Prediction of Battery Cycle Life Using Early-Cycle Data, Machine Learning and Data Management

The prediction of the degradation lithium-ion batteries is essential for various applications and optimized recycling schemes. In order to address this issue, study aims predict cycle lives using only data from early cycles. To reach such an objective, experimental raw 121 commercial lithium iron phosphate/graphite cells are gathered literature. analyzed, suitable input features generated use different machine learning algorithms. A final accuracy 99.81% life obtained with extremely randomized trees model. This work shows that data-driven models able successfully lifetimes early-cycle data. That aside, a considerable reduction in errors seen by incorporating management physical chemical understanding into analysis.