System and method for advanced condition monitoring of an asset system

• US 8,352,216 B2
• Filed: 05/29/2008
• Issued: 01/08/2013
• Est. Priority Date: 05/29/2008
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Subbu, Rajesh Venkat, Hershey, John Erik, Hu, Xiao, Mitchell, Robert James Jr., Taware, Avinash Vinayak, Bonissone, Piero Patrone
• Primary Examiner(s): Moffat, Jonathan C Teixeira
• Assistant Examiner(s): HENSON, MISCHITA L
• Application Number:
  US12/129,622
• Publication Number:
  US 20090299695A1
• Time in Patent Office: 1,685 Days
• Field of Search: 702/34, 702/59, 702181-183
• US Class Current: 702/181
• 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: G06F 11/30 Monitoring

Abstract

A method for advanced condition monitoring of an asset system includes sensing actual values of an operating condition for an operating regime of the asset system using at least one sensor; estimating sensed values of the operating condition by using an auto-associative neural network; determining a residual vector between the estimated sensed values and the actual values; and performing a fault diagnostic on the residual vector. In another method, an operating space of the asset system is segmented into operating regimes; the auto-associative neural network determines estimates of actual measured values; a residual vector is determined from the auto-associative neural network; a fault diagnostic is performed on the residual vector; and a change of the operation of the asset system is determined by analysis of the residual vector. An alert is provided if necessary. A smart sensor system includes an on-board processing unit for performing the method of the invention.

Claims

1. A method for advanced condition monitoring of an asset system, the method comprising the steps of:

segmenting an operational envelope of an asset system into a plurality of operating regimes;

sensing actual values of an operating condition for one of the plurality of operating regimes of the asset system using at least one sensor;

estimating sensed values of the operating condition by using an auto-associative neural network (AANN) of the actual values sensed by the at least one sensor;

determining a residual vector between the estimated sensed values and the actual values sensed by the at least one sensor;

performing a fault diagnostic on the residual vector; and

providing an alert if a change of the operation of the asset system has been determined.

2. The method of claim 1, wherein the AANN comprises hidden nodes having nonlinear tan-sigmoid functions.

3. The method of claim 1, wherein the AANN comprises a central bottleneck layer with embedded linear transformation functions.

4. The method of claim 1, wherein the performing step is performed using one of the group consisting of a physics-based model, a relationship between the actual sensed values and plant information, an operator note, a plant power supply parameter, a temporary change to an equipment operating point, and an environmental factor.

5. The method of claim 1, wherein the performing step comprises performing a sequential probability ratio test (SPRT).

6. The method of claim 1, further comprising the steps of:

normalizing the residual using an average of the actual sensed values;

computing a figure-of-merit based on the normalized residual;

comparing the figure-of-merit to a specified threshold; and

reporting a fault if the figure-of-merit is larger than a threshold value.

7. The method of claim 6, wherein the reported fault is one of the group consisting of a sensor fault, an asset system fault, and an AANN fault.

8. The method of claim 1, wherein the alerting step comprises distributing a message via an information transport medium selected from the group consisting of an electrical cable, power line conduction, an intranet, an Internet, and a wireless transmission.

9. The method of claim 1, wherein the at least one sensor comprises a smart sensor.

10. The method of claim 9, wherein the smart sensor is connected to a smart sensor system.

11. The method of claim 10, wherein the smart sensor system comprises an on-board processing unit for advanced condition monitoring of the asset system.

12. A method for advanced condition monitoring of an asset system, the method comprising the steps of:

segmenting an operational envelope of an asset system into a plurality of operating regimes;

using an auto-associative neural network (AANN) to determine estimates of actual values sensed by the at least one sensor;

determining a residual vector between the estimated sensed values and the actual values sensed by at least one sensor from the auto-associative neural network;

performing a fault diagnostic on the residual vector;

determining a change of the operation of the asset system by analysis of the residual vector; and

providing an alert if the change of the operation of the asset system has been determined.

13. The method of claim 12, wherein the AANN implements a global model over the plurality of operating regimes of the asset system.

14. The method of claim 12, wherein the at least one sensor comprises a smart sensor.

15. The method of claim 14, wherein the smart sensor is connected to a smart sensor system.

16. The method of claim 15, wherein the smart sensor system comprises an on-board processing unit for advanced condition monitoring of the asset system.

17. A smart sensor system for advanced condition monitoring of an asset system, comprising:

a smart sensor for sensing actual values of an operating condition for an operating regime of an asset system, the smart sensor being connected to an input port via a cable; and

an on-board processing unit for advanced condition monitoring of the asset system, the on-board processing unit estimating sensed values of the operating condition by segmenting an operational envelope of an asset system into a plurality of operating regimes, using an auto-associative neural network (AANN) of the actual values sensed by the smart sensor, determining a residual vector between the estimated sensed value and the actual value sensed by the smart sensor, performing a fault diagnostic on the residual vector, and providing an alert if a change of the operation of the asset system has been determined.

18. The system of claim 17, further comprising a wireless communications unit for wirelessly transmitting signals from the smart sensor system to a peripheral processing device.

19. The system of claim 17, further comprising a display and alarm unit for displaying computational results from the processing unit.