Insights into dendritic growth mechanisms in batteries: A combined machine learning and computational study

2025-03-02

AI Summary

Dendritic growth in lithium batteries poses severe safety risks—including internal short circuits, thermal runaway, and accelerated capacity degradation—yet its underlying multiphysics coupling mechanisms remain challenging to model accurately. To address this, we propose a dual-CNN framework: CNN-1 employs a purely data-driven approach to predict dendrite evolution; CNN-2 innovatively embeds key electrochemical–mechanical physical parameters (e.g., Li⁺ concentration and stress fields) directly into convolutional layers, enabling physics-informed and interpretable modeling. High-fidelity training data are generated via multiphysics simulations. Validated extensively, CNN-2 achieves superior dynamic prediction accuracy and generalization robustness for dendrite nucleation, preferential growth orientation, and branching evolution. This work delivers an intelligent predictive tool that simultaneously ensures high accuracy and physical interpretability, supporting the design of safer, longer-lasting solid-state and liquid-electrolyte lithium batteries.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Safety and Robustness

Application Category

• 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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

In recent years, researchers have increasingly sought batteries as an efficient and cost-effective solution for energy storage and supply, owing to their high energy density, low cost, and environmental resilience. However, the issue of dendrite growth has emerged as a significant obstacle in battery development. Excessive dendrite growth during charging and discharging processes can lead to battery short-circuiting, degradation of electrochemical performance, reduced cycle life, and abnormal exothermic events. Consequently, understanding the dendrite growth process has become a key challenge for researchers. In this study, we investigated dendrite growth mechanisms in batteries using a combined machine learning approach, specifically a two-dimensional artificial convolutional neural network (CNN) model, along with computational methods. We developed two distinct computer models to predict dendrite growth in batteries. The CNN-1 model employs standard convolutional neural network techniques for dendritic growth prediction, while CNN-2 integrates additional physical parameters to enhance model robustness. Our results demonstrate that CNN-2 significantly enhances prediction accuracy, offering deeper insights into the impact of physical factors on dendritic growth. This improved model effectively captures the dynamic nature of dendrite formation, exhibiting high accuracy and sensitivity. These findings contribute to the advancement of safer and more reliable energy storage systems.

Problem

• Understanding dendrite growth mechanisms in batteries
• Predicting dendrite growth using machine learning models
• Enhancing battery safety and reliability through improved models

Innovation

• Combined machine learning and computational methods
• Two-dimensional CNN models for dendrite prediction
• Enhanced CNN-2 with physical parameters integration