IEEE/CAA Journal of Automatica Sinica
Citation:  D. He, H. P. Wang, Y. Tian, and Y. Guo, “A fractionalorder ultralocal modelbased adaptive neural network sliding mode control of nDOF upperlimb exoskeleton with input deadzone,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 3, pp. 760–781, Mar. 2024. doi: 10.1109/JAS.2023.123882 
This paper proposes an adaptive neural network sliding mode control based on fractionalorder ultralocal model for nDOF upperlimb exoskeleton in presence of uncertainties, external disturbances and input deadzone. Considering the model complexity and input deadzone, a fractionalorder ultralocal model is proposed to formulate the original dynamic system for simple controller design. Firstly, the control gain of ultralocal model is considered as a constant. The fractionalorder sliding mode technique is designed to stabilize the closedloop system, while fractionalorder timedelay estimation is combined with neural network to estimate the lumped disturbance. Correspondingly, a fractionalorder ultralocal modelbased neural network sliding mode controller (FONNSMC) is proposed. Secondly, to avoid disadvantageous effect of improper gain selection on the control performance, the control gain of ultralocal model is considered as an unknown parameter. Then, the Nussbaum technique is introduced into the FONNSMC to deal with the stability problem with unknown gain. Correspondingly, a fractionalorder ultralocal modelbased adaptive neural network sliding mode controller (FOANNSMC) is proposed. Moreover, the stability analysis of the closedloop system with the proposed method is presented by using the Lyapunov theory. Finally, with the cosimulations on virtual prototype of 7DOF iReHave upperlimb exoskeleton and experiments on 2DOF upperlimb exoskeleton, the obtained compared results illustrate the effectiveness and superiority of the proposed method.
[1] 
A. Zhu, H. Shen, Z. Shen, J. Song, and Y. Tu, “Innovative design for portability of unpowered military load exoskeleton robot,” in Proc. 15th IEEE Int. Conf. Inform. Autom., Wuyishan, China, 2018, pp. 744−749.

[2] 
L. Grazi, E. Trigili, G. Proface, F. Giovacchini, S. Crea, and N. Vitiello, “Design and experimental evaluation of a semipassive upperlimb exoskeleton for workers with motorized tuning of assistance,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 10, pp. 2276–2285, 2020. doi: 10.1109/TNSRE.2020.3014408

[3] 
Y. Ren, Y. Wu, C. Yang, T. Xu, R. Harvey, and L. Zhang, “Developing a wearable ankle rehabilitation robotic device for inbed acute stroke rehabilitation,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 25, no. 6, pp. 589–596, 2017. doi: 10.1109/TNSRE.2016.2584003

[4] 
D.X. He, H.P. Wang, and Y. Tian, “Fractionalorder ultralocal modelbased optimal modelfree control for 7DOF iReHave upperlimb exoskeleton,” IEEE Trans. Circuits Syst. Ⅱ Express Briefs, vol. 69, no. 8, pp. 3510–3514, 2022. doi: 10.1109/TCSII.2022.3161659

[5] 
W. He, A. David, Z. Yin, and C. Sun, “Neural network control of a robotic manipulator with input deadzone and output constraint,” IEEE Trans. Syst. Man Cybern. Syst., vol. 46, no. 6, pp. 759–770, 2016. doi: 10.1109/TSMC.2015.2466194

[6] 
Y. Ouyang, L. Dong, L. Xue, and C. Sun, “Adaptive control based on neural networks for an uncertain 2DOF helicopter system with input deadzone and output constraints,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 3, pp. 807–815, 2019. doi: 10.1109/JAS.2019.1911495

[7] 
S. Han and J. Lee, “Outputtrackingerrorconstrained robust positioning control for a nonsmooth nonlinear dynamic system,” IEEE Trans. Ind. Electron., vol. 61, no. 12, pp. 6882–6891, 2014. doi: 10.1109/TIE.2014.2316263

[8] 
W. He, B. Huang, Y. Dong, Z. Li, and C. Su, “Adaptive neural network control for robotic manipulators with unknown deadzone,” IEEE Trans. Cybern., vol. 48, no. 9, pp. 2670–2682, 2018. doi: 10.1109/TCYB.2017.2748418

[9] 
J. Campos and F. Lewis, “Deadzone compensation in discrete time using adaptive fuzzy logic,” IEEE Trans. Fuzzy Syst., vol. 7, no. 6, pp. 697–707, 1999. doi: 10.1109/91.811238

[10] 
S. Tong, Y. Li, and S. Sui, “Adaptive fuzzy output feedback control for switched nonstrictfeedback nonlinear systems with input nonlinearities,” IEEE Trans. Fuzzy Syst., vol. 24, no. 6, pp. 1426–1440, 2016. doi: 10.1109/TFUZZ.2016.2516587

[11] 
S. Ibrir and C. Su, “Simultaneous state and deadzone parameter estimation for a class of boundedstate nonlinear systems,” IEEE Trans. Control Syst. Technol., vol. 19, no. 4, pp. 911–919, 2011. doi: 10.1109/TCST.2010.2054093

[12] 
Y. Yang, J. Huang, X. Su, and K. Wang, “Eventtriggered adaptive output feedback control of multivariable systems with nonsmooth actuator nonlinearities,” IEEE Trans. Syst. Man Cybern. Syst., vol. 51, no. 9, pp. 5557–5566, 2021. doi: 10.1109/TSMC.2019.2956056

[13] 
Z. Chen, Z. Li, and C. Chen, “Disturbance observerbased fuzzy control of uncertain mimo mechanical systems with input nonlinearities and its application to robotic exoskeleton,” IEEE Trans. Cybern., vol. 47, no. 4, pp. 984–994, 2017. doi: 10.1109/TCYB.2016.2536149

[14] 
W. He, X. He, and C. Sun, “Vibration control of an industrial moving strip in the presence of input deadzone,” IEEE Trans. Ind. Electron., vol. 64, no. 6, pp. 4680–4689, 2017. doi: 10.1109/TIE.2017.2674592

[15] 
T. Yang, N. Sun, and Y. Fang, “Adaptive fuzzy control for uncertain mechatronic systems with state estimation and input nonlinearities,” IEEE Trans. Ind. Inform., vol. 18, no. 3, pp. 1770–1780, 2022. doi: 10.1109/TII.2021.3089143

[16] 
J. Xu, J. Xu, and T. H. Lee, “Iterative learning control for systems with input deadzone,” IEEE Trans. Autom. Control, vol. 50, no. 9, pp. 1455–1459, 2005. doi: 10.1109/TAC.2005.854658

[17] 
S. Han and J. Lee, “Approximationfree tracking error constraint control for lagrangian systems,” IEEE Trans. Ind. Electron., vol. 64, no. 2, pp. 1269–1278, 2017. doi: 10.1109/TIE.2016.2613990

[18] 
Y. Zhang, Q. Yan, J. Cai, and X. Wu, “Adaptive iterative learning control for tank gun servo systems with input deadzone,” IEEE Access, vol. 8, pp. 63443–63451, 2020. doi: 10.1109/ACCESS.2020.2983454

[19] 
G. Peng, C. Chen, W. He, and C. Yang, “Neurallearningbased force sensorless admittance control for robots with input deadzone,” IEEE Trans. Ind. Electron., vol. 68, no. 6, pp. 5184–5196, 2021. doi: 10.1109/TIE.2020.2991929

[20] 
W. He, Y. Ouyang, and J. Hong, “Vibration control of a flexible robotic manipulator in the presence of input deadzone,” IEEE Trans. Ind. Inform., vol. 13, no. 1, pp. 48–59, 2017. doi: 10.1109/TII.2016.2608739

[21] 
S. Ge, F. Hong, and T. Lee, “Adaptive neural control of nonlinear timedelay systems with unknown virtual control coefficients,” IEEE Trans. Syst. Man Cybern. B Cybern., vol. 34, no. 1, pp. 499–516, 2004. doi: 10.1109/TSMCB.2003.817055

[22] 
S. Zhang, Y. Dong, Y. Ouyang, Z. Yin, and K. Peng, “Adaptive neural control for robotic manipulators with output constraints and uncertainties,” IEEE Trans. Neural Networks and Learning Syst., vol. 29, no. 11, pp. 5554–5564, 2018. doi: 10.1109/TNNLS.2018.2803827

[23] 
M. AlfaroPonce, A. Cruz, and I. Chairez, “Adaptive identifier for uncertain complex nonlinear systems based on continuous neural networks,” IEEE Trans. Neural Networks and Learning Syst., vol. 25, no. 3, pp. 483–494, 2014. doi: 10.1109/TNNLS.2013.2275959

[24] 
Z. Li, J. Li, S. Zhao, Y. Yuan, Y. Kang, and C. Chen, “Adaptive neural control of a kinematically redundant exoskeleton robot using brainmachine interfaces,” IEEE Trans. Neural Networks and Learning Syst., vol. 30, no. 12, pp. 3558–3571, 2019. doi: 10.1109/TNNLS.2018.2872595

[25] 
S. Chen, Z. Chen, B, Y ao, X. Zhu, S. Zhu, Q. Wang, and Y. Song, “Adaptive robust cascade force control of 1DOF hydraulic exoskeleton for human performance augmentation,” IEEE/ASME Trans. Mechatron., vol. 22, no. 2, pp. 589–600, 2017. doi: 10.1109/TMECH.2016.2614987

[26] 
M.H. Rahman, M.J. Rahman, O. Cristobal, M. Saad, J. P. Kenne, and P. S. Archambault, “Development of a whole arm wearable robotic exoskeleton for rehabilitation and to assist upper limb movements,” Robotica, vol. 33, pp. 19–39, 2015. doi: 10.1017/S0263574714000034

[27] 
Q. Wu, B. Chen, and H. Wu, “RBFNbased adaptive backstepping sliding mode control of an upperlimb exoskeleton with dynamic uncertainties,” IEEE Access, vol. 7, pp. 134635–134646, 2019. doi: 10.1109/ACCESS.2019.2941973

[28] 
C. Fallaha, M. Saad, J. Ghommam, and Y. Kali, “Sliding mode control with modelbased switching functions applied on a 7DOF exoskeleton arm,” IEEE/ASME Trans. Mechatron., vol. 26, no. 1, pp. 539–550, 2021.

[29] 
B. Brahmi, M. Saad, C. OchoaLuna, M. H. Rahman, and A. Brahmi, “Adaptive tracking control of an exoskeleton robot with uncertain dynamics based on estimated timedelay control,” IEEE/ASME Trans. Mechatron., vol. 23, no. 2, pp. 575–585, 2018. doi: 10.1109/TMECH.2018.2808235

[30] 
Z. Li, C. Su, G. Li, and H. Su, “Fuzzy approximationbased adaptive backstepping control of an exoskeleton for human upper limbs,” IEEE Trans. Fuzzy Syst., vol. 23, no. 3, pp. 555–566, 2015. doi: 10.1109/TFUZZ.2014.2317511

[31] 
Z. Li, C. Su, L. Wang, Z. Chen, and T. Chai, “Nonlinear disturbance observerbased control design for a robotic exoskeleton incorporating fuzzy approximation,” IEEE Trans. Ind. Electron., vol. 62, no. 9, pp. 5763–5775, 2015. doi: 10.1109/TIE.2015.2447498

[32] 
S. Han, H. P. Wang, Y. Tian, and N. Christov, “Timedelay estimation based computed torque control with robust adaptive RBF neural network compensator for a rehabilitation exoskeleton,” ISA Trans., vol. 97, pp. 171–181, 2020. doi: 10.1016/j.isatra.2019.07.030

[33] 
W. Cao, C. Chen, H. Hu, K. Fang, and X. Wu, “Effect of hip assistance modes on metabolic cost of walking with a soft exoskeleton,” IEEE Trans. Autom. Sci. Eng., vol. 18, no. 2, pp. 426–436, 2021. doi: 10.1109/TASE.2020.3027748

[34] 
V. Molazadeh, Q. Zhang, X. Bao, and N. Sharma, “An iterative learning controller for a switched cooperative allocation strategy during sittostand tasks with a hybrid exoskeleton,” IEEE Trans. Control Syst. Technol., vol. 30, no. 3, pp. 1021–1036, 2022. doi: 10.1109/TCST.2021.3089885

[35] 
X. Xiong, C. Do, and P. Manoonpong, “Learningbased multifunctional elbow exoskeleton control,” IEEE Trans. Ind. Electron., vol. 69, no. 9, pp. 9216–9224, 2022. doi: 10.1109/TIE.2021.3116572

[36] 
Z. Zhuang, H. Tao, Y. Chen, V. Stojanovic, and W. Paszke, “Iterative learning control for repetitive tasks with randomly varying trial lengths using successive projection,” Int. J. Adapt. Control Signal Process., vol. 36, no. 5, pp. 1196–1215, 2022. doi: 10.1002/acs.3396

[37] 
O. Narvaez Aroche, P. Meyer, S. Tu, A. Packard, and M. Arcak, “Robust control of the sittostand movement for a powered lower limb orthosis,” IEEE Trans. Control Syst. Technol., vol. 28, no. 6, pp. 2390–2403, 2020. doi: 10.1109/TCST.2019.2945908

[38] 
P. Cheng, H. Wang, V. Stojanovic, S. He, K. Shi, X. Luan, F. Liu, and C. Sun., “Asynchronous fault detection observer for 2D Markov jump systems,” IEEE Trans. Cybern., vol. 52, no. 12, pp. 13623–13634, 2022. doi: 10.1109/TCYB.2021.3112699

[39] 
V. Djordjevic, V. Stojanovic, H. Tao, X. Song, S. He, and W. Gao, “Datadriven control of hydraulic servo actuator based on adaptive dynamic programming,” Discrete Continuous Dyn. Syst. Ser. S, vol. 15, no. 7, pp. 1633–1650, 2022. doi: 10.3934/dcdss.2021145

[40] 
N. Nedic, V. Stojanovic, and V. Djordjevic, “Optimal control of hydraulically driven parallel robot platform based on firefly algorithm,” Nonlinear Dynamics, vol. 82, pp. 1457–1473, 2015. doi: 10.1007/s1107101522525

[41] 
H.P. Wang, G. Mustafa, and Y. Tian, “Modelfree fractionalorder sliding mode control for an active vehicle suspension system,” Adv. Eng. Softw., vol. 115, pp. 452–461, 2018. doi: 10.1016/j.advengsoft.2017.11.001

[42] 
S. Han, H. P. Wang, and Y. Tian, “Modelfree based adaptive nonsingular fast terminal sliding mode control with timedelay estimation for a 12 DOF multifunctional lower limb exoskeleton,” Adv. Eng. Softw., vol. 119, pp. 38–47, 2018. doi: 10.1016/j.advengsoft.2018.01.004

[43] 
S. Han, H. P. Wang, and Y. Tian, “A linear discretetime extended state observerbased intelligent PD controller for a 12 DOFs lower limb exoskeleton LLERePA,” Mech. Syst. Signal Process, vol. 138, p. 106547, 2020. doi: 10.1016/j.ymssp.2019.106547

[44] 
H.P. Wang, X. Ye, Y. Tian, and N. Christov, “Modelfreebased terminal SMC of quadrotor attitude and position,” IEEE Trans. Aerosp. Electron. Syst., vol. 52, no. 5, pp. 2519–2528, 2016. doi: 10.1109/TAES.2016.150303

[45] 
M. Fliess and C. Join, “Modelfree control,” Int. J. Control, vol. 86, no. 12, pp. 2228–2252, 2013. doi: 10.1080/00207179.2013.810345

[46] 
S. Bembli, N. Haddad, and S. Belghith, “Stability study and robustness analysis of an exoskeletonupper limb system,” in Proc. IEEE 18th Int. MultiConf. Syst. Signals Devices, Monastir, Tunisia, 2021, pp. 147–153.

[47] 
H. P. Wang, D. Zheng, and Y. Tian, “High pressure common rail injection system modeling and control,” ISA Trans., vol. 63, pp. 265–273, 2016. doi: 10.1016/j.isatra.2016.03.002

[48] 
J. Sun, J. Wang, P. Yang, and S. Guo, “Modelfree prescribed performance fixedtime control for wearable exoskeletons,” Appl. Math. Model., vol. 90, pp. 61–77, 2021. doi: 10.1016/j.apm.2020.09.010

[49] 
H. P. Wang, H. Xu, Y. Tian, and H. Tang, “αvariable adaptive model free control of iReHave upperlimb exoskeleton,” Adv. Eng. Softw., vol. 148, p. 102872, 2020. doi: 10.1016/j.advengsoft.2020.102872

[50] 
D. X. He, H. P. Wang, and Y. Tian, “An αvariable modelfree prescribedtime control for nonlinear system with uncertainties and disturbances,” Int. J. Robust Nonlinear Control, vol. 32, no. 9, pp. 5673–5693, 2022. doi: 10.1002/rnc.6105

[51] 
R. Nussbaum, “Some remarks on a conjecture in parameter adaptive control,” Syst. Control Lett., vol. 3, no. 5, pp. 243–246, 1983. doi: 10.1016/01676911(83)90021X

[52] 
C. Liu, X. Liu, H. Wang, S. Lu, and Y. Zhou, “Adaptive control and application for nonlinear systems with input nonlinearities and unknown virtual control coefficients,” IEEE Trans. Cybern., vol. 52, no. 9, pp. 8804–8817, 2022. doi: 10.1109/TCYB.2021.3054373

[53] 
L. Wang and C. Chen, “Adaptive fuzzy dynamic surface control of nonlinear constrained systems with unknown virtual control coefficients,” IEEE Trans. Fuzzy Syst., vol. 28, no. 8, pp. 1737–1747, 2020. doi: 10.1109/TFUZZ.2019.2921277

[54] 
C. Wang, C. Wen, and L. Guo, “Multivariable adaptive control with unknown signs of the highfrequency gain matrix using novel Nussbaum functions,” Automatica, vol. 111, p. 108618, 2020. doi: 10.1016/j.automatica.2019.108618

[55] 
C. Chen, Z. Liu, Y. Zhang, C. L. P. Chen, and S. Xie, “Adaptive control of MIMO mechanical systems with unknown actuator nonlinearities based on the Nussbaum gain approach,” IEEE CAA J. Autom. Sin., vol. 3, no. 1, pp. 26–34, 2016. doi: 10.1109/JAS.2016.7373759

[56] 
R. Wang and J. Liu, “Trajectory tracking control of a 6DOF quadrotor UAV with input saturation via backstepping,” J. Franklin Inst., vol. 355, no. 7, pp. 3288–3309, 2018. doi: 10.1016/j.jfranklin.2018.01.039

[57] 
U. M. AlSaggaf, R. Mansouri, M. Bettayeb, I. M. Mehedi, and K. Munawar, “Robustness improvement of the fractionalorder LADRC scheme for integer highorder system,” IEEE Trans. Ind. Electron., vol. 68, no. 9, pp. 8572–8581, 2021. doi: 10.1109/TIE.2020.3016258

[58] 
Y. Li, Y. Chen, and I. Podlubny, “MittagLeffler stability of fractional order nonlinear dynamic systems,” Automatica, vol. 45, no. 8, pp. 1965–1969, 2009. doi: 10.1016/j.automatica.2009.04.003

[59] 
M. De la Sen, “About robust stability of Caputo linear fractional dynamic systems with time delays through fixed point theory.,” Fixed Point Theory Appl., vol. 2011, p. 867932, 2011. doi: 10.1155/2011/867932

[60] 
M. Hou, G. Duan, and M. Guo, “New versions of Barbalat’s lemma with application,” J. Control Theory Appl., vol. 8, pp. 545–547, 2010. doi: 10.1007/s117680108178z

[61] 
W. Yu and J. Rosen, “Neural PID control of robot manipulators with application to an upper limb exoskeleton,” IEEE Trans. Cybern., vol. 43, no. 2, pp. 673–684, 2013. doi: 10.1109/TSMCB.2012.2214381

[62] 
S. Haykin, “Neural networks and learning machines,” Pearson Education India, 2009.

[63] 
A. Bartoszewicz and A. NowackaLeverton, “ITAE optimal sliding modes for thirdorder systems with input signal and state constraints,” IEEE Trans. Autom. Control, vol. 55, no. 8, pp. 1928–1932, 2010. doi: 10.1109/TAC.2010.2049688

[64] 
A. Awouda and R. Mamat, “Refine PID tuning rule using ITAE criteria,” in Proc. 2nd Int. Conf. Computer and Automation Engineering, Singapore, 2010, pp. 171–176.

[65] 
C. A. PérezGómez, J. LiceagaCastro, and I. SillerAlcalá, “Hard dead zone and friction modeling and identification of a permanent magnet DC motor nonlinear model,” WSEAS Trans. Syst. Control, vol. 15, pp. 527–536, 2020. doi: 10.37394/23203.2020.15.51
