Electromyographic signal-based portable real-time lower limb behavior pattern recognition system and method

Abstract

The invention provides an electromyographic signal-based portable real-time lower limb behavior pattern recognition system and method. The system particularly comprises an electromyographic signal acquisition module, an electromyographic signal preprocessing module, a multichannel AD data sampling module, an embedded main control module, a power module and a display device. electromyographic signal features for the lower limb behavior pattern are subjected to real-time recognition and output, the single decoding time for the electromyographic signal features is less than 300 microseconds, andthe real-time performance requirement is met; the total weight of a hardware system is about 100 g, the overall hardware control board size is 90 mm * 90 mm, and the portability requirement is met; the research purpose of the system is to be used in fields such as prosthesis or exoskeleton, real-time discrimination and recognition on the motion state can be realized through the system, and the system is further used as a basis for motion control on prosthesis / exoskeleton devices and a basis for providing motion control on prosthesis / exoskeleton.

Description

technical field [0001] The invention belongs to the intersecting field of biomedical engineering and mechatronic engineering, and in particular relates to a real-time identification system and method for portable lower limb behavior patterns based on electromyographic signals. Background technique [0002] Human-machine collaboration is the development trend of modern industry, and it will bring fundamental changes to the future industry. In more and more fields, collaborative robots will take on the job duties they are good at and become important assistants to humans. Humans and robots will have an interdependent relationship. [0003] Human-robot collaboration is the interaction and harmonious coexistence of humans and robots. In the Human-Machine Collaboration model, humans and machines work hand in hand to develop their respective expertise. Robots can assist humans to do some complicated and heavy work. Humans can adjust robot production according to actual needs. Hu...

AI Technical Summary

Problems solved by technology

But nowadays, the feature extraction of EMG signals for lower limb behavior mostly adopts offline data analysis method; even for online feature extraction, the feature extraction time is long and seriously lagged behind, and the human behavior intention cannot be sent out in real time, resulting in the inability to make collaborative robots Real-time perception of human intentions cannot meet the needs of practical applications

Images