Cycle life estimation of lithium-ion polymer batteries using artificial neural network and support vector machine with time-resolved thermography

A battery cycle life forecast method without requirements of contact measurement devices and long testing time would be beneficial for industrial applications. The combination of infrared thermography and supervised learning techniques provided the potential solution to this problem. This research investigates the application of machine learning techniques-artificial neural networks (ANNs) and support vector machines (SVMs)-in combination with thermography for cycle life estimation of lithium-ion polymer batteries. Infrared images were captured at 1 frame/min during 70 min of charging followed by 60 min of discharging for 410 cycles. The surface temperature profiles during either charging or discharging were used as the input nodes for ANN and SVM models. The results demonstrated that with thermal profiles as the input, ANN could estimate the current cycle life of studied cell with the error of < 10% under 10 min of testing time. While when compared to ANN, the accuracy of SVM-based forecast models was similar but generally required a longer amount of testing time.