Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Screw loosening and foreign matter detection method and system for train bottom bogie

A foreign object detection and bogie technology, which is applied in railway vehicle testing, neural architecture, computer components, etc., can solve the problems that the detection method or system detection accuracy, speed and efficiency cannot meet the needs of daily life, and achieve high safety, The effect of simple data acquisition and precise positioning

Inactive Publication Date: 2020-08-25
GUANGZHOU INST OF RAILWAY TECH +1
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the existing technology, due to the complexity of the train structure, the diversity of fault types, and the environmental factors of image acquisition, the existing detection methods or systems cannot meet the needs of people's daily life in terms of detection accuracy, speed, and efficiency.

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
  • Screw loosening and foreign matter detection method and system for train bottom bogie
  • Screw loosening and foreign matter detection method and system for train bottom bogie
  • Screw loosening and foreign matter detection method and system for train bottom bogie

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] A method for detecting loose screws and foreign matter of a bogie at the bottom of a train, comprising the following steps:

[0041] S1: collect the image of the bogie at the bottom of the train, and obtain a training data set, the training data set includes the category and position information of the fault point and foreign matter;

[0042] S2: Establish a fault recognition model according to the training data set;

[0043] S3: Input the image to be detected to the fault recognition model for detection, if a fault is detected, output the fault category and location and give an alarm.

[0044] The process of obtaining the training data set in the S1 is:

[0045] S101: converting the image of the bogie at the bottom of the train into a grayscale image to obtain a preprocessed image;

[0046] S102: Annotate the preprocessed image as a training data set, and the content of the annotation includes the category and location of the fault point and the foreign object.

[0...

Embodiment 2

[0075] like figure 2 As shown, on the basis of Example 1, the convolutional neural network outputs feature maps of three different dimensions of conv3, conv7, and conv11 layers respectively; the detection network includes a normalization module, three prediction modules and a maximum A value suppression module, the prediction module is used to respectively predict the feature maps of the conv3, conv7, and conv11 layers, and input the prediction result to the maximum value suppression module, and the maximum value suppression module outputs the final prediction result, Wherein, the normalization module is arranged between the output terminal of the conv3 and its corresponding prediction module, and is used to normalize the feature map output by the conv3.

[0076] Extract the feature maps of conv3, conv7, and conv11 for detection. The conv3 feature map, conv7 feature map, and conv11 feature map can be used to detect small, medium, and large objects respectively, and the detect...

Embodiment 3

[0111] On the basis of Embodiment 1 and Embodiment 2, a screw loosening and foreign matter detection system for a train bottom bogie includes: an image acquisition device, a fault identification device, a control device and an alarm device;

[0112] The image acquisition device is used to acquire the image of the bogie at the bottom of the train;

[0113]The fault identification device is used to generate a fault detection model based on the collected image of the bogie at the bottom of the train, detect the image to be detected through the fault detection model, and output an alarm signal to the controller when a fault is detected. device, and output the type and location of the fault;

[0114] The control device is used to control the alarm device to give an alarm.

[0115] The image acquisition device collects the image of the train bottom bogie, and the fault identification device generates a fault detection model according to the image of the collected train bottom bogie...

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 provides a screw loosening and foreign matter detection method and system for a train bottom bogie, and the method comprises the following steps: S1, collecting an image of the train bottom bogie, and obtaining a training data set which comprises the types and position information of a fault point and a foreign matter; S2, establishing a fault identification model according to the training data set; and S3, inputting a to-be-detected image to the fault identification model for detection, and if a fault is detected, outputting a fault type and a fault position and giving an alarm.When detection is needed, a to-be-detected image is input to the fault identification model, the fault identification model outputs positions and types of fault points and foreign matters and gives an alarm when detecting faults, the detection precision is high, the image is adopted for detection, contact type mechanical parameter acquisition is avoided, the safety is high, data acquisition is simple, accurate positioning is achieved, and the efficiency is high.

Description

technical field [0001] The invention relates to the field of motor vehicles, in particular to a method and system for detecting loose screws and foreign matter of a bogie at the bottom of a train. Background technique [0002] With the rapid development of China's high-speed railway, the construction of a train operation safety monitoring system is particularly important. The existing monitoring system lacks dynamic monitoring during operation. This will cause the train to travel sick for a long distance, increasing the probability of accidents. Due to the long-term transmission force and braking force of the train running at high speed, the key components of the train, such as the bogie, may loosen to varying degrees, causing safety hazards to continue high-speed operation. [0003] In terms of automatic detection of train operation faults, if the abnormality of key components is detected through manual inspection, it will consume a lot of manpower, material resources, an...

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): G06K9/00G06K9/62G06N3/04G01M17/08
CPCG01M17/08G06V20/52G06N3/048G06N3/045G06F18/24G06F18/214
Inventor 管春玲邱晓欢李恺曾子涛谭乐韬吴军
Owner GUANGZHOU INST OF RAILWAY TECH
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
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