Multi-objective Bayesian Optimization of Lithium-ion Battery Cells
2022-01-0858
03/29/2022
- Event
- Content
- In the last years, lithium-ion batteries (LIBs) have become the most important energy storage system for consumer electronics, electric vehicles, and smart grids. A LIB is composed of several unit cells. Therefore, one of the most important factors that determine the performance of a LIB is the design of the unit cell. The design of LIB cells is a challenging problem since it involves the evaluation of expensive black-box functions. These functions lack a closed-form expression, and therefore, they require long-running time simulations or physical experiments for their evaluation. Recently, Bayesian optimization has emerged as a powerful gradient-free optimization methodology to solve black-box function optimization problems. Bayesian optimization has two main components: a probabilistic surrogate model of the black-box function and an acquisition function that guides the optimization. This study employs Bayesian optimization in the design of cylindrical cells type 18650. The materials of the cathode, anode, and electrolyte are Nickel-Cobalt-Magnesium, graphite, and LiPF6 EC-EMC, respectively. The black-box functions are simulations of the cycling performance test in Simcenter Battery Design Studio. The design variables are the thickness of the LIB cell and the porosity of the cathode active material. Two objectives are optimized: maximization of the energy density and minimization of the capacity fade. The surrogate models of the energy density and capacity fade are Gaussian process regression models. This study explores the capabilities of two multi-objective acquisition functions in the design of LIB cells: aggregation-based and improvement-based functions. The results show that Bayesian optimization can identify high-performance LIB cells employing a reduced number of function evaluations. The formulation of the improvement-based acquisition function promotes well-distributed Pareto fronts while the performance of the aggregation-based strategy depends on the selected set of weighting vectors.
- Citation
- Gaonkar, A., Zhu, L., El-Mounayri, H., Tovar, A. et al., "Multi-objective Bayesian Optimization of Lithium-ion Battery Cells," SAE Technical Paper 2022-01-0858, 2022, .