Highway Performance Research Articles

Unravelling incipient accidents: a machine learning prediction of incident risks in highway operations

PurposeSafety research has focused on drivers, pedestrians and vehicles, with scarce attention given to highway traffic officers (HTOs). This paper develops a robust prediction model which enables highway safety authorities to predict exclusive incidents occurring on the highway such as incursions and environmental hazards, respond effectively to diverse safety risk incident scenarios and aid in timely safety precautions to minimise HTO incidents.Design/methodology/approachUsing data from a highway incident database, a supervised machine learning method that employs three algorithms [namely Support Vector Machine (SVM), Random Forests (RF) and Naïve Bayes (NB)] was applied, and their performances were comparatively analysed. Three data balancing algorithms were also applied to handle the class imbalance challenge. A five-phase sequential method, which includes (1) data collection, (2) data pre-processing, (3) model selection, (4) data balancing and (5) model evaluation, was implemented.FindingsThe findings indicate that SVM with a polynomial kernel combined with the Synthetic Minority Over-sampling Technique (SMOTE) algorithm is the best model to predict the various incidents, and the Random Under-sampling (RU) algorithm was the most inefficient in improving model accuracy. Weather/visibility, age range and location were the most significant factors in predicting highway incidents.Originality/valueThis is the first study to develop a prediction model for HTOs and utilise an incident database solely dedicated to HTOs to forecast various incident outcomes in highway operations. The prediction model will provide evidence-based information to safety officers to train HTOs on impending risks predicted by the model thereby equipping workers with resilient shocks such as awareness, anticipation and flexibility.

Comparative analysis of macroscopic traffic models for evaluating shockwaves under lane closures on an urban highway using the LWR model

ABSTRACT Lane closure due to traffic crashes is a complex phenomenon that negatively affects the operational performance of highways and leads to secondary lane closures. The present study investigates the effects of shockwaves caused by a heavy vehicle run-off-road crash on a three-lane urban highway in Isfahan, Iran. Additionally, the study simulates the effects of lane closures on shockwaves and density using the Lighthill, Whitham, and Richards (LWR) theory and macroscopic traffic flow based on field data. An analysis of traffic flow models revealed that one-lane and two-lane closures reduce maximum flow by 29% and 61%, respectively, compared to normal conditions. The results showed that the minimum relative error (RE) for lane closures is associated with shockwave models based on the Underwood speed-density model, expanded using the Taylor series. Therefore, the shockwave model based on the Underwood model with Taylor series expansion outperforms other models.

Koopman theory meets graph convolutional network: Learning the complex dynamics of non-stationary highway traffic flow for spatiotemporal prediction

Reliable and accurate traffic flow prediction is crucial for the construction and operation of smart highways, supporting scientific traffic management and planning. However, accurately predicting spatiotemporal traffic flow in non-stationary and unprecedented traffic patterns scenarios, such as holidays and adverse weather conditions, remains a challenging task. Considering that (1) Koopman theory effectively captures the underlying time-variant dynamics of the non-stationary temporal sequence (2) Graph convolutional network (GCN) effectively extracts complex spatial dependencies, combining the strengths of both is a promising solution. Therefore, this paper proposes a spatiotemporal prediction network that integrates Koopman theory and GCN, named KoopGCN, for predicting non-stationary and inexperienced highway traffic flow. KoopGCN decomposes the input into time-invariant and time-variant components based on Fast Fourier Transform. The dual engine block consisting of KoopGCN InvarEngine and KoopGCN VarEngine is designed to predict two types of components separately. And the dual engine block also passes the residual to the next block for modeling. The experiment is conducted on real monitored highway data in Ningde City, Fujian Province, China. The results indicate that even if there is a significant distribution difference between the training and testing sets, KoopGCN can achieve accurate prediction, significantly outperforms state-of-the-art baselines.

Development of Motorway Horizontal Alignment Databases for Accurate Accident Prediction Models

The safe and efficient operation of highways minimizes the environmental impact, reduces accidents, and promotes the reliability of the transportation infrastructure, all in support of sustainable transportation. The horizontal alignment of highways holds particular importance as it directly impacts driver behavior, vehicle stability, and overall road safety. In many cases, highway inventory data held by infrastructure operators may contain inaccurate or outdated information. The accuracy of the variables used in crash prediction models eliminates possible bias in the variable estimators. This research proposes a methodology to obtain accurate horizontal geometric features from digital imagery based on the analysis of the planimetry, feature geolocation and centerline azimuth sequence. The reliability of the method is verified by means of numerical and statistical procedures. This methodology is applied to 150 km of motorway segments in Portugal. Although it is found that the geometric characteristics of most of the inventory segments closely matched the extracted alignments, very significant differences are found in some sections. The results of the proposed procedure are illustrated with several examples. Finally, the propagation of error in the determination of the geometric design independent variables in the fitting of the statistical models is discussed based on the results.

Evaluation of public private partnerships in highways

This paper reviews and evaluates four U.S. P3 toll highways, identifying their performance and common challenges. Contrary to the conventional wisdom that federal and state governments should fund highways, this paper argues that users should bear the cost for both efficiency and equity considerations. The shift from government investment and operation of highways to Public-Private Partnerships (P3) was driven by the lack of public funding, more productive competitive business practices, and the government's desire for upfront payments to fund other unrelated public projects. However, these justifiable public benefits were accompanied by significant problems. Highways were often leased for 35 to 75 years, depending on the total equity and loans of the private partner and various risk factors.

Urban Roadway in America: The Amount, Extent, and Value

Problem, research strategy, and findings We predicted the amount, share, and value of land dedicated to roadways within and across 316 U.S. primary metropolitan statistical areas. Despite the amount and value of land dedicated to roadways, our study provides the first such estimate across a broad range of metropolitan areas. Our basic approach was to estimate roadway widths using a 10% sample of widths provided by the Highway Performance Monitoring System and apply our estimates to the rest of the roadway system. Multiplying estimated widths by segment length and netting out double counting at intersections provided estimates of land area. We also matched roadway segments and areas to existing land value estimates and satellite-based measures of urbanized land. We found that a little less than a quarter of urbanized land—roughly the size of West Virginia—was dedicated to roadway. This land was worth around $4.1 trillion in 2016 and had an annualized value that was higher than the total variable costs of the trucking sector and the total annual federal, state, and local expenditures on roadways. Conducting a back-of-the-envelope cost–benefit analysis, we found that the country likely has too much land dedicated to urban roads. Takeaway for practice Federal, state, and local agencies dedicate substantial time, money, and resources to providing roadways. Even with relatively generous assumptions and no external costs from driving, however, we estimated that the average cost of expanding roadways exceeded the benefits by a factor of nearly three when accounting for land value. Policymakers should question policies focused on roadway expansion and consider options to reduce the amount of space dedicated to roadway in favor of more housing, offices, and other land uses. In addition to our findings, we provide a novel data set that academics and policymakers can use to draw their own conclusions about the state of America’s urban roadways.

Explainable highway performance degradation prediction model based on LSTM

With the dense and huge highway network in China, the highway maintenance management system has become the most concerned issue for Chinese highway managers in recent years. Therefore, based on the highway network in Guizhou Province of China, this paper established the semi-rigid asphalt pavement performance multi-output Long Short-Term Memory (LSTM) prediction model with regional applicability, including Pavement Surface Condition Index (PCI), Pavement Rutting Depth Index (RDI), Pavement Riding Quality Index (RQI) and Pavement Skidding Resistance Index (SRI) and the hyperparameters of the model were optimized by Bayesian optimization algorithm and the casual analysis of the model was conducted based on SHapley Additive exPlanations (SHAP), providing a reference for China's highway network-level preventive maintenance decision-making. The results prove that the established model can effectively predict the performance of the following year through the data of the previous two years. The established model has a better comprehensive prediction effect in comparison to similar multi-output models. The average coefficient of determination (R2) of the four prediction indexes can reach 0.823. Besides, the prediction effect among the indexes is stable and multiple pavement performance indexes can be effectively and reliably predicted at the same time. In addition, the contribution of input feature variables to output is quantified based on SHAP. According to quantified the contribution, the association relationship of the neural network model is set-valued mapped to the causality relationship in the post hoc. The input feature variables with the main contribution are extracted for causal analysis. The causal analysis shows that the degradation of the four pavement performances all have obvious time memory characteristics and have significant differences, but their pavement performance degradation is the result of nonlinear changes caused by the coupling effects of traffic load, road age, climate, and pavement structure.

A Highway Monitoring Necessity Grading Method Considering Traffic State Stability

In order to meet the basic requirements of expressway operation and maintenance management in the new era,refine the monitoring requirements of different expressway sections,and maximize the operation benefit of expressway monitoring system,this paper puts forward the stability of traffic state related to overtaking frequency,speed difference and traffic fluctuation at the entrance and exit,and obtains the grading detection method of expressway through entropy method and global Moran index,which provides a basis for optimizing monitoring and improving road safety.

A non‐contact identification method of overweight vehicles based on computer vision and deep learning

AbstractThe phenomenon of overweight vehicles severely threatens traffic safety and the service life of transportation infrastructure. Rapid and effective identification of overweight vehicles is of significant importance for maintaining the healthy operation of highways and bridges and ensuring the safety of people's lives and property. With the problems of high cost and low efficiency, the traditional vehicle weighing systems can only meet some of the requirements of different scenarios. The development of artificial intelligence technologies, especially deep learning, has greatly enhanced the accuracy and efficiency of computer vision. To this end, the paper proposes a method using computer vision and deep learning for the non‐contact identification of overweight vehicles. By constructing two deep learning models and combining them with the vehicle vibration model and relevant specifications, the weight and maximum allowable weight of the vehicle are obtained to make a comparison for determining overweight. Experimental verification was performed using a two‐axle vehicle as an illustrative example, and the results demonstrate that the proposed method exhibits excellent feasibility and effectiveness. It shows significant potential in real‐world scenarios, laying a research foundation for practical engineering applications. Additionally, it provides a reference for the governance and decision‐making of overweight issues for relevant authorities.

Large scale monitoring of a highway bridge with remote sensing and distributed fiber optic techniques during load tests

Many bridges in western countries are at the end of their lifetime and hence Structural Health Monitoring is vital to ensure their safe operation. Load test are one way to assess the utilization grade and to decide if actions have to be taken. We report on a comprehensive monitoring campaign of load tests of a large highway bridge on the Brenner highway. The Brenner highway is the main alpine truck crossing passages from Germany to Italy. Several different remote sensing techniques like static and dynamic laser scanning, robotic total station measurements and interferometric radar were used to determine displacements of the bridge deck and girders. Strain changes and bending were observed with distributed fiber optic sensing. Furthermore, the movements of the bridge bearings were determined with IoT tilt sensors. Data was acquired during static and dynamic load tests. We demonstrate that the utilization grade of the bridge can be assessed by an integrated analysis of the different sensor data in combination with a numerical model of the structure. As a consequence of the investigations it was decided by the highway operator to close one of the three lanes of the bridge.

A Multi-Objective Evaluation Method for Smart Highway Operation and Management

Smart highways represent a novel highway concept in the era of big data, emphasizing the synergy among people, vehicles, road facilities, and the environment. However, the operation and management of smart highways have become more intricate, surpassing the adaptability of traditional highway evaluation and management methods. This study integrates the distinctive characteristics of smart highway facilities and operational objectives to enhance and modernize the existing highway evaluation system. Drawing from research on smart highway construction projects, a smart highway evaluation system encompassing facility structure, electromechanical facilities, and operation services is formulated based on a hierarchical analysis method. The quantitative evaluation of each indicator is achieved by combining existing specifications and expert questionnaire solicitation. The group decision-making method is initially employed to optimize subjective weights, followed by the calculation of combined weights using both the entropy weight method and critic method in objective evaluation. Finally, a comprehensive evaluation model is established and validated through engineering projects. The results demonstrate that the evaluation system effectively highlights the advantages and disadvantages in the operation and management of smart highways, thereby fostering the advancement of smart highway iteration.

Optimization of Highway Performance and Safety by Integrated Multi-Criteria Decision-Making Techniques

Optimization of Highway Performance and Safety by Integrated Multi-Criteria Decision-Making Techniques

Study on pile-soil contact effect of anti-sliding piles in swelling soil landslides

In recent years, it is not uncommon for swelling soil landslides to occur again after treatment, which has seriously affected the safe operation of highways and railways. The degree of consolidation and cementation of swelling soil is poor, and its fractures are developed and it has a certain expansibility. Under the action of expansion force, its shear strength is obviously reduced. Thus, anti-slide pile support is used to control swelling soil landslides in this study. Based on the geological conditions and genetic mechanism of swelling soil landslide, a three-dimensional geological model with a width of 40 m is established to simulate the interaction mechanism and influencing factors between soil and pile in the process of anti-slip pile support. The results show that the larger the cohesion and internal friction angle, the stronger the soil arch effect, but the sensitivity is higher when the value is small. Therefore, attention should be paid to the weakening effect of soil arch effect in soil with low shear strength. The larger the pile spacing, the less obvious the soil arch effect. The swelling force also has a great influence on the soil arch effect from scratch. With the increase of the expansive force, the soil arch effect is weakened and completely disappears. Therefore, the adverse effects of expansive force should be considered, when designing anti-slide piles in swelling soil areas.

A deep learning based encoder-decoder model for speed planning of autonomous electric truck platoons

Electric truck platooning offers a promising solution to extend the range of electric vehicles during long-haul operations. However, optimizing the platoon speed to ensure efficient energy utilization remains a critical challenge. The existing research on implementing data-driven solutions for truck platooning remains limited and implementing first principles solution is still a challenge. However, recognizing the resemblance of truck platoon data to a time series serves as a compelling motivation to explore suitable analytical techniques to address the problem. This paper presents a novel deep learning approach using a sequence-to-sequence encoder-decoder model to obtain the speed profile to be followed by an autonomous electric truck platoon considering various constraints such as the available state of charge (SOC) in the batteries along with other vehicles and road conditions while ensuring that the platoon is string stable. To ensure that the framework is suitable for long-haul highway operation, the model has been trained using various known highway drive cycles. Encoder-decoder models were trained and hyperparameter tuning was performed for the same. Finally, the most suitable model has been chosen for the application. For testing the entire framework, drive cycle/speed prediction corresponding to different desired SOC profiles has been presented. A case study showing the relevance of the proposed framework in predicting the drive cycle on various routes and its impact on taking critical policy decisions during the planning of electric truck platoons has also been presented. This study would help to efficiently plan the feasible routes for electric trucks considering multiple constraints such as battery capacity, expected discharge rate, charging infrastructure availability, route length/travel time, and other on-road operating conditions while also maintaining stability.

Analysis of the Impact of the Former Abandoned Dregs of Mountain Highways on the Construction and Safety of New Bridge Pile Foundations

In highway reconstruction and expansion projects, the impact of the abandoned dreg body produced by the original highway on the new bridge project cannot be ignored. If the abandoned dregs are not handled properly, they will cause great threat to the operation of the new highway as well as to the safety of the surrounding environment and personnel. In this paper, based on a South China highway reconstruction and expansion project, a model of the abandoned dreg body, bridge pile and anti-slide pile is established with the help of finite difference software FLAC3D 5.0. The calculation results show that compared with burying the anti-slide pile, slope cutting is more effective for improving the stability of the abandoned dreg body. Under the action of vertical force intensity, the displacement of the top of the pile increases continuously, and the maximum bending moment of the pile body increases firstly and then decreases. The pile displacement and bending moment of the bridge pile increase significantly in the storm condition compared with the normal condition. In addition, the abandoned dreg body hazard prevention and control technical measures are studied. The impacts of different locations of anti-slide pile burial on bridge piles are analyzed and compared, and it is determined that the optimal location of anti-slide pile burial is the middle of the secondary slope.

Performance Study of Hot & Cold Mix Using Bitumen and Emulsion

This project work describes laboratory experiments and presents results for the cold-mix mixtures. Construction of highway involves huge performances of hot and cold-mix mix outlay of investment. A precise design may save considerable amount of investment, as well, a reliable performance of the in-service highway can be achieved. Two things are of major considerations in this regard - pavement design and the mix design. This project work emphasizes some of the new considerations involved in the concept of mix design. Though there are a few equipment used for estimation of stability of the bituminous mixes in the laboratory. the Marshall test is the most popular one, possibly due to its simplicity and low cost.

ABCD method for determination of low-temperature properties of ordinary and modified binders

Introduction. The active introduction into practice of the system of volumetric and functional design (OFP) is aimed at the large-scale development by the Russian road construction industry of advanced foreign approaches to the technology of designing asphalt concrete pavements (Superpave). One of the fundamental differences between the OFP methodology and the previously established practice of evaluating technical, technological and operational indicators of road construction materials is the introduction of new methods that characterize quantitative indicators with a high degree of accuracy, based on the actual physical, chemical and mechanical properties of the components used. Thus, as methods for assessing the low-temperature properties of bitumen binders, it is proposed to use the bending beam method (BBR), which has proven itself quite well when working with traditional (ordinary) bitumen. However, the natural and climatic conditions of operation of highways in Russia clearly require the use of binders modified with high- and low-molecular compounds, including polymers. In this study, the task of applying the ABCD method to evaluate the low-temperature parameters of ordinary bitumen and polymer-bitumen binders was realized.Materials and methods. Samples of industrial batches of petroleum road viscous bitumen (GOST 33133-2014) and polymer-modified bitumen (GOST R 52056-2003) were used as objects of research. To determine the lowtemperature parameters, an ABCD 8.0 device and an air-cooled climate chamber were used. The study of bitumen binders according to the parameters laid down in the technical requirements of GOST R 58400.11–2019 ‘Automobile roads of general use. Petroleum-based bitumen binders. Method of determining the temperature of cracking using the device ABCD’ was carried out.Results. The values of the cracking temperature for ordinary and modified bitumen binders were determined. It is shown that the low-temperature parameters of polymer-bitumen binders significantly exceed similar properties of oxidized road bitumen.Discussion and conclusions. A comparative analysis of the low-temperature properties of ordinary and modified binders obtained during their determination by the direct method enables to confirm the effectiveness of the methodology developed in GOST R 58400.11-2019 for assessing the performance of binders of various component composition in difficult climatic conditions of Russia. The effectiveness of the domestic second-generation ABCD 8.0 device for direct assessment of the cracking temperature of bitumen binders of variable composition has been confirmed.

Assessment of compaction quality of highway subgrade via roller-integrated positive maximum velocity detection technique

ABSTRACT Quality control of compaction is vital for the long-term performance of highways. Specifically, the assessment of subgrade compaction quality is a key factor. Currently, compaction quality is primarily controlled by parameters set during compaction and subsequent random sampling tests post-construction. However, the impact of human factors and limitations of these sampling tests fall short of meeting the standards of large-scale precision construction. This study introduces a real-time monitoring index to characterise the compaction quality of silt subgrades: the maximum velocity compaction value (MVCV). This index is derived using a combination of the roller-integrated positive maximum velocity detection system and real-time kinematic Beidou positioning system (RTK-BDS). Furthermore, the Green spline interpolation method allows for estimating compaction quality values at any point. A case study from the Hengyong Highway project in China reveals a strong linear relationship between compaction parameters and compactness. This suggests the suitability of this method for characterising the compaction quality of such silt. This assessment approach facilitates a detailed evaluation of compaction quality across the entire construction zone. Hence, it aids in effectively minimising compaction defects, reducing unnecessary rework, and enhancing the overall compaction quality and efficiency of highway construction.

Review of Power Supply and Distribution Construction Technology for Highway Electromechanical Engineering

In recent years, China has made significant progress in the construction of highways, resulting in an improvedhighway network that has provided robust support for economic and social development. However, the rapid expansion of highway construction, power supply, and distribution has led to several challenges in mechanical and electrical engineering technology. Ensuring the safe, stable, and cost-effective operation of the power supply and distribution system to meet the diverse requirements of highway operations has become a pressing issue. This article takes an example of a highway electromechanical engineering power supply and distribution construction project to provide insight into the construction process of highway electromechanical engineering power supply and distribution technology.

Embedded Highway Health Maintenance System Based on Digital Twin Superposition Model

INTRODUCTION: The highway monitoring data acquisition technology develops quickly. Based on the traditional form of continuous monitoring, intelligent management system focuses on digital and wireless transmission. In the operation of highway maintenance system, each system is independent of each other, lacking of effective connection. Moreover, the level of continuous monitoring is obviously backward, which restricts the development of highway health monitoring. It is necessary to further study the level of integration to achieve the real-time tracking and the monitoring of highway’s healthy development.
 OBJECTIVES: This paper presents a highway health maintenance system based on digital twin technology, which intends to provide a solution for efficient, stable and automatic data transmission of the highway operation and maintenance management.
 METHODS: The output of the algorithm after the noise reduction effect is compared with the data containing the generated noise. The average number of nodes is set before running the algorithm to determine the actual length of the vertical position of the embedded sensor (calculating the position of two sensor nodes). The vertical length can be referred to the combined noise level formed and the combined test to determine the position. With the help of the overall data, it can be seen that the Kalman low-pass filtering algorithm can well describe the trend of the received signal and retain the key information in the received signal.
 RESULTS: It proves that the algorithm in this paper has fast calculation speed and high efficiency, and the basic working principle is simple. Thus, it is a good data denoising solution.
 CONCLUSION: The output in the paper ensures the data exchange and the update of the whole life cycle of highway, defines the digital twin entity model, and provides a reference for the establishment of information and data network.