Ai-Driven Closed-Loop Supply Chains: A Systematic Review Of Operational Mechanisms And Performance Outcomes In Battery Recycling

Abstract

Introduction: In response to the global rise in new energy vehicles and the accompanying surge in battery waste, this study systematically reviews the integration of artificial intelligence (AI) in closed-loop supply chains (CLSC) for battery recycling. Methods: The study draws upon 134 peer-reviewed articles published from 2015 to 2025 and adopts the PRISMA framework alongside a hybrid screening protocol to investigate dominant AI technologies, performance evaluation frameworks, and key implementation barriers in battery recycling closed-loop supply chains. Findings: The findings show that deep learning and genetic algorithms dominate technical applications across CLSC stages such as recycling, disassembly, and remanufacturing, improving efficiency and reducing operational costs. However, performance assessment suffers from inconsistent metrics and limited socio-environmental integration. While AI significantly enhances material recovery and traceability, its industrial scalability remains constrained by data fragmentation, algorithmic opacity, and policy-technology mismatches. Conclusion: The study concludes by identifying critical research gaps, particularly in the areas of blockchain-AI integration and hybrid intelligent systems, and proposes future research directions to unlock the projected USD 17.8 billion market value by 2030.