Predicting and Optimizing Coupling Effect in Magnetoelectric Multi-Phase Composites Based on Machine Learning Algorithm

Abstract In this paper, we present a machine learning (ML) method to search for geometric patterns of magnetoelectric multi-phase composites with optimal magnetoelectric coupling properties. The 2D finite element method is used to calculate the coupling coefficients and build the database for the training and testing of ML algorithms. Both the convolution neural network (CNN) and artificial neural network (ANN) algorithms are used as ML algorithms in this work. By investigating the effects of network parameters, such as training data density, iteration number and batch size, we construct the networks with proper parameters and good prediction accuracy. We present the predicted geometric patterns by two methods, CNN and ANN, and compare them with the FEM patterns. Two types of magnetoelectric composites, two -volume fractions of magnetostrictive phase and two system sizes are considered to investigate and improve the prediction efficiency. The presented results show that by using the ML methods, it can well predict the coupling effect and rank optimal patterns. The results also prove the feasibility that by using the ML method, we can accurately predict the coupling performance with very limited data. We aim to predict the optimal patterns instead of the best pattern. Therefore, this work demonstrates the feasibility and offers a new perspective way for the design and optimization of magnetoelectric multi-phase composites by using the ML algorithm.

[1]  S. Dong,et al.  Magnetoelectric Laminate Composites: An Overview , 2008 .

[2]  Alok Choudhary,et al.  A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials , 2016 .

[3]  Yuhao Wang,et al.  Accelerated design of Fe-based soft magnetic materials using machine learning and stochastic optimization , 2019, 2002.05225.

[4]  J. V. D. Boomgaard,et al.  Magnetoelectricity in piezoelectric-magnetostrictive composites , 1976 .

[5]  Yuksel C. Yabansu,et al.  Material structure-property linkages using three-dimensional convolutional neural networks , 2018 .

[6]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[7]  S. Dong,et al.  Detection of pico-Tesla magnetic fields using magneto-electric sensors at room temperature , 2006 .

[8]  Mario Fritz,et al.  Advanced Steel Microstructural Classification by Deep Learning Methods , 2017, Scientific Reports.

[9]  Ekin D. Cubuk,et al.  Holistic computational structure screening of more than 12 000 candidates for solid lithium-ion conductor materials , 2017 .

[10]  Arun Mannodi-Kanakkithodi,et al.  Mining materials design rules from data: The example of polymer dielectrics , 2017 .

[11]  S. Dong,et al.  Giant magnetoelectric effect in Metglas/polyvinylidene-fluoride laminates , 2006 .

[12]  Seiji Kajita,et al.  A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks , 2017, Scientific Reports.

[13]  Naif Alajlan,et al.  A novel deep learning based method for the computational material design of flexoelectric nanostructures with topology optimization , 2019, Finite Elements in Analysis and Design.

[14]  W. Xu,et al.  Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel , 2019, Acta Materialia.

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

[16]  Trenton Kirchdoerfer,et al.  Data-driven computational mechanics , 2015, 1510.04232.

[17]  Y. Kim,et al.  Optimal configuration of magnetoelectric composites under various mechanical boundary conditions , 2017 .

[18]  Ahmed Z. Al-Garni,et al.  Finite element modeling of thermopiezomagnetic smart structures , 2002 .

[19]  Y. Wan,et al.  Ferromagnetic, ferroelectric and magnetoelectric properties of (001)-oriented Pb(Zr0.52Ti0.48)O3/La0.67Sr0.33MnO3 composite films deposited on Si substrates using chemical solution deposition , 2017 .

[20]  Guole Wang,et al.  Strong flexural resonant magnetoelectric effect in Terfenol-D/epoxy-Pb(Zr,Ti)O-3 bilayer , 2005 .

[21]  M. A. Haque,et al.  Multiferroic Polymer Laminate Composites Exhibiting High Magnetoelectric Response Induced by Hydrogen‐Bonding Interactions , 2014 .

[22]  Romesh C. Batra,et al.  Cylindrical Bending of Laminated Plates with Distributed and Segmented Piezoelectric Actuators/Sensors , 2000 .

[23]  V. Petrov,et al.  Present status of theoretical modeling the magnetoelectric effect in magnetostrictive-piezoelectric nanostructures. Part I: Low frequency and electromechanical resonance ranges , 2010 .

[24]  C. Nan,et al.  Thermal Driven Giant Spin Dynamics at Three-Dimensional Heteroepitaxial Interface in Ni0.5Zn0.5Fe2O4/BaTiO3-Pillar Nanocomposites. , 2018, ACS nano.

[25]  Markys G. Cain,et al.  Verified finite element simulation of multiferroic structures: Solutions for conducting and insulating systems , 2008 .

[26]  Shuxiang Dong,et al.  Enhanced Resonance Magnetoelectric Coupling in (1‐1) Connectivity Composites , 2017, Advanced materials.

[27]  K. Loparo,et al.  Bearing fault diagnosis based on wavelet transform and fuzzy inference , 2004 .

[28]  K. Senapati,et al.  Miniature Hall sensor based ac susceptometer for measurements of vortex and superfluid dynamics in superconducting films , 2004 .

[29]  Luke E K Achenie,et al.  Machine-Learning-Augmented Chemisorption Model for CO2 Electroreduction Catalyst Screening. , 2015, The journal of physical chemistry letters.

[30]  D. Viehland,et al.  Enhanced sensitivity to direct current magnetic field changes in Metglas/Pb(Mg1/3Nb2/3)O3–PbTiO3 laminates , 2011 .

[31]  Markus J. Buehler,et al.  De novo composite design based on machine learning algorithm , 2018 .

[32]  Fei Xue,et al.  Magneto-electric coupling study in multiferroic La0.7Ba0.3MnO3–BaTiO3 composite ceramic at room temperature , 2015 .

[33]  C. Ross,et al.  Magnetostatic Interactions in Self-Assembled CoxNi1-xFe2O4/BiFeO3 Multiferroic Nanocomposites. , 2016, ACS nano.