Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Medium-voltage circuit breaker fault diagnosis method based on deep learning and intelligent optimization

A circuit breaker failure and intelligent optimization technology, applied in the direction of neural learning methods, kernel methods, instruments, etc., can solve the problems of increasing circuit breaker downtime and maintenance and overhaul time, poor generalization ability, slow diagnosis speed, etc., and achieve the elimination of local maximum Excellent phenomenon, excellent representation ability, and the effect of improving accuracy

Pending Publication Date: 2022-01-28
ZHEJIANG UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the diagnostic accuracy of traditional artificial intelligence algorithms has been significantly improved, they are also used in engineering practice to a certain extent, but these intelligent algorithms generally have problems such as slow diagnosis speed, poor generalization ability, and easy to generate local optimal solutions, which increase the Unnecessary downtime and maintenance time of circuit breakers limit the development of circuit breaker fault diagnosis technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Medium-voltage circuit breaker fault diagnosis method based on deep learning and intelligent optimization
  • Medium-voltage circuit breaker fault diagnosis method based on deep learning and intelligent optimization
  • Medium-voltage circuit breaker fault diagnosis method based on deep learning and intelligent optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] Example: for a medium voltage circuit breaker in the common type of fault categories, with reference to Figure 3-6 As shown in a medium voltage circuit breaker intelligent diagnostic method based on CNN-QPSO-SVM, comprising the steps of:

[0040] S1: an acceleration sensor vibration acceleration parameter recording circuit breaker / off process, the sampling frequency is 10kHz. An acceleration sensor mounted on the circuit breaker housing, for collecting the vertical vibration signals, a total of 7 sets of vibration signals collected data, comprising: a normal state; tripping the closing electromagnet blocked; spindle plug; 4 principal axle blockage fault types . Fault Type and number as shown in Table 1.

[0041] Table 1 Class 4 breaker common mechanical faults ID

[0042]

[0043] S2: The training data and test data is normalized, the normalized using the following formula:

[0044]

[0045] xi Original data sample, x max X i The maximum value, x min X i Minimum. In t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a medium-voltage circuit breaker fault diagnosis method based on deep learning and intelligent optimization. The method comprises the following steps: 1) collecting medium-voltage circuit breaker vibration signals in a normal state, tripping closing electromagnet blockage, main shaft blockage and half shaft blockage as an original data set; 2) performing normalization processing on training set data and test set data; 3) constructing a deep CNN model; 4) performing optimization training on an SVM classifier by combining the trained deep CNN model with quantum particle swarm optimization; and 5) inputting test sample data into a trained fault diagnosis model to carry out circuit breaker fault diagnosis. According to the invention, data features are effectively extracted by using the advantage of strong feature extraction capability of a convolutional neural network; and furthermore, the accuracy of data classification is improved by utilizing the advantage that the quantum particle swarm optimization can effectively eliminate a local optimum phenomenon.

Description

Technical field [0001] The present invention relates to the field of on-line diagnosis of major mechanical failure voltage circuit breaker, particularly, to a convolutional neural network-based and QPSO a medium voltage circuit breaker intelligent fault diagnosis method is applied to medium voltage circuit breaker in which solution troubleshooting problems. Background technique [0002] Breaker as an important power equipment plays an important role in the power system, the status of their work directly affects the safety and reliability of the power system. But the huge maintenance costs of the circuit breaker, and the traditional manual inspection mode, not only time consuming, but also bring a lot of unnecessary downtime. Non-invasive diagnostic method due to the failure to facilitate data collection, has become an important research direction breaker maintenance technology. [0003] Fault diagnosis technique mainly includes fault and fault diagnosis feature extraction algorit...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/00G06N3/04G06N3/08G06N20/10
CPCG06N20/10G06N3/08G06N3/006G06N3/047G06N3/045G06F2218/12G06F2218/08G06F18/241G06F18/2411G06F18/2415
Inventor 张丹黄钟汀陈永毅
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products