Comptes Rendus
Short paper
Modeling the butterfly behavior of SMA actuators using neural networks
Comptes Rendus. Mécanique, Volume 350 (2022), pp. 143-157.

Shape memory alloy (SMA) actuators are an important application of smart materials for robotics. However, the nonlinear behavior of SMA leads to difficulties in real-time simulations using numerical methods. Artificial Intelligence can be used to bypass this problem. In this paper, we study several neural networks (NNs) to model the superelastic or pseudo-elasticity effect (SEE) as well as the shape memory effect (SME) used in SMA. Focusing on antagonistic actuating, we first model a single wire to train the best NN with the proper characteristics that fit the behavior of SEE. Then, we model the SME of two linear antagonistic SMA wires used as an actuator. In both systems, single and antagonistic wires, we train the networks to obtain the stress–strain diagrams representing the behavior. The network type and training algorithm are key factors and are evaluated depending on the RMSE values. As a result, we find that the long short-term memory NN, used with a regression layer on standardized data sets, models the butterfly-shaped behavior of the actuator system with less RMSE value.

Published online:
DOI: 10.5802/crmeca.108
Keywords: Neural networks, Shape memory alloys, Shape memory effect, Superelastic effect, Hysteresis behavior, Antagonistic systems

Rodayna Hmede 1; Frédéric Chapelle 1; Yuri Lapusta 1

1 Université Clermont Auvergne, Clermont Auvergne INP, CNRS, Institut Pascal, F-63000 Clermont-Ferrand, France
License: CC-BY 4.0
Copyrights: The authors retain unrestricted copyrights and publishing rights
     author = {Rodayna Hmede and Fr\'ed\'eric Chapelle and Yuri Lapusta},
     title = {Modeling the butterfly behavior of {SMA} actuators using neural networks},
     journal = {Comptes Rendus. M\'ecanique},
     pages = {143--157},
     publisher = {Acad\'emie des sciences, Paris},
     volume = {350},
     year = {2022},
     doi = {10.5802/crmeca.108},
     language = {en},
AU  - Rodayna Hmede
AU  - Frédéric Chapelle
AU  - Yuri Lapusta
TI  - Modeling the butterfly behavior of SMA actuators using neural networks
JO  - Comptes Rendus. Mécanique
PY  - 2022
SP  - 143
EP  - 157
VL  - 350
PB  - Académie des sciences, Paris
DO  - 10.5802/crmeca.108
LA  - en
ID  - CRMECA_2022__350_G1_143_0
ER  - 
%0 Journal Article
%A Rodayna Hmede
%A Frédéric Chapelle
%A Yuri Lapusta
%T Modeling the butterfly behavior of SMA actuators using neural networks
%J Comptes Rendus. Mécanique
%D 2022
%P 143-157
%V 350
%I Académie des sciences, Paris
%R 10.5802/crmeca.108
%G en
%F CRMECA_2022__350_G1_143_0
Rodayna Hmede; Frédéric Chapelle; Yuri Lapusta. Modeling the butterfly behavior of SMA actuators using neural networks. Comptes Rendus. Mécanique, Volume 350 (2022), pp. 143-157. doi : 10.5802/crmeca.108.

[1] H. S. Tzou; H.-J. Lee; S. M. Arnold Smart materials, precision sensors/actuators, smart structures, and structronic systems, Mech. Adv. Mater. Struct., Volume 11 (2004) no. 4–5, pp. 367-393 | DOI

[2] A. Bellini; M. Colli; E. Dragoni Mechatronic design of a shape memory alloy actuator for automotive tumble flaps: a case study, IEEE Trans. Ind. Electron., Volume 56 (2009) no. 7, pp. 2644-2656 | DOI

[3] E. Choi; H. D. Nguyen; J.-S. Jeon; J.-W. Kang Self-centering and damping devices using SMA dual rings, Smart Mater. Struct., Volume 28 (2019) no. 8, 085005 | DOI

[4] M. W. Gifari; H. Naghibi; S. Stramigioli; M. Abayazid A review on recent advances in soft surgical robots for endoscopic applications, Int. J. Med. Robot., Volume 15 (2019) no. 5, e2010 | DOI

[5] C. Fang; Y. Zheng; J. Chen; M. C. H. Yam; W. Wang Superelastic NiTi SMA cables: Thermal-mechanical behavior, hysteretic modelling and seismic application, Eng. Struct., Volume 183 (2019), pp. 533-549 | DOI

[6] C. Naresh; P. S. C. Bose; C. S. P. Rao Shape memory alloys: a state of art review, IOP Conf. Ser. Mater. Sci. Eng., Volume 149 (2016), 012054 | DOI

[7] Y. Liu The superelastic anisotropy in a NiTi shape memory alloy thin sheet, Acta Mater., Volume 95 (2015), pp. 411-427 | DOI

[8] Y. Huo A mathematical model for the hysteresis in shape memory alloys, Contin. Mech. Thermodyn., Volume 1 (1989) no. 4, pp. 283-303 | DOI | MR

[9] T. E. Buchheit; J. A. Wert Predicting the orientation-dependent stress-induced transformation and detwinning response of shape memory alloy single crystals, Metall. Mater. Trans. A, Volume 27 (1996) no. 2, pp. 269-279 | DOI

[10] S. Nemat-Nasser; W.-G. Guo Superelastic and cyclic response of NiTi SMA at various strain rates and temperatures, Mech. Mater., Volume 38 (2006) no. 5–6, pp. 463-474 | DOI

[11] O. E. Ozbulut; S. Hurlebaus Evaluation of the performance of a sliding-type base isolation system with a NiTi shape memory alloy device considering temperature effects, Eng. Struct., Volume 32 (2010) no. 1, pp. 238-249 | DOI

[12] T. Fukuda; T. Shibata; M. Tokita; T. Mitsuoka Neural network application for robotic motion control-adaptation and learning, 1990 IJCNN International Joint Conference on Neural Networks, Volume 2, 1990, pp. 447-451 | DOI

[13] Josin; Charney; White Robot control using neural networks, IEEE 1988 International Conference on Neural Networks, Volume 2, Neural Systems, Inc., Vancouver, BC, Canada, 1988, pp. 625-631

[14] A. Karakasoglu; S. I. Sudharsanan; M. K. Sundareshan Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators, IEEE Trans. Neural Netw., Volume 4 (1993) no. 6, pp. 919-930 | DOI

[15] Y. H. Kim; F. L. Lewis Optimal design of CMAC neural-network controller for robot manipulators, IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., Volume 30 (2000) no. 1, pp. 22-31 | DOI

[16] S.-Y. King; J.-N. Hwang Neural network architectures for robotic applications, IEEE Trans. Robot. Autom., Volume 5 (1989) no. 5, pp. 641-657 | DOI

[17] F. Sun; Z. Sun; P.-Y. Woo Neural network-based adaptive controller design of robotic manipulators with an observer, IEEE Trans. Neural Netw., Volume 12 (2001) no. 1, pp. 54-67 | DOI

[18] H. S. Tzou; H.-J. Lee; S. M. Arnold Smart materials, precision sensors/actuators, smart structures, and structronic systems, Mech. Adv. Mater. Struct., Volume 11 (2004) no. 4–5, pp. 367-393 | DOI

[19] N. T. Tai; K. K. Ahn A hysteresis functional link artificial neural network for identification and model predictive control of SMA actuator, J. Process Control, Volume 22 (2012) no. 4, pp. 766-777 | DOI

[20] Y. I. E. Elbahy; M. N. Nehdi; M. A. Y. Youssef Artificial neural network model for deflection analysis of superelastic shape memory alloy reinforced concrete beams, Can. J. Civ. Eng., Volume 37 (2010) no. 6, pp. 855-865 | DOI

[21] S. Judd On the complexity of loading shallow neural networks, J. Complex., Volume 4 (1988) no. 3, pp. 177-192 | DOI | MR | Zbl

[22] A. Gómez-Espinosa; R. Castro Sundin; I. Loidi Eguren; E. Cuan-Urquizo; C. D. Treviño-Quintanilla Neural network direct control with online learning for shape memory alloy manipulators, Sensors, Volume 19 (2019) no. 11, 2576 | DOI

[23] R. Boufayed; F. Chapelle; J. F. Destrebecq; X. Balandraud Finite element analysis of a prestressed mechanism with multi-antagonistic and hysteretic SMA actuation, Meccanica, Volume 55 (2020) no. 5, pp. 1007-1024 | DOI | MR

[24] K. Divringi; C. Ozcan Advanced shape memory alloy material models for ANSYS, 2016

[25] A. Waibaye Création de structures actives à l’aide d’alliages à mémoire de forme, Ph. D. Thesis, Blaise Pascal University (2016)

Cited by Sources:

Comments - Policy