A partial discharge signal pattern recognition method and system
A technology of discharge signal and pattern recognition, which is applied in character and pattern recognition, neural learning methods, electrical measurement, etc., to achieve good recognition effect, good recognition accuracy, and good recognition performance
Active Publication Date: 2022-01-18
ELECTRIC POWER SCI & RES INST OF STATE GRID TIANJIN ELECTRIC POWER CO +2
View PDF13 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In terms of pattern recognition, the current existing research mainly uses laboratory experimental data, but few researches on partial discharge pattern recognition methods for the big data of on-site partial discharge signals with complex sources
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:
[0031] The partial discharge signal pattern recognition method proposed by the present invention is based on a deep convolutional neural network (Deep Convolution Neural Network, DCNN) to recognize the partial discharge signal pattern.
[0032] Since Deep Learning (DL) was proposed by Hinton in 2006, compared with other methods of machine learning, it has shown significant advantages in big data feature extraction and data dimensionality reduction. It has been widely used in image processing, speech recognition, etc. field. The deep learning network has the characteristics of autonomously learning feature information from massive data. Compared with traditional manual feature selection methods, it is more conducive to extracting intrinsic information of data. Among them, the deep convolutional neural network is currently the most widely used due 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
Login to View More Abstract
The invention relates to a partial discharge signal pattern recognition method and system, the main technical features of which are: obtaining large data samples of partial discharge signals; constructing a deep convolutional neural network model; training deep convolutional neural networks based on large data samples of partial discharge signals A network model: determining the pattern of the partial discharge signal to be identified based on the trained deep convolutional neural network model. The invention has a reasonable design, overcomes the shortcomings of the prior art in the partial discharge detection of the GIS at the substation site, can perform pattern recognition on the partial discharge with a large number and complex sources in the GIS at the substation site, and can obtain a higher accuracy rate of pattern recognition, It has better recognition performance and is more suitable for engineering applications under the big data platform.
Description
technical field [0001] The invention belongs to the technical field of power equipment monitoring, in particular to a partial discharge signal pattern recognition method and system. Background technique [0002] GIS (Gas Insulated Combined Electrical Appliance) has been widely used in the current power system, and the insulation status of its equipment is closely related to the safety of the power grid. Partial discharge can effectively reflect one of the main characteristics of internal insulation defects of power equipment. Partial discharge detection of GIS equipment can effectively obtain the insulation status of the equipment, thereby eliminating hidden dangers in time and avoiding major accidents. Therefore, the current GIS partial discharge detection technology has been vigorously promoted, and the on-site partial discharge detection data for GIS is also showing a trend of massive growth. [0003] Different insulation defects often correspond to different partial dis...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08G01R31/12
CPCG06N3/084G01R31/1254G06N3/045G06F2218/00
Inventor 何金刘创华郗晓光张弛满玉岩曹梦陈荣张春晖李松原宋晓博朱旭亮张黎明邢向上
Owner ELECTRIC POWER SCI & RES INST OF STATE GRID TIANJIN ELECTRIC POWER CO