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

Steel rail damage determination method and determination system based on convolutional neural network

A technology of convolutional neural network and determination method, which is applied in the field of rail damage determination method and determination system based on convolutional neural network, which can solve problems such as low efficiency and large manual investment, and achieve the effect of ensuring safety and reliability

Pending Publication Date: 2022-08-05
北京洞微科技发展有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the manual investment is large, the efficiency is low, and there are too many uncontrollable factors such as missed judgments.

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
  • Steel rail damage determination method and determination system based on convolutional neural network
  • Steel rail damage determination method and determination system based on convolutional neural network
  • Steel rail damage determination method and determination system based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The structured data of the probe channel is formed after training on the raw multi-dimensional time-series rail data.

[0044] S111 , after screening the original multi-dimensional time series rail data, artificially mark the support segment for the data type.

[0045] Wherein, in step S111, after screening the original multi-dimensional time series rail data, a sliding window of 60 steps is used to manually mark the data type.

[0046] The support segment annotation types include: support reinforcement position, support aluminothermic welding position, support base metal position, support switch position, support tip rail position, and support noise position.

[0047] S112. Perform matrix processing on the artificially marked support bit segment data, and form structured data of the probe channel after processing and processing through one-hot encoding.

[0048] The original multi-dimensional time series rail data is the rail data collected by the rail flaw detection ...

Embodiment 2

[0050] S11. After inferring the original multi-dimensional time series rail data, the structured data of the probe channel is formed.

[0051] S111. After expanding the original multi-dimensional time series rail data, filter out invalid data, and perform fixed-length interception on the retained valid data;

[0052] S112 , performing matrix processing on the intercepted fixed-length data, and forming structured data of the probe channel after processing and processing through one-hot encoding.

[0053] The original multi-dimensional time series rail data is the rail data collected by the rail flaw detection trolley.

[0054] S12, the convolutional neural network analyzes the structured data of the probe channel to output current rail support position information corresponding to the current rail structure.

[0055] In step S12, the convolutional neural network is divided into a data augmentation layer, a feature construction layer and a target classification layer, including...

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 steel rail damage determination method based on a convolutional neural network, and the method comprises the steps: carrying out the preprocessing of original multi-dimensional time sequence steel rail data, and outputting the current steel rail supporting position information after the analysis of the convolutional neural network; after the current steel rail supporting position information is compared with the historical steel rail supporting position information, the consistent supporting position information is marked as the same signal mark, and the abnormal supporting position information is marked as the abnormal signal mark; and carrying out steel rail artificial injury logic summary content and expert experience analysis on the abnormal supporting position information marked as the abnormal signal mark to obtain a steel rail suspected injury signal and current steel rail supporting position suspected injury information corresponding to the steel rail suspected injury signal. The determination system applying the method comprises a current steel rail supporting position information acquisition part, a supporting position information signal marking part and a steel rail suspected damage information analysis part. According to the invention, more accurate and rapid steel rail flaw information can be provided for steel rail flaw detection.

Description

technical field [0001] The invention relates to a rail damage determination method, in particular to a rail damage determination method and determination system based on a convolutional neural network. Background technique [0002] With the rapid development of road traffic, rails are the basis of railway operation to ensure the safe and reliable operation of trains, which is an important task in the daily maintenance of railways. The internal damage of the rail is the most important part of the rail damage, and it is also the part that requires more labor to ensure the safe operation of the rail. [0003] The common situation of manual flaw detection is the missed judgment and misjudgment caused by human unstable factors in the flaw detection process, resulting in the occurrence of rail breakage events, ranging from trains that cannot run normally in a short time, and endangering the lives and property safety of train personnel. . [0004] At present, the main form of man...

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): G06T7/00G06V10/764G06V10/44G06V10/82G06N3/04G06N3/08
CPCG06T7/0004G06N3/08G06T2207/10004G06T2207/20081G06T2207/30136G06N3/045G06F18/2415
Inventor 杜晓岱安勇侯勇
Owner 北京洞微科技发展有限公司
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