Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites

• Main Authors: Bash, Daniil, Cai, Yongqiang, Chellappan, Vijila, Wong, Swee Liang, Xu, Yang, Kumar, Pawan, Tan, Jin Da, Abutaha, Anas, Cheng, Jayce J. W., Lim, Yee‐Fun, Tian, Siyu Isaac Parker, Ren, Zekun, Mekki‐Berrada, Flore, Wong, Wai Kuan, Xie, Jiaxun, Kumar, Jatin, Khan, Saif A., Li, Qianxiao, Buonassisi, Tonio, Hippalgaonkar, Kedar
• 其他作者: School of Materials Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2022
• 主題: Engineering::Materials::Composite materials; Bayesian Optimization; Electrical Conductivity; Graphical Regression Models; High-Throughput Flow Mixing; Hypothesis Testing; Machine Learning; P3HT-CNT Composites
• 在線閱讀: https://hdl.handle.net/10356/156005
• 機構: Nanyang Technological University

Combining high-throughput experiments with machine learning accelerates materials and process optimization toward user-specified target properties. In this study, a rapid machine learning-driven automated flow mixing setup with a high-throughput drop-casting system is introduced for thin film preparation, followed by fast characterization of proxy optical and target electrical properties that completes one cycle of learning with 160 unique samples in a single day, a >10× improvement relative to quantified, manual-controlled baseline. Regio-regular poly-3-hexylthiophene is combined with various types of carbon nanotubes, to identify the optimum composition and synthesis conditions to realize electrical conductivities as high as state-of-the-art 1000 S cm−1. The results are subsequently verified and explained using offline high-fidelity experiments. Graph-based model selection strategies with classical regression that optimize among multi-fidelity noisy input-output measurements are introduced. These strategies present a robust machine-learning driven high-throughput experimental scheme that can be effectively applied to understand, optimize, and design new materials and composites.