Monitoring systems and methods for electrical machines

Patent metadata

Field	Value
Publication number	US-9976989-B2
Application number	US-201514969893-A
Country	US
Kind code	B2
Filing date	Dec 15, 2015
Priority date	Dec 15, 2015
Publication date	May 22, 2018
Grant date	May 22, 2018

Abstract

A monitoring system includes an acoustic emission monitoring system including acoustic emission sensors, a partial discharge monitoring system including partial discharge sensors and synchronized with the acoustic emission monitoring system, and a computer receiving acoustic emission data from the acoustic emission sensors and electrical data from the partial discharge sensors. The computer is configured to classify a first statistical event as a fatigue cracking event by pattern recognition of the acoustic emission data and determine a first location and a first damage condition resulting from the fatigue cracking event, classify a second statistical event as a partial discharge event by pattern recognition of the acoustic emission data or the electrical data, and fuse the acoustic emission data and the electrical data for the second statistical event and determine a second location and a second damage condition resulting from the partial discharge event. Methods of monitoring are also disclosed.

First claim

What is claimed is:

1. A method of monitoring an electrical system for statistical events, the method comprising:
synchronizing an acoustic emission monitoring system comprising a plurality of acoustic emission sensors located on a component of the electrical system with a partial discharge monitoring system comprising a plurality of partial discharge sensors located on the component of the electrical system;
directing collection by the acoustic emission sensors of acoustic emission signals from the component as acoustic emission data and directing collection by the partial discharge sensors of electrical signals as electrical data during an occurrence of a statistical event; and
fusing and performing pattern recognition of the acoustic emission data and the electrical data to detect and classify the statistical event as a fatigue cracking event or a partial discharge event in the electrical system.

2. The method of claim 1 , wherein the statistical event comprises the partial discharge event, the method further comprising determining from the acoustic emission data and the electrical current data a location and a damage condition resulting from the partial discharge event.

3. The method of claim 1 , wherein the statistical event comprises the fatigue cracking event, the performing comprising classifying the statistical event as the fatigue cracking event by the pattern recognition of the acoustic emission data.

4. The method of claim 3 further comprising determining from the acoustic emission data a location of the fatigue cracking event and a damage condition of the component resulting from the fatigue cracking event.

5. The method of claim 1 wherein the electrical system comprises an electric generator system.

6. The method of claim 1 wherein the pattern recognition occurs in real time.

7. The method of claim 6 further comprising implementing adaptive machine learning to enhance the pattern recognition.

8. The method of claim 1 wherein the acoustic emission sensors comprise fiber optic acoustic emission sensors.

9. A method of monitoring an electric generator system, for statistical events, the method comprising:
directing synchronized collection of:
acoustic emission signals from the component as acoustic emission data by a plurality of acoustic emission sensors located on a component of the electrical generator system; and
electrical signals from the component as electrical data by a plurality of partial discharge sensors located on the component of the electric generator system;

evaluating the acoustic emission data to identify acoustic events and the electrical data for electrical events; and
monitoring a ratio of acoustic events to electrical events over time and reporting increases in the ratio as fatigue cracking events.

10. The method of claim 9 further comprising determining from the acoustic emission data a location of the fatigue cracking event and a damage condition resulting from the fatigue cracking event.

11. The method of claim 9 wherein the partial discharge sensors comprise fiber optic acoustic emission sensors.

12. The method of claim 9 further comprising:
synchronizing the acoustic emission sensors with the partial discharge sensors;
and
confirming the fatigue cracking event by pattern recognition of the electrical data.

13. An electrical system monitoring system comprising:
an acoustic emission monitoring system comprising a plurality of acoustic emission sensors locatable on a component of the electrical system;
a partial discharge monitoring system comprising a plurality of partial discharge sensors locatable on a component of the electrical system and synchronized with the acoustic emission monitoring system; and
a computer receiving acoustic emission data from the acoustic emission sensors and electrical data from the partial discharge sensors, wherein the computer is configured to:
evaluate the acoustic emission data and the electrical data to identify an occurrence of a statistical event in the component;
fuse and perform pattern recognition of the acoustic emission data and the electrical data to classify the statistical event as a fatigue cracking event and determine a crack location and a crack damage condition resulting from the fatigue cracking event
or as a partial discharge event
and determine a discharge location and a discharge damage condition resulting from the partial discharge event; and
report the statistical event as the fatigue cracking event at the crack location with the crack damage condition or as the partial discharge event at the discharge location with the discharge damage condition.

14. The electrical system monitoring system of claim 13 wherein the acoustic emission sensors collect the acoustic emission data from acoustic emission signals and the partial discharge sensors collect the electrical data from electrical signals from a component of an electric generator system.

15. The electrical system monitoring system of claim 13 wherein the computer receives acoustic emission data from the acoustic emission sensors and electrical data from the partial discharge sensors in real time.

16. The electrical system monitoring system of claim 13 wherein the partial discharge sensors are selected from the group consisting of ultra-high frequency sensors, high frequency current transformers, transient earth voltage sensors, coupling capacitors, and combinations thereof.

17. The electrical system monitoring system of claim 13 wherein the acoustic emission sensors comprise fiber optic acoustic emission sensors.

18. The electrical system monitoring system of claim 13 wherein the computer is configured to conduct the pattern recognition in real time.

Assignees

• Gen Electric

Inventors

• Dehghan Niri Ehsan
• Rose Curtis Wayne
• Witney Andrew Batton

Classifications

• G01N29/4481

  Neural networks · CPC title

• G01N27/92

  by investigating breakdown voltage (G01N27/60, G01N27/62 take precedence) · CPC title

• G01N29/2418

  using optoacoustic interaction with the material, e.g. laser radiation, photoacoustics (photoacoustic cells G01N21/1702; measuring characteristics of vibrations by using radiation-sensitive means G01H9/00; acousto-optical conversion techniques for short-range imaging G01S15/8965; sound-producing devices using laser bundle G10K15/046) · CPC title

• G01R31/343 Primary

  in operation · CPC title

• G01R31/1272

  of cable, line or wire insulation, e.g. using partial discharge measurements (locating faults in cables G01R31/083) · CPC title