Machine learning assisted multi-objective optimization for materials processing parameters: A case study in Mg alloy

Abstract Optimizing two or more targeted properties simultaneously is demanded in developing new materials, however, the combinatorial possibilities of chemical compositions and processing parameters are too large for an Edisonian approach to be practical. In the present study, a machine learning assisted strategy is formulated to iteratively recommend the next experiment to accomplish the multi-objective optimization in an accelerated manner. The efficacy of the strategy is demonstrated by optimizing the two step aging treatment parameters with the aim of enhancing the strength and ductility of as-cast ZE62 (Mg-6 wt.% Zn-2 wt.% RE) Mg alloy. The strength and ductility of the alloy are increased by 27% and 13.5% respectively with only four new successive experiments. The short-range homogenization is considered as the reason to enhance both properties. This strategy offers a recipe to solve the multi-objective optimization problems in designing composition and processing parameters of materials.

[1]  D. Xue,et al.  Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models , 2020 .

[2]  R. Ritchie.  The conflicts between strength and toughness. , 2011, Nature materials.

[3]  T. Lookman,et al.  Multi-objective optimization techniques to design the Pareto front of organic dielectric polymers , 2016 .

[4]  Daokui Xu,et al.  Effect of W-phase on the mechanical properties of as-cast Mg–Zn–Y–Zr alloys , 2008 .

[5]  Turab Lookman,et al.  Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design , 2019, npj Computational Materials.

[6]  Yumei Zhou,et al.  Accelerated Search for BaTiO3‐Based Ceramics with Large Energy Storage at Low Fields Using Machine Learning and Experimental Design , 2019, Advanced science.

[7]  M. Ashby.  MULTI-OBJECTIVE OPTIMIZATION IN MATERIAL DESIGN AND SELECTION , 2000 .

[8]  Krishna Rajan,et al.  Application-Driven Data Analysis , 2009 .

[9]  S. Agnew,et al.  Preface to the viewpoint set on: The current state of magnesium alloy science and technology , 2010 .

[10]  Turab Lookman,et al.  Multi-objective Optimization for Materials Discovery via Adaptive Design , 2018, Scientific Reports.

[11]  Weinong W Chen,et al.  Bi-objective optimal design of a damage-tolerant multifunctional battery system , 2016 .

[12]  Dimitris C. Lagoudas,et al.  Multi-objective Bayesian materials discovery: Application on the discovery of precipitation strengthened NiTi shape memory alloys through micromechanical modeling , 2018, Materials & Design.

[13]  David Cebon,et al.  Materials Selection in Mechanical Design , 1992 .

[14]  T. Lookman,et al.  Accelerated Discovery of Large Electrostrains in BaTiO3‐Based Piezoelectrics Using Active Learning , 2018, Advanced materials.

[15]  Dierk Raabe,et al.  Enhanced strength and ductility in a high-entropy alloy via ordered oxygen complexes , 2018, Nature.

[16]  Martyn D. Wheeler,et al.  OH vibrational activation and decay dynamics of CH4–OH entrance channel complexes , 2000 .

[17]  Sergei V. Kalinin,et al.  Materials informatics: From the atomic-level to the continuum , 2019, Acta Materialia.

[18]  Turab Lookman,et al.  Machine learning assisted design of high entropy alloys with desired property , 2019, Acta Materialia.

[19]  Shigeharu Kamado,et al.  Strong and ductile heat-treatable Mg–Sn–Zn–Al wrought alloys , 2015 .

[20]  Kristin A. Persson,et al.  Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , 2013 .

[21]  K. Lu.  Making strong nanomaterials ductile with gradients , 2014, Science.

[22]  Z. Fan,et al.  Microstructural evolution of rheo-diecast AZ91D magnesium alloy during heat treatment , 2006 .

[23]  Chiho Kim,et al.  Machine learning in materials informatics: recent applications and prospects , 2017, npj Computational Materials.

[24]  B. C. Pai,et al.  Optimization of heat treatment parameters in ZA84 magnesium alloy , 2008 .

[25]  Alexis M Pietak,et al.  Magnesium and its alloys as orthopedic biomaterials: a review. , 2006, Biomaterials.

[26]  Ting Zhu,et al.  Towards strength–ductility synergy through the design of heterogeneous nanostructures in metals , 2017 .

[27]  Huamiao Wang,et al.  Study of slip activity in a Mg-Y alloy by in situ high energy X-ray diffraction microscopy and elastic viscoplastic self-consistent modeling , 2018, Acta Materialia.

[28]  Qudong Wang,et al.  Effect of Nd and Y addition on microstructure and mechanical properties of as-cast Mg–Zn–Zr alloy , 2007 .

[29]  B. Mordike,et al.  Magnesium: Properties — applications — potential , 2001 .

[30]  Xiaoning Qian,et al.  Accelerated search for BaTiO3-based piezoelectrics with vertical morphotropic phase boundary using Bayesian learning , 2016, Proceedings of the National Academy of Sciences.

[31]  T. Lookman,et al.  The Search for BaTiO3-Based Piezoelectrics With Large Piezoelectric Coefficient Using Machine Learning , 2019, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[32]  Jun Sun,et al.  An informatics approach to transformation temperatures of NiTi-based shape memory alloys , 2017 .

[33]  Ghanshyam Pilania,et al.  Rational design of all organic polymer dielectrics , 2014, Nature Communications.

[34]  Chenru Duan,et al.  Accurate Multiobjective Design in a Space of Millions of Transition Metal Complexes with Neural-Network-Driven Efficient Global Optimization , 2020, ACS central science.

[35]  C. Tasan,et al.  Metastable high-entropy dual-phase alloys overcome the strength–ductility trade-off , 2016, Nature.

[36]  Hyoung-Wook Kim,et al.  Effect of heat treatment on microstructure and mechanical properties of twin roll cast and sequential warm rolled ZK60 alloy sheets , 2009 .