Scholarlink

<p>Lithium-ion batteries are often retired while still retaining 70–80% of their rated capacity, creating economic and environmental challenges across their supply chain. Although reuse, recycling and remanufacturing offer alternatives to recover this otherwise&#xa0;under-utilized value, their implementation is hindered by the lack of reliable data on battery condition at retirement, making it difficult to determine whether, when and how these alternatives should be applied. In this Perspective, we discuss how artificial intelligence (AI) can help to&#xa0;overcome data barriers by enabling adaptive, data-informed decision-making throughout the battery life cycle. AI tools can be tailored to battery data scarcity and heterogeneity contexts, and integrated with data curation, model establishment and model deployment. For example, physics-based modelling can be used when data are unavailable, field-sensing when data are limited and federated AI when data sharing is restricted. Management&#xa0;of retired batteries can benefit from AI tools that are adequately accurate, stable, interpretable, transferable and deployable under these data uncertainties. Further adoption of AI into retired battery condition inspection, pretreatment, reutilization and governance could offer a framework towards safe and efficient battery life-cycle management at scale.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial intelligence for battery reuse, recycling and remanufacturing

  • 期刊论文

  • 发表日期：

    2026年4月28日

查看全文
  • Shengyu Tao,
  • Scott Moura,
  • Daniel Brandell,
  • Zhiyuan Han,
  • Shafiq Urréhman,
  • Changfu Zou,
  • Xuan Zhang,
  • Guangmin Zhou

摘要

Lithium-ion batteries are often retired while still retaining 70–80% of their rated capacity, creating economic and environmental challenges across their supply chain. Although reuse, recycling and remanufacturing offer alternatives to recover this otherwise under-utilized value, their implementation is hindered by the lack of reliable data on battery condition at retirement, making it difficult to determine whether, when and how these alternatives should be applied. In this Perspective, we discuss how artificial intelligence (AI) can help to overcome data barriers by enabling adaptive, data-informed decision-making throughout the battery life cycle. AI tools can be tailored to battery data scarcity and heterogeneity contexts, and integrated with data curation, model establishment and model deployment. For example, physics-based modelling can be used when data are unavailable, field-sensing when data are limited and federated AI when data sharing is restricted. Management of retired batteries can benefit from AI tools that are adequately accurate, stable, interpretable, transferable and deployable under these data uncertainties. Further adoption of AI into retired battery condition inspection, pretreatment, reutilization and governance could offer a framework towards safe and efficient battery life-cycle management at scale.