Prediction of martensite and austenite start temperatures of the Fe-based shape memory alloys by artificial neural networks

In this study, martensite start (Ms) and austenite start (As) temperatures of Fe-based shape memory alloys (SMAs) were predicted by using a back-propagation artificial neural network (ANN) that uses gradient descent learning algorithm. An ANN model is built, trained and tested using the test data of 85 Fe-based SMAs available in literature. The input parameters of the ANN model are weight percentages of seven elements (Fe, Mn, Si, Ni, Cr, Cu and Al) and three different treatment conditions (hot rolling, homogenizing temperature and quenching). The ANN model was found to predict the Ms and As temperature well in the range of input parameters considered. A computer program was devised in MATLAB and different ANN models were constructed with this program for prediction of As and Ms temperatures of iron-based SMAs. A comprehensive analysis of the prediction errors of Ms and As temperatures made by the ANN is presented. This study demonstrate that ANN is very efficient for predicting the Ms and As temperatures of iron-based SMAs.

[1]  V. Bliznuk,et al.  Effect of nitrogen and carbon on electron exchange and shape memory in a Fe–Mn–Si base shape memory alloy , 2003 .

[2]  Huijun Li,et al.  Factors influencing shape memory effect and phase transformation behaviour of Fe–Mn–Si based shape memory alloys , 1999 .

[3]  Jinhua Zhu,et al.  Effect of phase transformation on cavitation erosion resistance of some ferrous alloys , 2003 .

[4]  Kimio Nakamura,et al.  Characterization of Fe–Mn–Si–Cr shape memory alloys containing VN precipitates , 2004 .

[5]  Jinhua Zhu,et al.  Cavitation erosion of Fe–Mn–Si–Cr shape memory alloys , 2004 .

[6]  V. Buono,et al.  The influence of deformation on the microstructure and transformation temperatures of Fe–Mn–Si–Cr–Ni shape memory alloys , 1999 .

[7]  F. Nishimura,et al.  Evolution of martensite start condition in general thermomechanical loads of Fe-based shape memory alloy , 2000 .

[8]  O. Matsumura,et al.  Pseudoelasticity in an Fe–28Mn–6Si–5Cr shape memory alloy , 2000 .

[9]  Marcin Perzyk,et al.  Prediction of ductile cast iron quality by artificial neural networks , 2001 .

[10]  Y. Wen,et al.  Effect of quenching temperature on recovery stress of Fe-18Mn-5Si-8Cr-4Ni alloy , 2001 .

[11]  Kikuaki Tanaka,et al.  Phenomenological analysis of thermomechanical training in an Fe-based shape memory alloy , 1998 .

[12]  M. Yan,et al.  Effects of carbon addition and aging on the shape memory effect of Fe–Mn–Si–Cr–Ni alloys , 2004 .

[13]  T. Hsu,et al.  Thermodynamic calculation of stacking fault energy in Fe–Mn–Si shape memory alloys , 2000 .

[14]  Kikuaki Tanaka,et al.  Transformation conditions in an Fe-based shape memory alloy under tensile–torsional loads: martensite start surface and austenite start/finish planes , 1999 .

[15]  Xing Lu,et al.  Compositional dependence of the Néel transition, structural stability, magnetic properties and electrical resistivity in Fe–Mn–Al–Cr–Si alloys , 2002 .

[16]  M. Enokizono,et al.  Fe-based magnetic shape memory alloy-sheet specimen , 1999 .

[17]  S. M. R. Emami,et al.  PREDICTION OF PEAK HORIZONTAL ACCELERATION USING AN ARTIFICIAL NEURAL NETWORK MODEL , 1996 .

[18]  Kikuaki Tanaka,et al.  Back stress and shape recoverability during reverse transformation in an Fe-based shape memory alloy , 1998 .

[19]  Bikas C. Maji,et al.  The effect of microstructure on the shape recovery of a Fe–Mn–Si–Cr–Ni stainless steel shape memory alloy , 2003 .

[20]  N. Altinkok,et al.  Neural network approach to prediction of bending strength and hardening behaviour of particulate reinforced (Al-Si-Mg)-aluminium matrix composites , 2004 .

[21]  A. F. Guillermet,et al.  Phase stability and fcc/hcp martensitic transformation in Fe–Mn–Si alloys: Part I. Experimental study and systematics of the MS and AS temperatures , 1998 .

[22]  Genki Yagawa,et al.  Neural networks in computational mechanics , 1996 .

[23]  T. Hsu,et al.  Effect of the Neel temperature, TN, on martensitic transformation in Fe–Mn–Si-based shape memory alloys , 2000 .

[24]  Susan Eitelman,et al.  Matlab Version 6.5 Release 13. The MathWorks, Inc., 3 Apple Hill Dr., Natick, MA 01760-2098; 508/647-7000, Fax 508/647-7001, www.mathworks.com , 2003 .

[25]  N. Jost.  Thermal fatigue of Fe–Ni–Co–Ti shape-memory-alloys , 1999 .

[26]  M. Andrade,et al.  The influence of thermal cycling on the transition temperatures of a Fe-Mn-Si shape memory alloy , 1999 .

[27]  M. Wuttig,et al.  Magnetostriction in ferromagnetic shape memory alloys , 2001 .

[28]  C. Esnouf,et al.  Microstructural analysis of the stress-induced ε martensite in a Fe–Mn–Si–Cr–Ni shape memory alloy: Part II: Transformation reversibility , 1998 .

[29]  T. Todaka,et al.  Transformation behavior of Fe-Cr-Co-Ni-Si-Mn ferromagnetic shape memory ribbon , 2004 .

[30]  Minoru Taya,et al.  Magnetic field-induced reversible actuation using ferromagnetic shape memory alloys , 2003 .