TURBINE FAULT PREDICTION

• US 20130274898A1
• Filed: 04/11/2012
• Published: 10/17/2013
• Est. Priority Date: 04/11/2012
• Status: Active Grant

• Current Assignee: GE Infrastructure Technology, LLC (GE Vernova, Inc.)
• Original Assignee: General Electric Company
• Inventors: Thatikonda, Ravi Kanth Sai, Nemani, Subhash
• Granted Patent: US 9,360,864 B2
• Time in Patent Office: Days
• US Class Current: 700/44
• CPC Class Codes: F02C 9/00 Controlling gas-turbine plants; Controlling fuel supply in air- breathing jet-propulsion plants controlling air intakes F02C7/057; controlling turbines F01D; controlling compressors F04D27/00; controlling in general G05
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: F05D 2260/82 Forecasts
• CPC Class Codes: G05B 23/02 Electric testing or monitoring
• CPC Class Codes: G05B 23/0224 Process history based detection method, e.g. whereby history implies the availability of large amounts of data
• 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 system is provided. The system includes an industrial controller configured to control and obtain current parameter data from one or more components of an industrial system. Further, a storage is included and is configured to store historical data comprising parameter data from the one or more components. The system also includes a prediction controller configured to receive the current parameter data from the industrial controller, receive the historical data from the storage, and to generate an overall predictive score based at least in part upon the current parameter data and the historical data. The overall predictive score represents a likelihood of a fault within the industrial process control system.

Claims

1. A system, comprising:

an industrial controller configured to control and obtain current parameter data from one or more components of an industrial system;

a storage configured to store historical data comprising parameter data from the one or more components;

a prediction controller configured to;

receive the current parameter data from the industrial controller;

receive the historical data from the storage; and

generate an overall predictive score based at least in part upon the current parameter data and the historical data, wherein the overall predictive score represents a likelihood of a fault within the industrial system.

2. The system of claim 1, comprising a common controller having the prediction controller and the industrial controller.

3. The system of claim 1, wherein the industrial system comprises a turbine system, and the prediction controller is configured to generate the overall predictive score representing the likelihood of the fault within the turbine system.

4. The system of claim 3, wherein the prediction controller is configured to generate overall predictive scores representing the likelihood of a fault, a trip, a shutdown, a rollback, or combination thereof, of the turbine system.

5. The system of claim 1, wherein the prediction controller is configured to provide the overall predictive score to a human-machine interface (HMI).

6. The system of claim 1, wherein the prediction controller is configured to:

generate a current process predictive score based upon the current parameter data;

generate a historical predictive score based upon the historic data; and

generate the overall predictive score by combining the current process predictive score to the historical predictive score.

7. The system of claim 1, wherein the prediction controller is configured to vary the overall predictive score continuously or in periodic intervals as the industrial system is in operation.

8. The system of claim 1, comprising the industrial system, wherein the industrial system comprises a gas turbine engine drivingly coupled to an electrical generator.

9. A system, comprising:

a system configured to;

receive predictive score data relating to a likelihood of future faults of a turbine system, wherein the predictive score data is based on historical data relating to one or more components of the turbine system and current data relating to the one or more components; and

output an HMI image on a display, wherein the HMI image comprises an indication of the predictive score data.

10. The system of claim 9, wherein the indication of the predictive score data provides the likelihood of a trip, a shutdown, a runback, or combination thereof, occurring in the turbine system.

11. The system of claim 10, wherein the indication of the predictive score data comprises a quick indicator comprising a trip indicator configured to represent the likelihood of the trip, a shutdown indicator configured to represent the likelihood of the shutdown, and a runback indicator configured to represent the likelihood of the runback;

wherein the trip indicator, the shutdown indicator, and the runback indicator each comprise a graphical symbol that changes color as the likelihood of the trip, the shutdown, or the runback changes, respectively.

12. The system of claim 11, wherein each graphical symbol is configured to display a first color when no fault is predicted, to display a second color when potential issues are detected that may cause a fault, and display a third color when a fault is eminent unless something in the industrial process control system changes.

13. The system of claim 11, wherein each graphical symbol is configured to progressively increase in darkens between a low likelihood and a high likelihood of the trip, the shutdown, or the runback occurring.

14. The system of claim 9, wherein the HMI image comprises a detailed prediction screen, comprising:

identification data of one or more parameters affecting the predictive score data; and

an indication of the likelihood of a trip, a shutdown, a runback, or combination thereof, due to the one or more parameters.

15. The system of claim 9, wherein the HMI image comprises a reset interface configured to enable at least partial reset of the historical data for the one or more components.

16. The system of claim 9, wherein the HMI image comprises a tips section that provides remedial measures to affect the current data relating to the one or more components to reduce the likelihood of the future faults.

17. A method, comprising:

collecting current parameter data relating to one or more components of a turbine system;

collecting historical data comprising one or more faults and parameter data associated with the faults for the one or more components; and

generating a trip predictive score, a shutdown predictive score, and a runback predictive score based at least in part upon the current parameter data and the historical data, wherein the trip, shutdown, and runback predictive scores represent a likelihood of a trip, a shutdown, and a runback, respectively, of the turbine system.

18. The method of claim 17, comprising:

outputting the trip, shutdown, and runback predictive scores to a human-machine interface (HMI) for display of the trip, shutdown, and runback predictive scores to an operator.

19. The method of claim 17, wherein generating the trip predictive score, the shutdown predictive score, and the runback predictive score comprises:

determining a current trip predictive score, a current shutdown predictive score, and a current runback predictive score based upon the current parameter data;

determining a historical trip predictive score, a historical shutdown predictive score, and a historical runback predictive score based upon the historical data; and

generating the trip predictive score, the shutdown predictive score, and the runback predictive score by combining the current trip, the current shutdown, and the current runback predictive scores to the historical trip, historical shutdown, and historical runback predictive scores, respectively.

20. The method of claim 17, comprising enabling operator intervention to help avoid the trip, the shutdown, and/or the runback based on the trip predictive score, the shutdown predictive score, the runback predictive score, or a combination thereof.