Systems and methods for prediction of trips

• US 9,122,991 B2
• Filed: 08/31/2012
• Issued: 09/01/2015
• Est. Priority Date: 08/23/2007
• Status: Active Grant

• Current Assignee: GE Infrastructure Technology, LLC (General Electric Company)
• Original Assignee: General Electric Company
• Inventors: Babu, Ravi Yoganatha, Jammu, Vinay Bhaskar, Pandey, Achalesh Kumar
• Primary Examiner(s): Wong, Lut
• Application Number:
  US13/600,387
• Publication Number:
  US 20140244567A1
• Time in Patent Office: 1,096 Days
• Field of Search: 706/12, 706/47
• US Class Current: 1/1
• CPC Class Codes: F01D 21/00 Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
• 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 2270/44 active, predictive, or anticipative
• 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
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

A system is disclosed. The system includes a processing subsystem that receives component data signals corresponding to a plurality of parameters of a device, wherein the processing subsystem generates one or more sets of state category component data by allocating the component data signals into respective one or more sets of state category component data, determines a plurality of first dynamic thresholds and a plurality of second dynamic thresholds corresponding to at least one of the one or more sets of state category component data based upon a respective set of state category component data in the one or more sets of state category component data and a respective parameter in the plurality of parameters, and determines an impending trip of the device utilizing the plurality of first dynamic thresholds and the plurality of second dynamic thresholds.

Claims

1. A system, comprising:

a processing subsystem that receives component data signals corresponding to a plurality of parameters of a device, wherein the plurality of parameters of the device comprise at least inlet guide parameters including a VIGV Reference Angle (CSRGV) and a Position feedback IGV (CSGV), wherein the processing subsystem;

generates one or more sets of state category component data by allocating the component data signals into respective one or more sets of state category component data;

selects baseline component data and present component data from a respective set of state category component data in the one or more sets of state category component data;

determines a plurality of first dynamic thresholds based upon the baseline component data and a plurality of second dynamic thresholds based upon the present component data;

determines a variation abnormality by comparing a difference of the VIGV Reference Angle (CSRGV) and the Position feedback IGV (CSGV) to the plurality of first dynamic thresholds and the plurality of second dynamic thresholds;

determines abnormality information corresponding to the variation abnormality based on the plurality of first dynamic thresholds and the plurality of second dynamic thresholds;

determines an impending trip of the device based on the anomaly information; and

shuts down the gas turbine prior to the impending trip.

2. The system of claim 1, wherein the abnormality information comprises a plurality of corresponding abnormality values, wherein the processing subsystem is further programmed for:

fusing the plurality of corresponding abnormality values to determine a probability of tripping of the device; and

determining the impending trip of the device based upon the probability of tripping of the device.

3. The system of claim 2, wherein the plurality of corresponding abnormalities comprise a difference from expected abnormality, a variation abnormality, a mean difference abnormality, a mean shift abnormality, growth rate of an abnormality, a time period of existence of an abnormality, or combinations thereof.

4. The system of claim 1, wherein the plurality of parameters comprises:

operational parameters in addition to the inlet guide vane parameters.

5. The system of claim 4, wherein the inlet guide vane parameters further comprise IGV control servo current (CAGV).

6. The system of claim 4, wherein the operational parameters comprise Power generation in watts (DWATT), Compressor Inlet Flange Temperature (CTIM), Fuel Stroke Reference (FSR), Compressor Discharge Temperature (CTD), Compressor temperature-inlet flange (CTIF), Inlet heating control valve position (CSBHX), Inlet bleed heating (CSRBH), or combinations thereof.

7. The system of claim 1, wherein the one or more sets of state category component data comprise a start-up category component data, a transient category component data, a load category component data, a part load category component data, a full load category component data, or combinations thereof.

8. The system of claim 1, wherein the device is a turbine, a land based gas turbine or an axial compressor.

9. The system of claim 1, further comprising a display device that shows one or more alarms indicating the impending trip of the device.

10. A method, comprising:

generating one or more sets of state category component data by allocating component data signals corresponding to a plurality of parameters of a device into respective one or more sets of state category component data, wherein the plurality of parameters of the device comprise at least inlet guide parameters including a VIGV Reference Angle (CSRGV) and a Position feedback IGV (CSGV);

selecting baseline component data and present component data from a respective set of state category component data in the one or more sets of state category component data;

determining a plurality of first dynamic thresholds based upon the baseline component data and a plurality of second dynamic thresholds based upon the present component data;

determining a variation abnormality by comparing a difference of the VIGV Reference Angle (CSRGV) and the Position feedback IGV (CSGV) to the plurality of first dynamic thresholds and the plurality of second dynamic thresholds;

determining abnormality information corresponding to the variation abnormality based on the plurality of first dynamic thresholds and the plurality of second dynamic thresholds;

determining an impending trip of the device based on the anomaly information; and

shutting down the gas turbine prior to the impending trip.

11. The method of claim 10, wherein generating the one or more sets of state category component data comprises:

determining a state of the device at the time of generation of the component data signals; and

allocating the component data signals into the respective one or more sets of state category component data based upon the state of the device.

12. The method of claim 10, further comprising generating the plurality of first dynamic thresholds and the plurality of second dynamic thresholds for a determined time period.

13. The method of claim 10, wherein determining the first dynamic threshold is further based upon a first predetermined rule;

and

determining the second dynamic threshold is further based upon a second predetermined rule.

14. The method of claim 13, further comprising selecting the first predetermined rule and the second predetermined rule based upon respective parameter in the plurality of parameters and the respective state category component data in the one or more sets of state category component data.

15. The method of claim 10, wherein determining the abnormality information comprises determining a plurality of abnormality values based upon the plurality of first dynamic thresholds and the plurality of second dynamic thresholds;

and

wherein determining the impeding trip comprises fusing the plurality of abnormality values to determine a probability of tripping of the device; and

determining the impending trip of the device based upon the probability of tripping of the device.

16. The method of claim 15, wherein fusing the plurality of abnormality values to determine a probability of tripping of the device comprises fusing the plurality of abnormality values using a Bayesian fusion and an apriori probability assigned to the plurality of abnormality values.

17. The method of claim 16, further comprising assigning an apriori probability to each of the plurality of abnormality values using domain knowledge.

18. The method of claim 16, wherein fusing the plurality of abnormality values further comprises normalizing one or more of the plurality of abnormality values generated due to varnishing and calibration issues.