INVESTIGATION OF YIELD STRENGTH OF STEEL BARS PRODUCED BY TEMPCORE PROCESS BYUSING RS METHODOLOGY AND ANN
Keywords:
Tempcore, ANN, RS, RMSE, R2, MEPAbstract
Weldable reinforcing steel bars are produced by quenching and self-tempering in Tempcore process. These steel bars are used in construction industry, and require high values of yield strength. Thus measuring and characterising yield strength represents one of the most important aspects in manufacturing process. In this paper, experiments are carried out using statistical three level full factorial design technique. During the experiments, process parameters, quenching time, flow rate of water, and inside diameter of the tube through which bar travels are varied. An artificial neural network (ANN) and response surface (RS) model are developed to predict yield strength of steel bars. In the development of predictive models, quenching time, flow rate of water, and inside of the tube through which bar travels are considered as model variables. A series of experiments are conducted and yield strength is measured to obtain the required data for predictive models. Good agreement is observed between the predictive models results and the experimental results. The ANN and RS models for steel bars are compared with each other for accuracy and computational cost.
Downloads
References
Econompolous, M. Application of the Tempcore process to the fabrication high yields Strength concrete-reinforcing bars. CRM Report, 1-17,1975.
Simon.P, Economopoulos M. Iron steel engineer, 61, 1984.
Chatterjee. S. , Kundu, S. et al . Modeling of Micro structural Evolution during Controlled cooling of TEMPCORE Rebar. Tata search, 265-272, 2005.
P. Simon . Optimization of Tempcore installations for rebars. Metallurgical plant and Technology 1990,pp.61-70.
Cetinel,H. ,Toper, M. and Ozsoyeller,L. Artificial neural networks modeling of mechanical property and microstructure evolution in the Tempcore process. Computers and Structures 80 ,213-218, 2002.
Hicks ,Charles. R. Fundamental concepts in the design of experiment. New York,Holt, Rinehart and Winston,1973.
Myers, RH, Montgomery DC Response surface methodology process and product optimization using designed experiments. Wiley, New York ,USA, 1995.
Youngseog ,lee. Rod and Bar rolling Theory and Applications. Marker Dekker Inc New York.
E.Arcaklioglu, “Performance comparison of CFCs with their substitutes using artificial neural network”, International journal of Energy Research, Vol.28 (12), 1113-1125, 2004.
Ham FM :Principles of neurocomputing for science and engineering ,Mcgraw-Hill, New York, 2001.
P.lippmann :”An introduction to computing with neural nets”,IEEE ASSP Magazine,2, 4-22,1987.
D.E.Rummelhart, G.E. Hinton and R.J.Williams:” Learning internal representation by error propagation”,Parallel Distribution processing ,MIT press, Cambridge, MA, 318-362,1986.
Myers Raymond H. & D.C. Montgomery, 2002. “Response Surface Methodology: process and product optimization using designed experiment” A Wiley-Interscience Publication.
Box, G.E.P., and Wilson, K.B. “On the experimental attainment of optimum conditions”, Journal of the Royal Statistical Society, B, 13, 1-45, 1951.
Montgomery, D.C.. Design and Analysis of Experiments. John Wiley & Sons New York, 1997.
Montgomery, D.C., Peck, E.A., and Vining, G.G. 2000. Introduction to Linear Regression Analysis, New York, John Wiley.
Myers, R.H. and Montgomery, D.C. Response Surface Methodology. John Wiley & Sons, New York, 1995.
Kurtaran H, Dissertation, design optimization of structures under impact loading with approximation methods. George Washington University, Washington, C, USA, 2001.
