Hasil untuk "Highway engineering. Roads and pavements"

Jiahong Xiang, Wenxiao He, Xihua Wang et al.

The Rust programming language presents a steep learning curve and significant coding challenges, making the automation of issue resolution essential for its broader adoption. Recently, LLM-powered code agents have shown remarkable success in resolving complex software engineering tasks, yet their application to Rust has been limited by the absence of a large-scale, repository-level benchmark. To bridge this gap, we introduce Rust-SWE-bench, a benchmark comprising 500 real-world, repository-level software engineering tasks from 34 diverse and popular Rust repositories. We then perform a comprehensive study on Rust-SWE-bench with four representative agents and four state-of-the-art LLMs to establish a foundational understanding of their capabilities and limitations in the Rust ecosystem. Our extensive study reveals that while ReAct-style agents are promising, i.e., resolving up to 21.2% of issues, they are limited by two primary challenges: comprehending repository-wide code structure and complying with Rust's strict type and trait semantics. We also find that issue reproduction is rather critical for task resolution. Inspired by these findings, we propose RUSTFORGER, a novel agentic approach that integrates an automated test environment setup with a Rust metaprogramming-driven dynamic tracing strategy to facilitate reliable issue reproduction and dynamic analysis. The evaluation shows that RUSTFORGER using Claude-Sonnet-3.7 significantly outperforms all baselines, resolving 28.6% of tasks on Rust-SWE-bench, i.e., a 34.9% improvement over the strongest baseline, and, in aggregate, uniquely solves 46 tasks that no other agent could solve across all adopted advanced LLMs.

Qingyi Xiao, Miaomiao Zhu, Zhenchao Zhao et al.

With the vigorous development of China's transportation industry, the mileage of high-grade highways based on semi rigid base layers has been increasing year by year. However, the commonly used material for semi rigid base layers, cement stabilized crushed stone mixture (hereinafter referred to as water stabilized mixture), often experiences segregation during mixing, transportation, and paving. Separation of water stabilized mixture can greatly reduce the service life of roads and cause damage to people's property, the traditional separation detection method that relies on manual experience has problems of low detection efficiency and low recognition accuracy. In order to solve these problems and assist in the modernization of road construction, this article proposes a separation recognition method for water stabilized mixtures based on deep learning. Firstly, a database of segregation diseases of water stabilized mixture was built. Secondly, the control tests were set up by standard fine-tuning and feature extraction, and four different optimizers were set up respectively. By comparing accuracy, loss, precision, recall and F1-score at the end of the pre-trained network, the overall recognition effect of ResNet-101 as the network model was better. Thirdly, the ResNet-101 model was optimized by SpotTune, replacing cross entropy loss with focus loss, adding PReLU to the pre-trained network and a BN layer to the top layer of the pre-trained network, and using 1 ​× ​1. Convolutional replacement of the fully connected layer. Finally, build a web side water stabilized mixture segregation recognition platform, and its stability was verified in practical engineering.

Natalia Popovych

Introduction. Road safety is one of the most pressing global challenges, particularly in Ukraine. Every year, millions of people worldwide are injured or lose their lives as a result of road traffic accidents (RTAs). These are not only personal tragedies for families but also a serious burden on healthcare systems, the economy, and the social sphere. Problem statement. In the current conditions of Ukraine’s transport system development, ensuring road traffic safety is of particular importance. Each year, a significant number of RTAs occur on Ukrainian roads, the main causes of which are speeding and inappropriate choice of speed under specific traffic conditions. These factors are recognized as the primary contributors to both the frequency and severity of accidents. Excessive vehicle speed poses a critical problem, leading to fatalities, injuries, and material losses. The growing level of motorization, inadequate infrastructure, and insufficient enforcement of traffic regulations further exacerbate risks for all road users. Purpose. To improve road traffic safety on Ukrainian roads and reduce accident rates by implementing a set of effective organizational and technical measures. Materials and methods. The study applies statistical data processing to analyze accident rates on public roads. Current regulatory documents on traffic calming measures were also examined.

Muhammad Tayyab Khan, Zane Yong, Lequn Chen et al.

Accurate extraction of key information from 2D engineering drawings is crucial for high-precision manufacturing. Manual extraction is slow and labor-intensive, while traditional Optical Character Recognition (OCR) techniques often struggle with complex layouts and overlapping symbols, resulting in unstructured outputs. To address these challenges, this paper proposes a novel hybrid deep learning framework for structured information extraction by integrating an Oriented Bounding Box (OBB) detection model with a transformer-based document parsing model (Donut). An in-house annotated dataset is used to train YOLOv11 for detecting nine key categories: Geometric Dimensioning and Tolerancing (GD&T), General Tolerances, Measures, Materials, Notes, Radii, Surface Roughness, Threads, and Title Blocks. Detected OBBs are cropped into images and labeled to fine-tune Donut for structured JSON output. Fine-tuning strategies include a single model trained across all categories and category-specific models. Results show that the single model consistently outperforms category-specific ones across all evaluation metrics, achieving higher precision (94.77% for GD&T), recall (100% for most categories), and F1 score (97.3%), while reducing hallucinations (5.23%). The proposed framework improves accuracy, reduces manual effort, and supports scalable deployment in precision-driven industries.

Thiago Barradas, Aline Paes, Vânia de Oliveira Neves

The effective execution of tests for REST APIs remains a considerable challenge for development teams, driven by the inherent complexity of distributed systems, the multitude of possible scenarios, and the limited time available for test design. Exhaustive testing of all input combinations is impractical, often resulting in undetected failures, high manual effort, and limited test coverage. To address these issues, we introduce RestTSLLM, an approach that uses Test Specification Language (TSL) in conjunction with Large Language Models (LLMs) to automate the generation of test cases for REST APIs. The approach targets two core challenges: the creation of test scenarios and the definition of appropriate input data. The proposed solution integrates prompt engineering techniques with an automated pipeline to evaluate various LLMs on their ability to generate tests from OpenAPI specifications. The evaluation focused on metrics such as success rate, test coverage, and mutation score, enabling a systematic comparison of model performance. The results indicate that the best-performing LLMs - Claude 3.5 Sonnet (Anthropic), Deepseek R1 (Deepseek), Qwen 2.5 32b (Alibaba), and Sabia 3 (Maritaca) - consistently produced robust and contextually coherent REST API tests. Among them, Claude 3.5 Sonnet outperformed all other models across every metric, emerging in this study as the most suitable model for this task. These findings highlight the potential of LLMs to automate the generation of tests based on API specifications.

Chengjie Lu, Pablo Valle, Jiahui Wu et al.

FMs, particularly LLMs, are increasingly used to support various software engineering activities (e.g., coding and testing). Their applications in the software engineering of CPSs are also growing. However, research in this area remains limited. Moreover, existing studies have primarily focused on LLMs-only one type of FM-leaving ample opportunities to explore others, such as vision-language models. We argue that, in addition to LLMs, other FMs utilizing different data modalities (e.g., images, audio) and multimodal models (which integrate multiple modalities) hold great potential for supporting CPS software engineering, given that these systems process diverse data types. To address this, we present a research roadmap for integrating FMs into various phases of CPS software engineering, highlighting key research opportunities and challenges for the software engineering community. Moreover, we discuss the common challenges associated with applying FMs in this context, including the correctness of FM-generated artifacts, as well as the inherent uncertainty and hallucination associated with FMs. This roadmap is intended for researchers and practitioners in CPS software engineering, providing future research directions using FMs in this domain.

Nelson Alves Ferreira Neto

Low-latency intelligent systems are required for autonomous driving on non-uniform terrain in open-pit mines and developing countries. This work proposes a perception system for autonomous vehicles on unpaved roads and off-road environments, capable of navigating rough terrain without a predefined trail. The Configurable Modular Segmentation Network (CMSNet) framework is proposed, facilitating different architectural arrangements. CMSNet configurations were trained to segment obstacles and trafficable ground on new images from unpaved/off-road scenarios with adverse conditions (night, rain, dust). We investigated applying deep learning to detect drivable regions without explicit track boundaries, studied algorithm behavior under visibility impairment, and evaluated field tests with real-time semantic segmentation. A new dataset, Kamino, is presented with almost 12,000 images from an operating vehicle with eight synchronized cameras. The Kamino dataset has a high number of labeled pixels compared to similar public collections and includes images from an off-road proving ground emulating a mine under adverse visibility. To achieve real-time inference, CMSNet CNN layers were methodically removed and fused using TensorRT, C++, and CUDA. Empirical experiments on two datasets validated the proposed system's effectiveness.

Maximilian Böhle, Bernhard Schick, Steffen Müller

Steering feedback plays a substantial role in the validity of driving simulators for the virtual development of modern vehicles. Established objective steering characteristics typically assess the feedback behavior in the frequency range of up to 30 Hz while factors such as steering wheel and vehicle body vibrations at higher frequencies are mainly approached as comfort issues. This work investigates the influence of steering wheel and vehicle body excitations in the frequency range between 30 and 100 Hz on the subjective evaluation of steering feedback in a dynamic driving simulator. A controlled subject study with 42 participants was performed to compare a reference vehicle with an electrical power steering system to four variants of its virtual representation on a dynamic driving simulator. The effects of road-induced excitations were investigated by comparing a semi-empirical and a physics-based tire model, while the influence of non-road-induced excitations was investigated by implementing engine and wheel orders. The simulator variants were evaluated in comparison to the reference vehicle during closed-loop driving on a country road in a single-blind within-subjects design. The subjective evaluation focused on the perception of road feedback compared to the reference vehicle. The statistical analysis of subjective results shows that there is a strong effect of non-road-induced steering and vehicle body excitations, while the effect of road-induced excitations is considerably less pronounced.

Michael B. Healy, Reza Jokar, Soolu Thomas et al.

In this work, we describe the design and architecture of the open-source Quantum Engine Compiler (qe-compiler) currently used in production for IBM Quantum systems. The qe-compiler is built using LLVM's Multi-Level Intermediate Representation (MLIR) framework and includes definitions for several dialects to represent parameterized quantum computation at multiple levels of abstraction. The compiler also provides Python bindings and a diagnostic system. An open-source LALR lexer and parser built using Bison and Flex generates an Abstract Syntax Tree that is translated to a high-level MLIR dialect. An extensible hierarchical target system for modeling the heterogeneous nature of control systems at compilation time is included. Target-based and generic compilation passes are added using a pipeline interface to translate the input down to low-level intermediate representations (including LLVM IR) and can take advantage of LLVM backends and tooling to generate machine executable binaries. The qe-compiler is built to be extensible, maintainable, performant, and scalable to support the future of quantum computing.

Caleb Robinson, Isaac Corley, Anthony Ortiz et al.

Fully understanding a complex high-resolution satellite or aerial imagery scene often requires spatial reasoning over a broad relevant context. The human object recognition system is able to understand object in a scene over a long-range relevant context. For example, if a human observes an aerial scene that shows sections of road broken up by tree canopy, then they will be unlikely to conclude that the road has actually been broken up into disjoint pieces by trees and instead think that the canopy of nearby trees is occluding the road. However, there is limited research being conducted to understand long-range context understanding of modern machine learning models. In this work we propose a road segmentation benchmark dataset, Chesapeake Roads Spatial Context (RSC), for evaluating the spatial long-range context understanding of geospatial machine learning models and show how commonly used semantic segmentation models can fail at this task. For example, we show that a U-Net trained to segment roads from background in aerial imagery achieves an 84% recall on unoccluded roads, but just 63.5% recall on roads covered by tree canopy despite being trained to model both the same way. We further analyze how the performance of models changes as the relevant context for a decision (unoccluded roads in our case) varies in distance. We release the code to reproduce our experiments and dataset of imagery and masks to encourage future research in this direction -- https://github.com/isaaccorley/ChesapeakeRSC.

Andrzej Ambroziak, Maciej Malinowski

The structural analysis of an old steel riveted railway truss bridge located over the Maruska River on the Działdowo – Olsztyn, Poland railway line is performed in this paper to check its behaviour under today’s railway loads. The mechanical properties of construction steel extracted from the old steel bridge are investigated by tensile tests, impact tests through the Charpy pendulum impact V-notch, and an optical emission spectrometer. Structural analysis exhibits that the steel bridge requires proper structural bridge improvements to meet today’s load requirements in terms of bearing capacity and serviceability state. The paper begins with a wide survey of literature carried out on the investigation of steel riveted railway bridge subject matter. This paper can provide scientists, engineers, and designers with an experimental and structural basis in the field of old steel riveted railway truss bridge construction.

Liangguo Kang

Road safety development is affected by both motorization rates and economic growth. This phenomenon is studied using the Kuznets curve model, which uses data such as the number of road fatalities, the population, the number of vehicles, and the gross domestic product (GDP) per capita, all of which are verified by applying the data envelopment analysis (DEA) model. The results showed that there were strong links between road safety development and economic growth in China. As GDP per capita rose from 1979 to 2018, the number of vehicles per person increased and the number of fatalities per vehicle decreased, producing a relationship that followed an N-shaped curve. However, in 2002, the relationship between the road mortality rate and GDP per capita followed an inverted U-shaped curve; the point at which this happened in the Kuznets curve was the turning point for road safety performance in China. Thus, road mortality rates increased as GDP per capita increased, but declined once GDP per capita exceeded 17 187 CNY. The analysis that stems from the results of the Kuznets curve model is consistent with the performance evaluation derived from the DEA-based road safety model. The findings could provide an important reference for policymakers to improve road safety under harsh economic conditions.

Bradley P. Allen

We describe a method, based on Jennifer Nado's proposal for classification procedures as targets of conceptual engineering, that implements such procedures by prompting a large language model. We apply this method, using data from the Wikidata knowledge graph, to evaluate stipulative definitions related to two paradigmatic conceptual engineering projects: the International Astronomical Union's redefinition of PLANET and Haslanger's ameliorative analysis of WOMAN. Our results show that classification procedures built using our approach can exhibit good classification performance and, through the generation of rationales for their classifications, can contribute to the identification of issues in either the definitions or the data against which they are being evaluated. We consider objections to this method, and discuss implications of this work for three aspects of theory and practice of conceptual engineering: the definition of its targets, empirical methods for their investigation, and their practical roles. The data and code used for our experiments, together with the experimental results, are available in a Github repository.

Huishan Li, L. Jiao

The timing of preventive maintenance for asphalt pavement determines the effectiveness and cost-effectiveness of preventive maintenance measures. Firstly, a weighted average method combining subjective and objective factors is used to evaluate the performance index of road sections and select preventive maintenance measures. Secondly, a decision tree model for preventive maintenance of highways in Gansu Province is established using field measurement data to determine the timing of preventive maintenance for road sections. Finally, the model is validated using the example of the G22 Qingdao-Lanzhou Expressway by evaluating the pavement service performance index and the timing of preventive maintenance. The results show that compared to directly establishing decision trees based on uniform standards, the decision tree established using field measurement data reflects the differences in the importance of various decision indicators and respects the objectivity of road data. It improves the poor portability of the original decision tree model and enables more accurate determination of the timing of preventive maintenance.

A. Galkin

The design and construction of highways in the cryolithozone is associated with a number of difficulties, which are determined not only by geocryological and climatic operating conditions, but also by the complexity of the actual forecast of the thermal regime of road coverings and foundations. Many thermal calculations to substantiate technical solutions for the protection of highways in the cryolithozone from negative cryogenic phenomena are based on the determination and selection of a given thermal resistance of the structural layers of the pavement. The purpose of these studies was to assess the feasibility of using equivalent thermal resistance in modeling thermal processes and to determine the error in calculations that we make by replacing the layered pavement structure with an equivalent one.     Simple engineering dependences are obtained that allow us to determine the error in calculations when using equivalent thermal resistance. The calculation of the thermal resistance of the three-layer construction of the pavement is made. It is established that for a three-layer pavement structure, the error value in the calculation of thermal resistance is directly related to the degree of deviation of the values of the thermal conductivity coefficient of the materials of individual layers from each other. Moreover, the parameters of the inequality of thermal conductivity coefficients for individual structural layers when determining the minimum calculation error are functionally related to each other. The results of variant numerical calculations are presented in the form of 3D and 2D graphs, which allow us to visually assess the influence of the studied parameters on the relative error of calculating the thermal resistance of the pavement.

Jerzy Lejk

Abstract: The paper discusses the issue of risk in transport projects. The first part includes the analysis of definitions developed to describe the notion of risk. Based on the studies of the literature on the subject, the author discusses the ways the scholars dealing with this subject- matter perceive risk. The second part includes the discussion of risk sources and factors in transport projects, depending on individual project implementation stages. The third part consists in the author’s analysis of risk sources together with the presentation of basic risk factors assigned to such sources which affect the possibility of reaching the set objectives as part of a transport project being implemented. Keywords: Risk; Source of risks; Risk factor

Xinjun Feng, Hui Liang, Zijian Dai

In this paper, the surface activated crumb rubber with waste cooking oil (WCO) was studied to improve the performance of crumb rubber modified asphalt. The activated waste crumb rubber modified asphalt (OCRMA) with different amount of crumb rubber was prepared to study the microscopic appearance of OCRMA by scanning electron microscope and fluorescence microscope and analyze the surface performance. The rheological properties and microscopic mechanism of OCRMA were characterized by dynamic shear rheological test, multiple stress creep recovery (MSCR) test, BBR test and infrared spectroscopy. The results show that the dissolution degree of waste crumb rubber is improved after WCO activation, and the compatibility with asphalt components is enhanced, and the stable cross-linking structure is formed, which improves the asphalt performance. The several new absorption peaks, which were obvious, were all caused by the composition of WCO, that is, there was no significant chemical change during the interaction between the activated crumb rubber and base asphalt. Compared with the common waste crumb rubber modified asphalt (CRMA), activation with WCO can significantly reduce the viscosity of CRMA, decrease the difference of segregation softening point by 27%, and enhance the low temperature performance by 30%. The aging degree is greatly reduced, and the anti-aging performance of OCRMA is increased by about 20% with the same dosage. The high temperature performance, though higher than that of base asphalt, decreases to some extent. After comprehensive analysis, the optimal dosage of crumb rubber for OCRMA is 30%.

Chen Xu, Ba Trung Cao, Yong Yuan et al.

Recently, a class of machine learning methods called physics-informed neural networks (PINNs) has been proposed and gained prevalence in solving various scientific computing problems. This approach enables the solution of partial differential equations (PDEs) via embedding physical laws into the loss function. Many inverse problems can be tackled by simply combining the data from real life scenarios with existing PINN algorithms. In this paper, we present a multi-task learning method using uncertainty weighting to improve the training efficiency and accuracy of PINNs for inverse problems in linear elasticity and hyperelasticity. Furthermore, we demonstrate an application of PINNs to a practical inverse problem in structural analysis: prediction of external loads of diverse engineering structures based on limited displacement monitoring points. To this end, we first determine a simplified loading scenario at the offline stage. By setting unknown boundary conditions as learnable parameters, PINNs can predict the external loads with the support of measured data. When it comes to the online stage in real engineering projects, transfer learning is employed to fine-tune the pre-trained model from offline stage. Our results show that, even with noisy gappy data, satisfactory results can still be obtained from the PINN model due to the dual regularization of physics laws and prior knowledge, which exhibits better robustness compared to traditional analysis methods. Our approach is capable of bridging the gap between various structures with geometric scaling and under different loading scenarios, and the convergence of training is also greatly accelerated through not only the layer freezing but also the multi-task weight inheritance from pre-trained models, thus making it possible to be applied as surrogate models in actual engineering projects.

Chen Zhang, Yuxin Zheng

The traditional evaluation method of construction quality for asphalt pavement has gradually lagged behind the pace of development of the road industry. Big data, Internet of Things (IoT), and intelligent sensing technology have been reflected in the field of road engineering, but these technologies also have technical shortcomings in terms of applicability, durability, real-time performance, and portability in practice. To provide a new method for construction quality evaluation of asphalt pavement, this study developed an intelligent sensing aggregate (ISA) with low cost and high precision based on the 3D printing and Internet of Things (IoT) technology. Based on the laboratory test and field test, the sensing characteristics, high-temperature resistance, and mechanical properties of ISA are analyzed to verify the reliability of ISA. Through the quantitative analysis of ISA perception data, the Driving Perception Index (DPI) is proposed. By analyzing the quantitative correlation between the spatial angle of ISA and the compaction degree, the quantitative correlation between the DPI, International Roughness Index (IRI), and the deflection value, the evaluation standard of construction quality for asphalt pavement is established. The result shows that the best baud rate for ISA is 9600 bps, and the corresponding data transmission distance is 350 m. In the range of 6 m, the cars, trucks, trailers, and buses can be perceived by ISA. The maximum operating temperature of ISA is up to 200°C. Embedding ISA into asphalt mixture has no significant effect on original gradation of asphalt mixture. The established evaluation standard of construction quality for asphalt pavement takes into account the compaction quality, the requirements of bearing capacity, and the driving comfort of asphalt pavement, which is suitable for expressway and first-class highway.

Hardianefil H, Fadrizal Lubis, Alfian Saleh

Dengan melihat kondisi fisik ruas jalan Simpang Beringin - Meredan dan di hubungkan dengan peristiwa kecelakaan lalu lintas yang terjadi di ruas jalan tersebut, maka perlu dilakukan tinjauan kondisi ruas jalan tersebut dari segi geometriknya dengan berpedoman pada perhitungan metode Bina Marga. Penelitian dilakukan dengan melaksanakan survey dan pengukuran langsung dilapangan untuk mengetahui kondisi geometrik eksisting tikungan pada jalan tersebut, kemudian dianalisis dengan melakukan perhitungan ulang dengan metode Bina Marga. Dari hasil penelitian pada  tikungan STA 3+641 didapat eksisting lengkungan berbentuk full cirle dengan kecepatan kendaraan dilapangan sebesar 40 km/jam  dengan jari - jari tikungan R = 82,67 m. Setelah dilakukan perhitungan ulang dengan metode Bina Marga menggunakan jenis lengkung Spiral – Cirle – Sipral dengan kecepatan rencana sebesar 50 km/jam dan jari – jari tikungan  Rc = 90 m. Dari hasil perhitungan terdapat perbedaan antara as jalan eksisting dengan as jalan hasil perhitungan Metode Bina Marga dan tidak ditemukan superelevasi yang mengikuti standar perhitungan Bina Marga, sehingga perlu dilakukan perbaikan geometrik pada tikungan tersebut.