Systems and methods for predicting an anomaly in a combustor

Patent metadata

Field	Value
Publication number	US-11015479-B2
Application number	US-201716077138-A
Country	US
Kind code	B2
Filing date	Feb 1, 2017
Priority date	Feb 15, 2016
Publication date	May 25, 2021
Grant date	May 25, 2021

Abstract

A method for predicting an anomaly in a combustor (16) is presented. The method includes receiving signals representative of parameters in one or more combustion cans (22, 24) of the combustor, generating a plurality of patterns based on a permutation entropy window and the signals, identifying a plurality of pattern categories in the plurality of patterns, determining a permutation entropy based on the plurality of patterns and the plurality of pattern categories, and predicting an anomaly in the combustor based on the permutation entropy. The method further includes comparing the plurality of pattern categories to determined permutations of pattern categories if the anomaly is present in the combustor, and predicting a category of the anomaly based on the comparison of the plurality of pattern categories to the determined permutations of pattern categories.

First claim

The invention claimed is:

1. A method for predicting an anomaly in a combustor, comprising:
receiving, by a processing subsystem, signals representative of parameters in one or more combustion cans of the combustor;
generating, by the processing subsystem, a plurality of patterns based on a permutation entropy window and the signals;
identifying, by the processing subsystem, a plurality of pattern categories in the plurality of patterns;
determining, by the processing subsystem, a permutation entropy based on the plurality of patterns and the plurality of pattern categories, wherein determining the permutation entropy comprises:
determining a number of patterns in each of the plurality of pattern categories;
determining a plurality of relative occurrences of the plurality of pattern categories based on the number of patterns in each of the plurality of pattern categories and a total number of the plurality of patterns; and
determining the permutation entropy based on the plurality of relative occurrences of the plurality of pattern categories and an embedding dimension of the permutation entropy window;
predicting, by the processing subsystem, an anomaly in the combustor based on the permutation entropy;
if the anomaly is present in the combustor then comparing, by the processing subsystem, the plurality of pattern categories to determined permutations of pattern categories; and
predicting a category of the anomaly, by the processing subsystem, based on the comparison of the plurality of pattern categories to the determined permutations of pattern categories.

2. The method of claim 1 , wherein identifying the plurality of pattern categories comprises grouping the plurality of patterns into the plurality of pattern categories based on amplitudes of data points corresponding to the plurality of patterns.

3. The method of claim 1 , wherein the permutation entropy comprises a weighted permutation entropy.

4. The method of claim 3 , wherein determining the permutation entropy comprises determining a weighted permutation entropy, and wherein determining the weighted permutation entropy comprises:
assigning weights to the plurality of patterns based on a plurality of amplitudes of the signals; and
determining the weighted permutation entropy based on the number of patterns in each of the plurality of pattern categories and the corresponding weights of the plurality of patterns.

5. The method of claim 4 , wherein assigning the weights to the plurality of patterns comprises:
determining a mean of amplitudes of data points corresponding to the plurality of patterns;
determining a covariance of the amplitudes of the data points based on the mean of amplitudes; and
assigning the covariance as the weight to the plurality of patterns.

6. The method of claim 1 , wherein the category of the anomaly in the combustor comprises a lean blowout event, a rich blowout event, an instability in the combustor, or combinations thereof.

7. The method of claim 1 , further comprising generating pre-processed signals, wherein generating the pre-processed signals comprises:
receiving sensor-signals from one or more sensing devices;
generating resampled signals by resampling and de-trending the sensor-signals; and
generating the pre-processed signals by processing the resampled signals via a band-pass filter.

8. The method of claim 7 , wherein receiving the signals representative of the parameters in the one or more combustion cans comprises receiving the sensor-signals from the one or more sensing devices, receiving the pre-processed signals, or a combination thereof.

9. A system for predicting an anomaly in a combustor, comprising:
one or more sensing devices disposed on one or more combustion cans of the combustor and configured to generate sensor-signals representative of parameters in the one or more combustion cans of the combustor;
a processing subsystem operatively coupled to the one or more sensing devices and configured to:
pre-process the sensor-signals representative of parameters in the one or more combustion cans to generate pre-processed signals;
generate a plurality of patterns based on a permutation entropy window and the pre-processed signals;
identify a plurality of pattern categories in the plurality of patterns;
determine a permutation entropy based on the plurality of patterns and the plurality of pattern categories;
predict an anomaly in the combustor based on the permutation entropy;
if the anomaly is present then compare the plurality of pattern categories to determined permutations of pattern categories;
predict a category of the anomaly in the combustor based on the comparison of the plurality of pattern categories to the determined permutations of pattern categories; and
wherein the processing subsystem is further configured to:
determine a number of patterns in each of the plurality of pattern categories;
determine a plurality of relative occurrences of the plurality of pattern categories based on the number of patterns in each of the plurality of pattern categories and a total number of the plurality of patterns; and
determine the permutation entropy based on the plurality of relative occurrences of the plurality of pattern categories and an embedding dimension of the permutation entropy window.

10. The system of claim 9 , wherein the processing subsystem is configured to group the plurality of patterns into the plurality of pattern categories based on amplitudes of data points corresponding to the plurality of patterns to identify the plurality of pattern categories.

11. The system of claim 9 , wherein the processing subsystem is configured to predict the anomaly in the combustor by comparing the permutation entropy to a determined threshold, and wherein the determined threshold is a function of operating conditions of a gas turbine comprising the combustor.

12. The system of claim 9 , wherein the permutation entropy comprises a weighted permutation entropy, and the processing subsystem is configured to:
assign weights to the plurality of patterns based on a plurality of amplitudes of the pre-processed signals; and
determine the weighted permutation entropy based on the number of patterns in each of the plurality of pattern categories and the corresponding weights of the plurality of patterns.

13. The system of claim 12 , wherein the processing subsystem is configured to:
determine a mean of amplitudes of data points in the plurality of patterns;
determine a covariance of the amplitudes of the data points based on the mean of the amplitudes; and
assign the covariance as the weights to the plurality of patterns.

14. The system of claim 9 , wherein the processing subsystem is configured to:
generate resampled signals by resampling and de-trending the sensor-signals; and
generate the pre-processed signals by processing the resampled signals via a band-pass filter.

15. The system of claim 9 , wherein the category of the anomaly in the combustor comprises a lean blowout event, a rich blowout event, an instability in the combustor, or combinations thereof.

16. The system of claim 9 , wherein the parameters comprise a dynamic pressure in the one or more combustion cans, a pressure in the combustion cans, temperature, a flame intensity, or combinations thereof.

17. The system of claim 9 , wherein the one or more sensing devices comprise an acoustic sensor, a pressure sensor, a vibration sensor, a piezoelectric sensor, or combinations thereof.

18. A method for predicting an anomaly in a combustor, comprising:
rece

Assignees

• Gen Electric

Inventors

• Abrol Sidharth
• Balram Sangeeta
• Patchaikani Prem Kumar
• Kalya Prabhanjana

Classifications

• F23N5/10 Primary

  using thermocouples · CPC title

• F05D2260/82

  Forecasts · CPC title

• F23N5/242

  using electronic means · CPC title

• F05D2260/80

  Diagnostics · CPC title

• F23R2900/00013

  Reducing thermo-acoustic vibrations by active means · CPC title