SOC and SOH Estimation Technology for Lithium-ion Power Batteries in Electric Vehicles Based on Artificial Intelligence Algorithms
This article constructs a long short-term memory network model based on artificial intelligence algorithms and explores the estimation accuracy of the model for the SOC and SOH of lithium-ion power batteries under different conditions.In SOC estimation of power batteries,increasing the number of hidden layers and neurons on the hidden layers can improve the accuracy of the model in estimating battery SOC.When the hidden layer is 2 layers and there are 100 neurons,the model's estimated and measured values of battery SOC are very close,with an RMSE error of only 1.1％and a ME value of 2.4％.In the estimation of power battery SOH,the same long short-term memory network model was used for SOH estimation,and the results showed that the RMSE value was 0.85％and the ME value was 1.02％.It can be concluded that using an artificial neural network-based long short-term memory network model to estimate the SOC and SOH of power batteries can meet the accuracy requirements.
artificial intelligence algorithmslithium ion power batteriesSOCSOHelectric vehicle
万方数据
维普
