Research on control system of an exoskeleton upper-limb rehabilitation robot

被引：0
|
作者：
Wang L. [1 ,2 ]
Hu X. [2 ,3 ]
Hu J. [1 ,2 ]
Fang Y. [1 ,2 ]
He R. [1 ,2 ]
Yu H. [1 ,2 ]
机构：
[1] Institute of Biomechanics and Rehabilitation Engineering, School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai
[2] Shanghai Engineering Research Center of Assistive Devices, Shanghai
[3] Central Academy, Shanghai Electric Group Co., Ltd., Shanghai
来源：
Yu, Hongliu (yhl98@hotmail.com) | 1600年 / West China Hospital, Sichuan Institute of Biomedical Engineering卷 / 33期
关键词：
Electromyography control; Upper-limb exoskeleton rehabilitation robot; Voice control;
D O I：
10.7507/1001-5515.20160185
中图分类号：
学科分类号：
摘要：
In order to help the patients with upper-limb disfunction go on rehabilitation training, this paper proposed an upper-limb exoskeleton rehabilitation robot with four degrees of freedom (DOF), and realized two control schemes, i.e., voice control and electromyography control. The hardware and software design of the voice control system was completed based on RSC-4128 chips, which realized the speech recognition technology of a specific person. Besides, this study adapted self-made surface eletromyogram (sEMG) signal extraction electrodes to collect sEMG signals and realized pattern recognition by conducting sEMG signals processing, extracting time domain features and fixed threshold algorithm. In addition, the pulse-width modulation(PWM)algorithm was used to realize the speed adjustment of the system. Voice control and electromyography control experiments were then carried out, and the results showed that the mean recognition rate of the voice control and electromyography control reached 93.1% and 90.9%, respectively. The results proved the feasibility of the control system. This study is expected to lay a theoretical foundation for the further improvement of the control system of the upper-limb rehabilitation robot. � 2016, Editorial Office of Journal of Biomedical Engineering. All right reserved.
引用
收藏
页码：1168 / 1175
页数：7
相关论文
共 14 条
  • [11] Suresh M., Krishnamohan P.G., Holi M.S., Processing of natural signals like EMG for person identification using NUFB-GMM, Int j adv comput res, 4, 3, pp. 819-827, (2014)
  • [12] Phinyomark A., Phukpattaranont P., Limsakul C., Feature reduction and selection for EMG signal classification, Expert Syst Appl, 39, 8, pp. 7420-7431, (2012)
  • [13] Bin Ahmad Nadzri A.A., Ahmad S.A., Marhaban M.H., Et al., Characterization of surface electromyography using time domain features for determining hand motion and stages of contraction, Australas Phys Eng Sci Med, 37, 1, pp. 133-137, (2014)
  • [14] Al Omari F., Hui J., Mei C.-L., Et al., Pattern recognition of eight hand motions using feature extraction of forearm EMG signal, Proc Natl Acad Sci U S A, 84, 3, pp. 473-480, (2014)
12