Learning continuous SOC-dependent thermal decomposition kinetics for Li-ion cathodes using KA-CRNNs

2025-12-17

AI Summary

Lithium-ion battery thermal runaway exhibits strong state-of-charge (SOC) dependence, yet existing models calibrate kinetic parameters only at discrete SOC points, failing to capture their continuous evolution. To address this, we propose a physics-encoded Kolmogorov–Arnold chemical reaction neural network (KA-CRNN), the first framework enabling end-to-end learning of key kinetic parameters—including activation energy, pre-exponential factor, and enthalpy change—as continuous, interpretable functions of SOC. By embedding mechanistic reaction pathways, KA-CRNN seamlessly integrates physical fidelity with data adaptability. Validated against differential scanning calorimetry (DSC) data across NCA, NM, and NMA cathodes, it accurately reproduces exothermic behavior over the full SOC range. The model quantitatively uncovers SOC-dependent oxygen release and phase-transformation mechanisms, establishing an interpretable and scalable paradigm for multiphysics-coupled thermal runaway modeling.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Thermal runaway in lithium-ion batteries is strongly influenced by the state of charge (SOC). Existing predictive models typically infer scalar kinetic parameters at a full SOC or a few discrete SOC levels, preventing them from capturing the continuous SOC dependence that governs exothermic behavior during abuse conditions. To address this, we apply the Kolmogorov-Arnold Chemical Reaction Neural Network (KA-CRNN) framework to learn continuous and realistic SOC-dependent exothermic cathode-electrolyte interactions. We apply a physics-encoded KA-CRNN to learn SOC-dependent kinetic parameters for cathode-electrolyte decomposition directly from differential scanning calorimetry (DSC) data. A mechanistically informed reaction pathway is embedded into the network architecture, enabling the activation energies, pre-exponential factors, enthalpies, and related parameters to be represented as continuous and fully interpretable functions of the SOC. The framework is demonstrated for NCA, NM, and NMA cathodes, yielding models that reproduce DSC heat-release features across all SOCs and provide interpretable insight into SOC-dependent oxygen-release and phase-transformation mechanisms. This approach establishes a foundation for extending kinetic parameter dependencies to additional environmental and electrochemical variables, supporting more accurate and interpretable thermal-runaway prediction and monitoring.

Problem

• Learning continuous SOC-dependent thermal decomposition kinetics for Li-ion cathodes
• Capturing SOC-dependent exothermic behavior during abuse conditions
• Providing interpretable insight into SOC-dependent oxygen-release and phase-transformation mechanisms

Innovation

• KA-CRNN learns continuous SOC-dependent kinetics from DSC data
• Physics-encoded network embeds interpretable reaction pathway parameters
• Models reproduce heat-release and reveal oxygen-release mechanisms