data of motor system components.

14. The method of claim 11, wherein the developing the directed causal inference model includes developing a Bayesian Belief Network.

15. The method of claim 11, further comprising acquiring motor system operational parameter data using sensors disposed at the motor system.

16. The method of claim 15, wherein the acquiring motor system operational parameter data includes obtaining leakage current data using a tan delta sensor.

17. A system for determining reliability and a remaining time before failure with statistical confidence for a motor system, the system comprising:

a tan delta sensor disposed in electrical communication with the motor system to access data of the motor system;

a computer comprising;

a storage medium, readable by a processing circuit, storing instructions for execution by the processing circuit for;

acquiring historical motor data corresponding to the motor system in a computer system;

obtaining operational parameter data from sensors at the motor system, the sensors including a tan delta sensor;

uploading the operational parameter data to the computer system;

performing failure analysis based on a composite of reliability probability distributions corresponding to predetermined sub-populations of historical motor system failure causes;

developing a causal network for modeling reliability of one or more motor system components and assessing motor system component condition based on the causal network; and

performing an integrated causal network and reliability analysis of the motor system, wherein results from the performing failure analysis are integrated with results from the assessing motor system component condition based on the causal network to compute a quantitative value for a time remaining before failure with an ascertained statistical confidence; and

a transmission network in communication with the computer and the tan delta sensor configured to communicate the data from the tan delta sensor to the computer.

18. The system of claim 17, wherein the transmission network comprises:

a transmitter receptive of the data and transmitting the data;

a receiver in communication with the transmitter to receive the data;

an access point in communication with the receiver and the computer to relay the data to the computer.

19. The system of claim 18, wherein the receiver and transmitter are wireless.

20. The system of claim 17, wherein the tan delta sensor obtains leakage current data of the motor system, and the leakage current data includes at least one of:

leakage current phase data; and

leakage current amplitude data.