Abstract
Shape-memory alloys (SMAs) have received considerable amount of attentions for their engineering applications in recent years. The hysteresis in SMAs is sensitive to the state-varying tendency and frequency. Utilizing past information to estimate the hysteretic behavior gets increasing attention. In this paper, a time-delayed dynamic neural network (TDDNN) is proposed for modeling hysteresis of SMAs in online applications. By introducing a time delay between the input and output response, the TDDNN considers the time delay’s effect on the hysteresis. This proposed network was applied to a SMA wire actuator. Experimental results demonstrate the effectiveness of TDDNN. The identified results obtained by TDDNN are better than those obtained by dynamic neural network without considering the delay information. It demonstrates the importance of introducing the time delay. The different values of time delay item can also affect TDDNN’s identified results.
Similar content being viewed by others
References
Oishi R, Nagai H (2005) Strain sensors of shape memory alloys using acoustic emissions. Sens Actuators A Phys 122:39–44
Nespoli A, Besseghini S, Pittaccio S, Villa E, Viscuso S (2010) The high potential of shape memory alloys in developing miniature mechanical devices: a review on shape memory alloy mini-actuators. Sens Actuators A Phys 158:149–160
Abolmaali A, Treadway J, Aswath P, Lu F, McCarthy M (2006) Hysteresis behavior of t-stub connections with superelastic shape memory fasteners. J Constr Steel Res 62:831–838
Fu G, Menciassi A, Dario P (2012) Design of a miniature switchable connection system for stochastic modular robots. Sensor Actuators A Phys 173:267–276
Hendersona E, Nash DH, Dempster WM (2011) On the experimental testing of fine Nitinol wires for medical devices. J Mech Behav Biomed 4:261–268
Nespoli A, Bassani E, Besseghini S, Villa E (2010) Rotational mini-actuator activated by two antagonist shape memory alloy wire. Phys Procedia 10:182–188
Kirkby EL, Michaud VJ, Månson J-AE, Sottos NR, White SR (2009) Performance of self-healing epoxy with microencapsulated healing agent and shape memory alloy wires. Polymer 50:5533–5538
Denga Z, Li Q, Sun H (2006) Behavior of concrete beam with embedded shape memory alloy wires. Eng Struct 28:1691–1697
Song G, Chaudhry V, Batur C (2003) Precision tracking control of shape memory alloy actuators using neural networks and a sliding-mode based robust controller. Smart Mater Struct 12:223–231
Massad J, Smith R (2005) A homogenized free energy model for hysteresis in thin-film shape memory alloys. Thin Solid Films 489(1–2):266–290
Ma L, Tan Y, Shen Y (2011) A neural networks based model of inverse hysteresis. Phys B 406:4109–4114
Asua E, Etxebarria V, Garca-Arribas A (2008) Neural network-based micropositioning control of smart shape memory alloy actuators. Eng Appl Artif Intell 21:796–804
Ikuta K, Tsukamoto M, Hirose S (1991) Mathematical model and experimental verification of shape memory alloy for designing micro actuator. In: Proceedings of IEEE international conference on micro electro mechanical systems 103–111 (Nara, February 1991)
Jiles DC, Atherton DL (1986) Theory of ferromagnetic hysteresis. J Magn Magn Mater 61:48–60
Smith RC, Seelecke S, Ounaies Z, Smith J (2003) A free energy model for hysteresis in ferroelectric materials. J Intell Mater Syst Struct 14:719–739
Ahn KK, Kha NB (2008) Modeling and control of shape memory alloy actuators using Preisach model, genetic algorithm and fuzzy logic. Mechatronics 18:141–152
Kannan S, Giraud-Audine C, Patoor E (2013) Application of Laguerre based adaptive predictive control to shape memory alloy (SMA) actuator. ISA Trans 52:469–479
Natale C, Velardi F, Visone C (2001) Identification and compensation of Preisach hysteresis models for magnetostrictive actuators. Phys B 306:161–165
Krasnosel’skil MA, Pokrovskii AV (1980) Systems with hysteresis. Springer, New York
Brokate M, Sprekels J (1996) Hysteresis and phase transitions. Springer, New York
Feng Y, Rabbath CA, Chai T, Su C (2009) Robust adaptive control of systems with hysteretic nonlinearities: a Duhem hysteresis modelling approach. In: AFRICON 2009 AFRICON ‘09 1-6 (Nairobi, Sept. 2009)
Janaideh MA, Mao J, Rakheja S, Xie W, Su CY (2008) Generalized Prandtl-Ishlinskii hysteresis model: hysteresis modeling and its inverse for compensation in smart actuators. In: Proceedings of IEEE conference on advanced intelligent mechatronics, 5182–5187 (Xian, Dec 2008)
Ben Mrad R, Hu H (2002) A model for voltage-to-displacement dynamics in piezoceramic actuators subject to dynamic-voltage excitations. IEEE Trans Mech 7(4):479–489
Janaideh MA, Mao J, Rakheja S, Su CY (2009) Experimental characterization and modeling of rate-dependent hysteresis of a piezoceramic actuator. Mechatronics 19:656–670
Moallem M, Tabrizi VA (2009) Tracking control of an antagonistic shape memory alloy actuator pair. IEEE Trans Control Syst Technol 17(1):184–190
Webb GV, Lagoudas DC, Kurdila AJ (1998) Hysteresis modeling of SMA actuators for control applications. J Intell Mater Syst Struct 9:432–448
Tan X, Baras JS (2005) Adaptive Identification and control of hysteresis in smart materials. IEEE Trans Autom Control 50:827–839
Yu Y, Xiao Z, Naganathan NG, Dukkipati RV (2002) Dynamic Preisach modeling of hysteresis for the piezoceramic actuator system. Mech Mach Theory 37:75–89
Hu H (2003) Compensation of hysteresis in piezoceramic actuators and control of nanopositioning system Ph.D. thesis of University of Toronto Canada
Deng L, Tan Y (2009) Modeling hysteresis in piezoelectric actuators using NARMAX models. Sens Actuators A Phys 149:106–112
Al Janaideh M, Krejčí P (2013) Inverse rate-dependent Prandtl–Ishlinskii model for feedforward compensation of hysteresis in a Piezomicropositioning Actuator. IEEE ASME Trans Mechatron 18(5):1498–1507
Kirkpatrick K, Valasek J (2011) Active length control of shape memory alloy wires using reinforcement learning. J Intell Mater Syst 22:1595–1604
Sreekuma M, Singaperumal M, Nagarajan T, Zoppi M, Molfino R (2007) Recent advances in nonlinear control technologies for shape memory alloy actuators. J Zhejiang Univ Sci 8:818–829
Gédouin P-A, Delaleau E, Bourgeot J-M, Join C, Chirani SA, Calloch S (2011) Experimental comparison of classical PID and model-free control: position control of a shape memory alloy active spring. Control Eng Pract 19:433–441
Li C, Tan Y (2004) A neural networks model for hysteresis nonlinearity. Sens Actuators A Phys 112(1):49–54
Wei J, Sun C (2000) Constructing hysteretic memory in neural networks. IEEE Trans Syst Man Cybern B Cybern 30(4):601–609
Song G, Chaudhry V, Batur C (2003) A neural network inverse model for a shape memory alloy wire actuator. Smart Mater Struct 14:371–377
Dong R, Tan Y, Chen H, Xie Y (2008) A neural networks based model for rate-dependent hysteresis for piezoceramic actuators. Sens Actuators A Phys 143:370–376
Zhao X, Tan Y (2010) Modeling rate-dependent hysteresis in piezoelectric actuators using neural networks based on expanded input space method. In: Proceedings of IEEE international conference on control and automation, 2229–2233 (Xiamen, June 9–11 2010)
Asua E, Etxebarria V, Garca-Arribas A (2008) Micropositioning using shape memory alloy actuators. Eur Phys J Spec Top 158:231–236
Tian L, Collins C (2004) A dynamic recurrent neural network-based controller for a rigid–flexible manipulator system. Mechatronics 14:471–490
Tsung-Hsien TSAI, Chi-Kang LEE (2005) Design of dynamic neural networks to forecast short-item railway passenger demand. J East Asia Soc Transp Stud 6:1651–1666
Oysal Yusuf (2005) A comparative study of adaptive load frequency controller designs in a power system with dynamic neural network models. Energy Convers Manag 46:2656–2668
Campolucci P, Uncini A, Piazza F, Rao BD (1999) On-line learning algorithms for locally recurrent neural networks. IEEE Trans Neural Netw 10:253–271
Mai H, Song G, Liao X (2012) Adaptive online inverse control of a shape memory alloy wire actuator using a dynamic neural network. Smart Mater Struct 22(015001):1–9
Xu X (2003) Impulsive control in continuous and discrete-continuous. IEEE Trans Autom Control 48:2288–2289
Boyd S, Ghaoui L, Feron E, Balakrishnan V (1994) Linear matrix inequalities in system and control theory. SIAM, Philadelphia
Acknowledgments
The comments from Dr. Han Wang are greatly appreciated. We also appreciate the supports from Natural Science Foundation of Henan Province Education Office (No. 14A120001) and the supports from Henan University of Technology High level talent fund (No. 2013BS004).
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
For readers’ better understanding the manuscript, the differences between DNN and TDDNN are organized in the following Table 5.
Rights and permissions
About this article
Cite this article
Mai, H., Song, G. & Liao, X. Time-delayed dynamic neural network-based model for hysteresis behavior of shape-memory alloys. Neural Comput & Applic 27, 1519–1531 (2016). https://doi.org/10.1007/s00521-015-1950-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-015-1950-8