Abstract: Aiming at the problems of high false alarm rate, non recurrence of faults and long fault diagnosis time in the use of domestic charging piles, this paper proposes a comprehensive evaluation and prediction method of charging pile health status in the environment of Internet of vehicles. Firstly, from the perspective of safety performance and electrical performance, a hierarchical comprehensive evaluation system for the health status of charging piles is constructed. Then, the entropy weight method is used to initialize the weight of each evaluation index, and the health factor is introduced to dynamically measure the comprehensive weight of each evaluation index, so as to realize the dynamic evaluation of the health status of charging pile. Finally, Markov model is used to predict the short-term health status and remaining life of charging pile. In this paper, a charging station system in Shenzhen is taken as an example to verify the effectiveness of this method.