Remaining useful life prediction of Lithium-ion batteries based on PSO-RF algorithm

Accurately predicting the Remaining Useful Life (RUL) of lithium-ion batteries is key to battery health management system. However, problems unstable model output and extensive calculation limit prediction accuracy. This article proposes a Particle Swarm Optimization Random Forest (PSO-RF) method improve RUL First, capacity extracted from data set National Aeronautics Space Administration (NASA) University Maryland Center for Advanced Cycle Engineering (CALCE) as life factor. Then, PSO-RF established based on optimal parameters number trees random features split by PSO algorithm. Finally, experiment verified NASA CALCE sets. The results indicate that predicts with Mean Absolute Error (MAE) less than 2%, Root Square (RMSE) 3%, goodness fit greater 94%. solves problem parameter selection in RF