Identification of power system events using fuzzy logic

Patent metadata

Field	Value
Publication number	US-9336491-B2
Application number	US-201313758598-A
Country	US
Kind code	B2
Filing date	Feb 4, 2013
Priority date	Jun 26, 2008
Publication date	May 10, 2016
Grant date	May 10, 2016

Abstract

A method for analyzing an electrical power system using fuzzy logic includes: (a) acquiring data representing a signal of interest of the power system; (b) analyzing the signal using at least one fuzzy logic rule; and (c) based on the analysis, detecting and classifying at least one power system event within the power system.

First claim

What is claimed is:

1. A method for analyzing an electrical power system using fuzzy logic, comprising:
(a) acquiring data representing a signal of interest of the power system;
(b) analyzing the data using at least one fuzzy logic rule, wherein the fuzzy logic rules are arranged in a hierarchy of at least two levels; and
(c) based on the analysis, detecting and classifying at least one power system event within the power system.

2. The method of claim 1 further comprising, prior to step (b), segmenting the signal into a plurality of segments.

3. The method of claim 2 further comprising extracting selected features from the signal, wherein the analysis is carried out on the extracted features.

4. The method of claim 1 wherein the fuzzy logic rules include:
(a) phase level rules which are based on features extracted from a particular phase on the electric power system;
(b) segment level rules which are evaluated using information from different phases; and
(c) capture level rules which combine truth values obtained from one or more segments.

5. The method of claim 4 wherein the segment level rules are evaluated using features that are not associated with any single phase on the electric power system.

6. The method of claim 4 wherein the capture level rules are based on features that are common to all segments.

7. The method of claim 1 wherein the signal of interest is a derived parameter.

8. The method of claim 1 wherein the fuzzy logic rules comprise a plurality of selected rules, wherein the selected rules are collectively determinative of a particular type of event.

9. The method of claim 1 wherein step (b) includes computing a confidence value which associates the signal with a category of power system event.

10. A computer program product comprising one or more non-transitory computer readable media having stored thereon a plurality of instructions that, when executed by one or more processors of a system, causes the one or more processors to carry out a method comprising:
(a) analyzing data representing a signal of interest in an electrical power system, using at least one fuzzy logic rule, wherein the fuzzy logic rules are arranged in a hierarchy of at least two levels; and
(b) based on the analysis, detecting and classifying at least one power system event within the data.

11. The computer program product of claim 10 wherein the instructions further cause the one or more processors to, prior to step (a), segment the signal into a plurality of segments.

12. The computer program product of claim 11 wherein the instructions further cause the one or more processors to extract selected features from the signal, wherein the analysis is carried out on the extracted features.

13. The computer program product of claim 10 wherein the fuzzy logic rules include:
(a) phase level rules which are based on features extracted from a particular phase on the electric power system;
(b) segment level rules which are evaluated using information from different phases; and
(c) capture level rules which combine truth values obtained from one or more segments.

14. The computer program product of claim 13 wherein the segment level rules are evaluated using features that are not associated with any single phase on the electric power system.

15. The computer program product of claim 13 wherein the capture level rules are based on features that are common to all segments.

16. The computer program product of claim 10 wherein the signal of interest is a derived parameter.

17. The computer program product of claim 10 wherein the fuzzy logic rules comprise a plurality of selected rules, wherein the selected rules are collectively determinative of a particular type of event.

18. The computer program product of claim 10 wherein step (b) includes computing a confidence value which associates the signal with a category of power system event.

Assignees

• Texas A & M Univ Sys

Inventors

• Muthu-Manivannan Karthick
• Benner Carl L
• Xu Peng
• Russell Billy Don

Classifications

• G06N5/048

  Fuzzy inferencing · CPC title

• G06N5/025 Primary

  Extracting rules from data · CPC title

• G06N7/02 Primary

  using fuzzy logic (computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00) · CPC title