Virtual Axle Detector based on Analysis of Bridge Acceleration Measurements by Fully Convolutional Network

07/08/2022
by   Steven Robert Lorenzen, et al.
0

In the practical application of the Bridge Weigh-In-Motion (BWIM) methods, the position of the wheels or axles during the passage of a vehicle is in most cases a prerequisite. To avoid the use of conventional axle detectors and bridge type specific methods, we propose a novel method for axle detection through the placement of accelerometers at any point of a bridge. In order to develop a model that is as simple and comprehensible as possible, the axle detection task is implemented as a binary classification problem instead of a regression problem. The model is implemented as a Fully Convolutional Network to process signals in the form of Continuous Wavelet Transforms. This allows passages of any length to be processed in a single step with maximum efficiency while utilising multiple scales in a single evaluation. This enables our method to use acceleration signals at any location of the bridge structure serving as Virtual Axle Detectors (VADs) without being limited to specific structural types of bridges. To test the proposed method, we analysed 3787 train passages recorded on a steel trough railway bridge of a long-distance traffic line. Our results on the measurement data show that our model detects 95 thus, 128,599 of 134,800 previously unseen axles were correctly detected. In total, 90 with a maximum velocity of v_max=56,3 m/s. The analysis shows that our developed model can use accelerometers as VADs even under real operating conditions.

READ FULL TEXT

page 2

page 5

page 7

research
11/24/2016

3D Fully Convolutional Network for Vehicle Detection in Point Cloud

2D fully convolutional network has been recently successfully applied to...
research
08/29/2016

Vehicle Detection from 3D Lidar Using Fully Convolutional Network

Convolutional network techniques have recently achieved great success in...
research
05/26/2020

How the planned V0 railway line would increase the resilience of the railway network of Hungary against attacks

The spatial distribution of the railway crossings on the river Danube in...
research
04/22/2021

Fully Convolutional Line Parsing

We present a one-stage Fully Convolutional Line Parsing network (F-Clip)...
research
03/07/2023

Optimal design of Piezoelectric Energy Harvesters for bridge infrastructure: Effects of Location and Traffic Intensity on Energy Production

Piezoelectric energy harvesters (PEHs) can be used as an additional powe...
research
09/04/2023

Deep Learning Overloaded Vehicle Identification for Long Span Bridges Based on Structural Health Monitoring Data

Overloaded vehicles bring great harm to transportation infrastructures. ...
research
06/09/2018

Fully Convolutional Networks with Sequential Information for Robust Crop and Weed Detection in Precision Farming

Reducing the use of agrochemicals is an important component towards sust...

Please sign up or login with your details

Forgot password? Click here to reset