作者：Xuefeng Zhao, Qianwen Hao , Wei Zhang , Rui Wang , Chengjiang Li*

期刊：《Engineering Applications of Artificial Intelligence》

出版时间：2026年vol. 171

校内级别：T2类

DOI: 10.1016/j.engappai.2026.114287

Abstract

The continued expansion of Renewable Energy and Energy Storage Systems (REESS) has led to increasing  challenges related to material consumption and environmental sustainability. Recycling technologies (RT) have  emerged as key enablers of resource efficiency and circularity. However, the stage-specific contributions of  different RT types within REESS remain poorly understood. This study employs a large language model (LLM) to  generate search terms for constructing corpora and classifying patents, subdivides patent subsets, builds a Type &  Dependency mechanism for claim analysis, and uses three analytical approaches to elucidate the evolving role of  RTs in REESS development. The results reveal three main findings: (1) RTs display stage-specific application  patterns, with Chemical RTs dominating the control stage, while Biological RTs remain limited in the generation  stage; (2) Each RT type plays a distinct role across stages. Chemical RTs show the strongest impact, Physical RTs  offer stable support, and Biological RTs remain emerging with limited but growing potential; (3) RTs exhibit  increasing interconnectivity across REESS stages, indicating a shift toward more integrated and circular technological development. These findings contribute to a deeper understanding of RT integration in REESS and offer  valuable implications for advancing sustainable energy systems.

Keywords: Large language model ; Patent claim; Recycling technologies ; Renewable energy and energy storage systems

Funding：the National Natural Science Foundation of China [72464005] .