Noise‐Aware Active Learning to Develop High‐Temperature Shape Memory Alloys with Large Latent Heat

• DOI: 10.1002/advs.202406216
• Publication Date: 2024-10-03T10:30:17Z
• Authors: Yuan Tian; Bin Hu; Pengfei Dang; Jianbo Pang; Yumei Zhou; Dezhen Xue
• Keywords: Hysteresis

Abstract Shape memory alloys (SMAs) with large latent heat absorbed/released during phase transformation at elevated temperatures benefit their potential application on thermal energy storage (TES) in high temperature environment like power plants, etc. The desired can be designed quickly by searching the vast component space of doped NiTi‐based SMAs via data‐driven method, while challenging noisy experimental data. A noise‐aware active learning strategy is proposed to accelerate design based optimal noise level estimated minimizing model error incorporation a range levels as hyper‐parameters into Kriging model. employment this leads discovery alloy –36.08 J g −1 , 9.2% larger than best value (–33.04 ) original training dataset within another four experiments. Additionally, represents austenite finish (481.71°C) and relatively small hysteresis. This promotes TES circumstance. It expected that approach convenient for accelerated materials method