SOH Estimation of Battery Pack Composed on Reused Li-Ion Cells based on Adaptive ANN Machine Learning Algorithm

Abstract

An innovative state of health (SoH) estimation of the battery pack for the reused Li-Ion cells is presented in this paper. Its accuracy and calculation time are improved and accelerated using an online modeling approach (during operation) with optimal generalization. This model is based on the voltage and current characteristic data of a Li-Ion battery. By the voltage and current as the main inputs and with the help of secondary information as cycle usage, it can be possible to describe the actual quantity of energy, which is a key factor in applications. In this paper, the SoH estimation time is reduced to 40%, peak error and average error are reduced by 20% and 22%, comparing with the previous proposal. The number of input cells required for the ANN is 5000 also it is confirmed on this study that the proposed method can be applicable to a single cell as well to a battery pack. In simple words, this study proposes an alternative and cost-effective SoH estimation and diagnosis approach for the deteriorated battery, comparing to high-cost industrial devices.