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

TFDS fault automatic recognition method

A technology of automatic identification and fault discrimination, applied in character and pattern recognition, measuring devices, instruments, etc., can solve the problem of low efficiency and achieve the effect of strong robustness, high efficiency and robustness

Active Publication Date: 2016-12-14
BEIHANG UNIV
View PDF15 Cites 76 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] From the above analysis, it can be seen that the existing automatic fault identification methods are mainly based on manual feature extraction, these methods require a lot of engineering experience and prior knowledge, and need to design algorithms for different types of faults, usually inefficient

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
  • TFDS fault automatic recognition method
  • TFDS fault automatic recognition method
  • TFDS fault automatic recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0031] figure 1 It is a flow chart of the overall realization of the TFDS fault automatic identification method of the present invention, such as figure 1 As shown, the fault automatic identification method of the present invention comprises the following steps:

[0032] Step 11: Collect images, establish a training sample set and a test sample set, and make a training sample set annotation file, and crop and classify the target area to be detected for the training sample set.

[0033] The images collected by the dynamic detection system for fault images of railway freight cars (ie TFDS) are collected. The training sample set and the test sample set are randomly selected. The images in the test sample set are independent of the training sample set, and the images contained in the two have no intersection.

[0034] Make detailed anno...

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 a TFDS fault automatic recognition method. The method is formed by a two-stage cascaded convolution neural network model based on a deep learning theory: the first stage is a network model with multi-class fault region synchronous positioning, and with the combination of space mutual position relation constraint of multi-fault regions, synchronous and accurate positioning of the multi-fault target regions is realized; and the second stage is a fault determination network model, and determination of faults and non-faults for the regions located by the first stage is realized. According to the TFDS multi-class fault synchronous and automatic recognition method, the design of recognition methods for different faults is not needed, features are adaptively extracted through a learning training mode by the convolution neural network theory in deep learning, synchronous positioning and fault determination of multiple faults can be performed, and high effectiveness and high robustness are achieved.

Description

technical field [0001] The invention relates to the field of railway detection, in particular to an automatic fault identification method of a faulty rail edge image of a freight car. Background technique [0002] In order to promote the modernization of railways, improve the detection rate of train inspection faults, and reduce the labor intensity of train inspection personnel, the former Ministry of Railways vigorously promoted a series of dynamic image detection systems for train operation faults. At present, the dynamic fault detection system (TFDS) of freight trains has been promoted and used throughout the road. Multiple industrial cameras arranged on the track collect images of the sides and bottom of the running train, and transmit the images to the monitoring room through a dedicated network. server. In the monitoring room, train inspectors observe the collected images through the image playback terminal software to judge whether there is a fault. However, the TFD...

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): G01M13/00G01M17/08G06K9/62
CPCG01M13/00G01M17/08G06F18/217G06F18/214
Inventor 孙军华肖钟雯
Owner BEIHANG 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com