AC-DC Intrusion Signal Detection Method Based on Generative Adversarial Network for Secondary Panel Cabinet
Based on the unpredictable AC-DC intrusion caused by human error or detection equipment failure in the terminal of secondary screen cabinet of substation relay protection,a new intrusion signal detection method based on generative adversarial network and principal component analysis is proposed to solve the problem of poor quality and small quantity of data samples. Gaussian kernel smoothing is used to preprocess the terminal data to reduce noise interference,and then the cleaned data is amplified through the generated adversarial network ( GAN) to meet the subsequent principal component analysis processing and fault detection and identification of AC and DC intrusion signals.The identification accuracy of the proposed method reaches 95％,which realizes the accurate detection of the small sample fault data of the terminal of the secondary screen cabinet.
万方数据
维普
