Check patentability & draft patents in minutes with Patsnap Eureka AI!

Assembly torque monitoring system and method based on regression neural network

A regression neural network and monitoring system technology, applied in the field of intelligent manufacturing and assembly process monitoring, can solve the problems of reduced monitoring accuracy, performance degradation, and difficult replacement of sensors, so as to reduce assembly space constraints, reduce computation and parameters, and improve The effect of prediction accuracy

Active Publication Date: 2021-03-12
QINGDAO TECHNOLOGICAL UNIVERSITY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The first type of sensor is installed on the fixture or assembly line. The working environment of this type of sensor is limited and can only be used in the installed position.
Moreover, this type of sensor is not easy to replace. With the increase of working time, the performance will decrease and the monitoring accuracy will decrease.
The second type of sensor is installed on the assembly tool. This type of sensor has poor versatility. Different assembly tools need to be used for different assembly processes. There are also problems such as poor portability and limited installation space by the assembly space.

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
  • Assembly torque monitoring system and method based on regression neural network
  • Assembly torque monitoring system and method based on regression neural network
  • Assembly torque monitoring system and method based on regression neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] see figure 1 , an assembly torque monitoring system based on a regression neural network, including a wearable measuring device 1, a torque regression module 2 and a computer 4;

[0035] The wearable measurement device 1 is worn on the operator's arm, and includes a wireless communication unit 13 and a muscle measurement unit 11 and an inertial measurement unit 12 electrically connected to the wireless communication unit; the muscle measurement unit 11 and the inertial measurement unit 12 respectively collect The sEMG signal (surface electromyography signal) and inertial signal generated by the operator during the assembly process, the wireless communication unit 13 is connected to the computer for wireless communication, and is used to send the collected sEMG signal and inertial signal to the computer 4;

[0036] It also includes a torque sample collection device 3, which is arranged on the assembly sample and is electrically connected to the computer 4. The torque sam...

Embodiment 2

[0051] see Figure 4 , an assembly torque monitoring method based on a regression neural network, implemented based on the assembly torque monitoring system based on a regression neural network described in Embodiment 1, comprising the following steps:

[0052] Sample collection phase:

[0053] Step S1, the operator wears the wearable measuring device 1 to perform the assembly operation;

[0054] Step S2, the wearable measuring device 1 collects the sEMG signal and inertial signal of the operator, and the torque sample collection device 3 collects the torque information on the assembly, and transmits it to the computer 4 through the wireless communication unit 13;

[0055] Step S3, the sEMG signal, inertial signal and torque information pass through the data preprocessing module to eliminate signal power frequency interference and signal noise, and establish a sample data set, wherein the preprocessed sEMG signal and inertial signal are used as input, and the preprocessed To...

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 relates to an assembly torque monitoring system and method based on a regression neural network. The system comprises a wearable measuring device, a torque regression module and a computer. The wearable measuring device comprises a wireless communication unit, a muscle measuring unit and an inertia measuring unit. The muscle measuring unit and the inertia measuring unit respectivelycollect sEMG signals and inertia signals generated by an operator in the assembling process and send the signals to the computer through the wireless communication unit. The wearable measuring devicealso comprises a torque sample collection device which is used for collecting torque information generated in the process that an operator assembles the assembly body sample and sending the torque information to the computer; wherein the computer comprises a recurrent neural network model, and the computer takes sEMG signals and inertia signals as input and torque information as output to train the recurrent neural network model to obtain a torque monitoring model. The torque monitoring model is embedded in the torque regression module which is used for calculating the assembling torque through the sEMG signal and the inertia signal and feeding back the assembling torque to an operator.

Description

technical field [0001] The invention relates to an assembly torque monitoring system and a monitoring method based on a regression neural network, belonging to the technical field of intelligent manufacturing and assembly process monitoring. Background technique [0002] Mechanical assembly is an important part of the machinery manufacturing industry. It is the process of realizing the combination of mechanical parts and components and completing the assembly of the machine according to the technical requirements. Assembly process monitoring has become an important means to ensure product quality. At present, there are mainly three types of assembly process monitoring methods, namely assembly operator monitoring, assembly body monitoring and assembly force / torque monitoring. Among them, operator monitoring is the most direct monitoring method. It uses visual methods such as human body posture estimation, action recognition, and face recognition to judge the operator's assem...

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): G06F3/01G06F3/0346G01L3/00G01C21/16G06N3/04G06N3/08
CPCG06F3/011G06F3/015G06F3/0346G01L3/00G01C21/16G06N3/08G06N3/045
Inventor 陈成军黄凯李东年赵正旭高玮洪军
Owner QINGDAO TECHNOLOGICAL UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com