Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method and system for continuous prediction of wrist joint torque in multi-grasp mode

A prediction method and joint torque technology, which is applied in prediction, neural learning methods, medical simulation, etc., can solve the problems of huge price of instruments, unconsidered differences, torque prediction deviation, etc., and achieve the effect of improving robustness

Active Publication Date: 2021-03-23
XI AN JIAOTONG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The direct measurement method using isokinetic muscle force measurement equipment is large and expensive, so it is limited
Chinese patent CN109559826A proposes a knee joint torque estimation method based on surface electromyography and motion signals, using the sEMG of active and antagonistic muscles, knee joint angle, and knee joint angular velocity under knee joint extension and flexion to establish an offline model for joint torque Online estimation, the difference in various working conditions is not considered in the process of model building, so it has certain limitations
However, the function of existing myoelectric prosthetic hands is mainly to use the residual limb myoelectric signal to identify specific action patterns. Torque prediction under some specific grasping modes, when the change of grasping mode causes the EMG signal to change, the torque prediction will have a large deviation

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
  • A method and system for continuous prediction of wrist joint torque in multi-grasp mode
  • A method and system for continuous prediction of wrist joint torque in multi-grasp mode
  • A method and system for continuous prediction of wrist joint torque in multi-grasp mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0127] A method for continuously predicting wrist joint torque in a multi-grab mode, comprising the following steps:

[0128] S100, the multi-grabbing mode includes using multiple gestures to grab loads of different sizes. Gestures include but not limited to G gestures such as grasping gestures, thumb, index finger and middle finger three-finger pinching, and loads include but not limited to N common loads such as 60g, 480g, 960g, etc., use different gestures to grab different loads to form a total of I=G*N grabbing modes; After the collection, change the capture mode and continue to collect data. The following takes the sth gesture to capture the nth load as an example to describe in detail;

[0129] S200, using the three-dimensional motion capture system to record the wrist bending / extending angle information during the bending / extending movement of the wrist joint in the s gesture grasping the nth load grasping mode, specifically including the following steps:

[0130] S2...

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 an electromyographic continuous prediction method and system for wrist joint torque in multi-grabbing mode, and the prediction method comprises the steps of: collecting the electromyographic signals of the surface of a forearm in each grabbing mode, and carrying out the preprocessing and feature extraction; and inputting the electromyographic signal characteristics in eachgrabbing mode into a joint torque prediction model, outputting a wrist joint torque prediction value, and evaluating the accuracy of the electromyographic continuous prediction model of the wrist joint torque in the multi-grabbing mode by calculating a linear correlation coefficient between the wrist joint torque prediction value and the reference torque. The operation intention of a user on an artificial wrist joint is continuously predicted by using the electromyographic signals of a stump in various grabbing modes, and the artificial wrist joint is accurately driven according to the operation intention to realize human hand-like natural operation, so that the robustness in different modes is improved, and the man-machine natural driving of an artificial hand is realized.

Description

technical field [0001] The invention belongs to the field of electromechanical fusion, and relates to a method and system for continuously predicting wrist joint torque in multiple grasping modes. Background technique [0002] Myoelectric signal is a kind of bioelectric signal generated by human muscles during exercise. Its frequency, amplitude and other characteristics are closely related to the state of muscle movement and the size of the load. Therefore, the characteristics of myoelectric signal can be used to describe the current state of muscle movement, load etc. At present, the estimation of joint torque by electromyographic signals mainly involves the joints of the lower extremities. The estimation methods mainly include direct measurement with isokinetic muscle force measuring instruments and establishment of musculoskeletal models based on the Hill model. The direct measurement method using isokinetic muscle force measurement equipment is bulky and expensive, so i...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/50G06Q10/04G06F30/20G06F119/14G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06Q10/04G16H50/50
Inventor 张小栋张毅蒋志明陆竹风张腾王雅纯
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products