Fixed Point Neural Acceleration and Inverse Surrogate Model for Battery Parameter Identification

2025-10-28

AI Summary

Conventional metaheuristic methods for parameter identification in lithium-ion battery electrochemical models suffer from high computational cost and slow convergence, while existing machine learning approaches rely heavily on constant-current data and lack generalizability to dynamic load conditions. Method: This paper proposes a novel framework integrating a neural surrogate model with deep-learning-based fixed-point iteration. It employs a Neural Single-Particle Model (NeuralSPMe) to capture electrolyte dynamics and introduces a Parameter Update Network (PUNet) for end-to-end parameter optimization, trained exclusively on real-world driving cycle data. Contribution/Results: The framework achieves over 2000× speedup in parameter identification compared to conventional methods, drastically reduces iteration counts and sample requirements, and improves accuracy by more than an order of magnitude. It is the first method to enable high-accuracy, high-efficiency online parameter identification under dynamic operating conditions, providing a deployable solution for battery health assessment in electric vehicles.

Technology Category

• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• 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

Abstract

The rapid expansion of electric vehicles has intensified the need for accurate and efficient diagnosis of lithium-ion batteries. Parameter identification of electrochemical battery models is widely recognized as a powerful method for battery health assessment. However, conventional metaheuristic approaches suffer from high computational cost and slow convergence, and recent machine learning methods are limited by their reliance on constant current data, which may not be available in practice. To overcome these challenges, we propose deep learning-based framework for parameter identification of electrochemical battery models. The proposed framework combines a neural surrogate model of the single particle model with electrolyte (NeuralSPMe) and a deep learning-based fixed-point iteration method. NeuralSPMe is trained on realistic EV load profiles to accurately predict lithium concentration dynamics under dynamic operating conditions while a parameter update network (PUNet) performs fixed-point iterative updates to significantly reduce both the evaluation time per sample and the overall number of iterations required for convergence. Experimental evaluations demonstrate that the proposed framework accelerates the parameter identification by more than 2000 times, achieves superior sample efficiency and more than 10 times higher accuracy compared to conventional metaheuristic algorithms, particularly under dynamic load scenarios encountered in practical applications.

Problem

• Accelerating electrochemical battery model parameter identification
• Overcoming computational inefficiency in conventional metaheuristic methods
• Enabling parameter estimation under dynamic operating conditions

Innovation

• Neural surrogate model predicts lithium concentration dynamics
• Fixed-point iteration method accelerates parameter identification
• Deep learning framework enhances accuracy and efficiency