Partial discharge positioning method and system based on mode identification
A pattern recognition and partial discharge technology, which is applied in the direction of measuring electricity, measuring electrical variables, and testing dielectric strength, etc., can solve problems such as complex environment of substations, inaccurate range measurement of shadow models, unsuitable for partial discharge positioning, etc., to avoid major Accidents, good scalability, high-precision effects
Inactive Publication Date: 2017-09-19
STATE GRID CORP OF CHINA +2
View PDF5 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the complex environment of the substation, the distance measurement of the shadow model is not accurate, and it is not suitable for partial discharge location
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 approach
[0052] In some embodiments, the signal characteristic includes a signal strength characteristic.
[0053] In some embodiments, partial discharge signals are collected by several sensors fixedly located at different locations. Among them, several sensors are usually UHF sensors, and the number thereof is usually four.
[0054] In some embodiments, the pattern recognition includes at least one of pattern recognition based on BP neural network and pattern recognition based on KNN algorithm. Among them, when the pattern recognition is pattern recognition based on BP neural network and the number of sensors is 4, usually the number of neurons in the input layer of BP neural network is 4, the number of neurons in the output layer is 2, and the hidden value of BP neural network is 2. The number of neurons in the containing layer is preferably 15.
[0055] There are many methods of pattern recognition, such as BP neural network, KNN (K-Nearest Neighbor), etc. Among them, the BP neu...
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 discloses a partial discharge positioning method based on mode identification. The method includes the steps of (1) acquiring a plurality of partial discharge signals with known discharge source positions and correspondingly extracting a plurality of first signal characteristics; (2) establishing a partial discharge characteristic information database including a plurality of first signal characteristics and corresponding discharge source positions; (3) acquiring the partial discharge signals with the discharge source positions to be determined and correspondingly extracting second signal characteristics; and (4) based on the partial discharge characteristic information database, matching the second signal characteristics and the first signal characteristics based on the mode identification to find the first signal characteristics closest to the second signal characteristics, and taking the discharge source positions corresponding to the first signal characteristics as the discharge source positions of the second signal characteristics. In addition, the invention further discloses a corresponding system. The method and system can accurately position the discharge source positions of the partial discharge, and are easy to realize.
Description
technical field [0001] The invention relates to the field of electric equipment monitoring, in particular to a partial discharge location method and system. Background technique [0002] In the power industry, online monitoring and safety warning of power equipment can detect power failures in time, improve maintenance efficiency, and effectively avoid major accidents. In the fault of the power system, the insulation deterioration of the power equipment is one of the main causes of the fault. After the power equipment is put into operation, the existence of insulation degradation often leads to the occurrence of partial discharge (Partial Discharge, PD), which in turn will aggravate the degree of insulation degradation, and even lead to insulation breakdown, forming a vicious circle, which in turn leads to major Accidents happen. Therefore, locating the discharge source of the partial discharge of the power equipment can find the fault location of the power equipment in ti...
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 IPC IPC(8): G01R31/12
CPCG01R31/1227
Inventor 郝杰王美君梁英英张卫东许春华江丽姚朋飞于文牮侯军王晓鹏洪福牛闯刘毅邱卫孙承超李臻罗林根盛戈皞
Owner STATE GRID CORP OF CHINA