Intelligent disassembly of electric-vehicle batteries: a forward-looking overview

Retired electric-vehicle lithium-ion battery (EV-LIB) packs pose severe environmental hazards. Efficient recovery of these spent batteries is a significant way to achieve closed-loop lifecycle management and a green circular economy. It is crucial for carbon neutralization, and for coping with the environmental and resource challenges associated with the energy transition. EV-LIB disassembly is recognized as a critical bottleneck for mass-scale recycling. Automated disassembly of EV-LIBs is extremely challenging due to the large variety and uncertainty of retired EV-LIBs. Recent advances in artificial intelligence (AI) machine learning (ML) provide new ways for addressing these problems. This study aims to provide a systematic review and forward-looking perspective on how AI/ML methodology can significantly boost EV-LIB intelligent disassembly for achieving sustainable recovery. This work examines the key advances and research opportunities of emerging intelligent technologies for EV-LIB disassembly, and recycling and reuse of industrial products in general. We show that AI could benefit the whole disassembly process, particularly addressing the uncertainty and safety issues. Currently, EV-LIB state prognostics, disassembly decision-making as well as target detection are indicated as promising areas to realize intelligence. The challenges still exist for extensive autonomy due to present AI's inherent limitations, mechanical and chemical complexities, and sustainable benefits concerns. This paper provides the practical map to direct how to implement EV-LIB intelligent disassembly as well as forward-looking perspectives for addressing these challenges.

Automated summary

This study aims to enhance intelligent disassembly of retired electric-vehicle lithium-ion battery (EV-LIB) packs through the use of artificial intelligence and machine learning. The research shows that AI can effectively address uncertainties and safety concerns in the disassembly process, and identifies future research opportunities.