基于配方语言模型的钙钛矿太阳能电池制造用智能机器人箱

Zijian Chen; Wenjin Yu; Chuang Wu; Feibei Chen; Zixuan Wang; Chao Zhou; Yimeng You; Shaojie Li; Qiyuan Zhu; Ning Ma; Yao Sun; Donghui Li; Billy Fanady; Shengchou Jiang; Zhongliang Yan; Shumin Zhou; Liang Li; Chang-Yu Hsieh; Yang Bai; Lixin Xiao; Chi-yung Chung; Ching-chuen Chan; Zhanfeng Cui; Michael Grätzel; Haitao Zhao

doi:10.1016/j.eng.2026.04.002

工程（英文） ›› 2026, Vol. 61 ›› Issue (6) : 365 -374. DOI: 10.1016/j.eng.2026.04.002

研究论文

基于配方语言模型的钙钛矿太阳能电池制造用智能机器人箱

ⁱ

Zijian Chen ^a^,^c^,^d^,^# ,
Wenjin Yu ^b^,^h^,^# ,
Chuang Wu ^c^,^# ,
Feibei Chen ^a^,^c^,^# ,
Zixuan Wang ^c^,^# ,
Chao Zhou ^c ,
Yimeng You ^c ,
Shaojie Li ^c ,
Qiyuan Zhu ^c ,
Ning Ma ^a^,^c ,
Yao Sun ^a^,^c ,
Donghui Li ^c ,
Billy Fanady ^c ,
Shengchou Jiang ^c ,
Zhongliang Yan ^e ,
Shumin Zhou ^c ,
Liang Li ^f ,
Chang-Yu Hsieh ^g ,
Yang Bai ^e ,
Lixin Xiao ^h ,
Chi-yung Chung ^a ,
Ching-chuen Chan ^a ,
Zhanfeng Cui ⁱ ,
Michael Grätzel ^b^,^* ,
Haitao Zhao ^a^,^c^,^*

作者信息 +

Agentic Robotic Boxes for Perovskite Solar Cell Fabrication with Recipe Language Model

Zijian Chen ^a^,^c^,^d^,^# ,
Wenjin Yu ^b^,^h^,^# ,
Chuang Wu ^c^,^# ,
Feibei Chen ^a^,^c^,^# ,
Zixuan Wang ^c^,^# ,
Chao Zhou ^c ,
Yimeng You ^c ,
Shaojie Li ^c ,
Qiyuan Zhu ^c ,
Ning Ma ^a^,^c ,
Yao Sun ^a^,^c ,
Donghui Li ^c ,
Billy Fanady ^c ,
Shengchou Jiang ^c ,
Zhongliang Yan ^e ,
Shumin Zhou ^c ,
Liang Li ^f ,
Chang-Yu Hsieh ^g ,
Yang Bai ^e ,
Lixin Xiao ^h ,
Chi-yung Chung ^a ,
Ching-chuen Chan ^a ,
Zhanfeng Cui ⁱ ,
Michael Grätzel ^b^,^* ,
Haitao Zhao ^a^,^c^,^*

Author information +

^a Research Centre for Materials Intelligent Manufacturing, State Key Laboratory of Ultra-Precision Machining Technology, Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University (PolyU), Hong Kong 999077, China

^b Laboratory of Photonics and Interfaces, Ecole Polytechnique Fédérale de Lausanne, Lausanne 1015, Switzerland

^c Physical AI Evolution (PAlEvo) Laboratory, AI for Energy Key Laboratory, PolyU-WIT Research Centre for Materials Intelligent Manufacturing, Wenzhou Institute of Technology (WIT), Wenzhou 325000, China

^d Department of Chemical and Environmental Engineering, University of Nottingham Ningbo China, Ningbo 315100, China

^e Faculty of Materials Science and Energy Engineering, Shenzhen University of Advanced Technology, Shenzhen 518107, China

^f State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, School of New Energy, North China Electric Power University, Beijing 102206, China

^g College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, China

^h State Key Laboratory of Artificial Microstructure and Mesoscopic Physics, School of Physics, Peking University, Beijing 100871, China

ⁱ Department of Engineering Science, University of Oxford, Oxford OX1 3PJ, UK

*E-mail addresses: michael.graetzel@epfl.ch (M. Grätzel),

hai-tao.zhao@polyu.edu.hk (H. Zhao).

Show less

文章历史 +

Abstract

Perovskite solar cells (PSCs) have been undergoing rapid development with the vast combinatorial exploration of recipes; however, the related research suffers from time-consuming trial-and-error synthesis and labor-intensive fabrication. As a promising alternative, interconnected robotic boxes that integrate fabrication and characterization enable high-throughput experimentation and data collection; however, the resulting numerical datasets are often insufficiently analyzed and fail to provide effective feedback for semantic recipe optimization. Here, we conceived and realized an emerging scientific tool of robotic boxes enabled by a domain-specific recipe language model (RLM) and a coordinating language agent for PSCs research. The developed agent features two loops of seven artificial intelligence (AI) layers, in which both numerical and semantic recipes were continuously learned and optimized from the literature and robotic corpora for iterative fine-tuning of the RLM. Guided by the agent, 11 robotic boxes executed the controllable synthesis, fabrication, and characterization of 50 764 PSCs, increasing the power conversion efficiency (PCE) to 27.0% (26.5% certified). Simultaneously, more than 578 million tokens were generated and augmented to improve the ability to recommend a recipe and mechanistic reasoning, achieving an overall score of about 80% based on the dedicated evaluation criteria. Thus, such agentic robotic boxes provide an advanced tool for the next-generation synthesis, fabrication, characterization, and even mechanistic reasoning of PSCs and beyond.

关键词

Key words

Robotics / Language agent / Recipe language model / Materials intelligence / Perovskite solar cells / Device fabrication

引用本文

引用格式 ▾

Zijian Chen,Wenjin Yu,Chuang Wu,Feibei Chen,Zixuan Wang,Chao Zhou,Yimeng You,Shaojie Li,Qiyuan Zhu,Ning Ma,Yao Sun,Donghui Li,Billy Fanady,Shengchou Jiang,Zhongliang Yan,Shumin Zhou,Liang Li,Chang-Yu Hsieh,Yang Bai,Lixin Xiao,Chi-yung Chung,Ching-chuen Chan,Zhanfeng Cui,Michael Grätzel,Haitao Zhao. 基于配方语言模型的钙钛矿太阳能电池制造用智能机器人箱[J]. 工程（英文）, 2026, 61(6): 365-374 DOI:10.1016/j.eng.2026.04.002