Prediction of the flow stress of 6061 Al–15% SiC – MMC composites using adaptive network based fuzzy inference system

Abstract Silicon carbide reinforced aluminium composite materials are increasingly used in many engineering fields. Flow stress prediction for these materials is increasingly important. In the present work, flow stress of 1.0Mg – 0.6% Si – 0.3% Cu – 0.2% Cr rest Al with 15% SiC p during hot deformation is carried out using the conventional regression method, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) method. The temperature at which the aluminium is compressed are 300– 500 °C with strain rates ranging from 0.00857 to 2.7 s −1 and for the strains of 0.1–0.5. Simulation studies are carried out for analysis. By comparing the performances of various modeling techniques, ANFIS modeling can effectively be employed for prediction of flow stress of 6061 Al–15% SiC composites. The convergence speed of this algorithm is higher than that of the ANN.

[1]  R. K. Dube,et al.  Modeling Microstructural Evolution During Dynamic Recrystallization of Alloy D9 Using Artificial Neural Network , 2007, Journal of Materials Engineering and Performance.

[2]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[3]  Xueyu Ruan,et al.  Prediction of the flow stress of 0.4C–1.9Cr–1.5Mn–1.0Ni–0.2Mo steel during hot deformation , 2001 .

[4]  G. S. Ansell,et al.  SOME OBSERVATIONS ON THE SHRINKAGE BEHAVIOUR OF COPPER COMPACTS AND OF LOOSE POWDER AGGREGATES , 1961 .

[5]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Jue Zhong,et al.  Prediction of 42CrMo steel flow stress at high temperature and strain rate , 2008 .

[7]  Farghalli A. Mohamed,et al.  Particulate reinforced metal matrix composites — a review , 1991, Journal of Materials Science.

[8]  John J. Jonas,et al.  Prediction of steel flow stresses at high temperatures and strain rates , 1991 .

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

[10]  Prasad K. Yarlagadda,et al.  Neural network approach to flow stress evaluation in hot deformation , 1995 .

[11]  Joo-Hwa Tay,et al.  Neural fuzzy modeling of anaerobic biological wastewater treatment systems , 1999 .

[12]  D. J. C. Mackay,et al.  Estimation of Hot Torsion Stress Strain Curves in Iron Alloys Using a Neural Network Analysis , 1999 .

[13]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[14]  John G. Lenard,et al.  A comparative study of artificial neural networks for the prediction of constitutive behaviour of HSLA and carbon steels , 1996 .

[15]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[16]  Jue Zhong,et al.  Constitutive modeling for elevated temperature flow behavior of 42CrMo steel , 2008 .

[17]  C. Sellars,et al.  On the mechanism of hot deformation , 1966 .

[18]  Peter Hodgson,et al.  The Application of Constitutive and Artificial Neural Network Models to Predict the Hot Strength of Steels , 1999 .

[19]  Uday S. Dixit,et al.  Application of neural networks in generating processing map for hot working , 2003 .

[20]  Jing-Chung Shen,et al.  Fuzzy neural networks for tuning PID controller for plants with underdamped responses , 2001, IEEE Trans. Fuzzy Syst..