Cable partial discharge detection method and system based on multi-voiceprint characteristic spectrogram recognition

The invention discloses a cable partial discharge detection method and system based on multi-voiceprint characteristic spectrogram recognition. The method comprises the following steps: collecting a sound signal; preprocessing the sound signal to obtain a preprocessed sound signal; generating a time-frequency spectrogram and a Mel spectrogram according to the preprocessed sound signal; extracting formant positions and single discharge time in the spectrogram as characteristic parameters; using a fuzzy c-means clustering method to obtain a discrimination result of the to-be-identified sample under a certain spectrogram judgment; and comprehensively analyzing the discrimination results of different spectrograms, and determining the fault type of the partial discharge sample to be identified. According to the invention, abundant features contained in the ultrasonic signal can be mined, and the accuracy of partial discharge detection is improved. 本发明公开一种基于多声纹特征谱图识别的电缆局放检测方法及系统，该方法包括采集声音信号；对声音信号进行预处理，得到预处理后的声音信号；根