Multi-Objective Charging Optimization of Lithium-Ion Batteries Considering Electrical, Thermal, and Aging Behaviors Using Deep Reinforcement Learning

Lithium-ion battery charging involves many factors such as electricity, heat, aging, etc. Shortening the charging time of lithium-ion batteries while limiting aging and temperature rise is an urgent issue that needs to be addressed. In order to solve this problem, the pseudo-two-dimensions (P2D) model is used to describe the electrical behavior of batteries. Then, a parameter identification method is proposed using a deep deterministic policy gradient for P2D model. Besides, a multi-objective charging model considering time, health loss, and temperature rise is constructed by combining P2D, equivalent heat, and aging mechanism models. A multi- objective charging optimization strategy is proposed using Deep Q-Network algorithm. Under the condition of strong coupling of multiple parameters in the P2D model, the identification accuracy is improved by more than 20% compared to traditional optimization algorithms. Under fast charging conditions, the charging time decreases by 19%, and the health loss only increased by 2.5%. Finally, the impact of multi-stage current variance on battery health loss is discussed. Note to Practitioners—The core of this work is to solve the charging problem of lithium batteries. This paper proposes a new intelligent charging algorithm based on deep reinforcement learning. This method uses a multi-stage constant current charging algorithm as the framework, taking into account the strong adaptability of charging time, temperature, and battery aging to different charging scenarios. In this work, a multi-objective optimization function is constructed using the thermal model, aging model, and electrochemical model of the battery. Then, deep reinforcement learning is used to identify the parameters of the electrochemical model of the battery, which ensures the accuracy of subsequent calculations. Finally, a series of solution sets are obtained by combining neural networks with multi-objective optimization functions. Preliminary comparative experiments have shown that this method is feasible and has higher advantages in reducing charging time and battery aging compared to traditional charging methods, but its adaptability to battery aging is poor. In future research, we plan to propose an adaptive charging scheme by changing the objective function.