State Assessment and Fault Prediction Method of Distribution Terminal Based on SDAE and Hierarchical Bayesian

State Assessment and Fault Prediction mechanism of distribution terminal is the premise of ensuring safe and reliable operation of power grid. However, the sample size of fault rate data of distribution terminal is usually small and the data is missing seriously, so it is difficult to accurately evaluate and analyze the fault rate data. A reliability assessment and prediction model based on stacked denoising autoencoder and hierarchical bayesian is proposed in this paper. Firstly, the quantile method is used to detect abnormal values of distribution terminals. Then, features of fault data is extracted by stacked denoising autoencoder(SDAE), and the Hierarchical Bayesian(HB) model is used to evaluate the failure rate data of distribution terminals. Finally, the evaluation method is compared the traditional prior distribution and the second-order linear regression. The results show that the proposed method improves the accuracy of fault assessment by 5.37% and 10.09%, the accuracy of prediction by 10.23% and 19.94%. The proposed method has higher reliability, prediction efficiency and evaluation accuracy.