文献类型：期刊文献

英文题名：Design of multicomponent thermosetting polymers with enhanced tensile properties through active learning

作者：Zhao, Wenlin[1];Fu, Xuemeng[1];Xu, Xinyao[1];Zhang, Liangshun[1];Wang, Liquan[1];Lin, Jiaping[1];Hu, Yaxi[1];Gao, Liang[1];Du, Lei[1];Tian, Xiaohui[1]

机构：[1]East China Univ Sci & Technol, Frontiers Sci Ctr Materiobiol & Dynam Chem, Shanghai Key Lab Adv Polymer Mat, Key Lab Ultrafine Mat,Minist Educ,Sch Mat Sci & En, Shanghai 200237, Peoples R China

年份：2024

卷号：256

外文期刊名：COMPOSITES SCIENCE AND TECHNOLOGY

收录：;EI(收录号：20243216804365);WOS:【SCI-EXPANDED(收录号:WOS:001286439400001)】；

基金：This work was supported by the National Natural Science Foundationof China (52394271, 22173030, 51833003, and 21975073) and the National Key R&D & D Program of China (2022YFB3707302) . Support of the Shanghai Synchrotron Radiation Facility, Beamline BL16B1 (2022-SSRF-PT-500403) for WAXS testing is also appreciated.r of China (52394271, 22173030, 51833003, and 21975073) and the National Key R&D & D Program of China (2022YFB3707302) . Support of the Shanghai Synchrotron Radiation Facility, Beamline BL16B1 (2022-SSRF-PT-500403) for WAXS testing is also appreciated.

语种：英文

外文关键词：Thermosetting polymers; Machine learning; Active learning; Formulation design; Mechanical properties

摘要：Multicomponent thermosets can simultaneously achieve high strength, modulus, and toughness inaccessible by single-component materials, but efficiently designing those with exceptional mechanical properties relies on serendipity because knowledge-guided methodologies often fail in high-dimensional spaces and multi-objective problems. We proposed a multi-objective Bayesian-optimization-based active learning method enhanced by a dual-driver acquisition function to accelerate the formulation design of multicomponent epoxy resins. After several iterative experiments, we identified a multicomponent formulation of ultra-strong and high-tough samples that was much better than currently available epoxy resins. The molecular dynamic simulations and synchrotron radiation wide-angle X-ray scattering revealed that the exceptional mechanical properties of multicomponent thermosetting polymers originate from the larger meshes of crosslinking networks and the homogeneity of cured structures. The closed-loop, dual-driver Bayesian optimization strategy can be generalized for the fast discovery of high-performance materials that involve time-intensive experiments and multidimensional parameter spaces.