sEMG-based hand rehabilitation robot control method

Abstract

The invention relates to a sEMG-based hand rehabilitation robot control method. In an offline model training stage, the optimal threshold value of motion intention is obtained; the threshold value isused for judging whether a current hand has motion intention or not; furthermore, a hand motion intention classification model is obtained by training; in an online motion intention identification stage, whether the hand has motion intention or not is judged; furthermore, the specific motion type is identified by utilization of the hand motion intention classification model obtained in the offlinemodel training stage; and a hand rehabilitation robot is controlled in a rehabilitation robot control stage. According to the sEMG-based hand rehabilitation robot control method in the invention, thesubjective motion intention of a hand at the affected side is judged by utilization of sEMG signals at the front arm of the affected size of a patient, so that the hand rehabilitation robot is controlled to complete corresponding target actions; therefore, the patient is assisted to establish the forward mapping relation from the subjective motion intention of the hand at the affected side to theactual action; and the purpose of performing rehabilitation training on the hand at the affected side by utilizing the sEMG signals is achieved.

Description

technical field [0001] The invention relates to the fields of biological signal recognition technology and medical rehabilitation robots, in particular to a control method for hand rehabilitation robots based on sEMG. Background technique [0002] In recent years, with the aging population in my country, the incidence of stroke has shown a trend of increasing year by year. Stroke is a relatively common cerebrovascular disease, usually accompanied by neurological damage. The most common symptom is hemiplegia, that is, numbness and weakness of the affected side, hemiplegia, and the hand manifests as a clenched fist with five fingers clasped tightly, which is difficult to open. The palm or grabbing objects seriously affects the patient's ability to take care of himself. [0003] Medical research shows that effective rehabilitation training can stimulate the recovery of patients' neurological function and speed up the process of rehabilitation treatment. For stroke patients su...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a sEMG-based hand rehabilitation robot control method, which solves the problem of low efficiency of the traditional "one-to-one" treatment method between rehabilitation physicians and patients, and poor effect of simple passive rehabilitation treatment. problem, using the identification results to control the hand rehabilitation robot, so as to assist patients in rehabilitation treatment

Images