Life Prediction And Evaluation Of Power Lithium-ion Battery

With the development of science and technology,due to the deterioration of the environment and energy problem,electric vehicle has gradually got people’s attention.It has become the most promising new energy industry.Electric vehicle has incomparable advantages in environmental protection and energy-saving.Meanwhile,battery technology stands a core position of EV development.As a key index of the traction battery,research on life cycle characteristic of has been attached gradually by the industry.In this paper,the problem of battery’s capacity decline of electric vehicle is the main research object,and we researched the lithium-ion battery recession mechanism and remaining useful life(RUL)forecasts.First of all,I researched the fundamentals of lithium-ion battery to provide the theoretical basis to the following study.Next,I have studied the mechanism of power battery decline,and analyzed the mechanism and main external factors which influences the capacity decline of power battery.Based on the electrochemical theory,the reasons of the aging of the battery were analyzed.The mechanism of the degradation of the Li-ion battery under the shelving state,the recycling state,the charge-discharge process was studied.And by comparing the different temperature,different discharge current capacity decline curve,I reached the impact of lithium-ion service life of external factors.Finally,fuzzy information granulation of the training samples is made,and effective component information of each window is extracted according to the need,namely the minimum,average and maximum value of each window.Secondly,LS-SVM of the prediction models are established for each component,and then the adaptive particle swarm algorithm is used to optimize each component model.Finally,the optimized LS-SVM model is used for forecast remaining useful life of the lithium ion battery.In this paper,a least squares support vector machine algorithm based on fuzzy information granulation and particle swarm optimization algorithm is proposed to predict the remaining service life of lithium-ion battery.And compared with those based on gray prediction model,BP neural network and ARMA model,We found that the proposed method has a higher accuracy.