Myoelectric prosthesis gesture and force control method

Abstract

The invention relates to a myoelectric prosthesis gesture and force control method and belongs to the technical field of myoelectric prosthesis. The method comprises the steps of acquiring forearm surface electromyogram signals; transmitting the multiple channels of surface electromyogram signals into a gesture identification model and a finger force identification model by segments through a moving window; in the gesture identification model, detecting the mobile segment of each signal firstly, extracting biological electromyogram signal feature information, and conducting data dimension reduction on the feature information; conducting real-time action identification and classification according to the feature information obtained after dimension reduction; in the finger force identification model, conducting normalization on original data of the forearm surface electromyogram signals, selecting a channel of surface electromyogram signals most closely related to each finger force linearly through correlation analysis, and conducting linear control on the finger force of myoelectric prosthesis with the surface electromyogram signals corresponding to different fingers respectively. By the adoption of the method, a prosthesis user can naturally and directly control the gesture and finger force of myoelectric prosthesis to achieve basic daily movement, and therefore the identity sense and living convenience of the prosthesis user are improved.

Description

technical field [0001] The invention belongs to the technical field of myoelectric prosthesis, and relates to a gesture and force control method of myoelectric prosthesis. Background technique [0002] According to the 2006 National Bureau of Statistics sample survey data on my country's disabled population, among the various types of disabled people in the country, the physically disabled population is the largest, accounting for 24.12 million people, accounting for 29.07% of the total disabled population. Due to accidents, birth defects, diseases, natural disasters and other reasons, the number of people with physical disabilities is still increasing. [0003] At present, the commonly used and relatively advanced prostheses on the market include decorative prostheses, tool hands, traction mechanical prostheses, electric prostheses, voice-activated prostheses, and myoelectric prostheses. The traditional mechanical cable-controlled prosthesis uses the prosthesis user's own ...

AI Technical Summary

Problems solved by technology

[0005] Although the current research on gesture recognition based on forearm EMG signals is very rich, there are relatively few studies on the synchronous control of single-finger posture and fingertip force.

Images