The evaluation of battery pack SOH based on Monte Carlo simulation and support vector machine algorithm

This paper studies the storage life of ICR18650 lithium-ion batteries at different temperatures and different SOC (stage of charge). The author establishes a storage life prediction model. Based on the empirical model, the author analyzed the relationship between temperature and SOC about the influencing factors through experimental data, and used nonlinear regression fitting to determine the model parameters, and the storage life prediction model of irreversible capacity loss with respect to temperature, SOC, and time is finally established. Based on the differences of monomers and measurement errors during test, an error model was established, and a Monte Carlo simulation test was conducted on the battery storage life. Then we build a SVR model based on the obtained data. According to the SVR model, we can analyze the health state of the battery pack based on the given parameters of battery pack in storage. Thus, we can make a prognosis about the SOH of battery pack quickly and accurately. The innovation of the research is that based on the storage test of battery cells combined with data analysis and deductive simulation, we can predict the health state of the whole battery pack. The operation can greatly save experimental resources.