{"title":"化工领域人工智能的多尺度革命","authors":"Ying Li, Quanhu Sun, Zutao Zhu, Huaqiang Wen, Saimeng Jin, Xiangping Zhang, Zhigang Lei, Weifeng Shen","doi":"10.1007/s11705-025-2562-1","DOIUrl":null,"url":null,"abstract":"<div><p>With the advent of the fourth technological revolution, the new generation of artificial intelligence (AI) has imparted new significance and opportunities to the modeling of momentum, heat, and mass transfer, as well as chemical reaction processes with the realm of chemical engineering. AI techniques are being widely employed in the chemical industry and are constantly evolving to offer more effective solutions for tackling practical challenges. This review delves the transformation of the chemical industry from traditional digital simulations to advanced AI-based approaches, targeting high efficiency and low carbon emissions across the scale from molecules to factories. Particular emphasis is mainly placed on the research carried out within the research group of Weifeng Shen. At the molecular level, the intelligent capture of molecular characteristics and the precise determination of structure-property relationships have reached a mature stage. Furthermore, multifunction-driven reverse molecular design for solvents, reaction reagents, and other substances has been accomplished through AI-based high-throughput screening and generative models. To improve the safety, environmental friendliness, and carbon reduction performance of chemical separation processes, a series of innovative reinforcement strategies have been put forward, with a primary focus on the systematic optimization of solvent design. On the process scale of actual production, it frequently occurs that the constructed mechanism model fails to align with the actual system behavior, thereby restricting the industrial application of the model. To solve this issue, mechanism-data hybrid-driven frameworks have been successfully developed, leveraging AI-enhanced prediction, diagnosis, optimization, and control for complex separation systems in practice. Finally, as a bridge connecting big data intelligent technology and actual industrial processes, dynamic digital twin modeling is discussed for its potential to boost efficiency and sustainability in the chemical industry.\n</p><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":571,"journal":{"name":"Frontiers of Chemical Science and Engineering","volume":"19 7","pages":""},"PeriodicalIF":4.5000,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-scale revolution of artificial intelligence in chemical industry\",\"authors\":\"Ying Li, Quanhu Sun, Zutao Zhu, Huaqiang Wen, Saimeng Jin, Xiangping Zhang, Zhigang Lei, Weifeng Shen\",\"doi\":\"10.1007/s11705-025-2562-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>With the advent of the fourth technological revolution, the new generation of artificial intelligence (AI) has imparted new significance and opportunities to the modeling of momentum, heat, and mass transfer, as well as chemical reaction processes with the realm of chemical engineering. AI techniques are being widely employed in the chemical industry and are constantly evolving to offer more effective solutions for tackling practical challenges. This review delves the transformation of the chemical industry from traditional digital simulations to advanced AI-based approaches, targeting high efficiency and low carbon emissions across the scale from molecules to factories. Particular emphasis is mainly placed on the research carried out within the research group of Weifeng Shen. At the molecular level, the intelligent capture of molecular characteristics and the precise determination of structure-property relationships have reached a mature stage. Furthermore, multifunction-driven reverse molecular design for solvents, reaction reagents, and other substances has been accomplished through AI-based high-throughput screening and generative models. To improve the safety, environmental friendliness, and carbon reduction performance of chemical separation processes, a series of innovative reinforcement strategies have been put forward, with a primary focus on the systematic optimization of solvent design. On the process scale of actual production, it frequently occurs that the constructed mechanism model fails to align with the actual system behavior, thereby restricting the industrial application of the model. To solve this issue, mechanism-data hybrid-driven frameworks have been successfully developed, leveraging AI-enhanced prediction, diagnosis, optimization, and control for complex separation systems in practice. Finally, as a bridge connecting big data intelligent technology and actual industrial processes, dynamic digital twin modeling is discussed for its potential to boost efficiency and sustainability in the chemical industry.\\n</p><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>\",\"PeriodicalId\":571,\"journal\":{\"name\":\"Frontiers of Chemical Science and Engineering\",\"volume\":\"19 7\",\"pages\":\"\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2025-05-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers of Chemical Science and Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s11705-025-2562-1\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers of Chemical Science and Engineering","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s11705-025-2562-1","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
Multi-scale revolution of artificial intelligence in chemical industry
With the advent of the fourth technological revolution, the new generation of artificial intelligence (AI) has imparted new significance and opportunities to the modeling of momentum, heat, and mass transfer, as well as chemical reaction processes with the realm of chemical engineering. AI techniques are being widely employed in the chemical industry and are constantly evolving to offer more effective solutions for tackling practical challenges. This review delves the transformation of the chemical industry from traditional digital simulations to advanced AI-based approaches, targeting high efficiency and low carbon emissions across the scale from molecules to factories. Particular emphasis is mainly placed on the research carried out within the research group of Weifeng Shen. At the molecular level, the intelligent capture of molecular characteristics and the precise determination of structure-property relationships have reached a mature stage. Furthermore, multifunction-driven reverse molecular design for solvents, reaction reagents, and other substances has been accomplished through AI-based high-throughput screening and generative models. To improve the safety, environmental friendliness, and carbon reduction performance of chemical separation processes, a series of innovative reinforcement strategies have been put forward, with a primary focus on the systematic optimization of solvent design. On the process scale of actual production, it frequently occurs that the constructed mechanism model fails to align with the actual system behavior, thereby restricting the industrial application of the model. To solve this issue, mechanism-data hybrid-driven frameworks have been successfully developed, leveraging AI-enhanced prediction, diagnosis, optimization, and control for complex separation systems in practice. Finally, as a bridge connecting big data intelligent technology and actual industrial processes, dynamic digital twin modeling is discussed for its potential to boost efficiency and sustainability in the chemical industry.
期刊介绍:
Frontiers of Chemical Science and Engineering presents the latest developments in chemical science and engineering, emphasizing emerging and multidisciplinary fields and international trends in research and development. The journal promotes communication and exchange between scientists all over the world. The contents include original reviews, research papers and short communications. Coverage includes catalysis and reaction engineering, clean energy, functional material, nanotechnology and nanoscience, biomaterials and biotechnology, particle technology and multiphase processing, separation science and technology, sustainable technologies and green processing.