A filtering-based bridge weigh-in-motion system on a continuous multi-girder bridge considering the influence lines of different lanes

A real-time vehicle monitoring is crucial for effective bridge maintenance and traffic management because overloaded vehicles can cause damage to bridges,and in some extreme cases,it will directly lead to a bridge failure.Bridge weigh-in-motion(BWIM)system as a high performance and cost-effective technology has been extensively used to monitor vehicle speed and weight on highways.However,the dynamic effect and data noise may have an adverse impact on the bridge responses during and immediately following the vehicles pass the bridge.The fast Fourier transform(FFT)method,which can significantly purify the collected structural responses(dynamic strains)received from sensors or transducers,was used in axle counting,detection,and axle weighing technology in this study.To further improve the accuracy of the BWIM system,the field-calibrated influence lines(ILs)of a continuous multi-girder bridge were regarded as a reference to identify the vehicle weight based on the modified Moses algorithm and the least squares method.In situ experimental results indicated that the signals treated with FFT filter were far better than the original ones,the efficiency and the accuracy of axle detection were significantly improved by introducing the FFT method to the BWIM system.Moreover,the lateral load distribution effect on bridges should be considered by using the calculated average ILs of the specific lane individually for vehicle weight calculation of this lane.

Quick Weighing of Passing Vehicles Using the Transfer-Learning-Enhanced Convolutional Neural Network

Transfer learning could reduce the time and resources required by the training of new models and be therefore important for generalized applications of the trainedmachine learning algorithms.In this study,a transfer learningenhanced convolutional neural network(CNN)was proposed to identify the gross weight and the axle weight of moving vehicles on the bridge.The proposed transfer learning-enhanced CNN model was expected to weigh different bridges based on a small amount of training datasets and provide high identification accuracy.First of all,a CNN algorithm for bridge weigh-in-motion(B-WIM)technology was proposed to identify the axle weight and the gross weight of the typical two-axle,three-axle,and five-axle vehicles as they crossed the bridge with different loading routes and speeds.Then,the pre-trained CNN model was transferred by fine-tuning to weigh themoving vehicle on another bridge.Finally,the identification accuracy and the amount of training data required were compared between the two CNN models.Results showed that the pre-trained CNN model using transfer learning for B-WIM technology could be successfully used for the identification of the axle weight and the gross weight for moving vehicles on another bridge while reducing the training data by 63%.Moreover,the recognition accuracy of the pre-trained CNN model using transfer learning was comparable to that of the original model,showing its promising potentials in the actual applications.

Weighing axle weight of moving vehicle based on empirical mode decomposition

Dynanfic forces are the main factor that influences the axle weight measurement accuracy of moving vehicle. Empirical mode decomposition （EMD） is presented to separate the dynamic forces contained in the axle weight signal. The concept and algorithm of EMD are introduced. The characteristic of the axle weight signal is analyzed. The method of judging pseudo intrinsic mode function （pseudo-IMF） is presented to improve the weighing accuracy. Numerical simulation and field experiments are conducted to evaluate the performance of EMD. The result shows effectiveness of the proposed method. Maximum weighing errors of the front axle, the rear axle and the gross weight at the speed of 15 km/h or lower are 2.22%, 6.26% and 4.11% respectively.

Effect of Snow, Temperature and Their Interaction on Highway Truck Traffic

Based on statistical amount of traffic and weather data sets from three weigh-in-motion sites for the study period of from 2005 to 2009, permanent traffic counters and weather stations in Alberta, Canada, an investigation is carried out to study impacts of winter weather on volume of passenger car and truck traffic. Multiple regression models are developed to relate truck and passenger car traffic variations to winter weather conditions. Statistical validity of study results are confirmed by using statistical tests of significance. Considerable reductions in passenger car and truck volumes can be expected with decrease in cold temperatures. Such reductions are higher for passenger cars as compared to trucks. Due to cold and snow interactions, the reduction in car and truck traffic volume due to cold temperature could intensify with a rise in the amount of snowfall. For passenger cars, weekends experience higher traffic reductions as compared to weekdays. However, the impact of weather on truck traffic is generally similar for weekdays and weekends. Interestingly, an increase in truck traffic during severe weather conditions is noticed at one of the study sites. Such phenomenon is found statistically significant. None of the past studies in the literature have presented the possibility of traffic volume increases on highways during adverse weather conditions;which could happen due to shift of traffic from parallel roads with inadequate winter maintenance programs. It is believed that the findings of this study can benefit highway agencies in developing such programs and policies as efficient monitoring of passenger car and truck traffic, and plan for efficient winter roadway maintenance programs.

An Investigation on Safety Performance Assessment of Close-Following Behavior of Heavy Vehicle Using Empirical-Simulation Technique

One of the main causes of rear-end crashes is attributed to close-following and hazardous driving behavior. A study was conducted to investigate the close-following behavior of heavy vehicle under various heavy vehicle categories, travel speeds and gross vehicle weights (GVW). Investigation is based on data obtained from simulation and empirical observations. A safety performance assessment of close-following behavior of heavy vehicles by using empirical-simulation technique is proposed. The simulation, which incorporates vehicle dynamics, is to generate the minimum safe time gap (MSTG) for truck-following-car situations. MSTG is defined as the minimum time required by the following vehicle to decelerate and stop without hitting the leading vehicle when both leading and following vehicles apply the emergency brakes. Based on comparison between the actual time gap data and the MSTG, a safety performance assessment technique that considers vehicle type, vehicle braking characteristics, truck GVW and speed is proposed for truck-following-car situation.

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-inmotion(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 commonlyavailable axle load data,revealing uncertainties and data needs relevant for pavement design practice.

A practical multi-lane factor model of bridges based on multi-truck presence considering lane load disparities

Many bridge design specifications consider multi-lane factors(MLFs)a critical component of the traffic load model.Measured multi-lane traffic data generally exhibit significant lane disparities in traffic loads over multiple lanes.However,these disparities are not considered in current specifications.To address this drawback,a multi-coefficient MLF model was developed based on an improved probabilistic statistical approach that considers the presence of multiple trucks.The proposed MLF model and approach were calibrated and demonstrated through an example site.The model sensitivity analysis demonstrated the significant influence of lane disparity of truck traffic volume and truck weight distribution on the MLF.Using the proposed approach,the experimental site study yielded MLFs comparable with those directly calculated using traffic load effects.The exclusion of overloaded trucks caused the proposed approach,existing design specifications,and conventional approach of ignoring lane load disparity to generate comparable MLFs,while the MLFs based on the proposed approach were the most comprehensive.The inclusion of overloaded trucks caused the conventional approach and design specifications to overestimate the MLFs significantly.Finally,the benefits of the research results to bridge practitioners were discussed.