Neural networks estimation of truck static weights by fusing weight-in-motion data

Mangeas, Morgan; Glaser, Sébastien; Dolcemascolo, Vittorio

doi:10.1109/icif.2002.1021190

Cited by 10 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• calibration procedure and frequency of system calibration [1,9,8,9,11,14], • algorithm used for estimating static load and gross vehicle weight [13].…”

Section: Literature Reviewsmentioning

confidence: 99%

Geometric Optimization of a Beam Detector for a Wim System

Nieoczym¹,

Drozd²,

Wójcik³

2018

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

Weigh-in-Motion (WIM) systems are designed for weighing vehicles driving across a measurement site. Because during measurements the vehicle has to come in physical contact with the components of the system, WIM systems always use built-in sensors installed in road pavement. Each WIM system consists of force sensors placed in one, two or even several lines, perpendicular to the direction of traffic. The idea behind WIM systems is to measure the dynamic loads that the wheels of a moving vehicle exert on the road surface and, on this basis, to estimate static wheel loads as well as gross vehicle weight.

show abstract

“…• calibration procedure and frequency of system calibration [1,9,8,9,11,14], • algorithm used for estimating static load and gross vehicle weight [13].…”

Section: Literature Reviewsmentioning

confidence: 99%

Geometric Optimization of a Beam Detector for a Wim System

Nieoczym¹,

Drozd²,

Wójcik³

2018

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

show abstract

“…Artificial neural network (ANN) algorithm, using training samples to construct input-output mapping model, is able to avoid complicated mathematical modeling process and realize approximation of nonlinear function with arbitrary precision. [17][18][19] Shamseldin et al 20 used ANN to fuse the measurements of six sensors, and then the mean weighing errors were less than 2.96%. Gonza´lez et al 21 used ANN to perform the WIM fusion experiment on seven sensors, and then the weighing accuracy remained at A (5) level with increase of noise content.…”

Section: Introductionmentioning

confidence: 99%

Multiple optimized support vector regression for multi-sensor data fusion of weigh-in-motion system

Liu

Feng

Chen

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Weigh-in-motion is an efficient way to manage overload vehicles, and usually utilizes multi-sensor to measure vehicle weight at present. To increase generalization and accuracy of support vector regression (SVR) applied in multi-sensor weigh-in-motion data fusion, three improved algorithms are presented in this paper. The first improved algorithm divides train samples into two sets to construct SVR1 and SVR2, respectively, and then test samples are distributed to SVR1 or SVR2 based on the nearest distance principle. The second improved algorithm calculates the theoretical biases of two training samples closeted to one test sample, and then obtains the bias of the test sample by linear interpolation method. The third improved algorithm utilizes the second improved algorithm to realize adaptive adjustment of biases for SVR1 and SVR2. Five vehicles were selected to conduct multi-sensor weigh-in-motion experiments on the built test platform. According to the obtained experiment data, fusion tests of SVR and three improved algorithms are performed, respectively. The results show that three improved algorithms gradually increase accuracy of SVR with fast operation speed, and the third improved algorithm exhibits the best application prospect in multi-sensor weigh-in-motion data fusion.

show abstract

“…These strain sensors were mounted on the lower surface of the beam of a bridge. An artificial neural network (ANN) was used to fuse the measurements of multiple sensors to estimate the static weight [19,20,21,22]. Ryszard Sroka et al [23] used 16 polymer piezoelectric load sensors, 8 inductive loop sensors, and 8 temperature sensors in their MS-WIM.…”

Section: Introductionmentioning

confidence: 99%

Tire–Pavement Contact-Aware Weight Estimation for Multi-Sensor WIM Systems

Jia

Lin

2019

Sensors

View full text Add to dashboard Cite

Accurately estimating the weight of a moving vehicle at normal speed remains a challenging problem due to the complex vehicle dynamics and vehicle–pavement interaction. The weighing technique based on multiple sensors has proven to be an effective approach to this task. To improve the accuracy of weigh-in-motion (WIM) systems, this paper proposes a neural network-based method integrating identification and predication. A backpropagation neural network for signal classification (BPNN-i) was designed to identify ideal samples acquired by load sensors closest to the tire-pavement contact area. After that, ideal samples were used to predict the gross vehicle weight by using another backpropagation neural network (BPNN-e). The dataset for training and evaluation was collected from a multiple-sensor WIM (MS-WIM) system deployed in a public road. In our experiments, 96.89% of samples in the test set had an estimation error of less than 5%.

show abstract

Neural networks estimation of truck static weights by fusing weight-in-motion data

Cited by 10 publications

References 2 publications

Geometric Optimization of a Beam Detector for a Wim System

Geometric Optimization of a Beam Detector for a Wim System

Multiple optimized support vector regression for multi-sensor data fusion of weigh-in-motion system

Tire–Pavement Contact-Aware Weight Estimation for Multi-Sensor WIM Systems

Contact Info

Product

Resources

About