Circuit breaker contact system fault assessment method based on multi-task deep learning

A technology of fault assessment and contact system, applied in the direction of neural learning methods, information technology support systems, instruments, etc., can solve problems such as operators' distribution network security threats, circuit breaker property losses, etc., and achieve average accuracy and improve Accuracy, effect of reducing model parameters

Pending Publication Date: 2022-05-24
HEBEI UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The universal circuit breaker is a protection and control device in the low-voltage distribution network. Its health status has a huge impact on the performance and stability of the distribution system. Failure of the circuit breaker during operation will not only cause huge property losses, but also cause serious damage to the power distribution system. A huge threat to the safety of operators and the entire distribution network

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
  • Circuit breaker contact system fault assessment method based on multi-task deep learning
  • Circuit breaker contact system fault assessment method based on multi-task deep learning
  • Circuit breaker contact system fault assessment method based on multi-task deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] The fault evaluation method of the circuit breaker contact system based on multi-task deep learning of the present embodiment, the specific steps are as follows:

[0054] The first step is to build a fault test platform with DW15-1600 universal circuit breaker as the test product, and use the LC0159 acceleration sensor to measure the vibration signal, the acceleration sensor is powered by the LC0201 signal conditioner, and the vibration signal is sampled by the USB-7648A data acquisition card, the sampling frequency is 20kHz, and the single vibration sampling time is 250ms;

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 circuit breaker contact system fault assessment method based on multi-task deep learning, and the method comprises the steps: firstly carrying out the fault test of a circuit breaker contact system, and collecting contact vibration signals in different working states; secondly, the contact vibration signals are converted into a two-dimensional time-frequency diagram through continuous wavelet transform; then, ResNet18 is used as a trunk network to construct a fault assessment model based on multiple tasks, the model is composed of a sharing layer and two task layers, output feature maps of the sharing layer serve as inputs of the two task layers, one task layer is used for assessing the fault type, and the other task layer is used for assessing the fault degree; and finally, performing multi-task joint training on the fault assessment model based on multiple tasks, and using the pre-trained fault assessment model to assess the fault type and the fault degree. According to the method, deep information between fault types and degrees is extracted, so that a model performs mutual-aid learning on fault classification and degree evaluation tasks, and simultaneous evaluation of the fault types and degrees is realized.

Description

Technical field [0001] The present invention belongs to the field of universal circuit breaker contact system fault evaluation technology, specifically a multi-task based deep learning circuit breaker contact system fault assessment method. Background [0002] Universal circuit breaker is a low-voltage distribution network in the protection and control equipment, its health has a huge impact on the performance and stability of the distribution system, the circuit breaker operation failure will not only cause huge property losses, but also pose a huge threat to the safety of the operator and the entire distribution network. In the process of splitting and closing the circuit breaker, the dynamic and static contacts collide violently, and the vibration signal generated contains a wealth of contact system and its operating mechanism information, so the contact vibration signal can characterize the various operating states of the circuit breaker, especially the mechanical state. Sinc...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/06G06F2218/08G06F2218/12Y04S10/50
Inventor 孙曙光张婷婷王景芹孙靓李嘉伟李亚杰安春晖高辉
Owner HEBEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products