Ultrasonic partial discharge detection and analysis model based on big data

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;