Optimization of heat treatment technique of high-vanadium high-speed steel based on back-propagation neural networks

Abstract This paper is dedicated to the application of artificial neural networks in optimizing heat treatment technique of high-vanadium high-speed steel (HVHSS), including predictions of retained austenite content ( A ), hardness ( H ) and wear resistance ( e ) according to quenching and tempering temperatures ( T 1, T 2). Multilayer back-propagation (BP) networks are created and trained using comprehensive datasets tested by the authors. And very good performances of the neural networks are achieved. The prediction results show residual austenite content decreases with decreasing quenching temperature or increasing tempering temperature. The maximum value of relative wear resistance occurs at quenching of 1000–1050 °C and tempering of 530–560 °C, corresponding to the peak value of hardness and retained austenite content of about 20–40 vol%. The prediction values have sufficiently mined the basic domain knowledge of heat treatment process of HVHSS. A convenient and powerful method of optimizing heat treatment technique has been provided by the authors.

[1]  Sunghak Lee,et al.  Effects of alloying elements on microstructure, hardness, and fracture toughness of centrifugally cast high-speed steel rolls , 2005 .

[2]  Yoshikazu Sano,et al.  Characteristics of High-carbon High Speed Steel Rolls for Hot Strip Mill. , 1992 .

[3]  Min Qi,et al.  Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging , 2001, IEEE Trans. Neural Networks.

[4]  L. Hai.  Investigation of the Wear Resistance of High Carbon High Vanadium High Speed Steel , 2000 .

[5]  Shizhong Wei,et al.  Effects of carbon on microstructures and properties of high vanadium high-speed steel , 2006 .

[6]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[7]  B. S. Murty,et al.  Prediction of grain size of Al–7Si Alloy by neural networks , 2005 .

[8]  Ping Liu,et al.  Optimization of the processing parameters during internal oxidation of Cu–Al alloy powders using an artificial neural network , 2005 .

[9]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[10]  Sunghak Lee,et al.  Composition, microstructure, hardness, and wear properties of high-speed steel rolls , 1999 .

[11]  S. Kim,et al.  Solidification microstructures and mechanical properties of vertical centrifugal cast high speed steel , 2003 .

[12]  G. Sahoo,et al.  Pesticide prediction in ground water in North Carolina domestic wells using artificial neural networks , 2005 .

[13]  C. S. Li,et al.  Experimental investigation on thermal wear of high speed steel rolls in hot strip rolling , 2002 .

[14]  Sunghak Lee,et al.  Effects of alloying elements on microstructure and fracture properties of cast high speed steel rolls. Part I : Microstructural analysis , 1998 .