Combined machine learning and CALPHAD approach for discovering processing-structure relationships in soft magnetic alloys

Abstract FINEMET alloys have desirable soft magnetic properties due to the presence of Fe3Si nanocrystals with specific size and volume fraction. To guide future design of these alloys, we investigate relationships between select processing parameters (composition, temperature, annealing time) and structural parameters (mean radius and volume fraction) of the Fe3Si domains. We present a combined CALPHAD and machine learning approach leading to well-calibrated metamodels able to predict structural parameters quickly and accurately for any desired inputs. To generate data, we have used a known precipitation model to perform annealing simulations at several temperatures, for varying Fe and Si concentrations. Thereafter, we used the data to develop metamodels for mean radius and volume fraction via the k-Nearest Neighbour algorithm. The metamodels reproduce closely the results from the precipitation model over the entire annealing timescale. Our analysis via parallel coordinate charts shows the effect of composition, temperature, and annealing time, and helps identify combinations thereof that lead to the desired mean radius and volume fraction for nanocrystals. This work contributes to understanding the linkages between processing parameters and microstructural characteristics responsible for achieving targeted properties, and illustrates ways to reduce the time from alloy discovery to deployment.

[1]  Rajesh Jha,et al.  Combined Computational-Experimental Design of High-Temperature, High-Intensity Permanent Magnetic Alloys with Minimal Addition of Rare-Earth Elements , 2016 .

[2]  Nirupam Chakraborti,et al.  A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem , 2017 .

[3]  Rajesh Jha,et al.  Multi‐Objective Genetic Algorithms and Genetic Programming Models for Minimizing Input Carbon Rates in a Blast Furnace Compared with a Conventional Analytic Approach , 2014 .

[4]  N. Mattern,et al.  Effect of Cu and Nb on crystallization and magnetic properties of amorphous Fe77.5Si15.5B7 alloys , 1995 .

[5]  A. Inoue,et al.  ATOM PROBE ANALYSIS OF FE73.5SI13.5B9NB3CU1 NANOCRYSTALLINE SOFT MAGNETIC MATERIAL , 1991 .

[6]  F. Pettersson,et al.  A Combined Experimental-Computational Approach to Design Optimization of High Temperature Alloys , 2014 .

[7]  I. Sobol.  On the distribution of points in a cube and the approximate evaluation of integrals , 1967 .

[8]  George S. Dulikravich,et al.  On the evolution of Cu-Ni-rich bridges of Alnico alloys with tempering , 2016 .

[9]  Y. Yoshizawa,et al.  New Fe-based soft magnetic alloys composed of ultrafine grain structure , 1988 .

[10]  Xinyi Gong,et al.  Process-Structure Linkages Using a Data Science Approach: Application to Simulated Additive Manufacturing Data , 2017, Integrating Materials and Manufacturing Innovation.

[11]  A. Choudhary,et al.  Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters , 2014, Integrating Materials and Manufacturing Innovation.

[12]  George S. Dulikravich,et al.  On the Formation and Evolution of Cu–Ni-Rich Bridges of Alnico Alloys With Thermomagnetic Treatment , 2016, IEEE Transactions on Magnetics.

[13]  Lars Höglund,et al.  A scheme for more efficient usage of CALPHAD data in simulations , 2015 .

[14]  J. Sietsma,et al.  Nb-driven nanocrystallization of amorphous Fe75.5Cu1Nb3Si12.5B8 , 1993 .

[15]  A. Makino,et al.  Fe-Si-B-P-C-Cu nanocrystalline soft magnetic powders with high Bs and low core loss , 2017 .

[16]  A. Makino,et al.  Thermodynamic analysis of binary Fe85B15 to quinary Fe85Si2B8P4Cu1 alloys for primary crystallizations of α-Fe in nanocrystalline soft magnetic alloys , 2015 .

[17]  K. Hono,et al.  Cu CLUSTERING AND Si PARTITIONING IN THE EARLY CRYSTALLIZATION STAGE OF AN Fe 73 . 5 Si 13 . 5 B 9 Nb 3 Cu 1 AMORPHOUS ALLOY , 1998 .

[18]  George S. Dulikravich,et al.  Magnetic Alloys Design Using Multi-objective Optimization , 2017 .

[19]  G. Herzer.  Modern Soft Magnets: Amorphous and Nanocrystalline Materials , 2013 .

[20]  A. Makino,et al.  Thermodynamic Assessment of Fe-B-P-Cu Nanocrystalline Soft Magnetic Alloys for Their Crystallizations from Amorphous Phase , 2014 .

[21]  C. Poloni,et al.  Algorithms for design optimization of chemistry of hard magnetic alloys using experimental data , 2016 .

[22]  Michael E. McHenry,et al.  Amorphous and nanocrystalline materials for applications as soft magnets , 1999 .

[23]  Frank Pettersson,et al.  Genetic Programming Evolved through Bi-Objective Genetic Algorithms Applied to a Blast Furnace , 2013 .

[24]  A. Çeçen,et al.  Development of high throughput assays for establishing process-structure-property linkages in multiphase polycrystalline metals: Application to dual-phase steels , 2017 .

[25]  K. Hono,et al.  Cu clustering and Si partitioning in the early crystallization stage of an Fe73.5Si13.5B9Nb3Cu1 amorphous alloy , 1999 .

[26]  Nirupam Chakraborti,et al.  Self-organizing maps for pattern recognition in design of alloys , 2017 .

[27]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[28]  Nirupam Chakraborti,et al.  Evolutionary Design of Nickel-Based Superalloys Using Data-Driven Genetic Algorithms and Related Strategies , 2015 .

[29]  A. Adithya.  Parallel Coordinates , 2015 .

[30]  Matthew A. Willard,et al.  Nanocrystalline Soft Magnetic Alloys Two Decades of Progress , 2013 .

[31]  J. D. Ayers,et al.  A model for nucleation of nanocrystals in the soft magnetic alloy Fe73.5Nb3Cu1Si13.5B9 , 1997 .

[32]  Priyanka Devi Pantula,et al.  KERNEL: Enabler to build smart surrogates for online optimization and knowledge discovery , 2017 .

[33]  M. Ferry,et al.  Composition dependence of the microstructure and soft magnetic properties of Fe-based amorphous/nanocrystalline alloys: A review study , 2014 .

[34]  A. Conde,et al.  Crystallization of a FINEMET-type alloy: nanocrystallization kinetics , 1994 .

[35]  Willem J. Quadakkers,et al.  Methods to increase computational efficiency of CALPHAD-based thermodynamic and kinetic models employed in describing high temperature material degradation , 2016 .

[36]  Catriona Dutreuilh,et al.  Introduction , 2019 .

[37]  G. Herzer,et al.  Chapter 3 Nanocrystalline soft magnetic alloys , 1997 .

[38]  R. Wagner,et al.  Homogeneous Second‐Phase Precipitation , 2013 .

[39]  D. Crespo,et al.  Crystallisation kinetics and microstructure development in metallic systems , 2002 .

[40]  Thomas de Quincey.  [C] , 2000, The Works of Thomas De Quincey, Vol. 1: Writings, 1799–1820.

[41]  J. Langer,et al.  Kinetics of nucleation in near-critical fluids , 1980 .

[42]  G. Herzer,et al.  Nanocrystalline soft magnetic materials , 1993 .

[43]  G. Herzer,et al.  Effect of Stress Annealing on the Saturation Magnetostriction of Nanocrystalline Fe $_{73.5}$ Cu $_{1}$ Nb $_{3}$ Si $_{15.5}$ B $_{7}$ , 2010 .

[44]  Noah H. Paulson,et al.  Reduced-order structure-property linkages for polycrystalline microstructures based on 2-point statistics , 2017 .

[45]  Frank Pettersson,et al.  A genetic algorithms based multi-objective neural net applied to noisy blast furnace data , 2007, Appl. Soft Comput..

[46]  G. Herzer.  Magnetization process in nanocrystalline ferromagnets , 1991 .

[47]  P. Haasen,et al.  Decomposition of alloys, the early stages : proceedings of the 2nd Acta-Scripta Metallurgica Conference, Sonnenberg, Germany, 19-23 September 1983 , 1984 .

[48]  C. Ciobanu,et al.  Metastable Phase Diagram and Precipitation Kinetics of Magnetic Nanocrystals in FINEMET Alloys , 2017, 1709.08306.

[49]  Kenneth Kroenlein,et al.  Perspective: Data infrastructure for high throughput materials discovery , 2016 .