Characteristic-assisted partial discharge point positioning method

The invention discloses a feature-assisted partial discharge point positioning method, which comprises the following specific steps of: (1) collecting and primarily processing a partial discharge signal, collecting the partial discharge signal of power equipment through a partial discharge detection device, and obtaining position measurement information, a partial discharge pulse signal, a spectrogram and other information of a partial discharge point after processing; (2) modeling for time domain and frequency domain features, using amplitude as a time domain feature and using a frequency spectrum as a frequency domain feature; and (3) fusing the time domain and frequency domain features with Gaussian mixture probability hypothesis density filtering, and correcting the weight of the Gaussian component of the partial discharge point by using the features. According to the method, on the basis of Gaussian mixture probability hypothesis density filtering, time-frequency domain features are fused, so that clutte