Weigh-in-motion System Research Articles

Addressing wander effect in vehicle weight monitoring: An advanced hybrid weigh-in-motion system integrating computer vision and in-pavement sensors

The paper addressed the challenges of the two main weigh-in-motion (WIM) systems through a hybrid WIM system, which combines embedded in-pavement sensor systems and computer vision to enhance accuracy while minimizing human intervention. To establish a cost-effective system, this study employed a standard camera integrated with computer vision technique to improve the precision of identifying wheel location and automatically adjust distance calibration, particularly in response to variations in camera angle. In addition, the system achieved real-time vehicle weight detection efficiently by addressing the vehicle wander effect concerns of the in-pavement sensors through camera using computer vision. The system can achieve weight accuracy notably exceeding ASTM 1318E-09 standards, with over 90% accuracy for distances below 0.1 m, demonstrating its potential value in assisting traffic analysis and pavement maintenance by offering real-time, accurate WIM measurements at a low cost for instrumentation.

Weigh-in-Motion Site for Type Approval of Vehicle Mass Enforcement Systems in Poland.

The need to protect road infrastructure makes it necessary to direct the mass enforcement control of motor vehicles. Such control, in order to fulfil its role, must be continuous and universal. The only tool currently known to achieve these goals are weigh-in-motion (WIM) systems. The implementation of mass enforcement WIM systems is possible only if the requirements for their metrological properties are formulated, followed by the implementation of administrative procedures for the type approval of WIM systems, rules for their metrological examination, and administrative regulations for their practical use. The AGH University of Krakow, in cooperation with the Central Office of Measures (Polish National Metrological Institute), has been conducting research in this direction for many years, and, now, as part of a research project financed by the Ministry of Education and Science. In this paper, we describe a unique WIM system located in the south of Poland and the results of over two years of our research. These studies are intended to lead to the formulation of requirements for metrological legalisation procedures for this type of system. Our efforts are focused on implementing WIM systems in Poland for direct mass enforcement. The tests carried out confirmed that the constructed system is fully functional. Its equipment with quartz and bending plate load sensors allows for the comparison of both technologies and the measurement of many parameters of the weighed vehicle and environmental parameters affecting weighing accuracy. The tests confirmed the stability of its metrological parameters. The GVW maximal measurement error does not exceed 5%, and the single axle load maximal measurement error does not exceed 12%. The sensors of the environmental parameters allow for the search for correlations between weighing accuracy and the intensity of these parameters.

Assessing Vehicle Wandering Effects on the Accuracy of Weigh-in-Motion Measurement Based on In-Pavement Fiber Bragg Sensors through a Hybrid Sensor-Camera System.

Weigh-in-motion (WIM) systems are essential for efficient transportation and monitoring parameters such as vehicle number, speed, and weight to ensure regulatory compliance and enhance road safety. Recently, WIM measurements using the Glass Fiber Reinforced Polymer Fiber Bragg Grating (GFRP-FBG) sensors have shown robustness and effectiveness. However, the accuracy of weight evaluation using the WIM systems based on GFRP-FBG sensors can be significantly influenced by the vehicle-wandering effect, which introduces uncertainties in wheel position determination and weight calculations. This paper assessed the impact of vehicle wandering on the accuracy of a WIM measurement system based on GFRP-FBG sensors by utilizing a new hybrid sensor-camera system that integrates roadside cameras and in-pavement GFRP-FBG sensors. The detailed methodology and framework of the developed hybrid system are introduced, followed by field testing on Highway I-94 in the United States. The field testing results indicate that by using the hybrid system, the wheel load detection accuracy of the WIM system based on GFRP-FBG sensors can be controlled to be a Type I or Type III WIM according to the ASTM 1318E-09 standard, with an average accuracy ranging from 87.83% to 94.65%. At the same time, when the wander distance is less than or equal to 9 cm, the developed WIM system proves to be very cost-effective as it only comprises two GFRP-FBG sensors, one temperature FBG sensor, and one camera. These findings indicate the practical potential to enhance the accuracy of WIM systems based on GFRP-FBG sensors designed for highways for low-coast, reliable, and accurate measurements by addressing vehicle wandering effects.

Use of axle load spectra (ALS) for estimating calibration drift in weigh-in-motion (WIM) systems

The road agencies collect and submit weigh-in-motion (WIM) data to the Federal Highway Administration as part of their traffic monitoring program. Therefore, the WIM data should be precise and accurate. One way to evaluate WIM measurement errors is by using the test truck data collected immediately before and after equipment calibration. The limitation of this approach is that the data represent a snapshot in time and may not represent a long-term WIM site performance. This paper presents an approach for estimating WIM system accuracy based on axle load spectra attributes (normalized axle load spectra (NALS) shape factors). This alternative approach allows for characterizing temporal changes in WIM data consistency. The WIM error data collected before and after calibration were related to Class 9 NALS shape factors in the proposed methodology. This paper aims to determine WIM system errors based on axle loading without physically performing WIM equipment performance validation using test trucks. The presented methodology can be used to estimate systematic errors (drift) in the WIM system at any point in time after the equipment calibration. This approach can help highway agencies select optimum timings for routine maintenance and calibration of WIM equipment without compromising its accuracy. The results show that the WIM accuracy for the single axle (SA) and tandem axle (TA) can be estimated with SA and TA NALS shape factors with an acceptable degree of error for bending plate to quartz piezo sensors. Examples are included to demonstrate the application and significance of the developed models.

Monitoring vehicles with permits and that are illegally overweight on bridges using Weigh-In-Motion (WIM) devices: A case study from Brescia

Bridges are amongst the most vulnerable elements of road networks. Since vehicles with permits and that are illegally overweight can pose a threat to bridge safety, implementation of monitoring systems for these vehicles has become mandatory. Weigh-In-Motion (WIM) systems are an efficient weight-enforcement solution because they collect data on vehicular mass and other parameters in real time. However, installation and maintenance costs frequently hinder a widespread operational use of WIM systems. Thus, while WIM devices are widespread in America and Asia, they have not yet been applied broadly in Europe. Additionally, the relationships among Gross Vehicle Mass (GVM) and other vehicular characteristics have only been investigated in a fragmentary manner. This real-world case study adopted a data set of 14,800+ overweight vehicles in heavily industrialised northern Italy based on two-months of raw data from WIM devices to: (i) investigate the probability density function on the main characteristics of overweight vehicles, and (ii) to provide Road Authorities (RAs) with a Multiple Linear Regression (MLR) model to predict overweight vehicles’ GVM in a more cost-effective way than placing WIM systems on each road segment with bridges. Probability density functions revealed the existence of different vehicle typologies, including lorries with permits and that are illegally overweight, whereas inferential analysis showed MLR’s high performance in predicting vehicles’ GVM. Minimum axle distance and total axle number were factors that had greater positive effects on the predicted GVM respectively. Conversely, by increasing vehicles’ width and length, a reduction in GVM was predicted. These findings could help support practitioners, RAs, and governments to implement rational and less resource consuming administration policies for their bridge assets.

Empirical distributions of traffic loads from one year of weigh-in-motion data

In the state-of-the-art of structural engineering the actions for design or assessment of bridges should derive from a probabilistic (i.e., frequentist) characterization of the loads. Data from weigh-in-motion (WIM) systems can inform stochastic models for traffic loads. However, WIM is not widespread, and data of this kind are scarce in the literature and often not recent. Due to structural safety reasons, the 52 km long A3 highway in Italy, connecting the cities of Naples and Salerno, has been equipped with a WIM system which has been operational since the beginning of 2021. The system’s measurements of each vehicle transiting over the WIM devices, impede overloads on the many bridges featured in the transportation infrastructure. By the time of this writing the WIM system has seen one year of uninterrupted operation, collecting more than thirty-six million datapoints in the meantime. This short paper presents and discusses these WIM measurements, deriving the empirical distributions of traffic loads and making the original data available for further research and applications.

Accuracy Maps of Weigh-In-Motion Systems for Direct Enforcement

The need to protect road infrastructure and the environment, as well as to increase the safety of road users and to ensure fair conditions of competition in road transport, requires an increase in the efficiency of the elimination of overloaded vehicles from road traffic. The replacement of “manual” vehicle control (carried out by inspectors of the relevant services) by automatic control can ensure that these are highly effective. Such control can be implemented directly on the basis of weighing results obtained from weigh-in-motion (WIM) systems. The high sensitivity of WIM systems to various interfering factors is an obstacle to the full implementation of this goal. This paper presents a concept for accuracy maps determined for direct enforcement WIM systems. The use of such maps allows for the minimization of the probability of an error consisting in classifying a normative vehicle as an overloaded one.

Obstacles to the Application of Electronic Weigh in Motion Tickets

Vehicle load measurement tools can be carried out dynamically without the need to stop the vehicle first with the Weigh In Motion system. This writing aims to find out exactly what is related to the Electronic Ticketing System (E-TLE) in Kulon Progo. Based on this, this research study aims to determine the increase in the performance of the police and the Ministry of Transportation in implementing e-tickets and solving cases of criminal acts of traffic violations. This type of research is field research, namely a form of research that aims to reveal the meaning given by society to their behavior and reality. The research method used is a qualitative method, which is a research approach that reveals certain social situations by describing reality correctly. The results of this study can be seen that the performance of the traffic police and the Ministry of Transportation in disseminating e-tickets includes explaining the procedure for measuring vehicle loads using weigh-in-motion (WIM). The data that can be obtained from this measurement is the total weight of the vehicle, the weight of the vehicle axle, the type of vehicle, the speed of the vehicle, and the distance between the vehicle axles has not been running in accordance with applicable and optimal procedures.

Self-powered weigh-in-motion system combining vibration energy harvesting and self-sensing composite pavements

Overloaded vehicles are the primary cause of accelerated degradation of road infrastructures. In this context, although weigh-in-motion (WIM) systems are most efficient to enforce weight regulations, current technologies require costly investments limiting their extensive implementation. Recent advances in multifunctional composites enabled cost-efficient alternatives in the form of smart pavements. Nevertheless, the need for a stable power supply still represents a major practical limitation. This work presents a novel proof-of-concept self-sustainable WIM technology combining smart pavements and vibration-based energy harvesting (EH). The feasibility of piezoelectric bimorph cantilevered beams to harvest traffic-induced vibrations is firstly investigated, followed by the demonstration of the proposed technology under laboratory conditions. The main original contributions of this work comprise (i) the development of a new self-powered data acquisition system, (ii) a novel approach for the fabrication and electromechanical testing of the piezoresistive composite pavement, and (iii) laboratory feasibility analysis of the developed EH unit to conduct traffic load identification through electrical resistivity measurements of the smart pavement. While the presented results conclude the need for dense EH networks or combinations of different EH technologies to attain complete self-sustainability, this work represents an initial feasibility evidence paving the way towards the development of self-powered low-cost WIM systems.

Performance assessment of a bridge WIM system using optical strands

A bridge Weigh-in-Motion (WIM) system consists in estimating gross vehicle weight while they cross a bridge, without any sensor in the pavement. It comprises a set of sensors installed under the bridge deck and in bridge elements, and dedicated data analysis tools, allowing to assess the moving loads from the mechanical response of the bridge structure. In this paper, a novel Bridge WIM solution is described, which uses a low number of optical strands strain sensors, and has been implemented on 13 bridges worldwide. The accuracy of this system for gross vehicle weight is assessed on two bridges in France and Italy. The system met the accuracy class A(5) of the COST323 specifications on one bridge. Moreover, the data collected by the system is useful also for the structural health monitoring of the bridge.

Weigh-in-Motion System Based on an Improved Kalman and LSTM-Attention Algorithm

A weigh-in-motion (WIM) system continuously and automatically detects an object's weight during transmission. The WIM system is used widely in logistics and industry due to increasing labor and time costs. However, the accuracy and stability of WIM system measurements could be affected by shock and vibration under high speed and heavy load. A novel six degrees-of-freedom (DOF), mass-spring damping-based Kalman filter with time scale (KFTS) algorithm was proposed to filter noise due to the multiple-input noise and its frequency that is highly coupled with the basic sensor signal. Additionally, an attention-based long short-term memory (LSTM) model was built to predict the object's mass by using multiple time-series sensor signals. The results showed that the model has superior performance compared to support vector machine (SVM), fully connected network (FCN) and extreme gradient boosting (XGBoost) models. Experiments showed this improved deep learning model can provide remarkable accuracy under different loads, speed and working situations, which can be applied to the high-precision logistics industry.

Effect of static weight errors on Weigh-in-Motion (WIM) system accuracy

Weigh-in-Motion (WIM) systems require calibration to account for site conditions and regular calibrations (once or twice a year) to yield accurate and consistent loading data. Generally, the WIM system calibration compares the WIM weights with the reference static weights. However, the ground truth (static weights) accuracy may not be known and is uncertain. WIM protocols (ASTM 1318-09 and COST-323) specify the static error thresholds. Therefore, it is crucial to consider the errors induced due to static weighing procedures during the WIM equipment calibration and pre-validation. This paper uses the long-term pavement performance (LTPP) high-quality WIM data to study the effect of static weight measurement errors on the performance of the WIM system. The data analyses address two key concerns (a) modeling gross vehicle weight (GVW) errors while accounting for errors in the static and WIM weights, and (2) quantifying the effect of static truck weight errors for a variety of WIM sites with varying performance levels. The results show that the static weight errors are more critical for the WIM sites marginally meeting the desired ASTM 1318-09 accuracy class. A 2% static error may not change the overall performance of a WIM site (ASTM accuracy class based on tolerance limits), especially the sites with negligible bias or significantly higher bias. However, the ASTM accuracy class can change from higher to lower for WIM sites with intermediate bias (3 to 7%), even with a 1% increase in static weight errors.

A new approach for varied speed weigh-in-motion vehicle based on smartphone inertial sensors

<p>Dynamic vehicle weight measuring, weigh-in-motion (WIM), is an important metric that can reflect significantly vehicle driving behaviour and in turn, it will affect both safety and traffic status. Several accurate WIM systems are developed and implemented successfully. These systems are using under road weighing sensor which are costly to implement. Moreover, it is costly and not very practical to embed a continuous weighing system in used cars. In this work, a low-cost varied-speed weigh-in-motion approach was suggested to continuously measuring vehicle load based on the response of smartphone sensors which is a reflection of vehicle dynamics. This approach can apply to any moving vehicle at any driving speed without the need for extra added hardware which makes it very applicable because smartphone is widely used device. The approach was tested through a six-trips experiment. Three capacities of load had been designed in this approach to be classified using a neural network classifier. The classification performance metrics are calculated and show an accuracy of 91.2%. This accuracy level is within error limits of existing WIM systems especially for high speed and proved the success of the suggested approach.</p>

Deep-Learning-Based Temporal Prediction for Mitigating Dynamic Inconsistency in Vehicular Live Loads on Roads and Bridges

Weigh-In-Motion (WIM) data have been collected by state departments of transportation (DOT) in the U.S. and are anticipated to grow as state DOTs expand the number of WIM sites in order to better manage transportation infrastructure and enhance mobility. Traditional approaches for monitoring the vehicle weight measured in WIM systems include conducting statistical tests between two datasets obtained from two calibration visits. Depending on the frequency of visits, these traditional approaches are ineffective or resource-demanding for identifying calibration needs. Excessive vehicle-weight drifts exceeding 10% are usually indicative of poor performance by WIM systems. However, it has been difficult to consistently monitor such performance due to the sheer amount of data. In Georgia, the number of WIM sites have expanded from 12 to 29 in the past 3 years. This paper proposes a deep-learning-based temporal prediction approach for modeling sequential data and monitoring the time-history of the live loads imposed on roads and bridges. In total, 29 WIM sites in Georgia are analyzed to examine the effectiveness of a proposed temporal prediction approach for evaluating observed live loads. This study finds that the Jensen–Shannon divergence method is more effective than statistical difference tests, particularly when screening for live load anomalies. It is concluded that a LSTM neural network is able to capture temporal dynamics underlying the sequential load patterns observed in the WIM data and serves as an effective model for consistently monitoring the performance of WIM systems over time.

Long‐term bridge performance assessment using clustering and Bayesian linear regression for vehicle load and strain mapping model

The weigh-in-motion (WIM) system and the structural health monitoring (SHM) system have been used as two separate modules playing different roles in bridge operation and providing different information for bridge maintenance. This study proposes a novel bridge safety condition assessment method that utilizes long-term monitoring data from the WIM system and the SHM system. The method uses the slope of the established vehicle load and vehicle-induced strain mapping model as the evaluation indicator for bridge condition assessment and early warning by clustering and Bayesian linear regression. The proposed method is verified with the continuous monitoring data of a concrete box girder bridge. The results show that the slope indicator of the mapping model changes with the variation of bridge performance, which is stable and can reflect the bridge state in time. The evaluation method can integrate the WIM system with the SHM system and evaluate the bridge health condition based on the correspondence between the two systems, which can make full use of the data.

Continuous Calibration Weigh-in-Motion System Using Static Weight Data

This paper presents an advanced approach for continuously calibrating weigh-in-motion (WIM) sorting systems using the static scale data generated by downstream truck inspection stations. It presents an automated closed-loop algorithm developed to accurately match vehicles at the two locations and use the data at the static weigh scale as the WIM calibration reference through a feedback algorithm. Calibration is carried out automatically by minimizing the error between WIM and static gross vehicle weight (GVW) measurements by vehicle class and speed. The large sample of vehicles involved in these calculations ensures high reliability in the calibration factors and the resulting accuracy in WIM measurements. The proof of concept is provided by analyzing data from eight multi-lane WIM systems in three States. It is demonstrated that the system can maintain indefinitely the accuracy of WIM systems in measuring GVW and axle loads without the need for periodic on-site calibrations involving test trucks.

Hierarchical methodology to evaluate the quality of disparate axle load data sources for pavement design

Axle load data are an essential input for pavement design, yet for most North American agencies, there is uncertainty about the quality of axle load data obtained from weigh-in-motion (WIM) systems, the applicability of these data for pavement design, and potential opportunities to integrate axle load data from disparate sources. This article presents a novel and practical methodology to evaluate the quality of axle load data from WIM systems and roadside weigh scales through a series of hierarchical analyses designed to test data validity. When applied using data from Manitoba, Canada, the methodology quantified the uncertainty of axle loads measured at the weigh scales and piezo-quartz WIM, concluding that both could be used for pavement design applications. Data collected at piezo-polymer WIM sites exhibited poorer data validity; however, application of site-specific temperature correction factors significantly improved data validity at these sites. The article describes how other data quality dimensions, including spatial coverage, temporal coverage, and long-term data availability, could be considered when determining the suitability of disparate axle load data sources for pavement design. Application of the methodology enables a pragmatic evaluation of the quality and limitations of commonly-available axle load data, revealing uncertainties and data needs relevant for pavement design practice. • Hierarchical methodology was used to evaluate disparate axle load data sources. • Truck-pairing revealed reasonableness of piezo-quartz weigh-in-motion (WIM) data. • Temperature corrections improved data quality at piezo-polymer WIM sites. • Static weigh scales produce quality data but labor-intensive sampling is required. • Beyond validity, data suitability depends on temporal and spatial coverage.

Research on Weigh-in-Motion Algorithm of Vehicles Based on BSO-BP.

Weigh-in-motion (WIM) systems are used to measure the weight of moving vehicles. Aiming at the problem of low accuracy of the WIM system, this paper proposes a WIM model based on the beetle swarm optimization (BSO) algorithm and the error back propagation (BP) neural network. Firstly, the structure and principle of the WIM system used in this paper are analyzed. Secondly, the WIM signal is denoised and reconstructed by wavelet transform. Then, a BP neural network model optimized by BSO algorithm is established to process the WIM signal. Finally, the predictive ability of BP neural network models optimized by different algorithms are compared and conclusions are drawn. The experimental results show that the BSO-BP WIM model has fast convergence speed, high accuracy, the relative error of the maximum gross weight is 1.41%, and the relative error of the maximum axle weight is 6.69%.

Methodological Study on the Influence of Truck Driving State on the Accuracy of Weigh-in-Motion System

The weigh-in-motion (WIM) system weighs the entire vehicle by identifying the dynamic forces of each axle of the vehicle on the road. The load of each axle is very important to detect the total weight of the vehicle. Different drivers have different driving behaviors, and when large trucks pass through the weighing detection area, the driving state of the trucks may affect the weighing accuracy of the system. This paper proposes YOLOv3 network model as the basis for this algorithm, which uses the feature pyramid network (FPN) idea to achieve multi-scale prediction and the deep residual network (ResNet) idea to extract image features, so as to achieve a balance between detection speed and detection accuracy. In the paper, spatial pyramid pooling (SPP) network and cross stage partial (CSP) network are added to the original network model to improve the learning ability of the convolutional neural network and make the original network more lightweight. Then the detection-based target tracking method with Kalman filtering + RTS (rauch–tung–striebel) smoothing is used to extract the truck driving status information (vehicle trajectory and speed). Finally, the effective size of the vehicle in different driving states on the weighing accuracy is statistically analyzed. The experimental results show that the method has high accuracy and real-time performance in truck driving state extraction, can be used to analyze the influence of weighing accuracy, and provides theoretical support for personalized accuracy correction of WIM system. At the same time, it is beneficial for WIM system to assist the existing traffic system more accurately and provide a highway health management and effective decision making by providing reliable monitoring data.

Development and Validation of a Weigh-in-Motion Methodology for Railway Tracks.

In railways, weigh-in-motion (WIM) systems are composed of a series of sensors designed to capture and record the dynamic vertical forces applied by the passing train over the rail. From these forces, with specific algorithms, it is possible to estimate axle weights, wagon weights, the total train weight, vehicle speed, etc. Infrastructure managers have a particular interest in identifying these parameters for comparing real weights with permissible limits to warn when the train is overloaded. WIM is also particularly important for controlling non-uniform axle loads since it may damage the infrastructure and increase the risk of derailment. Hence, the real-time assessment of the axle loads of railway vehicles is of great interest for the protection of railways, planning track maintenance actions and for safety during the train operation. Although weigh-in-motion systems are used for the purpose of assessing the static loads enforced by the train onto the infrastructure, the present study proposes a new approach to deal with the issue. In this paper, a WIM algorithm developed for ballasted tracks is proposed and validated with synthetic data from trains that run in the Portuguese railway network. The proposed methodology to estimate the wheel static load is successfully accomplished, as the load falls within the confidence interval. This study constitutes a step forward in the development of WIM systems capable of estimating the weight of the train in motion. From the results, the algorithm is validated, demonstrating its potential for real-world application.