Research On SOH Estimation Algorithm Of Lithium Ion Battery

The questions of ecology pollution and resources lack are becoming more and more serious.New energy electric vehicles have slowly turn into the strategic goal of the longterm development of China’s automotive field.Power battery management skill is the key to guarantee the fast exercise of electric vehicles.Due to the three characteristics of lithium-ion battery,such as limited measurable parameters,mutual coupling between peculiarities and nonlinear,the exact prediction of lithium-ion battery state of Health(soh)has become the focus of relevant experiments and the difficulty of increasing research.Aiming at the problem of over fitting in lithium-ion battery SOH estimation,this paper first uses seagull optimization algorithm(SOA)to optimize the variational mode decomposition(VMD)algorithm,and then combines the optimized VMD with long short-term memory neural network(LSTM),The purpose of predicting SOH of lithium ion battery is realized by python.The major operation of this subject is as follows:(1)In order to solve the over fitting problem,an LSTM neural network based on VMD is designed.This method can decompose the input signal,so as to achieve the purpose of denoising and improve the accuracy of predicting SOH.However,the VMD used for denoising,the number of decomposed signals and the penalty factor can not select the optimal value.(2)For the defects of VMD,this topic selects SOA to optimize VMD,and then uses the optimized VMD to denoise and decompose the input capacity data,and the decomposed signal is put into neural network for training and prediction.(3)A set of data is obtained through charge discharge experiments,and then four sets of data sets are extracted from the battery aging experimental data published by NASA and the University of Maryland.The experimental results show that the LSTM neural network based on SOA optimized VMD designed in this paper has higher accuracy under the same conditions.The research methods and main conclusions used in this topic are still universal in other types of batteries,which will contribute to the future experimental exploration.Figure[59]table[14]reference[79]...