State of Health Prediction of Lithium-Ion Battery Using Machine Learning Algorithms

With the widespread use of lithium-ion batteries in various fields, estimating the State of Health (SOH) of batteries is essential to ensure efficiency and safety during operation. Although model-based methods have been widely applied for SOH estimation, challenges in battery modeling have led to increasing interest in machine learning approaches. This paper introduces a SOH evaluation method based on time-domain data analysis. The method focuses on processing and analyzing data in the time domain to identify relationships with the usable capacity of the battery. We also compare the effectiveness of this method with various neural network models such as Feedforward Neural Networks (FNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM). The results demonstrate that the time-domain analysis method can provide high accuracy and effectively meet the needs of SOH estimation, especially when the training data is limited.