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

Initial fault identification method for active power distribution system based on time-frequency memory recurrent neural network

A recurrent neural network and initial failure technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve related problems, application problems, inappropriate detection equipment initial failures and other problems, achieve strong generalization, The effect of meeting identification requirements and high-precision fault identification

Active Publication Date: 2021-07-13
HEFEI UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the accuracy of this method is related to the confidence factor, there are problems in practical application, and it is not suitable for detecting the initial failure of equipment

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
  • Initial fault identification method for active power distribution system based on time-frequency memory recurrent neural network
  • Initial fault identification method for active power distribution system based on time-frequency memory recurrent neural network
  • Initial fault identification method for active power distribution system based on time-frequency memory recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In this embodiment, a method for identifying initial faults in an active power distribution system based on a time-frequency memory recursive neural network is performed in the following steps:

[0056] Step 1, collecting three-phase current and three-phase voltage data;

[0057] Step 2, preprocessing the collected three-phase current and three-phase voltage data, including data enhancement and normalization processing;

[0058] The collected three-phase current data is I a , I b , I c , the three-phase voltage data is V a , V b , V c , rotate the three-phase data to get [I a I b I c V a V b V c ], [I a I c I b V a V c V b ], [I b I a I c V b V a V c ],

[0059] [I b I c I a V b V c V a ], [I c I b I a V c V b V a ], [I c I a I b V c V a V b ] Six groups of data; in the present embodiment, by adding a time window with a length of 164, the translation step is 10 to carry out time series expansion to ...

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 an initial fault identification method for an active power distribution system based on a time-frequency memory recurrent neural network. The method comprises the following steps: 1, preprocessing collected current and voltage data; 2, classifying different types of current and voltage data after preprocessing; 3, designing a time-frequency memory recurrent neural network core structure; 4, constructing a multi-layer time-frequency memory recurrent neural network; and 5, obtaining an output result of the test set sample based on the time-frequency memory recurrent neural network. According to the method, fine-grained analysis of the time sequence is provided through the time-frequency memory recurrent neural network, the characteristics of the data in the time domain and the frequency domain can be captured so as to improve the recognition precision of the initial fault, the detection can be completed by the method in a relatively small data period, and the actual requirements of accuracy and rapidness are met.

Description

technical field [0001] The invention relates to wavelet transform technology and deep learning technology, in particular to a method for identifying initial faults based on a time-frequency memory recursive neural network, which is suitable for real-time detection of initial faults in active power distribution systems. Background technique [0002] Before the equipment fails, some predictive abnormal signals are called incipient failures. Due to the infrequent and short-duration characteristics of incipient faults, only a small number of data samples can be collected in practical applications. Incipient failures in active power distribution systems can lead to catastrophic problems. Detecting initial faults is helpful for active fault management and predictive maintenance, so that defective devices can be replaced in advance, which is of great significance to effectively improve the reliability of power supply. [0003] The initial fault can be detected by traditional arti...

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): G06Q10/00G06Q50/06G01R31/00G06K9/62G06N3/04G06N3/08
CPCG06Q10/20G06Q50/06G06N3/08G01R31/00G06N3/044G06F18/214G06F18/241
Inventor 李奇越邓玉星唐皓辰操腾飞孙伟李帷韬程红戴胜全徐叶刚李希明
Owner HEFEI 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com