State-of-Charge Estimation of Battery Pack under Varying Ambient Temperature Using an Adaptive Sequential Extreme Learning Machine

An adaptive online sequential extreme learning machine (AOS-ELM) is proposed to predict the state-of-charge of the battery cells at different ambient temperatures. With limited samples and sequential data for training during the initial design stage, conventional neural network training gives higher errors and longer computing times when it maps the available inputs to SOC. The use of AOS-ELM allows a gradual increase in the dataset that can be time-consuming to obtain during the initial stage of the neural network training. The SOC prediction using AOS-ELM gives a smaller root mean squared error in testing (and small standard deviation in the trained results) and reasonable training time as compared to other types of ELM-based learnings and gradient-based machine learning. In addition, the subsequent identification of the cells' static capacity and battery parameters from actual experiments is not required to estimate the SOC of each cell and the battery stack.