Automatic Train Research Articles

Managerial Challenges in Implementing European Rail Traffic Management System, Remote Train Control, and Automatic Train Operation: A Literature Review

This paper explores the management of digitalization projects within the railway industry. It aims to increase and understand the opportunities presented by digitalization and automation in rail operations. Employing a scoping review methodology, this research investigates the execution of European Rail Traffic Management System (ERTMS), remote train control (RTC), and automatic train operation (ATO) projects spanning from 2005 to 2023, with a particular emphasis on metro automation, the remote control of freight and passenger trains, fully automated trains, and highly assisted driving. The refined selection process yielded 30 papers. The analysis of the retrieved papers identified managerial issues, with stakeholder management, change management, and organizational management emerging as recurring themes. Despite the increasing trend in publications, the limited representation managerial issues in ERTMS, RTC, and ATO projects in scientific research persists, with implications for the industry’s advancement. This research sheds light on the critical intersection of change management and digitalization within the railway industry by showing the impact of ERTMS, RTC, and ATO on organizational and scope dynamics. The need for human-centered systems is highlighted, showing the necessity of involving every echelon of the organization in the change management process. These findings provide insights for practitioners, researchers, and policymakers, emphasizing the need for understanding and addressing managerial aspects for successful and sustainable digitalization implementations.

TransImg: A Translation Algorithm of Visible-to-Infrared Image Based on Generative Adversarial Network

Infrared images of sensitive targets are difficult to obtain and cannot meet the design and training needs of target detection and tracking algorithms for mobile platforms such as aircraft. This paper proposes an image translation algorithm TransImg, which can achieve visible light image translation to the infrared domain to enrich the dataset. First, the algorithm designed a generator structure consisting of a deep residual connected encoder and a region perception feature fusion module to enhance feature learning, thereby avoiding issues such as generating infrared images with insufficient details in the transfer task. Afterward, a multi-scale discriminator and a composite loss function were designed to further improve the transfer effect. Finally, an automatic mixed-precision training strategy was designed for the overall migration algorithm architecture to accelerate the training and generation of infrared images. Experiments have shown that the image translation algorithm TransImg has good algorithm accuracy, and the infrared image generated by visible light image translation has richer texture details, faster generation speed, and lower video memory consumption, and the performance exceeds the mainstream traditional algorithm, and the generated images can meet the requirements of target detection and tracking algorithms design and training for mobile platforms such as aircraft.

Research on Multi-Objective Optimization Methods of Urban Rail Train Automatic Driving Based on NSGA-II

In order to improve the control performance of automatic train operation (ATO) in urban rail trains, five typical operating sequences of urban rail trains were studied. Under the condition of meeting the safety and comfort principles of train operation, a train dynamics model was established to achieve the goals of low energy consumption, short running time, and high stopping accuracy in urban rail transit trains. In the process of finding a multi-objective solution to this problem, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was used with an elite retention strategy, and the optimal Pareto multi-objective solution set was sought. In the process of optimal solution weight assignment, the hierarchical analysis Mahalanobis distance method, which combines subjective and objective analysis, was used. Finally, taking the Beijing Yizhuang subway line as the background design example, the simulation verified the effectiveness and feasibility of the algorithm and obtained high-quality automatic train driving curves under various working conditions. This research has important reference significance for the actual operation of automatic driving in urban rail trains.

State-Space Modeling and Feedback Control for Real-Time Automatic Train Timetable Rescheduling of Intercity HSRs

State-Space Modeling and Feedback Control for Real-Time Automatic Train Timetable Rescheduling of Intercity HSRs

Selected applications of satellite technologies in rail transport

Global Navigation Satellite Systems (GNSS) are increasingly being used in various modes of transport, including rail transport. When this technology is applied to railway traffic control, it is essential to ensure a high level of safety and reliability. The approval of a railway traffic control system requires a safety analysis, which includes hazard analysis and risk analysis. This also includes GNSS-based solutions in terms of their compliance with safety integrity requirements, i.e. THR (Tolerable Hazard Rate) and SIL (Safety Integrity Level) parameters, as defined in normative documents. In the case of railway traffic control systems, the level of dependability of the determined train position, referred to as position integrity, is very important in ensuring safety. Position integrity is affected by many factors, including: errors due to SIS (Signal-In-Space) propagation, multipath errors, signal interference or GNSS receiver errors. In order to improve position integrity, among other things, new data processing methods can be used to improve the accuracy and reliability of measurements. The paper presents the concept of satellite signal processing for precise determination of the position of objects in selected railway systems. The Kalman filter based model of satellite signal filtration and its selected applications, which were tested in the real condition, was presented. The application of Kalman filtration indicated in the paper is a universal method that improves the estimated measurement parameters and can be used in many applications of satellite systems for railway tasks. The applicability of satellite systems to automatic train operation, defect positioning in automatic and manual flaw detection tests, determining track spatial orientation and train integrity control have been considered. The conducted tests confirmed the correctness of the adopted concept and the model of satellite signals filtration developed for this purpose. According to the authors, the described methods can also be used in many other tasks related to rail transport.

Reinforced performance control for automatic train operation with speed measurement deviation: a recollection observer approach

Reinforced performance control for automatic train operation with speed measurement deviation: a recollection observer approach

Prospects of autonomous railway transport development

The implementation of unmanned train control systems offers a number of advantages, such as increasing the capacity of railway lines and traffi c volumes, reducing the ‘human factor’, as well as reducing operating costs. The paper considers the challenges arising from the use of automatic train control systems, and presents the prospects for the implementation of automatic technologies in railway transport for various railway systems. The social and economic aspects of changing professional activities in railway transport are described. Grades of automation applicable to surface urban railwaytransport are presented. The issues of proving the functional safety of machine vision systems as part of the train traffic control system and determining their level of safety completeness are discussed. Examples of railway transport automation in Russia and other countries are given. Basic scenarios of automatic control system operation describing normal and abnormal situations are formulated. In conclusion, the levels of technological readiness of the reviewed solutions in the fi eld of train traffic automation are defi ned. The tasks faced by railway companies in implementing these technologies are outlined, and possible ways of overcoming obstacles to the introduction of automatic systems are proposed, taking into account the current political situation.

Creating the Slider Tester Repair Recommendation System to Enhance the Repair Step by Using Machine Learning

This project aims to develop a recommendation system to mitigate looping issues in HDD slider testing using the Amber testing machine (Machine A). Components simulating the HDD often fail and require repair before re-testing. However, post-repair, there is a 34% probability that the component (referred to as Product A) will experience looping, characterized by repeated failures with error code A. This recurring issue significantly hampers testing efficiency by reducing the number of successful slider tests. To address this challenge, we propose a dual-approach recommendation system that provides technicians with actionable insights to minimize the occurrence of looping. For previously analyzed components, a collaborative filtering technique utilizing implicit ratings is employed to generate recommendations. For new components, for which prior data are unavailable, a cosine similarity approach is applied to suggest optimal actions. An automatic training system is implemented to retrain the model as new data become available, ensuring that the recommendation system remains robust and effective over time. The proposed system is expected to offer precise guidance to technicians, thereby improving the overall efficiency of the testing process by reducing the frequency of looping issues. This work represents a significant advancement in enhancing operational reliability and productivity in HDD slider testing.

Two-step Passenger-to-Train and Route Assignment Model for Urban Rail Transit

Accurate passenger flow assignment results are crucial for the operational organization of urban rail transit. However, because of barrier-free transfer, the transfer information of passengers is not recorded. The paper proposes the two-step passenger-to-train and route assignment (TPTRA) model to address this issue. Each passenger is assigned to the trains and one route considering the complex transfer situation using TPTRA compared with the existing passenger-to-train model. Constraints on passengers, trains, and routes are constructed based on a large amount of real automatic fare collection data, train schedules, and metro topology networks to improve accuracy and transferability over traditional survey-based methods. The generalized logistic is first used to evaluate the egress time, access time, and transfer time distributions. Finally, TPTRA is developed based on the constraints and distributions. The model estimates the probability of passengers choosing the feasible routes and boarding the first train. It also calculates transfer passenger flow values and the probability of passengers being left behind. The analysis demonstrates a notable enhancement in the accuracy of the egress time distribution fitting using the generalized logistic distribution, with an improvement of 84.41% compared with the lognormal distribution and 15.78% compared with the normal distribution. Furthermore, the model’s effectiveness is validated through sectional passenger flow comparisons, yielding R-squared values between 0.847 and 0.902, indicating the effectiveness and reliability of the TPTRA model.

Improving Automatic Parallel Training via Balanced Memory Workload Optimization

Improving Automatic Parallel Training via Balanced Memory Workload Optimization

Simulation and analysis of optimal energy-saving mode in microfield of underground rail transit

Underground rail transit has become one of the most popular transportation modes because of its advantages such as fast running speed, large passenger flow and punctuality. This mode of transportation can alleviate urban traffic congestion to a certain extent, so underground rail transit has been vigorously developed, and the number of rail lines has increased exponentially. However, with the continuous development of underground rail transit, the energy consumption of train operation is also increasing, resulting in a waste of energy. To solve this problem, this paper proposes to improve the energy-saving technology of train operation by using train autopilot control strategy. Firstly, a train operation optimization model considering train position and speed limit is established by using automatic train driving strategy, and the nonlinear problem of the optimization model is solved by genetic algorithm. The micro-field theory is introduced into the control strategy of automatic train driving, and the energy-saving model of underground rail transit is established. The energy consumption is optimized from three aspects: train energy-saving technology, line planning and overall operation planning of rail transit. The simulation results show that the average impact rate and energy consumption of trains under the proposed energy-saving model are significantly reduced compared with the other two groups of trains, and the average impact rate and energy consumption are significantly reduced compared with the other two groups of trains. The running time and energy consumption of the energy-saving model are lower than those of the experimental group. To sum up, the energy-saving model of underground rail transit proposed in this paper not only reduces the operating energy consumption, but also improves the passenger comfort, which can provide low-cost energy-saving technology for underground transportation field, and has positive significance for urban low-carbon development.

Railway Infrastructure Cybersecurity: An Overview

The railway infrastructure constitutes a type of operational technology (OT)-based critical infrastructure, which is expected to work 24x7, 365 days a year, and where the life expectancy of operational equipment often exceeds 30 years. In this domain, an operational anomaly compromising the OT system can cause a train accident or interrupt traffic, with potentially significant impact in terms of business as well as for passenger safety. Due to their relevance, railways are strategic assets of national interest and, consequently, targets of interest for cybercriminals and cyberwarfare activities. For instance, service interruptions may trigger ripple effects resulting in product shortages and widespread supply chain disruptions, with severe impacts for both the economy and national security. In a bid to optimise and streamline operations. the railway industry has recently started taking a series of significant steps towards digitization, with infrastructures experiencing a significant paradigm shift which, for instance, makes it possible to have centralised interlockings and Radio Block Centre (RBC) for an entire country, with geographical redundancy, ensuring the utmost availability and punctuality by moving the control logic to the cloud. Nevertheless, these developments must always be carried on within the scope of established cybersecurity standards and frameworks. This paper presents an analysis of the state of the art on railway cybersecurity, focused on the existing solutions based on the application of the CENELEC “Technical specification 50701 - Railway Application – Cybersecurity”, which is currently the latest European specification addressing railways, being designed to help suppliers, integrators, and operators to implement a cybersecurity risk assessment plan, the necessary controls, and the management of the complete system life cycle. Special attention will be paid to the conduit between the rail signal interlocking system, that controls the line signalling, and the Automatic Train Supervision (ATS) that runs in the Operational Control Centre (OCC), as this has been identified by the European Union Agency for Cybersecurity (ENISA) as one of the most critical systems identified by the operators of essential services.

Self-supervised 3D vehicle detection based on monocular images

The deep learning-based 3D object detection literature on monocular images has been dominated by methods that require supervision in the form of 3D bounding box annotations for training. However, obtaining sufficient 3D annotations is expensive, laborious and prone to introducing errors. To address this problem, we propose a monocular self-supervised approach towards 3D object detection relying solely on observed RGB data rather than 3D bounding boxes for training. We leverage differentiable rendering to apply visual alignment to depth maps, instance masks and point clouds for self-supervision. Furthermore, considering the complexity of autonomous driving scenes, we introduce a point cloud filter to reduce noise impact and design an automatic training set pruning strategy suitable for the self-supervised framework to further improve network performance. We provide detailed experiments on the KITTI benchmark and achieve competitive performance with existing self-supervised methods as well as some fully supervised methods.

Predicting cervical cancer risk probabilities using advanced H20 AutoML and local interpretable model-agnostic explanation techniques

Background Cancer is positioned as a major disease, particularly for middle-aged people, which remains a global concern that can develop in the form of abnormal growth of body cells at any place in the human body. Cervical cancer, often known as cervix cancer, is cancer present in the female cervix. In the area where the endocervix (upper two-thirds of the cervix) and ectocervix (lower third of the cervix) meet, the majority of cervical cancers begin. Despite an influx of people entering the healthcare industry, the demand for machine learning (ML) specialists has recently outpaced the supply. To close the gap, user-friendly applications, such as H2O, have made significant progress these days. However, traditional ML techniques handle each stage of the process separately; whereas H2O AutoML can automate a major portion of the ML workflow, such as automatic training and tuning of multiple models within a user-defined timeframe. Methods Thus, novel H2O AutoML with local interpretable model-agnostic explanations (LIME) techniques have been proposed in this research work that enhance the predictability of an ML model in a user-defined timeframe. We herein collected the cervical cancer dataset from the freely available Kaggle repository for our research work. The Stacked Ensembles approach, on the other hand, will automatically train H2O models to create a highly predictive ensemble model that will outperform the AutoML Leaderboard in most instances. The novelty of this research is aimed at training the best model using the AutoML technique that helps in reducing the human effort over traditional ML techniques in less amount of time. Additionally, LIME has been implemented over the H2O AutoML model, to uncover black boxes and to explain every individual prediction in our model. We have evaluated our model performance using the findprediction() function on three different idx values (i.e., 100, 120, and 150) to find the prediction probabilities of two classes for each feature. These experiments have been done in Lenovo core i7 NVidia GeForce 860M GPU laptop in Windows 10 operating system using Python 3.8.3 software on Jupyter 6.4.3 platform. Results The proposed model resulted in the prediction probabilities depending on the features as 87%, 95%, and 87% for class ‘0’ and 13%, 5%, and 13% for class ‘1’ when idx_value=100, 120, and 150 for the first case; 100% for class ‘0’ and 0% for class ‘1’, when idx_value= 10, 12, and 15 respectively. Additionally, a comparative analysis has been drawn where our proposed model outperforms previous results found in cervical cancer research.

Resilient Virtual Coupling Control of Automatic Train Convoys With Intermittent Communications

Resilient Virtual Coupling Control of Automatic Train Convoys With Intermittent Communications

АВТОМАТИЧЕСКАЯ ОБУЧАЮЩАЯ СИСТЕМА КОМПЬЮТЕРНОГО ТРЕНАЖЕРА

One of the effective tools of a computer simulator is considered – an automatic training system (AOS) designed to train operators of technological installations on a simulator in an autonomous mode without the participation of an instructor

ОСОБЕНННОСТИ РАЗРАБОТКИ СЦЕНАРИЕВ ДЛЯ АВТОМАТИЧЕСКОЙ ОБУЧАЮЩЕЙ СИСТЕМЫ КОМПЬЮТЕРНОГО ТРЕНАЖЕРА

The features that must be taken into account when developing scenarios for an automatic training system of a computer simulator are considered

Real‐time multi‐objective speed planning ATO considering assist driving for subway

AbstractSpeed curve planning is one of the most important functions of automatic train operation (ATO). To improve the real‐time optimization capability and driver‐friendliness of the existing ATO, an extended ATO framework considering both automatic driving and assisted driving is designed. A multi‐objective optimization model based on quadratic programming is established considering energy‐saving, punctuality, and comfort. However, due to the influence of the weight of multi‐objectives, this method cannot directly obtain the speed curve satisfying the trip time constraint. Further, based on the analysis about the weight of multi‐objects, a time‐constrained quadratic programming algorithm is proposed. With the proposed method, the speed curve can be calculated in real‐time both before operations and during operations. For the former, time‐varying train mass and trip time are considered to guarantee an optimal solution. For the latter, deviations, delays, and maloperations on the way are corrected. Simulation experiments verify the solvability and real‐time performance of the proposed method. In particular, compared with the dynamic programming and (mixed‐integer linear programming) MILP method, the proposed method is more energy‐efficient and easier to be followed by the driver. In addition, a prototype is developed for commercial tests on a Beijing subway line. The relevant performance is verified in commercial tests.

Federated learning-based edge computing for automatic train operation in communication-based train control systems

Federated learning-based edge computing for automatic train operation in communication-based train control systems

Developing automated machine learning approach for fast and robust crop yield prediction using a fusion of remote sensing, soil, and weather dataset

Estimating smallholder crop yields robustly and timely is crucial for improving agronomic practices, determining yield gaps, guiding investment, and policymaking to ensure food security. However, there is poor estimation of yield for most smallholders due to lack of technology, and field scale data, particularly in Egypt. Automated machine learning (AutoML) can be used to automate the machine learning workflow, including automatic training and optimization of multiple models within a user-specified time frame, but it has less attention so far. Here, we combined extensive field survey yield across wheat cultivated area in Egypt with diverse dataset of remote sensing, soil, and weather to predict field-level wheat yield using 22 Ml models in AutoML. The models showed robust accuracies for yield predictions, recording Willmott degree of agreement, (d > 0.80) with higher accuracy when super learner (stacked ensemble) was used (R2 = 0.51, d = 0.82). The trained AutoML was deployed to predict yield using remote sensing (RS) vegetative indices (VIs), demonstrating a good correlation with actual yield (R2 = 0.7). This is very important since it is considered a low-cost tool and could be used to explore early yield predictions. Since climate change has negative impacts on agricultural production and food security with some uncertainties, AutoML was deployed to predict wheat yield under recent climate scenarios from the Coupled Model Intercomparison Project Phase 6 (CMIP6). These scenarios included single downscaled General Circulation Model (GCM) as CanESM5 and two shared socioeconomic pathways (SSPs) as SSP2-4.5and SSP5-8.5during the mid-term period (2050). The stacked ensemble model displayed declines in yield of 21% and 5% under SSP5-8.5 and SSP2-4.5 respectively during mid-century, with higher uncertainty under the highest emission scenario (SSP5-8.5). The developed approach could be used as a rapid, accurate and low-cost method to predict yield for stakeholder farms all over the world where ground data is scarce.