Research On Battery State Of Charge Estimation Method Based On Model Fusion

At present,the two major crises of resource shortage and environmental pollution are bothering all mankind all the time.Smart grid came into being,new energy has become the mainstream.The development of smart grid is inseparable from the energy storage system.The core of the energy storage system is the battery management system.Scientists pay more and more attention to the research of the battery management system,but at present,the technical research of the energy storage battery is not mature enough.Accurate estimation of state of charge is one of the most important technologies in the battery management system.SOC can reflect the remaining capacity of the current battery.Accurate estimation of SOC is the guarantee of efficient and safe battery charging and discharging,prolonging battery life,ensuring the normal operation of the power system and accelerating the promotion One of the essential ways to develop smart grid.Therefore,in this paper,the state of charge estimation of lithium-ion battery is studied in depth,and the work is as follows:(1)The missing data and abnormal data are processed,and the extended method of battery state of charge feature is proposed;(2)An improved particle swarm optimization algorithm is proposed to optimize the parameters of traditional support vector regression algorithm;(3)The algorithm of SOC estimation based on stacking model fusion is proposed.