Unlock instant, AI-driven research and patent intelligence for your innovation.

High-speed rail overhead line system pipe cap automatic detection method based on deep learning technology

A deep learning and automatic detection technology, which is applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of relying on staff, low efficiency and accuracy of tube cap positioning and detection methods

Inactive Publication Date: 2019-11-22
SHIJIAZHUANG TIEDAO UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a high-speed rail catenary cap automatic detection method based on deep learning technology to solve the problems of low efficiency and accuracy of the existing cap positioning detection method and over-reliance on the experience of staff

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
  • High-speed rail overhead line system pipe cap automatic detection method based on deep learning technology
  • High-speed rail overhead line system pipe cap automatic detection method based on deep learning technology
  • High-speed rail overhead line system pipe cap automatic detection method based on deep learning technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described in further detail below in conjunction with the accompanying drawings, and those skilled in the art can realize the present invention from the contents disclosed in this specification.

[0031] The present invention uses images provided by the high-speed railway power supply safety detection and monitoring system (6C system) to construct a training set and a test set. The high-definition image data captured by the 4C device is massive, mostly at night, and the background is mostly black, so it is relatively simple and easy to detect. And the number of pipe caps on the catenary suspension device is fixed, which is 3, and its position is also fixed, all at the end of the wrist arm and the positioning pipe.

[0032] Selecting a suitable deep learning tool is an important condition to ensure the actual application effect of the catenary cap positioning and detection model. Comparing open source frameworks such as TensorFlow, PyTorch,...

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 a high-speed rail overhead line system pipe cap automatic detection method based on a deep learning technology, and the method comprises the following steps: a, collecting a high-speed rail overhead line system image, marking the position of a pipe cap in the image, and building a sample library of each state of the pipe cap; b, constructing a training set by using the labeled images, and constructing a test set by using the unlabeled images; c, under a TensorFlow framework, carrying out training by utilizing a Faster R-CNN algorithm based on VGG16, and establishing anoverhead line system pipe cap positioning and detecting model based on a deep learning technology; and d, importing the test set into the model for test verification. According to the method, the accuracy of identifying and positioning the small target object is very high, the problem that the accuracy and the running speed of a traditional image processing technology cannot be considered at thesame time is solved, and the high-accuracy positioning function of the contact network pipe cap is achieved.

Description

technical field [0001] The invention relates to the technical field of high-speed rail catenary cap detection, in particular to an automatic detection method for high-speed rail catenary caps based on deep learning technology. Background technique [0002] The failure of the key equipment of the high-speed railway catenary suspension system will have a huge impact on the stable operation of the train. Therefore, it is particularly important to find the faulty parts in time. Based on this, the China Railway Corporation has established the "High-speed Railway Power Supply Safety Detection and Monitoring System (6C System)", in which the catenary suspension state detection and monitoring device is the technical specification of the 4C device, including the implementation of high-precision imaging detection of the state of the catenary suspension components , involving fault detection of catenary geometric parameters and components in the suspension. [0003] The large-scale pr...

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): G06K9/00G06K9/62
CPCG06V20/10G06F18/214
Inventor 常宇健金格陈恩利王硕禾蔡承才
Owner SHIJIAZHUANG TIEDAO UNIV