Train dynamic weighing system and weighing method based on deep learning

A deep learning and train technology, applied in neural learning methods, weighing, biological neural network models, etc., can solve problems such as large amount of calculation, difficult to directly obtain analytical solutions, and difficult to realize real-time identification of moving train load parameters, etc. The effect of reducing the amount of calculation

Active Publication Date: 2020-05-12
SOUTHEAST UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The load identification of moving trains is a multi-body dynamics problem, involving multiple systems such as vehicles, wheels, rails, and bridges. Multiple systems are coupled to each other, and it is difficult to directly obtain an analytical solution
Scholars at home and abroad usually conduct research on the method of establishing accurate models based on multiple measured data a...

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
  • Train dynamic weighing system and weighing method based on deep learning
  • Train dynamic weighing system and weighing method based on deep learning
  • Train dynamic weighing system and weighing method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Train load identification involves multiple systems such as vehicles, wheels and rails, and railway bridges, and multiple systems are coupled with each other. Aiming at the characteristics of difficult real-time identification of load parameters of moving trains and many environmental factors, the present invention proposes a dynamic train weighing method based on deep learning to realize complex nonlinear modeling of railway bridge structural response, bridge temperature field and train load parameters. Then, the train load parameters are identified in real time based on the structural response of the railway bridge under the train load.

[0038] The train dynamic weighing method based on deep learning proposed by the present invention mainly includes a sensor system, a training stage and a prediction stage, such as Figure 1-3 shown. The sensor system includes trigger sensors, ultra-clear high-speed image acquisition systems and bridge temperature acquisition systems...

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 train dynamic weighing system and a weighing method based on deep learning. The method comprises the steps of correcting a bridge finite element model in real time based on actually measured bridge structure response information; considering the train-rail-bridge coupling effect and the bridge temperature field, and calculating bridge structure response data under different train load effects; then, training a neural network model by taking the response data and the vehicle speed as input data and taking the train weight, the axle load and the axle distance as outputdata, and verifying the accuracy of a training result based on the bridge structure response data under the known train load effect; and finally, according to the image acquisition instruments at thetwo ends of the bridge, based on a multi-target tracking algorithm, identifying the train speed and the structural response in real time, inputting the train speed and the structural response into theneural network model, and calculating other train load parameters. According to the method, the train load parameters can be quickly and effectively identified, and reference is provided for railroadbridge operation management.

Description

Technical field: [0001] The invention relates to an intelligent train load identification method using a neural network, which is suitable for automatic identification of moving train load parameters based on the structural response of railway bridges, and specifically relates to a train dynamic weighing system and weighing method based on deep learning. Background technique: [0002] Railway is the backbone and one of the main modes of transportation in my country's comprehensive transportation system. Railway bridges, especially long-span railway bridges, as key node projects on railway lines, are the core of railway construction and the key to promoting north-south communication and balanced development between east and west. An important link plays an extremely important role in promoting the coordinated and rapid development of the national economy. But it is worth noting that the construction of my country's railway bridges began in the 1950s, and most of them are facin...

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): G06F30/23G06F119/14G06F119/08G06N3/04G06N3/08G01G19/04
CPCG06N3/08G01G19/045G06N3/045
Inventor 王浩祝青鑫
Owner SOUTHEAST UNIV
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