Multimodal Sensing‐Driven Intelligent Disassembly System for Power Batteries: A Collaborative Architecture of Localisation‐Early Warning‐Control Based on Deep Learning

作者：Wenhong Wang, Xiangpu Meng, Shuo Li, Cheng Luo, Zhijia Zhang, Meina Zhai, Mingzhe Yuan, Dunxin Huang · 发表于：Energy Internet · 年份：2025 · DOI：10.1049/ein2.70004

Driven by green energy advancements and system integration, the surge in retired lithium‐ion batteries from electric vehicles has intensified battery recycling challenges. Traditional crushing methods suffer from low material purity, limited economic value, and environmental pollution, necessitating advanced, eco‐friendly recycling technologies. Fine disassembly, an emerging low‐carbon approach, enhances resource recovery but faces stability and safety challenges due to the diversity of power batteries. This study innovatively applies deep learning to fine disassembly, employing the YOLOv8s model for precise cell localisation and counting, an LSTM‐thermal infrared mechanism for fire risk prediction during cutting, and image segmentation for optimised electrode winding control. These methods address battery complexity, offering intelligent, safe solutions for disassembly, improving recycling efficiency, and advancing green energy systems and environmental sustainability.