China News Service, Beijing, October 5 (Reporter Sun Zifa) Can robots not only become scientists' research assistants, but also scientists? The young scientific research team of the University of Science and Technology of China (UST ) gave a positive answer through the latest R&D results.
The latest news from of the Chinese Academy of Sciences ( ) says that under the Youth Team Program of the Academy’s “Data-driven Chemistry, Materials and Bioscience Machine Scientists” and the National Natural Science Foundation of China’s National Science Foundation of China’s team, Professor Luo Yi and Jiang Jun’s team of the School of Chemistry and Materials Science of China University of Science and Technology cooperated with Shang Weiwei, the Department of Automation, to develop a full-process machine chemist driven by data intelligence through the development and integration of mobile robots, chemical workstations, intelligent operating systems, and scientific databases, and has initially realized the intelligent chemistry paradigm.
Mobile robots and intelligent workstations complete the entire chemical experiment process of high-throughput synthesis, characterization and testing. Photo provided by University of Science and Technology of China
, a research paper on "Data intelligence-driven full-process artificial intelligence machine chemist", has been published in the latest issue of the National Science Review (NSR) academic journal. International reviewers commented that the " robot system , workstations and intelligent chemical brains are all the most advanced" and "will have a huge impact on chemical science." Industry experts believe that the research work of machine chemists is separated from the limitations of the traditional trial and error research paradigm, showing the huge advantages of the new intelligent paradigm guided by the "strongest chemical brain", leading chemistry research towards the future trend of digitalization, operation instruction, and creation templateization of knowledge, and establishing China's global leading position in the field of intelligent chemistry innovation.
According to the research team of the University of Science and Technology of China, the machine chemist platform realizes the full process of chemical synthesis-characterization-test development under the dual drive of big data and intelligent models. It has surpassed similar devices in Europe and the United States in terms of software and hardware. As the only intelligent platform equipped with computing brains, theoretical models and open operating systems, it has stronger chemical intelligence and extensive chemical development capabilities. It currently covers photocatalytic and electrocatalytic materials, luminescent molecules, optical film materials, etc., and its scope of application will continue to expand with the platform upgrade and expansion.
The machine chemist platform realizes the efficient creation of high-entropy non-precious metal oxygen evolution reaction catalysts. Photo provided by the University of Science and Technology of China
machine chemist platform can use machine intelligence to find and read literature, draw expert experience from massive research data, propose scientific hypotheses and formulate experimental plans based on the knowledge and data of predecessors; dispatch 2 mobile robots and 15 independently developed intelligent chemistry workstations to complete the entire process of high-throughput synthesis, characterization, and testing, and reserve standard interfaces for scalability; through the supporting backend operating system, automatic data collection, processing, analysis and visualization are realized, and cloud databases are loaded, which can call and update database information in real time; the unique computing brain allows intelligent models to be integrated into the underlying theoretical laws and complex chemical experimental evolution by calling physical models, theoretical calculations, machine learning and Bayesian optimization, so that machine scientists can understand chemistry more and be better at chemical creation.
The popular science interpretation of the research team of the University of Science and Technology of China said that the objects of chemistry are becoming increasingly complex and high-dimensional, and the traditional research paradigm mainly relies on the means of "exhaustion" and "trial and error". Faced with the huge chemical space, the search for formulas and processes often stops at local optimality and cannot conduct global exploration. Taking the high-entropy (high complex, high disorder) compound catalyst with huge potential as an example, the highly disordered mixing of multiple elements brings high stability, which also brings great challenges to manual experiments to find the optimal ratio. Obtaining the optimal formula requires traversal testing of extremely large chemical combination combinations, which are currently limited to optimizing up to 3 metal combinations.
The latest machine chemists have used their advantages of data-driven and intelligent optimization to intelligently read 16,000 papers and independently select 5 non-precious metal elements, combine 20,000 sets of theoretical calculation data and 207 sets of full-process machine experimental data, establish an intelligent model that integrates theory and reality, guide the Bayesian optimization program to find the optimal high-entropy catalyst from 550,000 possible metal ratios, and shorten the 1,400 years required for traditional "frying dishes" traversal search to 5 weeks. (End)
(Source: China News Network)
For more exciting information, please download the "Jimu News" client in the application market. Please do not reprint without authorization. You are welcome to provide news clues and you will be paid once adopted. 24-hour information reporting hotline 027-86777777.
