Neural Network Based Adaptation Algorithm for Online Prediction of Mechanical Properties of Steel

S. Rath (Research & Development Centre for Iron & Steel (RDCIS), Ranchi, India)


After production of a steel product in a steel plant, a sample of the product is tested in a laboratory for its mechanical properties like yield strength (YS), ultimate tensile strength (UTS) and percentage elongation. This paper describes a mathematical model based method which can predict the mechanical properties without testing. A neural network based adaptation algorithm was developed to reduce the prediction error. The uniqueness of this adaptation algorithm is that the model trains itself very fast when predicted and measured data are incorporated to the model. Based on the algorithm, an ASP.Net based intranet website has also been developed for calculation of the mechanical properties. In the starting Furnace Module webpage, austenite grain size is calculated using semi-empirical equations of austenite grain size during heating of slab in a reheating furnace. In the Mill Module webpage, different conditions of static, dynamic and metadynamic recrystallization are calculated. In this module, austenite grain size is calculated from the recrystallization conditions using corresponding recrystallization and grain growth equations. The last module is a cooling module. In this module, the phase transformation equations are used to predict the grain size of ferrite phase. In this module, structure-property correlation is used to predict the final mechanical properties. In the Training Module, the neural network based adapation algorithm trains the model and stores the weights and bias in a database for future predictions. Finally, the model was trained and validated with measured property data.


Artificial Neural Network;Mathematical model;Plate rolling;Hybrid model

Full Text:



[1] C.M. Sellars, J.A. Whiteman. Metal Science, 1979, 13: 187-194.

[2] C.M. Sellars, Proc. Hot Working and Forming Processes, Ed. C.M. Sellars and G.J. Davies, Inst. of Metals, London, 1980: 3-15.

[3] Tadeusz Siwecki. Modelling of Microstructure Evolution during Recrystallization Controlled Rolling. ISIJ International, 1992, 32(3): 368-376.

[4] Andreas Kern, Joachim Degenkolbe, Bruno Musgen, Udo Schriever. Computer Modelling for the Prediction of Microstructure Development and Mechanical Properties of HSLA Steel Plates. ISIJ International, 1992, 32(3): 387-394.

[5] Yoshiyuki Saito, Chiaki Shiga. Computer Simulation of Microstructural Evolution in Thermo- mechanical Processing of Steel Plates. ISIJ International, 1992, 32(3): 414-422.

[6] Takehide Senuma, Masayoshi Suehiro, Hiroshi Yada. Mathematical Models for Predicting Microstructural Evolution and Mechanical Properties of Hot Strips. ISIJ International, 1992, 32(3): 423-432.

[7] Masayoshi Suehiro, Takehide Senuma, Hiroshi Yada, Kazuaki Sato. Application of Mathematical Model for Predicting Microstructural Evolution to High Carbon Steels. ISIJ International, 1992, 32(3): 433-439.

[8] J. C. Herman, B. Donnay, V. Leroy. Precipitation Kinetics of Microalloying Additions during Hot-rolling of HSLA Steels. ISIJ International, 1992, 32(6): 779- 785.

[9] P. D. Hodgson, R. K. Gibbs. A Mathematical Model to Predict the Mechanical Properties of Hot Rolled C-Mn and Microalloyed Steels. ISIJ International, 1992, 32(12): 1329-1338.

[10] F. Siciliano, Jr., K. Minami, T. M. Maccagno, J.J. Jonas. Mathematical Modeling of the Mean Flow Stress, Fractional Softening and Grain Size during the Hot Strip Rolling of C-Mn Steels. ISIJ International, 1996, 36(12): 1500-1506

[11] H. K. D. H. Bhadeshia. Neural Networks in Materials Science. ISIJ International, 1999, 39(10): 966-979.

[12] Christian Dumortier, Philippe Lehert. Statistical Modelling of Mechanical Tensile Properties of Steels by Using Neural Networks and Multivariate Data Analysis. ISIJ International, 1999, 39(10): 980-985.

[13] S. Datta, J. Sil, M. K. Banerjee. Petri Neural Network Model for the Effect of Controlled Thermomechanical Process Parameters on the Mechanical Properties of HSLA Steels. ISIJ International, 1999, 39(10): 986-990.

[14] J. Warde, D. M. Kimowles. Application of Neural Networks to Mechanical Property Determination of Ni-base Superalloys. ISIJ International, 1999, 39(10): 1006-1014.

[15] O.P.Femminella, M.J.Starink, M.Brown, I. Sinclair, C. J. Harris, P. A. S. Reed. Data Pre-Processing/Model Initialisation in Neurofuzzy Modelling of Structure-Property Relationships in Al-Zn-Mg-Cu Alloys. ISIJ International, 1999, 39(10): 1027-1037.

[16] Jiajun Wang, Pieter J. van der Wolk, Sybrand van derZwaag. Effects of Carbon Concentration and Cooling Rate on Continuous Cooling Transformations Predicted by Artificial Neural Network. ISIJ International, 1999, 39(10): 1038-1046.

[17] P.S. Sikdar, A. Mukhopadhyay, O.N. Mohanty. Microstructure Evolution and Mechanical Properties in Hot Rolled Low Carbon Steels: Prediction through Modelling. Proc. Int. Conf. on Thermomechanical simulation and Processing of Steel (Simpro'04), Ranchi, India, 2004: 237-254.

[18] A.P. Singh, S. Rath, Vinod Kumar, D. Sengupta, Sudhaker Jha. An integrated mathematical model for prediction of microstructure evolution and mechanical properties of C-Mn and microalloyed steels during plate rolling. Proc. Int. Conf. on Thermomechanical simulation and Processing of Steel (Simpro'04), Ranchi, India, 2004: 265-284.

[19] B. Pereda, J. M. Rodriguez-Ibabe, B. López. Improved Model of Kinetics of Strain Induced Precipitation and Microstructure Evolution of Nb Microalloyed Steels during Multipass Rolling. ISIJ International, 2008, 48(10): 1457-1466.

[20] Takehide Senuma, Yoshito Takemoto. Model for Predicting the Microstructural Evolution of Extralow Carbon Steels. ISIJ International, 2008, 48(11): 1635-1639.

[21] Thomas Schambron, Andrew W. Phillips, David M. O’brien, Joshua Burg, Elena V. Pereloma, Chris C. Killmore, Jim A. Williams. Thermomechanical Processing of Pipeline Steels with a Reduced Mn Content. ISIJ International, 2009, 49(2): 284-292.

[22] T. Jia, M. Militzer, Z. Y. Liu. General Method of Phase Transformation Modeling in Advanced High Strength Steels. ISIJ International, 2010, 50(4): 583- 590.

[23] Riidiger Doll, Giinter Sorgel, Matthias Daum, Custav Zouhar. Control of mechanical properties. Asia Steel, 1999: 200-202.

[24] S. Rath, P.P. Sengupta, A.P. Singh, A.K. Marik, P. Talukdar. Mathematical-artificial neural network hybrid model to predict roll force during hot rolling of steel. International Journal of Computational Materials Science and Engineering, 2013, 2(1):1350004 (1-16).

[25] S. Rath, A.P. Singh, P.P. Sengupta, U. Bhaskar, B. Krishna. Determination of flow stress coefficient for Nb-microalloyed steel using parameter estimation techniques. Steel India, 2007, 29(2): 100-104.

[26] J.G. Lenard, M. Pietrzyk, L. Cser. Mathematical and Physical Simulation of the Properties of Hot Rolled Products, 1st Edn., Elsevier, UK, 1999: 172-177.

[27] V.B. Ginzburg, Metallurgical Design of Flat Rolled Steels, Marcel Dekker, New York, 2005: 447-48.

[28] S. Rath, A. P. Singh, U. Bhaskar, B. Krishna, B. K. Santra, D. Rai, N. Neogi. Artificial neural network modeling for prediction of roll force during plate rolling process. International journal of Materials and Manufacturing Processes, Taylor & Francis, 2010, 25(2010): 149-153.



  • There are currently no refbacks.
Copyright © 2020 Author(s)

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.