An Adaptive Method Based on Machine Learning for the State-of-Charge and State-of-Health Estimation of Lithium-Ion Batteries

The accurate estimation of the state-of-charge (SOC) and the state-of-health (SOH) of lithium-ion batteries is crucial for reliability assurance and maintenance of the energy systems in various applications including electric vehicles, cell phones, and aerospace satellite missions. Due to the complicated and nonlinear nature of the physical mechanisms involved in these batteries and their dependence on several variables, in the past few years, various algorithms based on machine learning have been used for the SOC/SOH estimation. One of the challenges is that the estimator models need to be adaptive for different batteries, application scenarios, and environmental parameters. We present a novel adaptive method for SOC/SOH estimation of lithium-ion batteries based on techniques in machine learning. We apply the proposed method on real datasets of battery operation, and we compare the performance of various algorithms used in this context. Our findings contribute to the growing field of efficient battery management systems and facilitate creating effective maintenance schedules and enhancing the reliability and safety of battery-powered applications.