Application of artificial neural networks in modelling of normalised structural steels mechanical properties

Purpose: This paper presents the application of artificial neural networks for mechanical properties prediction Design/methodology/approach: impact resistance or hardness are predicted. Findings: Results obtained in the given ranges of input parameters show very good ability of constructed neural networks to predict described mechanical properties for steels after heat treatment. The uniform distribution of descriptive vectors in all, training, validation and testing sets, indicate about the good ability of the networks to results generalisation. Practical implications: Created tool makes possible the easy modelling of described properties and allows the better selection of both chemical composition and the processing parameters of investigated materials. At the same time the obtainment of steels, which are qualitatively better, cheaper and more optimised under customers needs is made possible. Originality/value: The prediction possibility of the material mechanical properties is valuable for manufacturers and constructors. It allows preserving the customers quality requirements and brings also measurable financial advantages.

[1]  R. Honysz,et al.  Virtual tensile test machine as an example of Material Science Virtual Laboratory post , 2008 .

[2]  J. Zhong,et al.  Application of neural networks to predict the elevated temperature flow behavior of a low alloy steel , 2008 .

[3]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[4]  John Wulff,et al.  Introduction To Materials Science And Engineering , 1976 .

[5]  L. A. Dobrzański,et al.  The modelling of high-speed steels' properties using neural networks , 2004 .

[6]  L. A. Dobrzański,et al.  Application of neural networks for designing the chemical composition of steel with the assumed hardness after cooling from the austenitising temperature , 2005 .

[7]  Pierre Baldi,et al.  Neural Networks: Applications , 2001 .

[8]  Wei You,et al.  RBF-Type Artificial Neural Network Model Applied in Alloy Design of Steels , 2008 .

[9]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[10]  John Norrish,et al.  Artificial neural networks for modelling the mechanical properties of steels in various applications , 2005 .

[11]  R. Honysz,et al.  Materials science virtual laboratory innovatory didactic tool in the teaching of material engineering performed by traditional and e-learning methods , 2008 .

[12]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[13]  H. Dyja,et al.  Using neural network models for predicting mechanical properties after hot plate rolling processes , 1998 .