부산대학교 도서관

With the number of stroke patients increasing year by year, rehabilitation exoskeleton robot has been paid more and more attention. For the rehabilitation exoskeleton robot, human-computer interaction ability is an important index, which affects the effect of rehabilitation therapy to a great extent. Surface Electromyography (sEMG) signals are the combined effect of sEMG signals and electrical activities on nerve stem on the skin surface, which can reflect neuromuscular activities in advance and can be used to predict movement intention by sEMG signals. Therefore, this article proposes to use sEMG signals to monitor the motion information of the healthy leg in real-time, extract the characteristics of the electromyography signals, use the sEMG of the healthy leg as the control signal, reflect the motion patterns reflected by the sEMG collected from the healthy side, and then use the motion intention recognition method of Long Short Term Memory(LSTM) neural network to identify the motion intention of the prosthetic limb by identifying the motion patterns of the swing phase of the healthy side. The results indicate that the predicted maximum Root Mean Squared Error(RMSE) is 5.3729, which proves the feasibility of using LSTM model for motion intention recognition and contributes to the real-time and accuracy of lower limb exoskeleton rehabilitation.