Non-Linear Motorized Prosthetic Hand System With Gradient Descent Tuning Technique

• Main Authors: Jali, Mohd Hafiz, Ghazali, Rozaimi, Soon, Chong Chee, Muhammad, Ahmad Razif
• Format: Article
• Language: English
• Published: International Journal Of Mechanical Engineering And Robotics Research (IJMERR) 2021
• Online Access: http://eprints.utem.edu.my/id/eprint/25636/2/20210709022533736.PDF; http://eprints.utem.edu.my/id/eprint/25636/; http://www.ijmerr.com/uploadfile/2021/0709/20210709022533736.pdf
• Institution: Universiti Teknikal Malaysia Melaka

This paper describes the controller design for a nonlinear motorized prosthetic finger system. This system can be used as a human assistive device for amputee. Since the prosthetic device is worn by human, the accuracy of the system is crucial to avoid unnecessary injury. In addition, the mathematical modelling of the system needs to be developed appropriately to ensure the accuracy of the system. Various types of controllers can be used to obtain a stable nonlinear actuated finger system, such as Proportional Integral (PI), Proportional Integral and Derivative (PID), and Fuzzy Logic controllers. In this work, the Proportional, Integral, and Derivative (PID) controller will be used. The tuning of the PID control parameter is for positioning feedback control of the motor. To improve the transient response performance of the motor, Gradient Descent and Auto--Tuning techniques have been used to obtain the parameters of the PID controller. Comparison between these techniques and the comparison with the previous work is carried out. It is observed from the results, Gradient Descent tuning technique outperforms the AutoTuning technique.