A noise reduction method and system for partial discharge signal detection

Abstract

The application discloses a noise reduction method for partial discharge signal detection, which comprises the following steps: extracting time domain features, frequency domain features and wavelet domain features of sample partial discharge signals; combining the time domain features, the frequency domain features and the wavelet domain features of the sample partial discharge signals into a sample feature vector, and training a constructed deep learning model by using the sample feature vector so that the deep learning model outputs corresponding noise reduction signals; and performing noise reduction processing on to-be-processed partial discharge signals by using the trained deep learning model. Accordingly, the application further discloses a noise reduction system for partial discharge signal detection.

Images