Materials Science and Engineering A 508 (2009) 93–105 Contents lists available at ScienceDirect Materials Science and Engineering A journal homepage: www.elsevier.com/locate/msea Modeling medium carbon steels by using artificial neural networks N.S. Reddy a,∗ , J. Krishnaiah b , Seong-Gu Hong c , Jae Sang Lee a a Alternative Technology Laboratory, Graduate Institute of Ferrous Technology (GIFT), Pohang University of Science and Technology, Pohang (POSTECH), Kyungbuk 790-784, Republic of Korea b Formerly scholar at Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur 721302, India c Center for New and Renewable Energy Measurement, Division of Industrial Metrology, Korea Research Institute of Standards and Science, 209 Gajeong-Ro, Yuseong-Gu, Daejeon 305-340, Republic of Korea article info Article history: Received 7 October 2008 Received in revised form 11 December 2008 Accepted 11 December 2008 Keywords: Artificial neural networks Low alloys steels Mechanical properties Heat treatment parameters Alloy design abstract An artificial neural network (ANN) model has been developed for the analysis and simulation of the correlation between the mechanical properties and composition and heat treatment parameters of low alloy steels. The input parameters of the model consist of alloy compositions (C, Si, Mn, S, P, Ni, Cr, Mo, Ti, and Ni) and heat treatment parameters (cooling rate and tempering temperature). The outputs of the ANN model include property parameters namely: ultimate tensile strength, yield strength, percentage elongation, reduction in area and impact energy. The model can be used to calculate the properties of low alloy steels as a function of alloy composition and heat treatment variables. The individual and the combined influence of inputs on properties of medium carbon steels is simulated using the model. The current study achieved a good performance of the ANN model, and the results are in agreement with experimental knowledge. Explanation of the calculated results from the metallurgical point of view is attempted. The developed model can be used as a guide for further alloy development. © 2008 Elsevier B.V. All rights reserved. 1. Introduction The properties of alloy steels mainly depend on the mechanical treatment, alloying elements and heat treatment variables. These three affect the microstructure, which in turn affects the proper- ties. All alloys have defects such as intrusions, micro-blowholes and cracks. Apart from these defects, when alloys are made under industrial conditions, some amount of inhomogeneity and inconsis- tencies invariably creep in. These make the system-model chaotic. Besides this, the input variables that are considered are in reality fuzzy in nature. The first hurdle to overcome during modeling of steels is to acquire a reliable database. The industries that manufac- ture these alloys (or steels) tend to classify their process variables for obvious reasons. It is therefore very difficult to get a data set or information that would consist all of the above details. As the relationships between these outputs and inputs are nonlinear and complex in nature, it is impossible to develop them in the form of mathematical equations. Techniques such as linear regression are not well suited for accurate modeling of data which exhibits considerable ‘noise’, which is usually the case. Regression analy- sis to model non-linear data necessitates the use of an equation to attempt to transform the data into a linear form [1]. This rep- resents an approximation that inevitably introduces a significant ∗ Corresponding author. Tel.: +82 54 279 5035; fax: +82 54 279 4499. E-mail address: nsreddy@postech.ac.kr (N.S. Reddy). degree of error. Similarly, it is not easy to use statistical methods to relate multiple inputs to multiple process outputs. The method using neural networks (NN), on the other hand, has been iden- tified as a suitable way for overcoming these difficulties. NN are mathematical models and algorithms that imitate certain aspects of the information-processing and knowledge-gathering methods of the human nervous system [2–5]. A NN can perform highly complex mappings on nonlinearly related data by inferring sub- tle relationships between input and output parameters [6–8]. It can, in principle, generalize from a limited quantity of training data to overall trends in functional relationships [9]. Although several network architectures and training algorithms are available, the feed-forward neural network with the back-propagation (BP) learn- ing algorithm is more commonly used [8]. Therefore, within the last decade, the application of neural networks in the materials sci- ence research has steadily increased. A number of reviews carried out recently have identified the application of neural networks to a diverse range of materials science applications [10,11]. The objec- tive of the present work is, therefore, to develop a neural network model, which can predict the properties for a given composition and heat treatment, and the relationship of the properties with respect to these input variables. 2. Back-propagation neural networks (BPNN) modeling A BPNN model consists of an input layer and an output layer with as many units as their respective number of variables. In-between 0921-5093/$ – see front matter © 2008 Elsevier B.V. All rights reserved. doi:10.1016/j.msea.2008.12.022