A D V A N C E D M A T E R I A L S & P R O C E S S E S | J U L Y / A U G U S T 2 0 2 1 6 MACHINE LEARNING | AI AI DRIVES CERAMIC COATINGS INNOVATION Tanvir Hussain, a materials scientist at the University of Nottingham, U.K., received nearly $3 million to develop new coatings for use in aerospace that could reduce CO2 emissions and help spacecraft travel further into the solar system. The five-year fellowship, funded by the Engineering and Physical Sciences Research Council, aims to find newmodeling and processing techniques to overhaul the design and manufacture of advanced ceramic materials for next-generation air and space travel. Using artificial intelligence and advanced chemistry, Hussain will manipulate the molecular architecture of ceramic materials to make themmore durable and sustainable. The project aims to produce ceramic coatings designed and manufactured with thermal, electrical, and environmental barrier properties that can be fine-tuned to specific aerospace applications. Ex- amples include thermal barrier coatings to protect superalloys from high temperatures, environmental barrier coatings to protect ceramic composites from steam, insulating coatings for electric motors for the electrification of aircrafts, and corrosion and wear- resistant coatings for critical engine components. “The research will lead to the creation of products for the aerospace industry with improved properties, performance, and reduced materials processing times that can be manufactured in large volumes at a fraction of the cost of today’s methods,” says Hussain. www. nottingham.ac.uk. FINDING SINGLE-ATOM-ALLOY CATALYSTS WITH AI Researchers from Skolkovo Institute of Science and Technology (Skoltech), Russia, and their colleagues from China and Germany developed a new search algorithm for single- atom-alloy catalysts (SAACs) that found more than 200 new candidates. SAACs, where single atoms of rare and expensive metals such as platinum are dispersed on an inert metal host, are highly efficient in numerous catalytic reactions, including selective hydrogenations, dehydrogenations, C-C and C-O coupling reactions, NO reduction, and CO oxidation. Assistant professor Sergey Lev- chenko and his colleagues were able to identify accurate and reliable machine learning models based on first-principles calculations for the description of the hydrogen binding energy, dissociation energy, and guest-atom segregation energy for SAACs. This led them to make a much faster (by a factor of 1000) yet reliable prediction of the catalytic performance of thousands of SAACs. They used artificial intelligence to extract important parameters (descriptors) from computational data that correlate with the catalytic performance of SAACs and at the same time are very fast to calculate. “The developed methodology can be easily adapted to designing new functional materials for various applications, including electrocatalysis, fuel cells, reforming of methane, and water- gas shift reactions,” says Levchenko. www.skoltech.ru. Flower-like ceramic coating structure inspired by nature, for use in aero engines. Materials scientist Ming Tang of Rice University, Houston, in collaboration with physicist Fei Zhou at Lawrence Livermore National Laboratory, Calif., developed a technique to predict the evolution of microstructures in materials. The research explores how neural networks can train themselves to predict how a structure will grow in a certain environment. Tang believes the computation efficiency of neural networks could speed development of new materials, such as for his lab’s design of more efficient batteries. rice.edu. BRIEF New research is using machine learning to find promising single-atom-alloy catalysts (SAACs), providing a recipe to determine the best SAACs for a range of applications. Courtesy of pixabay.com.
RkJQdWJsaXNoZXIy MTYyMzk3NQ==