Abstract
An algorithm for controlling servo electric drives of the lower-extremity joint angles of an exoskeleton using a neural network to compensate for the effects of stochastic external disturbances, uncertain parameters of the dynamic model, and nonlinear elements in the form of friction and elasticity is presented. The control method, which is based on a neural network, which has the ability to learn and adapt, makes a new approach to the study possible, as well as making it possible to adapt the model with any errors, without regard to the structure of the nonlinear object. A mathematical model of the motion dynamics of an exoskeleton (two legs with five joints) has been constructed with allowance for nonlinear electric drives. The results of an experiment are obtained to illustrate the effectiveness of the proposed control strategy in the MATLAB/Simulink program, including in comparison with a conventional PID-controller.
Similar content being viewed by others
REFERENCES
Iandolo, R., Marini, F., Semprini, M., Laffranchi, M., Mugnosso, M., Cherif, A., De Michieli, L., Chiappalone, M., and Zenzeri, J., Perspectives and challenges in robotic neurorehabilitation, Appl. Sci., 2019, vol. 9, no. 15, p. 3183. https://doi.org/10.3390/app9153183
Park, J.-H., Lee, J.-S., Shin, J.-S., and Cho, B.-K., Design of a lower limb exoskeleton including roll actuation to assist walking and standing up, IEEE-RAS 15th Int. Conf. on Humanoid Robots (Humanoids), Seoul, 2015, IEEE, 2015, pp. 359–364. https://doi.org/10.1109/HUMANOIDS.2015.7363575
Belforte, G., Eula, G., Appendino, S., and Sirolli, S., Pneumatic interactive gait rehabilitation orthosis: design and preliminary testing, Proc. Inst. Mech. Eng. H: J. Eng. Med., 2010, vol. 225, no. 2, pp. 158–169. https://doi.org/10.1243/09544119JEIM803
Belkadi, A., Oulhadj, H., Touati, Y., Khan, S.A., and Daachi, B., On the robust PID adaptive controller for exoskeletons: A particle swarm optimization based approach, Appl. Soft Comput., 2017, vol. 60, pp. 87–100. https://doi.org/10.1016/j.asoc.2017.06.012
Yang, Y., Huang, D., and Dong, X., Enhanced neural network control of lower limb rehabilitation exoskeleton by add-on repetitive learning, Neurocomputing, 2019, vol. 323, pp. 256–264. https://doi.org/10.1016/j.neucom.2018.09.085
Belov, M.P., Sovremennye podkhody k strukturno-parametricheskomu sintezu, issledovaniyu i upravleniyu avtomatizirovannymi elektroprivodami promyshlennykh agregatov (Modern Approaches to Structural and Parametric Synthesis, Study, and Control of Automated Electric Drives of Industrial Facilities), St. Petersburg: St. Petersburg Gos. Elektrotekh. Univ. LETI, 2012.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by A. Kolemesin
About this article
Cite this article
Kozlova, L.P., Belov, M.P. & Chyong, D.D. Application of a Neural Network for Controlling Servo Electric Drives of the Lower-Extremity Powered Exoskeleton. Russ. Electr. Engin. 93, 179–183 (2022). https://doi.org/10.3103/S1068371222030099
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1068371222030099