Accelerated Search for BaTiO3‐Based Ceramics with Large Energy Storage at Low Fields Using Machine Learning and Experimental Design

Abstract The problem that is considered is that of maximizing the energy storage density of Pb‐free BaTiO3‐based dielectrics at low electric fields. It is demonstrated that how varying the size of the combinatorial search space influences the efficiency of material discovery by comparing the performance of two machine learning based approaches where different levels of physical insights are involved. It is started with physics intuition to provide guiding principles to find better performers lying in the crossover region in the composition–temperature phase diagram between the ferroelectric phase and relaxor ferroelectric phase. Such an approach is limiting for multidopant solid solutions and motivates the use of two data‐driven machine learning and design strategies with a feedback loop to experiments. Strategy I considers learning and property prediction on all the compounds, and strategy II learns to preselect compounds in the crossover region on which prediction is carried out. By performing only two active learning loops via strategy II, the compound (Ba0.86Ca0.14)(Ti0.79Zr0.11Hf0.10)O3 is synthesized with the largest energy storage density ≈73 mJ cm−3 at a field of 20 kV cm−1, and an insight into the relative performance of the strategies using varying levels of knowledge is provided.

[1]  X. Ren,et al.  Enhancing dielectric permittivity for energy-storage devices through tricritical phenomenon , 2017, Scientific Reports.

[2]  S. Curtarolo,et al.  Accelerated discovery of new magnets in the Heusler alloy family , 2017, Science Advances.

[3]  Qichen Xu,et al.  Thermodynamic Stability Landscape of Halide Double Perovskites via High‐Throughput Computing and Machine Learning , 2019, Advanced Functional Materials.

[4]  Fei Li,et al.  Local Structural Heterogeneity and Electromechanical Responses of Ferroelectrics: Learning from Relaxor Ferroelectrics , 2018, Advanced Functional Materials.

[5]  Xin Zhou,et al.  A Dielectric Polymer with High Electric Energy Density and Fast Discharge Speed , 2006, Science.

[6]  Surya R. Kalidindi,et al.  Materials informatics , 2018, Journal of Intelligent Manufacturing.

[7]  Relaxor Ferroelectrics,et al.  Relaxor Ferroelectrics , 2018 .

[8]  Qinghua Zhang,et al.  Giant Energy Density and Improved Discharge Efficiency of Solution‐Processed Polymer Nanocomposites for Dielectric Energy Storage , 2016, Advanced materials.

[9]  Prateek,et al.  Recent Progress on Ferroelectric Polymer-Based Nanocomposites for High Energy Density Capacitors: Synthesis, Dielectric Properties, and Future Aspects. , 2016, Chemical reviews.

[10]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[11]  X. Ren,et al.  Laminated Modulation of Tricritical Ferroelectrics Exhibiting Highly Enhanced Dielectric Permittivity and Temperature Stability , 2019, Advanced Functional Materials.

[12]  X. Moya,et al.  Giant Electrocaloric Strength in Single‐Crystal BaTiO3 , 2013, Advanced materials.

[13]  Kyle G. Webber,et al.  Transferring lead-free piezoelectric ceramics into application , 2015 .

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

[15]  M. Lanagan,et al.  Homogeneous/Inhomogeneous‐Structured Dielectrics and their Energy‐Storage Performances , 2017, Advanced materials.

[16]  X. Ren,et al.  Large piezoelectric effect in Pb-free ceramics. , 2009, Physical review letters.

[17]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[18]  M. Nardelli,et al.  Phase equilibria in high energy density PVDF-based polymers. , 2007, Physical review letters.

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

[20]  W. Westphal,et al.  Dielectric and X-Ray Studies of CaxBa1-xTiO3 and CaxSr1-xTiO3 , 1961 .

[21]  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.

[22]  Christopher Wolverton,et al.  Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments , 2018, Science Advances.

[23]  N. Obuchowski.  Receiver operating characteristic curves and their use in radiology. , 2003, Radiology.

[24]  James Theiler,et al.  A Perspective on Materials Informatics: State-of-the-Art and Challenges , 2016 .

[25]  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.

[26]  Haijun Wu,et al.  Large piezoelectricity and dielectric permittivity in BaTiO3-xBaSnO3 system: The role of phase coexisting , 2012 .

[27]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[28]  G. Psarras,et al.  Dielectric response, functionality and energy storage in epoxy nanocomposites: Barium titanate vs exfoliated graphite nanoplatelets , 2012 .

[29]  J. Hogden,et al.  Statistical inference and adaptive design for materials discovery , 2017 .

[30]  Qing Wang,et al.  Ferroelectric polymer networks with high energy density and improved discharged efficiency for dielectric energy storage , 2013, Nature Communications.

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

[32]  James Theiler,et al.  Adaptive Strategies for Materials Design using Uncertainties , 2016, Scientific Reports.

[33]  James Theiler,et al.  Accelerated search for materials with targeted properties by adaptive design , 2016, Nature Communications.

[34]  Jinlan Wang,et al.  Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning , 2018, Nature Communications.

[35]  James Theiler,et al.  Selecting the selector: Comparison of update rules for discrete global optimization , 2017, Stat. Anal. Data Min..

[36]  Turab Lookman,et al.  Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning , 2018, Nature Communications.

[37]  Westphal,et al.  Diffuse phase transitions and random-field-induced domain states of the "relaxor" ferroelectric PbMg1/3Nb2/3O3. , 1992, Physical review letters.

[38]  Ruyan Guo,et al.  Piezoelectric and strain properties of Ba(Ti1−xZrx)O3 ceramics , 2002 .

[39]  Paul Raccuglia,et al.  Machine-learning-assisted materials discovery using failed experiments , 2016, Nature.

[40]  Yang Shen,et al.  Polymer-Based Dielectrics with High Energy Storage Density , 2015 .

[41]  Z. Ye,et al.  Ferroelectric to relaxor crossover and dielectric phase diagram in the BaTiO3–BaSnO3 system , 2007 .

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