GIS partial discharge ultrasonic signal identification method

Abstract

The invention discloses a GIS partial discharge ultrasonic signal identification method which solves the problem that the accuracy and the reliability of GIS partial discharge ultrasonic detecting and diagnosing are not high. The method comprise a network learning process and a defect identification process and specifically comprises the following steps that first, a known sample of a GIS partial discharge ultrasonic signal is subjected to preprocessing, then an average amplitude value, a root-mean-square, a peak value index, kurtosis, a waveform index, a pulse index, a margin index and other discharge characteristic parameters are extracted, finally a fuzzy logic cluster neuron network is established, the GIS partial discharge ultrasonic signal to be identified is subjected to preprocessing, then the corresponding characteristic parameters are extracted, finally an established model is used for carrying out classification on all samples including samples to be identified, the fuzzy nearness of the samples to be identified and other known samples in the same type is computed, and the defect type is judged according to the magnitude of the nearness. The method has significance in GIS insulation condition assessment and reasonable overhaul strategy generating.

Description

technical field [0001] The invention relates to the technical field of electrical equipment insulation detection, in particular to a GIS partial discharge ultrasonic signal recognition method based on a fuzzy logic clustering neuron network. Background technique [0002] Gas-insulated switchgear (GIS) has the advantages of small footprint, high reliability, strong safety, and convenient operation and maintenance, so it has been widely used in power systems. In recent years, many GIS faults or accidents have occurred in the power grid one after another, seriously affecting the safe and stable operation of the system. Therefore, it is of great significance to study the partial discharge fault diagnosis technology of GIS equipment. [0003] At present, ultrasonic detection of partial discharge is an important means for fault diagnosis and insulation condition evaluation of GIS equipment. Partial discharge will cause the insulation system to age, cause insulation failure, and s...

AI Technical Summary

Problems solved by technology

The existing GIS partial discharge identification methods mostly use ultra-high frequency partial discharge signals for identification, extract the three-dimensional spectrum, statistical characteristic parameters, fractal parameters, image moment characteristic parameters, etc. of the partial discharge ultrahigh frequency signal, and then use the pattern recognition algorithm to carry out However, partial discharge ultrasonic signals have limitations in specific identification because they cannot extract the phase information of discharge occurrence

At present, most of the pattern recognition algorithms used are based on BP neural network, but due to the gradient descent method used in BP neural network, it is inevitable that there will be problems such as slow convergence speed, easy to fall into local minimum points, and difficulty in determining the number of hidden layer nodes.

Images