Accurate positioning method for sleeve puller bolt of high-speed rail contact net supporting device

A technology for supporting devices and tightening bolts, which is applied in neural learning methods, biological neural network models, image data processing, etc., can solve the problems of sensitivity to size differences, adverse effects, and impact failures, so as to achieve intelligent analysis and reduce huge work Quantity, to achieve the effect of location extraction

Inactive Publication Date: 2019-08-02
SOUTHWEST JIAOTONG UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the complexity and diversity of catenary support device components
It brings serious challenges to the further application of the current inspection vehicle; the template matching positioning method, which is widely used in the automatic inspection technology of the current inspection vehicle, is sensitive to size differences, especially for the mispositioning of small parts such as sleeve jacking bolts Due to the high rate and missing location rate, it is necessary to further check the location results manually, which will affect the timely maintenance and treatment of the fault. During this process, the fault may further develop into an accident, and even bring significant losses and adverse effects.

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
  • Accurate positioning method for sleeve puller bolt of high-speed rail contact net supporting device
  • Accurate positioning method for sleeve puller bolt of high-speed rail contact net supporting device
  • Accurate positioning method for sleeve puller bolt of high-speed rail contact net supporting device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0030] A method for precise positioning of a socket tightening bolt of a catenary support device for a high-speed railway, comprising the following steps:

[0031] Step 1: Obtain the marked sample library of components of the high-speed rail catenary support device;

[0032] A special comprehensive train inspection vehicle is used to image the support and suspension devices of the high-speed railway catenary. The special comprehensive train inspection vehicle performs uplink and downlink high-definition image storage of the high-speed railway catenary support device at a certain operating speed. The global image is as follows: figure 1 shown.

[0033] The collected images are screened, and a labeled sample library of catenary support device components is constructed.

[0034] The Tag Sample Gallery includes images from the following categorie...

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 accurate positioning method for a sleeve puller bolt of a high-speed rail contact net supporting device. The accurate positioning method comprises the following steps that 1, obtaining a mark sample library of parts of the high-speed rail contact net supporting device; 2, constructing a deep convolutional neural network based on an improved Faster RCNN algorithm, whereinthe deep convolutional neural network comprises a feature extraction network, ROI generation, sample classification and frame regression; step 3, training the built deep convolutional neural network;and 4, adopting the trained deep convolutional neural network to accurately position the sleeve puller bolt of the high-speed rail overhead line system supporting device. According to the method, thehuge workload of manual recognition can be reduced, field image intelligent analysis is achieved, and positioning extraction of the small-scale sleeve puller bolt is achieved.

Description

technical field [0001] The invention relates to the technical field of high-speed railway image intelligent detection, in particular to a precise positioning method for a sleeve tightening bolt of a high-speed railway catenary support device. Background technique [0002] As of the end of 2018, the total mileage of my country's high-speed rail operations exceeded 29,000 kilometers, and the world's largest high-speed rail network has been built. At the same time, high-speed rail has become one of the most important means of transportation in China, which puts forward higher requirements for the safety performance of high-speed rail. The catenary support device is the main facility of the overhead catenary of the high-speed rail, which determines whether the catenary can operate safely. As the key power supply facility in the traction power supply system of the high-speed rail, the catenary mainly undertakes the power supply function of the high-speed rail EMU. Its reliability...

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): G06T7/73G06K9/32G06K9/46G06N3/04G06N3/08
CPCG06T7/73G06N3/08G06T2207/20081G06T2207/20084G06T2207/20104G06T2207/30252G06V10/25G06V10/44G06N3/045
Inventor 刘志刚吕洋
Owner SOUTHWEST JIAOTONG 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