A novel approach to predict green density by high-velocity compaction based on the materials informatics method

Abstract

High-velocity compaction is an advanced compaction technique to obtain high-density compacts at a compaction velocity of ≤10 m/s. It was applied to various metallic powders and was verified to achieve a density greater than 7.5 g/cm³ for the Fe-based powders. The ability to rapidly and accurately predict the green density of compacts is important, especially as an alternative to costly and time-consuming materials design by trial and error. In this paper, we propose a machine-learning approach based on materials informatics to predict the green density of compacts using relevant material descriptors, including chemical composition, powder properties, and compaction energy. We investigated four models using an experimental dataset for appropriate model selection and found the multilayer perceptron model worked well, providing distinguished prediction performance, with a high correlation coefficient and low error values. Applying this model, we predicted the green density of nine materials on the basis of specific processing parameters. The predicted green density agreed very well with the experimental results for each material, with an inaccuracy less than 2%. The prediction accuracy of the developed method was thus confirmed by comparison with experimental results.

Keywords

powder metallurgy / high-velocity compaction / green density / data mining / multilayer perceptron

References

[1] Jauffrès D., Lame O., Vigier G., Doré F. Microstructural origin of physical and mechanical properties of ultra high molecular weight polyethylene processed by high velocity compaction. Polymer, 2007, 48(21): 6374.

[2] Skoglund P. High density PM parts by high velocity compaction. Powder Metall., 2001, 44(3): 199.

[3] Wang J.Z., Yin H.Q., Qu X.H. Analysis of density and mechanical properties of high velocity compacted iron powder. Acta Metall. Sin. Engl. Lett., 2009, 22(6): 447.

[4] Sethi G., Hauck E., German R.M. High velocity compaction compared with conventional compaction. Mater. Sci. Technol., 2006, 22(8): 955.

[5] Yan Z.Q., Chen F., Cai Y.X., Yin J., Zheng Y.K. Preparation and properties of Ti-4.5Al-6.8Mo-1.5Fe alloy by high-velocity compaction. Powder Technol., 2013, 246, 345.

[6] Huang P.Y. The Principle of Powder Metallurgy, 1997, Beijing, Metallurgical Industry Press.

[7] APL Mater., 2013, 1(1)

[8] Holdren J.P. Materials Genome Initiative for Global Competitiveness, 2011, Washington, National Science and Technology Council OSTP Washington.

[9] Schmitz G.J., Prahl U. Integrative Computational Materials Engineering: Concepts Applications of a Modular Simulation Platform, 2012, New Jersey, John Wiley & Sons

[10] Rajan K. Materials informatics: The materials “gene” and big data. Annu. Rev. Mater. Res., 2015, 45, 153.

[11] Yang X.Y., Wang Z.G., Zhao X.S., Song J.L., Zhang M.M., Liu H.D. MatCloud: A high-throughput computational infrastructure for integrated management of materials simulation, data and resources. Comput. Mater. Sci., 2018, 146, 319.

[12] Zhao L.R., Chen K., Yang Q., Rodgers J.R., Chiou S.H. Materials informatics for the design of novel coatings. Surf. Coat. Technol., 2005, 200(5–6): 1595.

[13] Nørskov J.K., Bligaard T. The catalyst genome. Angew. Chem. Int. Ed., 2013, 52(3): 776.

[14] Takahashi K., Tanaka Y. Materials informatics: a journey towards material design and synthesis. Dalton Trans., 2016, 45(26): 10497.

[15] Ohno H. Empirical studies of Gaussian process based Bayesian optimization using evolutionary computation for materials informatics. Expert Syst. Appl., 2018, 96, 25.

[16] Xue D.Z., Xue D.Q., Yuan R.H., Zhou Y.M., Balachandran P.V., Ding X.D., Sun J., Lookman T. An informatics approach to transformation temperatures of NiTi-based shape memory alloys. Acta Mater., 2017, 125, 532.

[17] D.Z. Xue, P.V. Balachandran, J. Hogden, J. Theiler, D.Q. Xue, and T. Lookman, Accelerated search for materials with targeted properties by adaptive design, Nat. Commun., 7(2016), Art. No. 11241.

[18] Raccuglia P., Elbert K.C., Adler P.D.F., Falk C., Wenny M.B., Mollo A., Zeller M., Friedler S.A., Schrier J., Norquist A.J. Machine-learning-assisted materials discovery using failed experiments. Nature, 2016, 533, 73.

[19] Hu B., Lu K.L., Zhang Q., Ji X.B., Lu W.C. Data mining assisted materials design of layered double hydroxide with desired specific surface area. Comput. Mater. Sci., 2017, 136, 29.

[20] Smola A., Vishwanathan S.V.N. Introduction to Machine Learning, 2004, Cambridge, Cambridge University Press.

[21] Marwala T. Finite-element-model Updating Using Computational Intelligence Techniques: Applications to Structural Dynamics, 2010, London, Springer-Verlag

[22] Möller J.J., Körner W., Krugel G., Urban D.F., Elsässer C. Compositional optimization of hard-magnetic phases with machine-learning models. Acta Mater., 2018, 153, 53.

[23] Cai J., Luo J.W., Wang S.L., Yang S. Feature selection in machine learning: A new perspective. Neurocomputing, 2018, 300, 70.

[24] Fischmeister H.F., Arzt E., Olsson L.R. Particle deformation and sliding during compaction of spherical powders: A study by quantitative metallography. Powder Metall., 1978, 21(4): 179.

[25] Bortzmeyer D., Langguth G., Orange G. Fracture mechanics of green products. J. Eur. Ceram. Soc., 1993, 11(1): 9.

[26] Liu Z.Y., Sercombe T.B., Schaffer G.B. The effect of particle shape on the sintering of aluminum. Metall. Mater. Trans. A, 2007, 38(6): 1351.

[27] Rosato A.D., Vreeland T., Prinz F.B. Manufacture of powder compacts. Int. Mater. Rev., 1991, 36(2): 45.

[28] Yang D.W., Miao L. Probability Theory and Mathematical Statistics, 2014, Beijing, Science Press.

[29] German R.M. Powder Metallurgy and Particulate Materials Processing, 2005, New Jersey, Metal Powder Industry.

[30] Maldonado S., López J., Carrasco M. A second-order cone programming formulation for twin support vector machines. Appl. Intell., 2016, 45(2): 265.

[31] Luts J., Ojeda F., de Van R.V., De Moor B., Van Huffel S., Suykens J.A.K. A tutorial on support vector machine-based methods for classification problems in chemometrics. Anal. Chim. Acta, 2010, 665(2): 129.

[32] Richhariya B., Tanveer M. EEG signal classification using universum support vector machine. Expert Syst. Appl., 2018, 106, 169.

[33] Gardner M.W., Dorling S.R. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmos. Environ., 1998, 32(14–15): 2627.

[34] Varol T., Canakci A., Ozsahin S. Modeling of the prediction of densification behavior of powder metallurgy Al-Cu-Mg/B₄C composites using artificial neural networks. Acta Metall. Sin. Engl. Lett., 2015, 28(2): 182.

[35] Shunag B. Growing random forest on deep convolutional neural networks for scene categorization. Expert Syst. Appl., 2017, 71, 279.

[36] Jiang X., Yin H.Q., Zhang C., Zhang R.J., Zhang K.Q., Deng Z.H., Liu G.Q., Qu X.H. A materials informatics approach to Ni-based single crystal superalloys lattice misfit prediction. Comput. Mater. Sci., 2018, 143, 295.

[37] Chai T., Draxler R.R. Root mean square error (RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Geosci. Model Dev., 2014, 7, 1247.