Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Parameter Identification for Electrochemical Models of Lithium-Ion Batteries Using Bayesian Optimization

Jianzong Pi, Samuel Filgueira da Silva, Mehmet Fatih Ozkan, Abhishek Gupta, Marcello Canova

TL;DR

The paper addresses robust parameter identification for Li-ion battery models by applying Bayesian Optimization to tune three dynamic parameters in a reduced-order Electrochemical Equivalent Circuit Model (E-ECM). By modeling the objective with a Gaussian Process and using an acquisition function (EI), the method efficiently navigates the high-dimensional, expensive evaluation landscape, and is benchmarked against Gradient Descent and PSO using experimental drive-cycle data. Results show Bayesian optimization achieves notably lower training and testing losses and dramatically reduces variance, indicating superior accuracy and robustness in multi-parameter calibration of the E-ECM for an NMC-graphite cell. The work highlights practical potential for reliable battery state estimation and control with reduced computational cost, and suggests extending the parameter set and incorporating sensitivity information for further gains.

Abstract

Efficient parameter identification of electrochemical models is crucial for accurate monitoring and control of lithium-ion cells. This process becomes challenging when applied to complex models that rely on a considerable number of interdependent parameters that affect the output response. Gradient-based and metaheuristic optimization techniques, although previously employed for this task, are limited by their lack of robustness, high computational costs, and susceptibility to local minima. In this study, Bayesian Optimization is used for tuning the dynamic parameters of an electrochemical equivalent circuit battery model (E-ECM) for a nickel-manganese-cobalt (NMC)-graphite cell. The performance of the Bayesian Optimization is compared with baseline methods based on gradient-based and metaheuristic approaches. The robustness of the parameter optimization method is tested by performing verification using an experimental drive cycle. The results indicate that Bayesian Optimization outperforms Gradient Descent and PSO optimization techniques, achieving reductions on average testing loss by 28.8% and 5.8%, respectively. Moreover, Bayesian optimization significantly reduces the variance in testing loss by 95.8% and 72.7%, respectively.

Parameter Identification for Electrochemical Models of Lithium-Ion Batteries Using Bayesian Optimization

TL;DR

The paper addresses robust parameter identification for Li-ion battery models by applying Bayesian Optimization to tune three dynamic parameters in a reduced-order Electrochemical Equivalent Circuit Model (E-ECM). By modeling the objective with a Gaussian Process and using an acquisition function (EI), the method efficiently navigates the high-dimensional, expensive evaluation landscape, and is benchmarked against Gradient Descent and PSO using experimental drive-cycle data. Results show Bayesian optimization achieves notably lower training and testing losses and dramatically reduces variance, indicating superior accuracy and robustness in multi-parameter calibration of the E-ECM for an NMC-graphite cell. The work highlights practical potential for reliable battery state estimation and control with reduced computational cost, and suggests extending the parameter set and incorporating sensitivity information for further gains.

Abstract

Efficient parameter identification of electrochemical models is crucial for accurate monitoring and control of lithium-ion cells. This process becomes challenging when applied to complex models that rely on a considerable number of interdependent parameters that affect the output response. Gradient-based and metaheuristic optimization techniques, although previously employed for this task, are limited by their lack of robustness, high computational costs, and susceptibility to local minima. In this study, Bayesian Optimization is used for tuning the dynamic parameters of an electrochemical equivalent circuit battery model (E-ECM) for a nickel-manganese-cobalt (NMC)-graphite cell. The performance of the Bayesian Optimization is compared with baseline methods based on gradient-based and metaheuristic approaches. The robustness of the parameter optimization method is tested by performing verification using an experimental drive cycle. The results indicate that Bayesian Optimization outperforms Gradient Descent and PSO optimization techniques, achieving reductions on average testing loss by 28.8% and 5.8%, respectively. Moreover, Bayesian optimization significantly reduces the variance in testing loss by 95.8% and 72.7%, respectively.
Paper Structure (11 sections, 16 equations, 5 figures, 1 table, 1 algorithm)

This paper contains 11 sections, 16 equations, 5 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Overview of li-ion Cell Model Equations
  3. Bayesian Optimization
  4. Notations
  5. Preliminaries
  6. Gaussian Process
  7. Aquisition Function
  8. Problem Formulation
  9. Case Study
  10. Results and Discussion
  11. Conclusion

Figures (5)

  • Figure 1: Schematic of the E-ECM model.
  • Figure 2: The RCID (training set) and drive cycle (verification set) input current profiles.
  • Figure 3: Cell terminal voltage error in RCID test among converged parameters in gradient descent, PSO and Bayesian optimization (data collected at $T=25^\circ C$).
  • Figure 4: Cell terminal voltage error in drive cycle testamong converged parameters in gradient descent, PSO and Bayesian optimization (data collected at $T=45^\circ C$).
  • Figure 5: Box plot for the testing losses.