State Detection Method of Secondary Equipment in Smart Substation Based on Deep Belief Network and Trend Prediction

Information sharing and interoperability before equipment can provide abundant operation and status information of secondary equipment in smart substation, which brings great convenience to condition monitoring and condition maintenance of secondary equipment. However, the accuracy of detection methods for secondary equipment is not high, and there is a certain lag in state detection and evaluation. Therefore, this paper presents a state detection method for secondary equipment in Smart Substation based on Deep Belief Network and trend prediction. Firstly, the feature extraction ability of Deep Belief Network is used to extract the feature from the measured state data, which solves the problem of over-reliance on expert experience for feature extraction by manual method, and the multi-hidden layer structure network learning feature is used to realize equipment state identification. Then, using the penalty correction strategy of information trend prediction, the running state of the equipment is predicted according to the real-time self-checking state characteristics and key historical state characteristics, in order to prepare for the system and make early warning in time. Finally, the proposed method is compared with the existing typical methods. The results show that the proposed method is superior in feature extraction and identification, and can effectively improve the accuracy and timeliness of secondary equipment condition detection results, which is suitable for practical engineering.