Hasil untuk "Railroad engineering and operation"

Patricia G. F. Matsubara, Tayana Conte

Over twenty years ago, the Software Engineering (SE) research community have been involved with Evidence-Based Software Engineering (EBSE). EBSE aims to inform industrial practice with the best evidence from rigorous research, preferably from systematic literature reviews (SLRs). Since then, SE researchers have conducted many SLRs, perfected their SLR procedures, proposed alternative ways of presenting their results (such as Evidence Briefings), and profusely discussed how to conduct research that impacts practice. Nevertheless, there is still a feeling that SLRs' results are not reaching practitioners. Something is missing. In this vision paper, we introduce Evidence to Decision (EtD) frameworks from the health sciences, which propose gathering experts in panels to assess the existing best evidence about the impact of an intervention in all relevant outcomes and make structured recommendations based on them. The insight we can leverage from EtD frameworks is not their structure per se but all the relevant criteria for making recommendations to practitioners from SLRs. Furthermore, we provide a worked example based on an SE SLR. We also discuss the challenges the SE research and practice community may face when adopting EtD frameworks, highlighting the need for more comprehensive criteria in our recommendations to industry practitioners.

ZHANG Xuhao, TONG Runfang, WANG Mengqian et al.

Bearing faults are a typical failure mode in motors. Traditional diagnostic methods based on vibration signals face high costs and strong noise interference, while current signal-based methods struggle to extract fault features due to dominant fundamental components. To address these issues, this paper proposes an intelligent diagnostic method. This method suppresses interference from fundamental current components and main harmonics through a time-shift cancellation technique, converts preprocessed one-dimensional signals into two-dimensional time-frequency feature maps using the smoothed pseudo Wigner-Ville distribution (SPWVD), performs cropping and stitching on these maps according to bearing fault characteristic frequencies, and finally the object detection model is built based on YOLO11 for automatic fault positioning and classification. Experimental results demonstrate that this method achieves up to 99.54% diagnostic accuracy under steady-state operating conditions, and can effectively extracts features from low-sampling-frequency current signals, significantly reducing hardware costs. Compared with traditional vibration signal methods, it exhibits stronger noise resistance and lower hardware dependence. Additionally, the three-stage diagnosis framework, consisting of signal preprocessing, time-frequency feature extraction, and intelligent classification, offers a low-cost and high-reliability solution for effective fault diagnosis of motor bearings.

WU Weiwei, DING Hao, HE Guanqiang et al.

To study the simulation effect of rail plate harmonic displacement excitation on wheel high-order wheel polygon geometric excitation, a wheel-plate rolling contact finite element model was developed based on simulation analysis software for the bogie high-frequency excitation test bench. The wheel-plate rolling vibration behaviors under 20^th-order polygon excitation with a wave depth of 0.05 mm were investigated through a solving process at a speed of 440 km/h. A comparative analysis was then conducted in both the time domain and frequency domain to identify similarities and differences between the two excitation modes. The simulation results for a 20^th-order polygon with a wave depth of 0.05 mm, under an axle weight of 17 t and a speed of 440 km/h, show that the maximum time-domain wheel-plate vertical force differed by only 1.5% between displacement excitation and geometric excitation. The spectral peak of wheel-plate vertical forces and the power spectral density (PSD) peak of axle box accelerations at the polygon excitation frequency of 840 Hz under displacement excitation are in good agreement with those under geometric excitation. The constant local curvature radius at the wheel-plate contact point under displacement excitation results in a larger contact spot area and a corresponding 21.7% reduction in contact stress. The amplitude of the wheel-plate vertical force spectrum and the power spectrum density of axle box accelerations increase with higher rail plate displacement amplitudes, while the peak frequency is basically unchanged. In summary, wheel polygon can be effectively simulated using displacement excitation as an alternative to geometric excitation on the bogie high-frequency excitation test bench.

C. Radhika, D. Hanirex

Predicting the traffic in the railroad is the secret to successful operation of the railroad and contented passengers. RNN-based real-time predictive model. The model training was in the form of real-time tracking data, weather reports, past train schedules, and maintenance records. The model was evaluated based on such metrics as MAE, RMSE, and R2. These promising values are the MAE of 2.3 minutes and RMSE of 3.1 minutes of the testing set, which indicates the model is correct in predicting the traffic situation. Moreover, the explanatory power of the model is enormous, with a value of R2 of 0.89. The flexibility is also seen in the fact that the model can always work in many different environments, including in bad weather or even when there is a need to carry out some repairs. According to the comparative analysis, there is evident improvement that leads to the better performance of the proposed work with an MAE of 2.3 minutes, RMSE of 3.1 minutes, and an R2 of 0.92. The results obtained demonstrate the quality of an RNN-based solution to improve the predictive railroad traffic forecasting in real time to obtain valuable information that can help to improve the operation of railways and to guarantee the satisfaction of passengers.

Guangyue Qi, Hongcheng Ding, Yu Zhang et al.

This study centers on the impact of water level fluctuations in water transfer tunnels regarding the mechanical response characteristics of railroad tunnels. Via a meticulously designed model test, the variation pattern of tunnel lining strain under diverse water level circumstances is thoroughly examined, furnishing a crucial foundation for the design, construction, and safe operation of tunnel engineering. The outcomes denote that water level alterations remarkably influence the tunnel's mechanical response. Each parameter exhibits disparate trends with the ascending water level, and discrepancies exist in the response features of different cross-sectional locations. The test results are as follows: (1) When the water level in the water transfer tunnel is 1 cm, the compressive strain at the outer elevated arch of section I reaches the maximum, and the compressive strain at the inner left arch foot is also the largest. (2) The tensile strain at the outer right arch waist of section II is the greatest, and the compression at the inner right arch waist is severe; the tensile strain at the outer right arch foot of section II exceeds the compressive strain at the arch top, and the compressive strain at the inner right arch foot is the largest. These findings offer a scientific underpinning for exploring the effect of water level loading on the mechanical response of the tunnel structure within the tunnel section beneath the water transfer tunnel, which is highly significant for enhancing project quality and ensuring operational safety.

Muneera Bano, Hashini Gunatilake, Rashina Hoda

Large language models (LLMs) have rapidly gained popularity and are being embedded into professional applications due to their capabilities in generating human-like content. However, unquestioned reliance on their outputs and recommendations can be problematic as LLMs can reinforce societal biases and stereotypes. This study investigates how LLMs, specifically OpenAI's GPT-4 and Microsoft Copilot, can reinforce gender and racial stereotypes within the software engineering (SE) profession through both textual and graphical outputs. We used each LLM to generate 300 profiles, consisting of 100 gender-based and 50 gender-neutral profiles, for a recruitment scenario in SE roles. Recommendations were generated for each profile and evaluated against the job requirements for four distinct SE positions. Each LLM was asked to select the top 5 candidates and subsequently the best candidate for each role. Each LLM was also asked to generate images for the top 5 candidates, providing a dataset for analysing potential biases in both text-based selections and visual representations. Our analysis reveals that both models preferred male and Caucasian profiles, particularly for senior roles, and favoured images featuring traits such as lighter skin tones, slimmer body types, and younger appearances. These findings highlight underlying societal biases influence the outputs of LLMs, contributing to narrow, exclusionary stereotypes that can further limit diversity and perpetuate inequities in the SE field. As LLMs are increasingly adopted within SE research and professional practices, awareness of these biases is crucial to prevent the reinforcement of discriminatory norms and to ensure that AI tools are leveraged to promote an inclusive and equitable engineering culture rather than hinder it.

Hayato Ishida, Amal Elsokary, Maria Aslam et al.

Realisation of significant advances in capabilities of sensors, computing, timing, and communication enabled by quantum technologies is dependent on engineering highly complex systems that integrate quantum devices into existing classical infrastructure. A systems engineering approach is considered to address the growing need for quantum-secure telecommunications that overcome the threat to encryption caused by maturing quantum computation. This work explores a range of existing and future quantum communication networks, specifically quantum key distribution network proposals, to model and demonstrate the evolution of quantum key distribution network architectures. Leveraging Orthogonal Variability Modelling and Systems Modelling Language as candidate modelling languages, the study creates traceable artefacts to promote modular architectures that are reusable for future studies. We propose a variability-driven framework for managing fast-evolving network architectures with respect to increasing stakeholder expectations. The result contributes to the systematic development of viable quantum key distribution networks and supports the investigation of similar integration challenges relevant to the broader context of quantum systems engineering.

LAN Weiyin, CUI Wei, CHEN Wenxuan et al.

The precise junction temperature monitoring is of paramount importance for enhancing the reliability of insulated gate bipolar transistor (IGBT) modules and extending the lifespan of devices. This paper introduces a method for monitoring junction temperature of IGBT modules based on turn-off voltages (TOV), which highlights resistance to load currents. The study initially verified the rationality of using TOVs as a temperature-sensitive electrical parameter. The deep neural network (DNN) technology was subsequently employed to eradicate the dependence of TOVs on load currents, facilitating accurate junction temperature prediction under varying operational conditions. The proposed method was validated through a single-phase pulse width modulation (PWM) experiment. The findings reveal an error range of ±5 ℃ for this method, demonstrating the feasibility of optimizing junction temperature monitoring through DNN utilization.

Sri Viknesh Permalu, Karthigesu Nagarajoo

Purpose – In an increasingly interconnected world, transportation infrastructure has emerged as a critical determinant of economic growth and global competitiveness. High-speed rail (HSR), characterized by its exceptional speed and efficiency, has garnered widespread attention as a transformative mode of transportation that transcends borders and fosters economic development. The Kuala Lumpur – Singapore (KL-SG) HSR project stands as a prominent exemplar of this paradigm, symbolizing the potential of HSR to serve as a catalyst for national economic advancement. Design/methodology/approach – This paper is prepared to provide an insight into the benefits and advantages of HSR based on proven case studies and references from global HSRs, including China, Spain, France and Japan. Findings – The findings that have been obtained focus on enhanced connectivity and accessibility, attracting foreign direct investment, revitalizing regional economies, urban development and city regeneration, boosting tourism and cultural exchange, human capital development, regional integration and environmental and sustainability benefits. Originality/value – The KL-SG HSR, linking Kuala Lumpur and Singapore, epitomizes the potential for HSR to be a transformative agent in the realm of economic development. This project encapsulates the aspirations of two dynamic Southeast Asian economies, united in their pursuit of sustainable growth, enhanced connectivity and global competitiveness. By scrutinizing the KL-SG High-Speed Rail through the lens of economic benchmarking, a deeper understanding emerges of how such projects can drive progress in areas such as cross-border trade, tourism, urban development and technological innovation.

Qiliang Li, Yuqing Sun, Menghan Ouyang et al.

Abstract Segregated incompressible large eddy simulation and acoustic perturbation equations were used to obtain the flow field and sound field of 1:25 scale trains with three, six and eight coaches in a long tunnel, and the aerodynamic results were verified by wind tunnel test with the same scale two-coach train model. Time-averaged drag coefficients of the head coach of three trains are similar, but at the tail coach of the multi-group trains it is much larger than that of the three-coach train. The eight-coach train presents the largest increment from the head coach to the tail coach in the standard deviation (STD) of aerodynamic force coefficients: 0.0110 for drag coefficient (C d), 0.0198 for lift coefficient (C l) and 0.0371 for side coefficient (C s). Total sound pressure level at the bottom of multi-group trains presents a significant streamwise increase, which is different from the three-coach train. Tunnel walls affect the acoustic distribution at the bottom, only after the coach number reaches a certain value, and the streamwise increase in the sound pressure fluctuation of multi-group trains is strengthened by coach number. Fourier transform of the turbulent and sound pressures presents that coach number has little influence on the peak frequencies, but increases the sound pressure level values at the tail bogie cavities. Furthermore, different from the turbulent pressure, the first two sound pressure proper orthogonal decomposition (POD) modes in the bogie cavities contain 90% of the total energy, and the spatial distributions indicate that the acoustic distributions in the head and tail bogies are not related to coach number.

Xiaofeng Hua, Lei Sun, Huaqiong Liu

Railroad transportation is an efficient and economical way of cargo transportation. Due to the imbalance of supply and demand in the railroad freight market, various factors have complex forms and different degrees of influence on the freight volume, which makes the forecasting of the railroad freight volume complexity and non-linear characteristics. This paper combines grey relation analysis and BP neural network to forecast the national railroad freight volume. Firstly, the data of the factors affecting the railroad freight volume from 2012 to 2022 are selected, and the grey relation analysis is used to obtain the relatively high correlation of the four influencing factors, namely the proportion of highway freight volume, the proportion of water freight volume, the mileage of railroad operation and the value added of the primary industry, which are used as the input layer of the BP neural network; then, according to the corresponding relationship between the influencing factors and the volume of railroad freight volume, the model is trained; finally, the model based on the model of railroad freight volume is trained; and the model based on the model of railroad freight volume is trained. Then, the model was trained according to the correspondence between each influential factor and railway freight volume; finally, the grey relation-based BP neural network model was compared with the traditional BP neural network model. Finally, the grey relation-based BP neural network model is compared with the traditional BP neural network model. The results show that the grey relation-based BP neural network can not only get better solutions, but also shorten the training time.

Marcus Kessel, Colin Atkinson

The ability of Generative AI (GAI) technology to automatically check, synthesize and modify software engineering artifacts promises to revolutionize all aspects of software engineering. Using GAI for software engineering tasks is consequently one of the most rapidly expanding fields of software engineering research, with over a hundred LLM-based code models having been published since 2021. However, the overwhelming majority of existing code models share a major weakness - they are exclusively trained on the syntactic facet of software, significantly lowering their trustworthiness in tasks dependent on software semantics. To address this problem, a new class of "Morescient" GAI is needed that is "aware" of (i.e., trained on) both the semantic and static facets of software. This, in turn, will require a new generation of software observation platforms capable of generating large quantities of execution observations in a structured and readily analyzable way. In this paper, we present a vision and roadmap for how such "Morescient" GAI models can be engineered, evolved and disseminated according to the principles of open science.

Roberto Casadei, Gianluca Aguzzi, Giorgio Audrito et al.

Today's distributed and pervasive computing addresses large-scale cyber-physical ecosystems, characterised by dense and large networks of devices capable of computation, communication and interaction with the environment and people. While most research focusses on treating these systems as "composites" (i.e., heterogeneous functional complexes), recent developments in fields such as self-organising systems and swarm robotics have opened up a complementary perspective: treating systems as "collectives" (i.e., uniform, collaborative, and self-organising groups of entities). This article explores the motivations, state of the art, and implications of this "collective computing paradigm" in software engineering, discusses its peculiar challenges, and outlines a path for future research, touching on aspects such as macroprogramming, collective intelligence, self-adaptive middleware, learning, synthesis, and experimentation of collective behaviour.

Valerio Terragni, Annie Vella, Partha Roop et al.

A paradigm shift is underway in Software Engineering, with AI systems such as LLMs playing an increasingly important role in boosting software development productivity. This trend is anticipated to persist. In the next years, we expect a growing symbiotic partnership between human software developers and AI. The Software Engineering research community cannot afford to overlook this trend; we must address the key research challenges posed by the integration of AI into the software development process. In this paper, we present our vision of the future of software development in an AI-driven world and explore the key challenges that our research community should address to realize this vision.

Arthur Pilone, Paulo Meirelles, Fabio Kon et al.

A central challenge for ensuring the success of software projects is to assure the convergence of developers' and users' views. While the availability of large amounts of user data from social media, app store reviews, and support channels bears many benefits, it still remains unclear how software development teams can effectively use this data. We present an LLM-powered approach called DeeperMatcher that helps agile teams use crowd-based requirements engineering (CrowdRE) in their issue and task management. We are currently implementing a command-line tool that enables developers to match issues with relevant user reviews. We validated our approach on an existing English dataset from a well-known open-source project. Additionally, to check how well DeeperMatcher works for other languages, we conducted a single-case mechanism experiment alongside developers of a local project that has issues and user feedback in Brazilian Portuguese. Our preliminary analysis indicates that the accuracy of our approach is highly dependent on the text embedding method used. We discuss further refinements needed for reliable crowd-based requirements engineering with multilingual support.

Dezhi Ran, Mengzhou Wu, Wei Yang et al.

By treating data and models as the source code, Foundation Models (FMs) become a new type of software. Mirroring the concept of software crisis, the increasing complexity of FMs making FM crisis a tangible concern in the coming decade, appealing for new theories and methodologies from the field of software engineering. In this paper, we outline our vision of introducing Foundation Model (FM) engineering, a strategic response to the anticipated FM crisis with principled engineering methodologies. FM engineering aims to mitigate potential issues in FM development and application through the introduction of declarative, automated, and unified programming interfaces for both data and model management, reducing the complexities involved in working with FMs by providing a more structured and intuitive process for developers. Through the establishment of FM engineering, we aim to provide a robust, automated, and extensible framework that addresses the imminent challenges, and discovering new research opportunities for the software engineering field.

O. Ablyalimov, A. Osipov, D. Kurilkin

The paper presents the results of research on the justification of parameters of transport operation of three-section main (train) UzTE16M3 freight diesel locomotives on the high-speed railway section Marokand- Kattakurgan of JSC “Uzbekistan Temir Yullari” when moving freight trains without stops and with stops at intermediate stations, passing points, and separate points. The specified results were obtained by methods of locomotive traction theory in the form of tabular data, graphical dependences, and regression equations for determining logistical kinematic parameters of freight train traffic and the main energy efficiency indicators of the investigated diesel locomotives in a given section. The research results obtained by the authors can be used by drivers - instructors in thermal engineering and specialists of linear enterprises of JSC “Uzbekistan Temir Yullari” locomotive complex, whose professional and production activity is connected with the issues of saving of natural diesel fuel consumption by diesel locomotives on high-speed sections of the railroads.

Хлуднев Александр Александрович

The article is aimed at describing the tool of process analytics in the re-engineering of technological operations in the operation of railway transportation of an industrial enterprise. Efficiency improvement in process management is considered on the basis of their structuring with subsequent visualization. In particular, the article presents a target model of unsuitable railway rolling stock management aimed at reducing the risks of failure to fulfill the sales plan of industrial enterprises, where railway transportation dominates in the shipment of finished products.

Jie JW Wu

Machine learning (ML) components are being added to more and more critical and impactful software systems, but the software development process of real-world production systems from prototyped ML models remains challenging with additional complexity and interdisciplinary collaboration challenges. This poses difficulties in using traditional software lifecycle models such as waterfall, spiral, or agile models when building ML-enabled systems. In this research, we apply a Systems Engineering lens to investigate the use of V-Model in addressing the interdisciplinary collaboration challenges when building ML-enabled systems. By interviewing practitioners from software companies, we established a set of 8 propositions for using V-Model to manage interdisciplinary collaborations when building products with ML components. Based on the propositions, we found that despite requiring additional efforts, the characteristics of V-Model align effectively with several collaboration challenges encountered by practitioners when building ML-enabled systems. We recommend future research to investigate new process models, frameworks and tools that leverage the characteristics of V-Model such as the system decomposition, clear system boundary, and consistency of Validation & Verification (V&V) for building ML-enabled systems.

YANG Fengping, ZHOU Mingzhi, CHENG Quan et al.

For the traditional PI controlled urban rail hybrid energy storage system, there are problems such as cumbersome parameter adjustment and lag in response to train start and stop conditions. An improved multi-step prediction control algorithm for urban rail hybrid energy storage system was proposed in this paper. The multi-step predictive current control loop was used to replace the traditional PI current inner loop to avoid the prediction error defect of single-step prediction and improve the dynamic response speed of the system. For the problem of large current ripple caused by non-zero equivalent duty cycle in the predicted current algorithm, the current fluctuation range at the optimal switching time was calculated in real time, and the switching action time was updated online. Finally, a hybrid energy storage system model for urban rail trains was built on the MATLAB/Simulink platform. The simulation results show that under the conditions of train acceleration and braking, the network voltage recovery time is reduced by 0.543 s and 0.644 s respectively, the overshoot is reduced by 5.98% and 4.83%, and the change rate of current ripple is significantly improved, which verifies the correctness and superiority of the strategy proposed in this paper.