Ultrasonic partial discharge detection and analysis model based on big data

Abstract

The invention provides an ultrasonic partial discharge detection and analysis model based on big data, and the model comprises an input unit which obtains a to-be-detected ultrasonic signal collectedfrom power distribution equipment; a big data unit which is used for acquiring big data samples of the ultrasonic signals generated by partial discharge of the power distribution equipment, wherein the big data samples comprise a plurality of sample ultrasonic signals and corresponding partial discharge types; a feature extraction unit which is used for carrying out feature extraction processing on the ultrasonic signal to be detected and the sample ultrasonic signal and outputting the feature parameters of the ultrasonic signal; a model training unit which is used for forming a training set by adopting the characteristic parameters of the sample ultrasonic signals and the corresponding partial discharge types to train a partial discharge detection model and outputting the trained partialdischarge detection model; and a partial discharge analysis unit which is used for inputting the characteristic parameters of the ultrasonic signal to be detected into the trained partial discharge detection model and outputting the partial discharge type of the ultrasonic signal to be detected. Partial discharge detection is carried out according to the big data samples, the accuracy is high andthe reliability is high.

Description

technical field [0001] The invention relates to the technical field of partial discharge detection, in particular to an ultrasonic partial discharge detection analysis model based on big data. Background technique [0002] Nowadays, equipment with insulation performance is widely used in the current power system, and the insulation status of the 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 power distribution equipment can effectively obtain the insulation status of the equipment, thereby eliminating hidden dangers in time and avoiding major accidents. [0003] In the prior art, it is found that when the power distribution equipment generates partial discharge, it will generate shocking vibration and sound waves. The ultrasonic detector can receive the discharge ultrasonic signal, and through the identific...

AI Technical Summary

Problems solved by technology

However, due to the complex and diverse operating environment of the power distribution site, there are large differences in the collected ultrasonic signals. The current method of judging the ultrasonic signal and identifying the partial discharge mode through a single feature cannot meet people's requirements for the accuracy and accuracy of partial discharge mode recognition. the need for objectivity

Images