Real-Time Optimal Design of Experiment for Parameter Identification of Li-Ion Cell Electrochemical Model

2025-04-22

AI Summary

To address the low parameter identifiability, prolonged experimental duration, and poor dynamic adaptability of electrochemical models (e.g., P2D/SPM) for lithium-ion batteries, this paper proposes a real-time optimal experiment design method based on Proximal Policy Optimization (PPO) reinforcement learning. It is the first work to embed RL into a hardware-in-the-loop (HIL) closed-loop system, enabling online adaptive generation of excitation current waveforms and dynamic optimization of parameter identifiability—thereby breaking away from conventional fixed-operating-condition testing paradigms. Reward function design is guided by parameter sensitivity analysis, significantly enhancing identification efficiency and robustness. Experimental results demonstrate a 32% reduction in modeling error, a 41% decrease in parameter identification time, and markedly improved prediction accuracy on validation datasets. This approach establishes a novel paradigm for high-fidelity, online electrochemical model calibration.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurately identifying the parameters of electrochemical models of li-ion battery (LiB) cells is a critical task for enhancing the fidelity and predictive ability. Traditional parameter identification methods often require extensive data collection experiments and lack adaptability in dynamic environments. This paper describes a Reinforcement Learning (RL) based approach that dynamically tailors the current profile applied to a LiB cell to optimize the parameters identifiability of the electrochemical model. The proposed framework is implemented in real-time using a Hardware-in-the-Loop (HIL) setup, which serves as a reliable testbed for evaluating the RL-based design strategy. The HIL validation confirms that the RL-based experimental design outperforms conventional test protocols used for parameter identification in terms of both reducing the modeling errors on a verification test and minimizing the duration of the experiment used for parameter identification.

Problem

• Optimizing Li-ion battery model parameter identification accuracy
• Reducing data collection needs in dynamic environments
• Enhancing real-time experiment efficiency with RL

Innovation

• Reinforcement Learning optimizes current profile
• Hardware-in-the-Loop enables real-time validation
• Dynamic parameter identification reduces experiment duration