Processing Optimization and Property Predictions of Hot‐Extruded Bi–Te–Se Thermoelectric Materials via Machine Learning. Issue 1 (19th November 2019)

• Record Type: Journal Article
• Authors: Wang, Zhi‐Lei; Adachi, Yoshitaka; Chen, Zhong‐Chun
• Is Part Of: Advanced theory and simulations. Volume 3:Issue 1(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-11-19
• Subjects: data‐driven materials design -- inverse analysis -- machine learning -- property prediction -- thermoelectric materials; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.201900197
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: Traditional experiment‐based materials research is becoming increasingly insufficient to thoroughly understand materials' characteristics and thus it is becoming difficult to develop novel materials with better performance. Machine learning is applied to hot‐extruded Cu x Bi2 Te2.85+ y Se0.15 thermoelectric materials, and the relationships between the processing, microstructure, and properties are further investigated via a data‐driven approach. A properties‐to‐microstructure‐to‐processing inverse analysis is proposed and performed by a genetic algorithm. The analysis results indicate that hot‐extruded materials have a potential best figure of merit ( ZT ) value of 1.15, which is 1.32 times larger than their best experimental value (0.87). To obtain this optimal property, processing variables such as higher extrusion temperature and larger Cu content and microstructure with a larger average grain size and higher density are required. The proposed data‐driven approach is expected to provide a new avenue for designing high‐performance Bi–Te–Se thermoelectric materials and thus to accelerate discoveries of novel materials. Abstract : Experiment‐based materials research generally develops a material under given processing conditions and composition, which is insufficient to find novel materials with better performances. A data‐driven approach carried out by machine learning is proposed to thoroughly investigate the characteristics of Bi2 Te3 ‐based thermoelectric materials, where the potential material property and its corresponding microstructure and processing are successfully inversely explored.