查看文章

The safe application of discharge equipment, such as transformers, is related to the reliability of smart power grid and is crucial to the stable operation of the power system. Partial discharge pattern recognition has been identified as a standard diagnostic tool for monitoring the operation of electrical equipment. In this paper, we design a hybrid deep learning model that combines CNN and LSTM to automatically recognize the partial discharge pattern of power transformers, in which the dual channel images jointly constructed by PRPD and PRPS are used as inputs. To the best of our knowledge, this is the first attempt to use the dual channel spectrum of discharge signals as a joint driver to help optimize the neural network model to complete the classification of discharge spectrums. Compared with a series of traditional machine learning methods and advanced deep learning models, experimental results illustrate …