TBI Rehabilitation

[Abstract + References] Research on Control Method of Arm Rehabilitation Robot Based on BP Neural Network – Proceedings

Kostas Pantremenos

ABSTRACT

Rehabilitation robot is a kind of human-computer interaction robot, and its motion mode must conform to the motion characteristics of patients’ limbs in recovery period and meet the training requirements of patients in different recovery periods. The arm rehabilitation robot is a bionic manipulator which takes the patients with arm hemiplegia as the object and carries out a series of rehabilitation training based on rehabilitation medicine. Patients with arm hemiplegia only need to wear the arm rehabilitation robot on the affected limb, and then choose passive exercise, active auxiliary exercise and active damping training methods according to the recovery of their own arms, and complete daily rehabilitation training independently. For the rehabilitation treatment of upper limb dysfunction, it is very important to adhere to long-term and effective scientific treatment. Compared with the traditional methods, BP neural network has faster convergence, higher learning accuracy and better network generalization ability. According to the structure of the arm rehabilitation robot, this paper discusses the control method of arm rehabilitation robot based on BP neural network from the perspective of intelligent control.

References

  1. Shi Xiaohua, Lu Hao, Liao Ziyu, et al. Active lower limb rehabilitation training based on surface EMG signal[J]. Science Technology and Engineering, 2018, 18(17): 61–66.
  2. Cai Gaipin, Liu Xin, Luo Xiaoyan, et al. Research on inverse kinematics solution of mining robot using APSO-LM-BP neural network[J]. Mechanical Science and Technology, 2020, 303(05): 56–63.
  3. Al-Quraishi M S S. Classification of ankle joint movements based on surface electromyography signals for rehabilitation robot applications[J]. Medical & Biological Engineering & Computing, 2016, 55(5): 1–12.
  4. Agarwal P, Fox J, Yun Y, et al. An index finger exoskeleton with series elastic actuation for rehabilitation: Design, control and performance characterization[J]. International Journal of Robotics Research, 2015, 34(14):1747 -1772.
  5. Fateh M M, Khoshdel V. Voltage-based adaptive impedance force control for a lower-limb rehabilitation robot[J]. Advanced Robotics, 2015, 29(15): 961–971.
  6. Liang Feng, Xiong Ling. Mobile robot UWB indoor positioning based on GA-BP neural network[J]. Microelectronics and Computer, 2019, 36(4): 33–37.
  7. Li Zeguo, Li Guodong. Layered control of flexible joint robot based on neural network gravity feedforward compensation[J]. Journal of Tianjin University of Science and Technology, 2017, 32(6): 53–58.
  8. Wang Jinchao, Lei Yi, Yu Hongliu, et al. Research on a new type of intelligent interactive arm rehabilitation robot[J]. Chinese Journal of Rehabilitation Medicine, 2016, 31(12): 1371–1374.
  9. Mohammadi E, Zohoor H, Khadem S M. Control system design of an active assistive exoskeletal robot for rehabilitation of elbow and wrist[J]. entia Iranica, 2016, 23(3): 998–1005.
  10. Santos C P, Alves N, Moreno J C. Biped Locomotion Control through a Biomimetic CPG-based Controller[J]. Journal of Intelligent & Robotic Systems, 2017, 85(1): 47–70.
  11. Hu Jie, Zhu Lin, Liu Lin, et al. The effect of arm rehabilitation robot combined with conventional rehabilitation training on upper limb function of patients with acute stroke[J]. China Rehabilitation, 2018, 33(6): 448–450.
  12. Zhang Linling, Yu Hongliu, Fang Youfang, et al. Design of motion direction information processing system for arm rehabilitation robot[J]. Electronic Science and Technology, 2017, 30(5): 142–146.

Source