A Neural Network Model of Restrained Recovery for Shape Memory Alloys


Article Preview

The methods of constitutive modeling of restrained recovery for Shape memory alloys (SMAs) were described in this paper and experiments were carried out to provide the essential data for the methods. The present mathematical constitutive models are inconvenient for engineering applications. Then a back propagation (BP) neural network model was developed for restrained recovery of SMAs. This BP neural network model can learn the hysteresis of SMAs in the process of heating and cooling based on its properties of nonlinear function mapping and adaptation, and it can predict the complete restrained recovery stress of SMAs with different initial strains. The predicted results obtained from the proposed BP model agree well with the experimental data. Moreover, the proposed BP model is more simple, convenient and low cost compared with the present mathematical constitutive models.



Edited by:

Ying Zhang and Ping He




S. Wu et al., "A Neural Network Model of Restrained Recovery for Shape Memory Alloys", Advanced Materials Research, Vol. 650, pp. 172-177, 2013

Online since:

January 2013




[1] Muller I. A model for a body with shape-memory. Arch. Rat. Mech. Anal. 1979; 70: 61-77.

[2] Ghaboussi J, Garrett J H, Wu X. Knowledge-based modeling of material behavior with neural networks. J. Eng. Mech. 1991; 117: 132-53.

[3] Ghaboussi J, Lade P V, Sidarta D E. Neural networks based modeling in geomechanics. Proc. 8th Int. Conf. on Computer Methods and Advances in Geomechanics. Morgantown, WV, (1994).

[4] Vassilopoulos A P, Georgopoulos E F, Dionysopoulos V. Artificial neural networks in spectrum fatigue life prediction of composite materials. International Journal of Fatigue 2007; 29: 20-9.

DOI: https://doi.org/10.1016/j.ijfatigue.2006.03.004

[5] Lee H J, Lee J J. Evaluation of the characteristics of a shape memory alloy spring actuator. Smart Mater. Struct. 2000; 9: 817-23.

DOI: https://doi.org/10.1088/0964-1726/9/6/311

[6] Parvizi S, Hafizpour H R, Sadrnezhaad S K, Akhondzadeh A, Abbasi Gharacheh M. Neural network prediction of mechanical properties of porous NiTi shape memory alloy. Powder Metallurgy 2011; 54: 450-4.

DOI: https://doi.org/10.1179/003258910x12827272082588

[7] Brinson L C. One-dimensional constitutive behavior of shape memory alloys: thermomechanical derivation with non-constant material functions and redefined martensite internal variable. J. Intell. Mater. Syst. Struct. 1993; 4: 229-42.

DOI: https://doi.org/10.1177/1045389x9300400213

[8] Haykin S. Neural Networks: A Comprehensive Foundation. New York: Macmillan; (1994).

[9] De la Flor S, Urbina C, Ferrando F. Constitutive model of shape memory alloys: theoretical formulation and experimental validation. Materials Science and Engineering A 2006; 427: 112-22.

DOI: https://doi.org/10.1016/j.msea.2006.04.008

[10] Elbahy Y I, Nehdi M, Youssef M A. Artificial neural network model for deflection analysis of superelastic shape memory alloy reinforced concrete beams. Can. J. Civ. Eng. 2010; 37: 855-65.

DOI: https://doi.org/10.1139/l10-039

[11] Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks 1989; 2: 359-66.

DOI: https://doi.org/10.1016/0893-6080(89)90020-8

[12] Asua E, Etxebarria V, Garca-Arribas A. Neural network-based micropositioning control of smart shape memory alloy actuators. Engineering Applications of Artificial Intelligence 2008; 21: 796-804.

DOI: https://doi.org/10.1016/j.engappai.2007.07.003

Fetching data from Crossref.
This may take some time to load.