Correlation Analysis Of Electric Vehicle Charging/Discharging Faults Based On Artificial Intelligence

In recent years,with the development of new energy technology and the country’s strong support for electric vehicles,the number of electric vehicles and the construction of charging/discharging facilities have been increasing rapidly,what follows is the frequent occurrence of electric vehicle charging/discharging faults and safety accidents.Because of the lack of research on charging/discharging faults and safety of power batteries and charging/discharging equipment at this stage,and the lack of effective analysis and analysis of electric vehicle charging/discharging fault analysis and diagnosis methods,this article studies the correlation of electric vehicle charging/discharging faults,provides theoretical support for diagnosis and maintenance of charging/discharging faults of electric vehicles,guarantees the safety of electric vehicle charging and discharging,and is of great significance to the stable and sustainable development of electric vehicles.In view of the problems of electric vehicles are prone to faults during charging and discharging process,this paper studies the correlation analysis of charging/discharging faults of electric vehicles.First,on the basis of a comprehensive analysis of the structure and working principle of the power battery and charging/discharging equipment involved in the charging and discharging process of electric vehicles,the common fault phenomena and fault mechanisms of the power battery and charging/discharging equipment are analyzed and summarized.On the basis of clarifying the fault mechanism of power batteries and charging/discharging equipment,analyze the fault-related factors affecting power batteries and charging/discharging equipment from multiple angles,and summarize the characteristic parameters related to power batteries and charging/discharging equipment faults,determine the temperature change rate,ambient temperature,charge overvoltage rate,discharge overcurrent rate,internal resistance,internal resistance change rate,battery state of charge SOC,and battery pack fault history as characteristic parameters that characterize power battery fault-related factors,and determine the charging voltage error rate,ambient temperature,continuous running time,charging current error rate,response rate of charging/discharging equipment and BMS,discharging current error rate,historical fault times as characteristic parameters that characterize charging/discharging equipment fault-related factors.Secondly,in view of the continuity and largeness of the fault characteristic parameter data of power batteries and charging/discharging equipment,the K-means clustering algorithm is used to discretize the characteristic parameter data,determine the numerical interval for discretization of each characteristic parameter,and obtain a transaction data set that can be mined for association rules.Finally,the weight-based optimized FP-Growth algorithm is used to mine out the association rules between the faults of power batteries and charging/discharging equipment and the characteristic parameters of the fault-related factors.Then analyze the correlation of the fault based on the association rules,and get the correlation level between the fault-related factors and fault.