Search

Cable termination is an important part of energy transmission in high-speed trains, and it is also a weak link in the insulation. It is important to determine the insulation status of cable terminals by the detection results of partial discharge signals, but the partial discharge signals in the field test circuit are mixed with a large amount of external corona interference, which affects the detection accuracy. This paper proposes a signal recognition model that incorporates Stockwell transform (ST) and 2DCNN, which in combination with wavelet noise reduction can achieve a high-precision classification effect for partial discharge and corona interference with an accuracy rate of up to 98.75%. By selecting the maximum energy moment in the ST matrix to correct the position of the time window during the recognition of long time series signals, the problem of corona interference being truncated by the time window and being misidentified as partial discharge is overcome, and the generalization ability of the model is enhanced. Experimental results show that the method has an excellent performance in separating partial discharge and corona interference in long time series signals.

Cable termination serves as a crucial carrier for high-speed train power transmission and a weak part of the cable insulation system. Partial discharge detection plays a significant role in evaluating insulation status. However, field testing signals are often contaminated by external corona interference, which affects detection accuracy. This paper proposes a classification model based on wavelet transform (WT) and deep belief network (DBN) to accurately and rapidly identify corona discharge in the partial discharge signals of vehicle-mounted cable terminals. The method utilizes wavelet transform for noise reduction, employing the sigmoid activation function and analyzing the impact of WT on DBN classification performance. Research indicates that this method can achieve an accuracy of over 89% even with limited training samples. Finally, the reliability of the proposed classification model is verified using measured mixed signals.