WIM System Research Articles

Exploring Kriging metamodeling to alleviate speed reading dependence in Bridge Weigh-In-Motion predictions

Bridge Weigh-In-Motion (BWIM) systems can be installed and serviced on highway bridges to provide measurements of moving vehicle’s gross weight, axle load, axle separation, and so on, without interrupting traffic. This data can be used to provide information of the heavy traffic over the bridge to management. This article presents the application of Kriging metamodeling to BWIM through the simulation of traffic streams. The Kriging methodology, with its prediction of metamodel variance, allows for the strategic selection of vehicles to train the BWIM metamodel. The proposed approach extends the BWIM concept of influence area from response time histories to geometric input spaces from the strain response wave (RW). The simulated dynamic response of simply supported bridges in the US Interstate Highway System were performed using Finite Element Modeling (FEM) of moving loads, generating RWs captured in different sensor locations. Three independent input spaces based on geometric properties of the RWs are the input to train the Kriging metamodel of a defined training truck group. In this approach, the measurement of the vehicle speed is not needed as an improvement of traditional BWIM methods. The results show that the Kriging prediction can fulfill at least the Type II WIM Systems performance defined in the ASTM’s Standard, using a comparable number of training runs to the number of calibration runs defined in the standard.

Fiber Optic Sensor Based WIM System Innovation for Implementing Zero Over Dimension Overload

<p class="Abstract"><span lang="EN-US">Vehicles loaded with Over Dimension Overload (ODOL) cause damage to road infrastructure, traffic accidents, and endanger crossing transportation. ODOL vehicles also contribute to the death of people. This research focuses on characterizing the effect of moving loads on fiber optic light loss. Problem-solving approach through the optical fiber macrobending method. This research aims to be implemented in the WIM system concept. Macrobending comes from the weights contained in the body dump. The types of loading carried out are static and dynamic. Under dynamic loading, the speed variation is 0.1 m/s, 0.2m/s, and 0.3 m/s. The research results show that the greater the loading value, the greater the attenuation value of the optical fiber. This research applies to all three speed variations of the dummy dump truck, both front and rear wheels. Apart from that, the best sensitivity value is found at a speed variation of 0.1 m/s. The value is 2.029. This data can be used as a reference for the most recommended speed when a loaded vehicle passes through a fiber optic sensor-based WIM system.</span></p>

A multispectral vision-based machine learning framework for non-contact vehicle weigh-in-motion

The present study proposes an automated non-contact weigh-in-motion framework using multispectral vision and machine learning method, which provides an all-weather monitoring of heavy vehicles on transportation infrastructures. Multispectral based computer vision techniques consist of two steps, one is acquiring the tire deformation parameters from thermal imaging camera and the latter is obtaining the sidewall characters from the ordinary one. A novel edge detection algorithm is designed for thermal image-based tire deformation estimation. A general recognition model with well-established tire characters database for universal tire sidewall markings, such as non-standard fonts or non-text characters, curved markings or inverted markings, and is developed based on Efficient neural network (E-NET) and YOLOV5S methods. A machine learning-based model for estimating the various vehicles tire-roadway contact forces is established based on eXtreme Gradient Boosting (XGBoost). A database of different vehicles’ tires with a total of 1127 samples from 19 types of tires and 648 of laboratory datasets from common vehicles are collected to train the model. The Bayesian optimization is employed to capture the optimal model, and a hybrid training strategy including biased data is applied to update the model. An importance analysis for 11 features is conducted to validate the performance proposed model. The accuracy, feasibility, and effectiveness of the proposed method is carefully investigated by field experiments for trucks and sport utility vehicles under static and low-speed drive. A maximum of 5 % difference is witnessed by comparing the results with that of the traditional WIM system. The present method presents a cost-effective means with no sensors on structures for vehicle weighting, that demonstrates a great potential to implement in toll station, highway infrastructures as well as health monitoring of civil engineering fields.

Analysis of Secondary Influencing Factors for the WIM System Used in Overload Enforcement

Analysis of Secondary Influencing Factors for the WIM System Used in Overload Enforcement

Structural Bridge WIM Diagnostics

By combining the data collected from bridge WIM systems and structural sensors in real-time, infrastructure owners can gain invaluable insights into the condition of bridges and roads

ЕФЕКТИВНІСТЬ ЗАСТОСУВАННЯ СИСТЕМ WIM НА АВТОМОБІЛЬНИХ ДОРОГАХ

Introduction. The introduction to the paper highlights the general role of the weight control of motor vehicles on roads by WiM – methods (Wegh-in-Motion) in the assurance of the traffic safety and in the transportation infrastructure preservation. Problem statement. The issues of the paper concern the problems of implementation of contemporary technologies of the High-Speed WiM (HS-WiM) where the conditions of the measurements of the loads from the vehicle generate high measurement error. Purpose. The main goal of the paper is to perform an analytical review of methods of the weight control of vehicles and of competitive aspects of existing WiM technologies and also the analysis of the practice of WiM application. Results. The analytical reviewing led to the following results: it was revealed that the basic principle of WiM systems operation consists in determining the dynamic wheel/axle loading of a vehicle transmitted to the pavement; data thus obtained shall be used to reveal the overloading. Modern WiM systems give possibilities to obtain data concerning axle number, axle spaces, vehicle length and speed, axle (or wheel) dynamic loading, number of equivalents of standard axle loading, and also data regarding the traffic flow characteristics; it was concluded that WiM systems can be divided into two main types: the systems operating at low speed of a vehicle (up to 15 km/h, LS WiM) and those operating at steady speed of the traffic flow (up to 130 km/h, or high speed, HS WiM). LS WiM ensure the accuracy of the measurement in a range from 3 % to 5 % and belong to the methods of weight control of motor vehicles approved by the legal metrology as well as the static weighing does. HS WiM control is more sensitive to the external factors due to the effect of a vehicle dynamic and thus cannot assure the above stated accuracy of measurements, moreover, cannot assure the appropriate accuracy for the satisfactory number of trucks. HS WiM systems are not approved by the legal metrology; factors affecting the accuracy of measurements in HS WiM systems were analyzed. It was revealed that the effect of a vehicle dynamic on the measurement error can be mitigated assuring the compliance of the road pavement surface condition with the standard requirements mainly with those concerning pavement surface roughness.

Application of bridge weigh-in-motion system in bridge health monitoring: a state-of-the-art review

Bridge health monitoring (BHM) has grown as an essential component of the maintenance paradigm in any transportation network around the world. The mostly used visual inspection method has limitations such as inspector bias, inaccessibility in remote areas, need for human physical presence at the bridge location, etc. On the other hand, vibration-based BHM methods require artificial excitation to the bridge. This motivates researchers to explore potential alternatives for BHM. The bridge weigh-in-motion (B-WIM) system has emerged as a promising alternative with the potential to augment traditional BHM techniques. The advantages of B-WIM systems are durability, portability, easy installation, etc. In addition to weight estimation of passing vehicles, it provides other structural informations that are helpful for bridge assessment. It also overcomes the limitations of pavement-based WIM systems. Most importantly, a B-WIM system uses the same components as a standard BHM system, making BHM a by-product and economical compared to a standalone BHM system. With the development of B-WIM theory, recent researches have revealed the feasibility of B-WIM system for BHM. However, the applicability of the B-WIM system for BHM in any type of bridge and condition is limited. Through the fundamentals of B-WIM theory, this paper reviews the existing bridge response-based BHM methods that involved B-WIM algorithm. The findings are discussed in order to identify the remaining challenges and provide insight to the future aspects.

Intelligent Simulation Method of Bridge Traffic Flow Load Combining Machine Vision and Weigh-in-Motion Monitoring

Random traffic flow load (TFL) simulation is an important analysis method for bridge design and safety assessment, and accurate TFL modelling is a prerequisite for high-quality simulation. The existing TFL modelling methods almost all rely on the load data monitored by the weigh-in-motion system (WIM system). However, the WIM system has natural defects such as unsatisfactory measurement accuracy at low speed and the inability to measure vehicle lengths and transverse positions in the lane, limiting the improvement of TFL simulation accuracy. Regarding this, a TFL monitoring system that integrates the functions of machine vision and WIM system is developed in this paper. In this system, a deep learning method is applied, for the accurate detection of vehicles and wheels in the video, and the extraction of key parameters for TFL modelling based on detection results. According to the long-term monitoring value, statistical distributions of key parameters are determined, and then an intelligent TFL model is derived from the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Intelligent Driver Model</i> (IDM), considering the car-following behavior of vehicles. Correspondingly, this paper further suggests a TFL simulation method and achieves an accurate TFL simulation. A cable-stayed bridge is taken as an example to verify the feasibility of the method. The results show that, compared to the modelling and simulation methods that only rely on the WIM system, the proposed method not only reduces the measurement error of vehicle dimensions by nearly 4 times, but also performs higher resolution in time measurement. The proposed method effectively overcomes the shortcomings of existing schemes and has good application potential in engineering.

Effect of Weight in Motion Detection System on Road Enforcement Network of Hungary

After two years of legislative preparation, the introduction of National Dynamic Axle Weight Measurement System was done in 2018. More than 100 control points were deployed in Hungary. This paper aims to present a brief summary of the technological background of a large-scale integration of High Speed WIM systems, and their effect on road usage. Detailed statistical analyses of preliminary results were conducted. The introduction of vehicle in motion dynamic mass measurement system in Hungary had not caused significant changes in road usage in the investigated period on the investigated road segment. The ratio between nationality (domestic or foreign) of heavy road vehicles had not changed due to introduction of vehicle in motion dynamic mass measurement system.

Effect of Static Weight Errors on Weigh-in-Motion (Wim) System Accuracy

Effect of Static Weight Errors on Weigh-in-Motion (Wim) System Accuracy

Influence of Trajectory and Dynamics of Vehicle Motion on Signal Patterns in the WIM System.

This paper presents the analyses of the signals recorded by the main sensors of a WIM test station in the cases of abnormal runs (i.e., runs with the changes of trajectory or the dynamics of vehicle motion). The research involved strain gauges which are used for measuring the weight of vehicles, inductive loops, as well as piezoelectric sensors used, inter alia, to detect twin wheels and to determine where a vehicle passes through a station. Since the designers intend the station to be able to implement the direct enforcement function, the selection of runs deviating from the normative ones constitutes an important issue for the assessment of the measurement reliability. The study considered the location of the trajectory of the runs, the dynamics (acceleration/braking) and the trajectory changes. The change in the amplitude and the value of the signal recorded by the strain gauges as a function of the location (position) of the contact between sensor and tires is a noteworthy observation which indicates the need to monitor this parameter in automatic WIM systems. Other tests also demonstrated the influence of the analysed driving parameters on the recorded results. However, by equipping the WIM station with a set of duplicate strain gauges, the measurement errors of the gross weight and axle loads are normally within the accuracy limits of class A(5) stations. Only in the case of accelerating/decelerating, does the error in measuring the load of a single axle reach several per cent.

Bridges to Success

Install, measure and move: the importance of portability in WIM systems

METROLOGICAL REQUIREMENTS OF WEIGH-IN-MOTION SYSTEMS FOR VEHICLES

The article analyzes and proposes solutions for metrological support of weight information systems of road vehicles in motion, including the method of classification of WIM systems by purpose and accuracy classes, metrological requirements for them and control methods for testing and verification, as well as the main metrological risks for Weigh-in-motion systems for road vehicles and requirements for determining and calculating reliability.

Improvement of vehicle axle load test method based on portable WIM

An improved portable weigh-in-motion test method was proposed based on the polyvinylidene fluoride piezoelectric sensor. Four different kinds of installation method were compared and the optimal installation method was confirmed. The influence of vehicle speed on the accuracy of axle load was studied and result showed that the maximum relative error was less than 14% under the same pavement temperature with constant automatic adjustment factor. At the same vehicle speed, the integral value of axle load increased linearly with the increase of temperature and an improved axle load calculation method was proposed to reduce the influence of temperature. The self-developed portable WIM system was compared with a portable WIM product in the real road test. Result showed that the deviation of the two systems was less than 13% and most of the deviations were under 8%, which showed the self-developed system can meet the requirement of the real road test.

Development and Testing of a Railway Bridge Weigh-in-Motion System

This study describes the development and testing of a railway bridge weigh-in-motion (RB-WIM) system. The traditional bridge WIM (B-WIM) system developed for road bridges was extended here to calculate the weights of railway carriages. The system was tested using the measured response from a test bridge in Poland, and the accuracy of the system was assessed using statically-weighed trains. To accommodate variable velocity of the trains, the standard B-WIM algorithm, which assumes a constant velocity during the passage of a vehicle, was adjusted and the algorithm revised accordingly. The results showed that the vast majority of the calculated carriage weights fell within ±5% of their true, statically-weighed values. The sensitivity of the method to the calibration methods was then assessed using regression models, trained by different combinations of calibration trains.

Sensor Data Fusion in Multi-Sensor Weigh-In-Motion Systems.

In this paper, we present the results of a comparison of two estimators of the gross vehicle weight (GVW) and the static load of individual axles of vehicles. The estimators were used to process measurement data derived from Multi-Sensor Weigh-In-Motion systems (MS-WIM). The term estimator is understood as an algorithm according to which the dynamic axle load measurement results are processed in order to determine the static load. The result obtained is called static load estimate. As a measure of measurement uncertainty, we adopted the standard deviation of the static load estimate. The mean value and the maximum likelihood estimators were compared. Studies were conducted using simulation methods based on synthetic data and experimental data obtained from a WIM system equipped with 16 lines of polymer axle load sensors. We have shown a substantially lower uncertainty of estimates determined using the maximum likelihood estimator. The results obtained have considerable practical significance, particularly during long-term usage of multi-sensor WIM systems.

Increasing WIM Accuracy and System Robustness

Increasing WIM Accuracy and System Robustness

Reducing the urban pollution by integrating weigh-in-motion sensors into intelligent transportation systems. State of the art and future trends

This paper is a short review of Weigh-in-Motion systems used to determine the pollution of the smart cities. The E.U. legislation concerns about the level of pollution in the big cities and how this pollution can be reduced. The main objective of E.U. is to reduce the level of pollution, respectively CO2 emissions, until 2050 by 60% compared with 1990. Thus, a lot of articles provide new techniques for collecting data info from the WIM systems and use them for reducing the pollution from the cities. The main problem of the transportation is the overloading vehicles, which leads to accelerated wear of road infrastructure (wear increases in proportion to the fourth power ratio of the current load on the axle / standard load, which is 70kN). WIM sensors for interurban traffic are currently performing many other important functions as: estimation of the static load on the wheel, estimation of travel speed, identification of each type of vehicle, providing real-time data needed for intelligent transport systems. This paper presents how the levels of the pollution in some specific areas are influenced by the traffic jams and how we can avoid increasing of pollution.

Tackling Traffic Noise Levels with Effective WIM Systems

Traffic Technology InternationalVol. 2019, No. 3 Technology ProfilesTackling Traffic Noise Levels with Effective WIM SystemsKirk SteudleKirk SteudleSearch for more papers by this authorKirk SteudlePublished Online:20 Jan 2023https://doi.org/10.12968/S1356-9252(23)40217-1AboutSectionsView articleView Full TextPDF/EPUB ToolsAdd to favoritesDownload CitationsTrack CitationsPermissions ShareShare onFacebookTwitterLinked InEmail View article FiguresReferencesRelatedDetails 1 August 2019Volume 2019Issue 3ISSN (print): 1356-9252ISSN (online): 2397-5970 Metrics History Published online 20 January 2023 Published in print 1 August 2019 Information© MA Business Ltd.PDF download

Feasibility Study for Using Piezoelectric-Based Weigh-In-Motion (WIM) System on Public Roadway

Weigh-in-Motion system has been the primary selection of U.S. government agencies as the weighing enforcement for decades to protect the road pavement. In recent years, the number of trucks has increased by about 40% and in 2017, they travel 25% more annually than in 2016. The lack of the budget has slowed down the expansion of weighing enforcement to catch up with the growing workload of vehicle weighing. Unsupervised pavement section suffers more pavement damage and increased repairing cost. In this work, a piezoelectric material based WIM system (P-WIM) is developed. Such a system consists of several piezoelectric material disks that are capable of generating characteristic voltage output from passing vehicles. The axle loading of the vehicle can be determined by analyzing the voltage generated from the P-WIM. Compared to traditional WIM system, P-WIM requires nearly zero maintenance and costs 80% less on capital investment and less labor and effort to integrate. To evaluate the feasibility of this technology to serve as weighing enforcement on public roadways, prototype P-WIMs are fabricated and installed at a weigh station. The vehicle loading information provided by the weigh station is used to determine the force transmission percentage of the installed P-WIMs, which is an important parameter to determine the vehicles’ axle loading by generated voltage.