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

Method and system for recognizing power equipment fault through multi-algorithm fusion voice

A technology of voice recognition and power equipment, which is applied in the field of fault classification of power station equipment, can solve problems such as insufficient coverage of voice recognition, and achieve the effects of improving recognition accuracy, efficiency, and accuracy

Pending Publication Date: 2022-04-26
STATE GRID XINJIANG ELECTRIC POWER CO URUMQI ELECTRIC POWER SUPPLY CO +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention aims at the technical problem of insufficient voice recognition coverage of power equipment existing in the prior art, and technically improves the method for identifying power equipment faults based on sound features

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
  • Method and system for recognizing power equipment fault through multi-algorithm fusion voice
  • Method and system for recognizing power equipment fault through multi-algorithm fusion voice
  • Method and system for recognizing power equipment fault through multi-algorithm fusion voice

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] This embodiment implements a multi-algorithm fusion sound identification method for power equipment faults.

[0044] figure 1 It is a multi-algorithm fusion sound recognition model pre-training flow chart of a method for multi-algorithm fusion sound recognition power equipment faults. as attached figure 1 As shown in this embodiment, a multi-algorithm fusion sound recognition method for power equipment faults is pre-trained for a multi-algorithm fusion sound recognition model. First, the sound of the power equipment in different states is obtained through experiments in the laboratory or on-site collection. , and label their types; after that, the sound is preprocessed, and the labeled data is used to train the initial random forest algorithm, ResNet algorithm, and Transformer algorithm; after the initial random forest algorithm, ResNet algorithm, and Transformer algorithm are trained , according to the recognition situation of different algorithms, give these algorit...

Embodiment 2

[0048] This embodiment implements a multi-algorithm fusion voice recognition system for power equipment faults, which is used to implement the multi-algorithm fusion voice recognition power equipment fault method described in Embodiment 1.

[0049] Figure 4 It is a structural frame diagram of a multi-algorithm fusion sound recognition power equipment fault system. as attached Figure 4 As shown, in this embodiment, a multi-algorithm fusion sound recognition power equipment fault system integrates sound sensors, preprocessing algorithms, random forest algorithms, ResNet algorithms, Transformer algorithms, front-end user interface programs and server background running programs. Among them, the sound sensor collects the sound of the electric equipment, and transmits the sound to the server through the wireless network. After the server preprocesses the sound, the effective features of the sound are obtained, and the random forest algorithm, ResNet algorithm, and Transformer a...

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 relates to a method and system for recognizing a power equipment fault through multi-algorithm fusion voice, and the method comprises the following steps: S1, carrying out the pre-training of a multi-algorithm fusion voice recognition model, giving different weights to multiple algorithms according to the multi-algorithm voice recognition condition, and carrying out the pre-training of a multi-algorithm fusion voice recognition model; the weighted multi-algorithm fusion sound recognition model can effectively recognize power equipment fault sound samples under different conditions; s2, processing and classifying the sound samples of the power equipment, multiplying the sound samples by different given weights to obtain a final classification result of the sound samples of the power equipment, and identifying a fault of the power equipment according to the final classification result; and S3, a worker feeds back whether the recognized power equipment fault is correct or not, a correct power equipment fault sound sample is used for training a multi-algorithm fusion sound recognition model, multi-algorithm parameters are updated, multi-algorithm weights are adjusted, and the recognition accuracy of the multi-algorithm fusion sound recognition model is further improved. The method has the beneficial effects of complete coverage and continuously improved accuracy.

Description

【Technical field】 [0001] The invention relates to the technical field of fault classification of power station equipment, in particular to a method and system for identifying faults of power equipment with multi-algorithm fusion sound. 【Background technique】 [0002] In the computer field, sound detection and classification technology based on machine learning is an important artificial intelligence application direction. The research goal of sound detection technology is to extract its effective features according to the collected sound, and use algorithms to classify the audio. [0003] In the power industry, the use of sound to detect the status of power equipment is gradually becoming an important part of the smart grid. The traditional electric equipment detection method has problems such as cumbersome detection equipment, difficult movement and installation, complex fault analysis methods, and relying on manual judgment. It is impossible to detect electric equipment f...

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): G06K9/00G06N20/00G10L15/22
CPCG10L15/22G06N20/00G06F2218/02G06F2218/08G06F2218/12
Inventor 陈林陈臻胡赵宇刘彪钱念书李喆胡健民艾则孜江.加帕尔汪兆奇刘鹏吴艳梅马超尚文明
Owner STATE GRID XINJIANG ELECTRIC POWER CO URUMQI ELECTRIC POWER SUPPLY CO
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