Bolt axial force monitoring system and monitoring method based on visual deep learning

A visual depth and monitoring system technology, applied in the direction of integrated learning, force/torque/work measuring instrument, measuring device, etc., can solve the problems of cost increase, complex project implementation, and reduced necessity of bolt monitoring, etc., to achieve convenient engineering use, Cost reduction, excellent technical effect

Active Publication Date: 2021-03-23
北京艾法斯特科技发展有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004](1) High monitoring cost: using contact-type bolt axial force monitoring technologies such as ultrasound, force rings, strain gauges, and gratings, it is necessary to increase the number of monitored bolts For the sensor part, the monitoring of a large number of bolts will lead to a substantial increase in cost;
[0005](2) The project implementation is complex: for each bolt using the contact bolt axial force monitoring technology, it is necessary to use wires or wireless methods, resulting in on-site construction Complexity and substantial increase in engineering costs;
[0006] (3) Changing the bolt connection structure: Some contact bolt monitoring technologies, such as strain gauges, gratings, and force rings, will change or damage the bolt connection structure, so that the necessity of bolt monitoring is greatly reduced;
[0007](4) Quantity of monitoring bolts: Due to the limitation of monitoring cost, the contact bolt monitoring technology can only conduct sampling monitoring on bolts, and it is impossible to monitor the large Some bolts are monitored, which greatly reduces the significance of monitoring
[0009] Bolted connection is the most widely used assembly and assembly method in the industry. Its axial force is an important indicator of structural health. However, due to the design of bolted connection and the quality of bolts Due to reasons such as fastening process, the quality of bolted connections is often difficult to control, and a large number of structural failures are caused by the failure of bolted connections; due to the huge number of bolted connections, it is difficult to quickly, effectively and low-cost the axial force attenuation. Geometry, making it a thorny problem for industry
Due to the inherent limitations of contact bolt axial force monitoring technology, all contact bolt monitoring technologies cannot solve the above 1-4 problems, resulting in contact bolt axial force measurement technology can only be used in the design verification and prototype stage of product structure , but it is difficult to use it on a large scale in engineering practice

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
  • Bolt axial force monitoring system and monitoring method based on visual deep learning
  • Bolt axial force monitoring system and monitoring method based on visual deep learning
  • Bolt axial force monitoring system and monitoring method based on visual deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] The bolt axial force monitoring system based on visual deep learning provided by the embodiment of the present invention includes: a camera, a bolt marking device, and a software algorithm part.

[0063] When the bolt is tightened, the nut rotates clockwise under the action of torque, generating axial force in the bolt. Contrary to this process, the bolt axial force attenuation is divided into two parts: the non-rotating bolt axial force attenuation and the rotating bolt axial force attenuation. Among them, the non-rotational axial force attenuation refers to the attenuation of the axial force when the nut does not rotate backwards. This is mainly because the surface of the clamped object is embedded or compressed under the action of the axial force of the bolt. It is caused by the collapse phenomenon, and part of it is caused by the plastic deformation of the screw thread; the non-rotational axial force attenuation generally occurs within 24 hours after the bolt is tig...

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 belongs to the technical field of bolt axial force information monitoring, and discloses a bolt axial force monitoring system and method based on visual deep learning. The method comprises the steps that: a camera takes a picture or record a video of a bolt, and the video can be decomposed into images in a frame format; a bolt marking device is installed in a visual range near bolt connection, and the marking device can uniquely determine one or more bolt connections and is used for shooting a plurality of bolts at different angles to identify and measure different bolt individuals; and a bolt axial force monitoring module automatically identifies and extracts bolt connection in the image through a deep learning algorithm, measures the reverse rotation angle of the nut, calculates the elongation change of the bolt, and obtains a bolt axial force attenuation value, wherein the corresponding relationship between the bolt elongation and the bolt axial force is calibrated andobtained by an ultrasonic bolt axial force measurement technology. According to the invention, a visual non-contact mode and a deep learning algorithm are utilized to detect or monitor the axial force or attenuation condition of a bolt or a bolt group.

Description

technical field [0001] The invention belongs to the technical field of bolt axial force information monitoring, and in particular relates to a bolt axial force monitoring system and monitoring method based on visual deep learning. Background technique [0002] At present, bolted connections are affected by external factors, such as: vibration, thermal shock, axial force relaxation, premature failure and fracture. Structures often have many or even a large number of bolt connections. For contact monitoring methods of bolt axial force, such as: ultrasonic, force ring, strain gauge, grating, etc., under the constraints of economy and engineering, it is impossible to measure the quantity. Numerous bolts are used for axial force monitoring, which greatly reduces the application significance of monitoring. [0003] In summary, the problems in the prior art are: [0004] (1) High monitoring cost: Using contact-type bolt axial force monitoring technologies such as ultrasound, forc...

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 Applications(China)
IPC IPC(8): G01L5/24G06T7/00G06K9/62G06N20/20
CPCG01L5/24G01L5/246G06T7/0004G06N20/20G06T2207/10004G06T2207/20081G06T2207/30164G06F18/214
Inventor 杜青阳申文涛常明亮刘坤杜祖良任海蔡莉慧
Owner 北京艾法斯特科技发展有限公司
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