System and method for detecting turbine underperformance and operation anomaly

Patent metadata

Field	Value
Publication number	US-11378063-B2
Application number	US-202016797593-A
Country	US
Kind code	B2
Filing date	Feb 21, 2020
Priority date	Feb 21, 2020
Publication date	Jul 5, 2022
Grant date	Jul 5, 2022

Abstract

A method of correcting turbine underperformance includes calculating a power production curve using monitored data, detecting changes between the monitored data and a baseline power production curve, generating operability curves for paired operational variables from the monitored data, detecting changes between the operability curves and corresponding baseline operability curves, comparing the changes to a respective predetermined metric, and if the change exceeds the metric, providing feedback to a turbine control system identifying at least one of the paired operational variables for each paired variable in excess of the metric. A system and a non-transitory computer-readable medium are also disclosed.

First claim

The invention claimed is:

1. A method of correcting turbine underperformance, the method comprising:
accessing monitored operational data for the turbine;
calculating a power production curve using at least a portion of the monitored operational data;
predicting a baseline power production curve based on expected performance of the turbine;
detecting a first set of changes between at least the portion of the monitored operational data and the baseline power production curve;
generating one or more monitored operability curves from the at least a portion of the monitored operational data, each of the one or more monitored operability curves describing a relationship between monitored values for paired operational variables;
generating one or more baseline operability curves for the turbine, each of the one or more baseline operability curves describing an expected relationship between the paired operational variables;
detecting a set of changes between the one or more monitored operability curves and a corresponding one of the one or more baseline operability curves;
comparing one or more of the set of changes to a respective predetermined metric for each of the paired operational variables; and
based on a determination that one or more members of the set of changes is in excess of the respective predetermined metric, providing feedback to a turbine control system identifying at least one of the paired operational variables that corresponds to the member of the set of changes in excess of the predetermined metric.

2. The method of claim 1 , including preconditioning the portion of the monitored operational data to exclude at least one of data representing periods of at least one of turbine downtime and turbine curtailment.

3. The method of claim 1 , including in the baseline power production curve one or more elements of historic measured data for the turbine.

4. The method of claim 1 , including applying smoothing techniques to the expected baseline power production curve.

5. The method of claim 1 , including generating a time series plot of power residuals prior to detecting the set of changes.

6. The method of claim 5 , including applying a change point detection algorithm to detect the set of changes.

7. The method of claim 1 , including at least one member of the paired operational variables identified to the turbine control system having a value controllable by the turbine control system.

8. A non-transitory computer-readable medium having stored thereon instructions which when executed by a control processor cause the control processor to perform a method of correcting turbine underperformance, the method comprising:
accessing monitored operational data for the turbine;
calculating a power production curve using at least a portion of the monitored operational data;
predicting a baseline power production curve based on expected performance of the turbine;
detecting a first set of changes between at least the portion of the monitored operational data and the baseline power production curve;
generating one or more monitored operability curves from the at least a portion of the monitored operational data, each of the one or more monitored operability curves describing a relationship between monitored values for paired operational variables;
generating one or more baseline operability curves for the turbine, each of the one or more baseline operability curves describing an expected relationship between the paired operational variables;
detecting a set of changes between the one or more monitored operability curves and a corresponding one of the one or more baseline operability curves;
comparing one or more of the set of changes to a respective predetermined metric for each of the paired operational variables; and
based on a determination that one or more members of the set of changes is in excess of the respective predetermined metric, providing feedback to the turbine control system identifying at least one of the paired operational variables that corresponds to the member of the set of changes in excess of the predetermined metric.

9. The non-transitory computer-readable medium of claim 8 , the instructions further configured to cause the control processor to perform the method by including preconditioning the portion of the monitored operational data to exclude at least one of data representing periods of at least one of turbine downtime and turbine curtailment.

10. The non-transitory computer-readable medium of claim 8 , the instructions further configured to cause the control processor to perform the method by including in the baseline power production curve one or more elements of historic measured data for the turbine.

11. The non-transitory computer-readable medium of claim 8 , the instructions further configured to cause the control processor to perform the method by including applying smoothing techniques to the expected baseline power production curve.

12. The non-transitory computer-readable medium of claim 8 , the instructions further configured to cause the control processor to perform the method by including generating a time series plot of power residuals prior to detecting the set of changes.

13. The non-transitory computer-readable medium of claim 12 , the instructions further configured to cause the control processor to perform the method by including applying a change point detection algorithm to detect the set of changes.

14. The non-transitory computer-readable medium of claim 8 , the instructions further configured to cause the control processor to perform the method by including at least one member of the paired operational variables identified to the turbine control system having a value controllable by the turbine control system.

15. A turbine control system for correcting turbine underperformance, the system comprising:
a turbine having a control processor in communication with a memory unit and a data store;
the control processor including a processing unit, the control processor in communication with one or more turbine actuators;
the memory unit including non-transitory computer-readable executable instructions which when executed by the control processor cause the control processor to perform a method of correcting turbine underperformance, the method comprising:
accessing monitored operational data for the turbine;
calculating a power production curve using at least a portion of the monitored operational data;
predicting a baseline power production curve based on expected performance of the turbine;
detecting a first set of changes between at least the portion of the monitored operational data and the baseline power production curve;
generating one or more monitored operability curves from the at least a portion of the monitored operational data, each of the one or more monitored operability curves describing a relationship between monitored values for paired operational variables;
generating one or more baseline operability curves for the turbine, each of the one or more baseline operability curves describing an expected relationship between the paired operational variables;
detecting a set of changes between the one or more monitored operability curves and a corresponding one of the one or more baseline operability curves;
comparing one or more of the set of changes to a respective predetermined metric for each of the paired operational variables; and
based on a determination that one or more members of the set of changes is in excess of the respective predetermined metric, providing feedback to control one or more turbine actuators that impact a value f

Assignees

• Gen Electric

Inventors

• Zhang Zhanpan
• Gregg Peter Alan
• Xia Jin
• Mihok John
• Zhao Guangliang
• Bouqata Bouchra

Classifications

• F03D7/046

  with learning or adaptive control, e.g. self-tuning, fuzzy logic or neural network · CPC title

• F05B2220/704

  the other apparatus being a gas turbine · CPC title

• G05B23/024

  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 title

• G05B23/0275 Primary

  Fault isolation and identification, e.g. classify fault; estimate cause or root of failure · CPC title

• F03D17/00 Primary

  Monitoring or testing of wind motors, e.g. diagnostics (testing during commissioning of wind motors F03D13/30) · CPC title