A station freight train carriage abnormity and fault automatic identification method

A freight train and fault identification technology, which is applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as fault misdetection, fault missed detection, and recording errors

Pending Publication Date: 2021-03-09
WUHAN UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at identifying abnormalities and faults of freight trains by manually checking images, manually recording information such as train numbers, vehicle types, and faults, which is prone to missed detection of faults, false detections of faults, recording errors and efficiency caused by manual identification. In order to solve the problems of inferiority, an automatic identification method for the abnormality and failure of freight train carriages at the station is proposed

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
  • A station freight train carriage abnormity and fault automatic identification method
  • A station freight train carriage abnormity and fault automatic identification method
  • A station freight train carriage abnormity and fault automatic identification method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0120] Step 1: Use a high-speed line-scan camera to capture high-resolution images on the left, high-resolution images on the right, and high-resolution images on the top of each carriage to construct high-resolution image data of the carriages without stopping the freight train Set, the high-resolution image of the carriage is scaled down to an appropriate ratio using the linear interpolation method, and then cut into four overlapping image blocks of the same size, and the image samples of the carriage containing faults are screened out from all the image blocks. The faulty car image samples are used to construct the car fault image data set;

[0121] The compartment fault image data set described in step 1 is:

[0122] {train s (m, n), s ∈ [1, S], m ∈ [1, M], n ∈ [1, N]}

[0123] Among them, train s (m, n) represents the pixel information of the mth row and nth column of the sth carriage fault image data set in the carriage fault image data set, S=18031 represents the num...

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 station freight train carriage abnormity and fault automatic identification method. The method includes, firstly, using a high-speed linear array camera for shooting images ofthe left side, the right side and the top of each carriage to construct a carriage image data set under the condition that a freight train does not stop, and forming a carriage fault image training set after preprocessing operations such as cutting, screening and manual labeling; then constructing a train carriage abnormal fault identification network and a loss function, inputting carriage faultimages in the training set, and optimizing the identification network through a gradient descent algorithm; during testing, inputting a to-be-identified image into the optimized train compartment abnormal fault identification network to obtain a preliminary identification result; and carrying out confidence filtering, non-maximum suppression and other post-processing operations to obtain a finalidentification result. The invention has the advantages of being high in recognition rate, high in speed, high in real-time performance and the like, the functions of monitoring the running state of the train and automatically giving an alarm for abnormalities or faults are achieved, and the intelligent level of railway transportation is further improved.

Description

technical field [0001] The invention relates to the field of intelligent supervision of railway traffic safety, in particular to an automatic identification method for abnormal failures of freight train carriages at stations. Background technique [0002] Aiming at the safety problems of railway wagons during operation, some safety monitoring systems have been put into use. Among them, the most widely used is the railway vehicle operation safety monitoring system, which is mainly composed of five subsystems, namely THDS (intelligent detection system for vehicle axle temperature), TPDS (trackside dynamic monitoring system for vehicle operation quality), TADS (vehicle rolling bearing Faulty Trackside Acoustic Diagnosis System), TFDS (Truck Faulty Trackside Image Detection System), and TCDS (Passenger Car Running Safety Monitoring System). Infrared technology, acoustics, mechanics, image acquisition, computer and other technologies are used to collect relevant data during trai...

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
CPCG06V20/00G06V20/52G06F18/241G06F18/214
Inventor 刘清刘同财李雪琪谢兆青王靖博郭建明
Owner WUHAN UNIV OF 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap