Multi-dimensional surface myoelectricity signal artificial hand control method based on principal component analysis

A technology of principal component analysis and control method, which is applied in the field of multi-dimensional surface electromyography signal prosthetic hand control, can solve the problems of complex finger movements and difficulty in extracting individual universal motion laws, so as to save debugging time, shorten training time and calculation The effect of time and concise structure

Active Publication Date: 2017-11-24
SOUTHEAST UNIV
View PDF8 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Due to the different degrees of forearm muscle development and operating habits of different subjects, it is often difficult to extract universal motion rules for all individuals.
[0005] Human finger movements are very complex. Existing research focuses on the recognition of isolated gestures, an...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-dimensional surface myoelectricity signal artificial hand control method based on principal component analysis
  • Multi-dimensional surface myoelectricity signal artificial hand control method based on principal component analysis
  • Multi-dimensional surface myoelectricity signal artificial hand control method based on principal component analysis

Examples

Experimental program
Comparison scheme
Effect test

example

[0054] (5.1) represent the 24-dimensional myoelectric data with a column vector, then multiply with the principal component analysis transformation matrix to obtain a 5-dimensional column vector;

[0055] (6) After using the neural network to calculate the estimated finger bending angle, the angle change of the finger bending is converted into the actual control amount of the motor. After using the neural network to calculate the expected finger bending angle, the angle change of the finger bending is converted into the actual control amount of the motor, which is used to control (5.2). Substitute the 5-dimensional column vector in step (5.1) into the trained neural network model Perform calculations to obtain the expected finger bending angle.

[0056] The bending and stretching of the fingers of the prosthetic hand specifically includes the following steps:

[0057] (1) Design such as Figure 4 The finger underactuation control model of the prosthetic hand; wherein, the st...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a multi-dimensional surface myoelectricity signal artificial hand control method based on a principal component analysis. The control method comprises the follow steps that 1, an arm ring provided with a 24-channel array myoelectricity sensor is worn to a front arm of a testee, and five finger joint posture sensors are worn at the distal phalanx of a thumb of the subject and at the middle phalanxes of rest fingers of the testee respectively; 2, the testee conducts a five-finger independent bending and stretching training, and meanwhile, the myoelectricity sensing array data and the data of the finger joint posture sensors are collected; 3, the principal component analysis is used for decoupling the myoelectricity sensing data to form a finger movement training set; 4, the sensors worn on the fingers are removed after the training is finished; 5, data fitting is performed on the finger movement training set by adopting a neural network method, and a finger continuous motion prediction model is constructed; and 6, current bending angles of the fingers are predicted through the finger continuous motion model. According to the control method, the non-consistency of the discrete action modal classification can be overcome, and finally smooth control on an artificial hand is achieved.

Description

technical field [0001] The invention relates to a control method for a manipulator, in particular to a method for controlling a prosthetic hand based on a principal component analysis method with multi-dimensional surface electromyography signals. Background technique [0002] Biomechatronics dexterously operated prosthesis is an intelligent interactive device that can work with the environment, humans and other robots. It recognizes the operator's action intentions by collecting bioelectrical signals from the human body. Research on artificial limbs can drive technological innovation in the field of functional reconstruction and rehabilitation engineering for the disabled, and extend and develop the scientific connotation of equipment manufacturing. Its scientific and technological achievements can be radiated and applied to high-end medical equipment, mechanical and electrical integration intelligent robots, hazardous environment exploration and disaster rescue equipment, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): B25J9/16B25J9/10B25J15/00G06F3/01G06N3/08G06K9/62
CPCG06F3/015G06F3/017G06N3/084B25J9/1075B25J9/161B25J15/0009G06F18/2135G06F18/24A61F2/586A61F2/72A61F2002/587A61F2002/701A61F2002/704G16H40/63G16H20/30G16H50/50G16H50/20
Inventor 宋爱国胡旭晖曾洪徐宝国李会军
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap