基于粒子群算法估计实际工况下锂电池SOH

A new method was proposed based on the particle swarm algorithm and the empirical capacity model of lithium batteries to estimate the state of health (SOH) of the battery under actual operating conditions. A linear model was established for charging curve characteristics and battery health under electric vehicle operating conditions. A battery empirical capacity model was supplied to make it conform to the actual situation of supervised learning and to be able to fit the parameters with a computer. Based on NASA's battery aging data, a training set and a validation set were established, training the model and verifying the trained model experimentally. Results show that, the SOH estimation error can reduce to less than 7%. In actual working conditions, the health of lithium batteries of electric vehicles can be accurately estimated quickly.