Abstract
Finding new materials with targeted properties has traditionally been guided by intuition, and trial and error. With increasing chemical complexity, the combinatorial possibilities are too large for an Edisonian approach to be practical. Here we show how an adaptive design strategy, tightly coupled with experiments, can accelerate the discovery process by sequentially identifying the next experiments or calculations, to effectively navigate the complex search space. Our strategy uses inference and global optimization to balance the trade-off between exploitation and exploration of the search space. We demonstrate this by finding very low thermal hysteresis (ΔT) NiTi-based shape memory alloys, with Ti50.0Ni46.7Cu0.8Fe2.3Pd0.2 possessing the smallest ΔT (1.84 K). We synthesize and characterize 36 predicted compositions (9 feedback loops) from a potential space of ∼800,000 compositions. Of these, 14 had smaller ΔT than any of the 22 in the original data set.
Highlights
Finding new materials with targeted properties has traditionally been guided by intuition, and trial and error
L2 1⁄4 1 is an elastic condition and it is possible for two or more alloys with l2 close to 1 to possess quite different desired property (DT), in which case thermal hysteresis would be influenced by thermodynamics (Supplementary Fig. 3)
As SVR with a radial basis function kernel (SVRrbf) works well or better than the other techniques beyond three training samples—as we have more than three training samples and as we do not have any compelling argument for using less than our full training set on the problem—the results indicate that we should choose SVRrbf:Knowledge Gradient (KG)
Summary
Finding new materials with targeted properties has traditionally been guided by intuition, and trial and error. Our strategy uses inference and global optimization to balance the trade-off between exploitation and exploration of the search space We demonstrate this by finding very low thermal hysteresis (DT) NiTi-based shape memory alloys, with Ti50.0Ni46.7Cu0.8Fe2.3Pd0.2 possessing the smallest DT (1.84 K). Adaptive design has been successfully applied in areas spanning computer science[8], operations research[7] and cancer genomics[9] The novelty of this approach is that it provides a robust, guided basis for the selection of the material for experimental measurements by using uncertainties and maximizing the ‘expected improvement’ from the best-so-far material in an iterative loop with feedback from experiments. Our design framework accelerates the process of finding materials with desired properties offering the opportunity to significantly reduce the number of costly and time-consuming experiments
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
