System and method for advanced condition monitoring of an asset system

• US 8,144,005 B2
• Filed: 05/29/2008
• Issued: 03/27/2012
• Est. Priority Date: 05/29/2008
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Mitchell, Jr., Robert James, Subbu, Rajesh Venkat, Taware, Avinash Vinayak, Bonissone, Piero Patrone, Hu, Xiao, Hershey, John Erik
• Primary Examiner(s): CROSLAND, DONNIE L
• Application Number:
  US12/129,611
• Publication Number:
  US 20090295561A1
• Time in Patent Office: 1,398 Days
• Field of Search: 340/501
• US Class Current: 340/501
• CPC Class Codes: G05B 19/41875 characterised by quality surveillance of production
• CPC Class Codes: G05B 2219/31455 Monitor process status
• CPC Class Codes: G05B 2219/32201 Build statistical model of past normal proces, compare with actual process
• CPC Class Codes: G05B 2219/33027 Artificial neural network controller
• CPC Class Codes: Y02P 90/02 Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

A method for advanced condition monitoring of an asset system includes monitoring a variable of an asset system using the at least one sensor of a smart sensor system; determining whether the asset system has departed from normal operation; and identifying the variable of the asset system indicating the departure from normal operation. In another method, the time sequential values of the monitored variable is analyzed by using a Rank Permutation Transformation test, a Hotelling'"'"'s T² statistic test, and a Likelihood Ratio Test; and a change of an operating condition of the asset system is determined using the analyzed values. 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:

monitoring at least one variable of an asset system using at least one sensor of a smart sensor system;

determining whether the asset system has departed from normal operation using a Hotelling'"'"'s T² statistic technique;

identifying the at least one variable of the asset system indicating the departure from normal operation; and

providing an alert if the asset system departs from normal operation.

2. The method of claim 1, further comprising the step of applying a post-processing technique to the Hotelling'"'"'s T² statistic technique.

3. The method of claim 2, wherein the post-processing technique is selected from the group consisting of a curve fitting technique, a wavelet technique, a norm minimization technique, a model fitting technique, a median filtering technique, a calculation of excess kurtosis testing technique, a higher order moment statistical technique, an entropy measurement, a minority-decision measurement, and a combination thereof.

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

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

6. The method of claim 5, wherein the smart sensor is connected to a smart sensor system.

7. The method of claim 6, wherein the smart sensor system comprises an on-board processing unit for advanced condition monitoring of the asset system.

8. A smart sensor system, comprising:

a smart sensor for monitoring an operating condition 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 using the method of claim 1.

9. The system of claim 8, further comprising a wireless communications unit for wirelessly transmitting signals from the smart sensor system to a peripheral processing device.

10. The system of claim 8, further comprising a display and alarm unit for displaying computational results from the processing unit.

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

monitoring at least one variable of an asset system using at least one sensor of a smart sensor system;

determining whether the asset system has departed from normal operation;

identifying the at least one variable of the asset system indicating the departure from normal operation by;

expressing a Hotelling'"'"'s T² statistic technique in terms of its principal components;

normalizing the scores of the principal components;

calculating the contributions of variables appearing in the normalized scores;

normalizing the contributions of the variables;

ordering a ranking of the normalized contributions of the variables from largest magnitude to smallest magnitude; and

interpreting the ranking order as an order of the significance of the variables, and

providing an alert if the asset system departs from normal operation.

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

monitoring a variable of an asset system using a smart sensor;

analyzing time sequential values of the monitored variable by using a group consisting of a Rank Permutation Transformation test, a Hotelling'"'"'s T² statistic test, and a Likelihood Ratio Test;

determining a change of an operating condition of the asset system using the analyzed time sequential values of the monitored variable; and

alerting of the change of the operating condition of the asset system.

13. The method of claim 12, further comprising the step of applying a post-processing technique to the Hotelling'"'"'s T² statistic test.

14. The method of claim 13, wherein the post-processing technique is selected from the group consisting of a curve fitting technique, a wavelet technique, a norm minimization technique, a model fitting technique, a median filtering technique, a calculation of excess kurtosis testing technique, a higher order moment statistical technique, an entropy measurement, a minority-decision measurement, and a combination thereof.

15. The method of claim 12, 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.