Automatic Train Research Articles

A Literature Review on Train Motion Model Calibration

The dynamics of a moving train are usually described by means of a motion model based on Newton’s second law. This model uses as input track geometry data and train characteristics like mass, the parameters that model the running resistance, the maximum tractive effort and power, and the brake rates to be applied. It can reproduce and predict train dynamics accurately if the mentioned train characteristics are carefully calibrated. The model constitutes the core element of a broad variety of railway applications, from timetabling tools to Driver Advisory Systems and Automatic Train Operation. Among the existing train motion model calibration techniques, those that use operational data are of particular interest, as they benefit from on- board recorded data, capturing the train dynamics during operation. In this literature review article we provide an overview of the train motion model calibration techniques that have been published in the scientific literature between January 2000 and December 2021 and either use operational data or can be minimally adapted to use it. To this end, we present a critical overview of the existing train motion model calibration approaches, distinguishing online calibration that analyzes data on- the-go and offline calibration that analyzes historical data batchwise. We propose a research agenda and highlight some potential goals to be tackled in the near future: from devising accurate online calibrators for eco-driving applications to quantitizing the physical sources of parameter variation. Last, we discuss practical recommendations for practitioners and scholars inferred from the current state of the art.

The Efficacy of Trunk Bracing With an Instrumented Corrective Exercise on Spinal Deformity, Pulmonary Function, Trunk Muscle Endurance, and Quality of Life in Adolescent Idiopathic Scoliosis: Protocol for a Parallel Groups Clinical Study.

Adolescent idiopathic scoliosis is a 3D spine distortion with an unidentified etiology. It results in noticeable trunk deformity, decreased muscle strength and endurance at the trunk, changes in chest volume, breathing issues, and ultimately a decline in the quality of life. Trunk bracing and corrective exercises make up most of the treatment of patients with scoliosis when their deformity is between 20° and 45°, and they have not yet attained skeletal maturity. Evidence suggests that spinal deformity in people with scoliosis may result from improper motor control. Automatic response training is an exercise therapy technique that can modify the pattern of trunk muscle control for supporting the spinal column in normal alignment. An apparatus called a cantilever device is required for this type of exercise, which facilitates training at home. In spite of research showing the benefit of braces and therapeutic exercise in adolescents with scoliosis, less emphasis has been given to the impact of home-based training, especially when this intervention is paired with braces. We aim to compare the efficacy of bracing and a conventional exercise program to a combination treatment that includes trunk bracing and exercises with a cantilever device performed at home on the degree of spine curvature, pulmonary function, trunk muscular endurance, and quality of life. This study was a 2-arms parallel-group clinical study. A total of 16 adolescents with idiopathic scoliosis and single lumbar and thoracolumbar curves of 20°-45° were recruited and randomly assigned into 2 groups. Group A received a combination of trunk bracing and exercise using an instrument known as a "cantilever." Group B (controls) received trunk bracing and a conventional exercise program (without a tool). The study outcomes were the Cobb angle of the scoliotic curve, pulmonary function, the endurance of the trunk muscles, and quality of life. The study outcomes were measured at 2 time points: before the intervention (T1) and 12 weeks following the start of the intervention (T2; at this time, the intervention period has been completed). Multivariate analysis of variance was used to test between- and within-group differences. Recruitment for this study began in fall 2022 and is expected to be completed by the end of summer 2023. We studied the efficacy of a combined trunk bracing program and postural response exercises using a cantilever device in treating adolescent idiopathic scoliosis and compared it with trunk bracing and conventional home exercises. Exercises performed at home using a cantilever device are anticipated to raise the endurance of trunk muscles, which will help reduce trunk deformity, enhance pulmonary function, and improve the quality of life of participants. Iranian Registry of Clinical Trials IRCT20220330054371N1; https://www.irct.ir/trial/62811. PRR1-10.2196/43265.

An energy‐efficient train control approach with dynamic efficiency of the traction system

AbstractThe efficiency of the train traction system (TTS) changes dynamically with operating conditions. In this paper, a more realistic dynamic efficiency model of TTS is established considering the power flow and non‐linear loss of TTS. Based on the real model, the optimal control problem of the train with the minimum electric power consumption on the grid side is constructed. The optimal control condition (OCC) and corresponding control force are derived based on the Pontryagin maximum principle (PMP). A dynamic programming algorithm (DP2) with the OCC curve as the state space is designed to obtain optimal results. The proposed model and the method are validated by the comparison of conventional dynamic programming (DP1) and automatic train operation (ATO) measured data. The simulation results show that compared with the traditional TTS constant efficiency model, considering that the TTS dynamic efficiency model has a better energy‐saving effect, and the designed DP2 algorithm has a more obvious energy‐saving effect than DP1.

Determinants of autonomous train operation adoption in rail freight: knowledge-based assessment with Delphi-ANP approach

Railways are the backbone of complex and multimodal transport systems in Europe. To secure a larger share of the transport market and attract existing and future freight customers, further improvement in services is required. To achieve this goal, the use of new technologies in the era of railway automation and digitalization is required. Automatic train operation (ATO) in rail transport is considered a promising solution for providing cost-effective rail products. In this study, we define ATO as autonomous train operation and the feasibility of ATO deployment in rail freight is investigated. For this purpose, a knowledge-based approach is introduced to identify opportunities, problems, and the most appropriate grade of automation in rail freight. In a multi-stage process, Delphi questionnaires were combined with the analytic network process (ANP) method to investigate, define, and weight the determinants for ATO deployment. The final phase of the survey estimated the potential costs and drivers for different grades of automation. The results show that, in addition to the positive impacts of ATO, there are numerous challenges and risks that need to be analysed before ATO is implemented. In addition, the Delphi-ANP approach was used to identify the key determinants for decision-making prior to ATO implementation and the most viable alternative based on them. Investment cost, level of safety, energy saving, and reliability of management system are the most important determinants for the decision to implement ATO. The results of this study can effectively support rail infrastructure managers and operators in strategic planning and decision-making for ATO implementation in rail freight.

Estimating the safety and reliability of the control system of a locomotive with machine vision

Abstract. Aim. The paper aims to evaluate the indicators of safety and reliability of the MALS suite of technology that ensures the control of locomotives. Increased indicators are achieved through the use of additional controls. As such, a second virtual channel is proposed. The latter allows detecting MALS failures without affecting the shunting engine control algorithms.Methods. The paper uses the graph method. Using a modified topological semi-Markov method, formulas were deduced for calculating the mean time to failure and the safety factor.Results. The paper individually examines the mean time of the automatic train operation system of a shunting engine remaining in at least SIL3 and mean time to hazardous failure. The authors research the dependence of the above indicators on the failure rate of the MALS equipment and the machine vision. Using the graph method, the level of the system’s functional safety was evaluated by calculating the safety factor and the danger factor. The dependence of the above factors on the system recovery time and probability of detection of component failures was examined.

Spatial adaptive iterative learning control for high-speed train with unknown speed delays

This article focuses on the high-speed train with unknown speed delays; a spatial adaptive iterative learning control (SAILC) algorithm is designed to solve the displacement-speed trajectory tracking problem by using the spatial differential operator to transform the train temporal dynamic model into a spatial model. First, parametric adaptive control is used to reduce the influence of system uncertainties. Second, a Lyapunov-Krasovskii-like spatial composite energy function (SCEF) is established, the stability of the designed controller and the convergence of the tracking error are demonstrated by verifying the differential negative definiteness and boundedness of the function. In addition, the train speed needs to be maintained within a certain range due to the speed loss when it passes through the neutral zone and overspeed protection. Therefore, the state-constrained mechanism is implanted into the train control algorithm to ensure that the train operates within the speed limits. Finally, the proposed SAILC algorithm is compared with proportional-integral-derivative (PID) and iterative learning control (ILC) algorithm; the results of the numerical simulations prove the effectiveness of the proposed method. After 20 iterations, the maximum absolute error of SAILC is 0.05 m/s, which is 4.7% of PID and 10.7% of ILC. It meets the requirements of Automatic Train Operation (ATO) that the tracking error should not be greater than 1% of the train operating speed.

A Two-Stage Optimization Algorithm of the Train Traction Energy Consumption in Urban Rail Transit

The optimization of the train traction energy consumption in urban rail transit is a nonlinear optimization problem, and its solution is a very difficult task. This article focuses on the optimization of train traction energy consumption on the line with multiple stations. First, a single-objective nonlinear energy-saving optimization model is established for a given line and total travel time. Second, a two-stage optimization algorithm is proposed to solve this model. In the first stage, for a given interval and travel time, an optimization model of the traction energy consumption is established by using the distance discretization method. A dichotomous iterative algorithm based on energy consumption is proposed to search the optimal traction energy consumption. By calling this algorithm repeatedly, the energy–time curve of each interval can be obtained. In the second stage, according to these energy–time curves, the total travel time of a train on the line is allocated to each interval one by one in the form of time slices. And finally the optimal travel time and optimal traction energy consumption of the train on each interval are obtained. This method does not need to set the train operation mode sequence in advance but adaptively selects the energy-saving operation mode according to the line constraints and the train parameters. The up-direction from Yizhuang to Tongjinan of the Beijing Metro Yizhuang line in China is selected as the test section. The experimental results demonstrate the effectiveness and computational efficiency of our proposed methods and algorithms. Moreover, the dichotomous iterative algorithm runs so fast that it can be used in real-time driver advisory systems or automatic train operation systems.

Hierarchical optimal control framework to automatic train regulation combined with energy-efficient speed trajectory calculation in metro lines

In high-density metro lines, frequent disturbances could lead to a domino effect of train delays if no adjustment strategy is imposed timely. In this paper, to enhance train timetable adherence and reduce energy consumption, we provide a hierarchical optimal control framework for the automatic train regulation problem with energy-efficient speed trajectory based on the model predictive control method. Specifically, by considering the dynamic passenger flows, the non-linear train regulation model is proposed at the higher level to enhance timetable adherence, while at the lower level the energy-efficient speed trajectories of the trains are generated on-line in a distributed manner. The interaction of real-time information exists between the higher level and the lower level, i.e., the upper model provides the train running time and the numbers of onboard passengers to the lower model, while the lower model feedbacks the updated train information (e.g., the actual arrival time) to the upper model, which provides the potential for the proposed framework to respond to disturbances at the operational stage. Moreover, a customized model predictive control method combined with Radau pseudospectral method (RPM) is designed to generate the energy-efficient train speed trajectory at the lower level in response to uncertain operational conditions. Numerical cases based on the Beijing Metro Yizhuang line demonstrate the effectiveness and robustness of our proposed hierarchical optimal control framework to deal with uncertain disturbances.

Sudden Cardiac Death in Athletes: Facts and Fallacies

The benefits of exercise for cardiovascular and general health are many. However, sudden cardiac death (SCD) may occur in apparently healthy athletes who perform at the highest levels. A diverse spectrum of diseases is implicated in SCD in athletes, and while atherosclerotic coronary artery disease predominates in individuals of >35 years of age, primary cardiomyopathies and ion channelopathies are prevalent in young individuals. Prevention of SCD in athletes relies on the implementation of health policies aimed at the early identification of arrhythmogenic diseases (such as cardiac screening) and successful resuscitation (such as widespread utilization of automatic external defibrillators and training members of the public on cardiopulmonary resuscitation). This review will focus on the epidemiology and aetiologies of SCD in athletes, and examine fallacies in the approach to this controversial field. Furthermore, potential strategies to prevent these tragic events will be discussed, analysing current practice, gaps in knowledge and future directions.

Research on Information Fusion Preview Control for Freight Train Speed Tracking

Background: With the increase in the speed and capacity of freight trains, the safety, energy efficiency and intelligent operation of train operation have become increasingly important. Automatic freight trains operation can replace manual operation with automated control systems, which can guarantee the safety of train operation, and improve operational efficiency and reduce operational energy consumption. Objective: Solve the problem of tracking accuracy and stability deterioration caused by multi-information of freight train. Methods: Global navigation satellite system, inertial navigation system and speed measuring motor are selected to construct a speed fusion measurement model by using loosely coupled integrated navigation and improved entropy weight method. Calculate the information quantity of performance index and control quantity in preview control, get the controlled quantity of information fusion optimal preview control. Results: The average tracking error of the multi-source information fusion preview controller is 0.038m/s, which is 49% lower than that of the control experiment. Conclusion: Multi-source information fusion preview controller can effectively reduce the tracking error of freight train speed tracking system and improve the accuracy of automatic freight trains operation.

Time Series Prediction Method of Metrics of Dispatching Automation System Based on AI Platform

In view of the shortcomings of manual operation mode and passive anomaly perception in the current dispatching automation system, this paper provides a time series prediction method for the metrics of the dispatching automation system based on the artificial intelligence platform. Firstly, based on the collected metrics of the dispatching automation system, the time series prediction algorithm of metrics based on Long Short-Term Memory(LSTM) and LightGBM(LGB) combined model is studied. Then, the algorithm is integrated into a one-stop graphical interactive modeling tool and the model training process is drawn. Through the task is automatic split and distributed model training is automatically carried out on a regular basis. Then, the AI model service sharing technology based on Kubernetes is used to realize the model service release and automatic update, and the platform interactive development component is used to realize automatic online prediction and rolling iterative update. Finally, the actual data of the system metrics is used for example analysis, and the results show that the proposed method can realize the advance prediction of the system metrics, and realize the whole process automatic integration model training and prediction based on the artificial intelligence platform, and effectively improve the model training efficiency, meet the real-time and security requirements of the dispatching automation system, and is more suitable for engineering application scenarios.

Haberleşme Tabanlı Tren Kontrolünün (CBTC) Otomatik Tren Korumasına (ATP) İlişkin Dağıtılmış-Hiyerarşik Kontrol Yaklaşımı

Kentleşme ile birlikte metropollerde yaşayan insan sayısı artmaktadır, nüfus artışına paralel olarak şehir içi ulaşımda çok önemli bir yer tutan raylı ulaşım sistemlerine olan talep, kalabalık şehirlerde her geçen gün daha da artmaktadır.Artan talebe paralel olarak raylarda artacak trafik yoğunluğu, sinyalizasyon sistemlerini güvenlik, kapasite ve rayların verimine etkisi açısından oldukça önemli kılmaktadır. Günümüzde birçok raylı ulaşım sistemlerinde sinyalizasyon sistemi olarak Haberleşme Tabanlı Tren Kontrol (CBTC) tercih edilmektedir. CBTC, Otomatik Tren Koruması (ATP), Otomatik Tren Denetimi (ATS) ve Otomatik Tren İşletmesi (ATO) gibi bazı alt sistemlerden meydana gelmektedir. Alt sistemlerin kendine özgü tanımlanan bazı görevleri bulunmaktadır. Bu görevleri yerine getirirken, alt sistemlerden artan gereksinimlerden etkilenmeden, istenen emniyet fonksiyonlarını en üst düzeyde güvenle uygulaması beklenmektedir. Ancak, bu sistemlerin genel tasarımının, ihtiyaç duyulan yeni gereksinimlere göre değiştirilmesi gerekebilir. Bu bağlamda çeşitli standartların sağlarken, alt sistemlerin kontrol edilmesi ve modellenmeleri büyük önem taşımaktadır. Bu çalışmada, CBTC’nin alt sistemi ATP, ayrık olay sistemi yaklaşımıyla sonlu durum otomatları ile modellenmiştir ve alt sistemlere ait denetimsel gözetleyicilerin tasarımı yapılarak, kontrol edilebilirlik ve kilitlenmesiz kontrol koşullarını karşıladığı gösterilerek, elde edilen sonuçlar yekpare yaklaşım modeli ile karşılaştırılmıştır.

The identification of interacting brain networks during robot-assisted training with multimodal stimulation

Objective. Robot-assisted rehabilitation training is an effective way to assist rehabilitation therapy. So far, various robotic devices have been developed for automatic training of central nervous system following injury. Multimodal stimulation such as visual and auditory stimulus and even virtual reality technology were usually introduced in these robotic devices to improve the effect of rehabilitation training. This may need to be explained from a neurological perspective, but there are few relevant studies. Approach. In this study, ten participants performed right arm rehabilitation training tasks using an upper limb rehabilitation robotic device. The tasks were completed under four different feedback conditions including multiple combinations of visual and auditory components: auditory feedback; visual feedback; visual and auditory feedback (VAF); non-feedback. The functional near-infrared spectroscopy devices record blood oxygen signals in bilateral motor, visual and auditory areas. Using hemoglobin concentration as an indicator of cortical activation, the effective connectivity of these regions was then calculated through Granger causality. Main results. We found that overall stronger activation and effective connectivity between related brain regions were associated with VAF. When participants completed the training task without VAF, the trends in activation and connectivity were diminished. Significance. This study revealed cerebral cortex activation and interacting networks of brain regions in robot-assisted rehabilitation training with multimodal stimulation, which is expected to provide indicators for further evaluation of the effect of rehabilitation training, and promote further exploration of the interaction network in the brain during a variety of external stimuli, and to explore the best sensory combination.

Differentially Private Speaker Anonymization

Sharing real-world speech utterances is key to the training and deployment of voice-based services. However, it also raises privacy risks as speech contains a wealth of personal data. Speaker anonymization aims to remove speaker information from a speech utterance while leaving its linguistic and prosodic attributes intact. State-of-the-art techniques operate by disentangling the speaker information (represented via a speaker embedding) from these attributes and re-synthesizing speech based on the speaker embedding of another speaker. Prior research in the privacy community has shown that anonymization often provides brittle privacy protection, even less so any provable guarantee. In this work, we show that disentanglement is indeed not perfect: linguistic and prosodic attributes still contain speaker information. We remove speaker information from these attributes by introducing differentially private feature extractors based on an autoencoder and an automatic speech recognizer, respectively, trained using noise layers. We plug these extractors in the state-of-the-art anonymization pipeline and generate, for the first time, private speech utterances with a provable upper bound on the speaker information they contain. We evaluate empirically the privacy and utility resulting from our differentially private speaker anonymization approach on the LibriSpeech data set. Experimental results show that the generated utterances retain very high utility for automatic speech recognition training and inference, while being much better protected against strong adversaries who leverage the full knowledge of the anonymization process to try to infer the speaker identity.

IndustrialEdgeML - End-to-end edge-based computer vision systemfor Industry 5.0

State-of-the-art object detection methods gain increasing attention in various industrial applications. However, current vision systems typically rely on cloud services for data storage and training of AI models. In this work, we present an end-to-end vision system for bin-picking applications at the edge of industrial premises via industrial computers, where bin-picking refers to the dedicated selection and displacement of objects into designated areas. Our system is designed for human-robot collaboration in a range of distinct challenging industrial environments with a focus on automatically learning new objects. To this end, we propose a new approach for automated oriented object detection consisting of three stages: (i) automatic training data labeling for the new object based on autoencoders, (ii) object detection using the YOLOR-S architecture, and (iii) inference of the object's orientation, more precisely, rotated bounding box detection based on attention maps using the TS-CAM algorithm. Our method achieves state-of-the-art performance, without the need for annotations of rotated bounding boxes, when compared to the single-stage architecture S2A-Net for rotated bounding box detection. In particular, the system maintains high-quality performance not only for learning all objects at once but also for incrementally learning one object after another.

Design of Nonlinear Active Disturbance Rejection Controller Based on the Adaptive Particle Swarm Optimization Algorithm for the Maglev Train Traction Control System

This paper focuses on speed tracking control of the maglev train operation system. Given the complexity and instability of the maglev train operation system, traditional speed‐tracking control algorithms demonstrate poor tracking accuracy and large tracking errors. The maglev train is easily affected by external interference, increasing train energy consumption and reducing passengers’ riding comfort. This study proposes a control algorithm called APSO‐NLADRC to address the deficiencies of the automatic train operation control algorithms. The APSO‐NLADRC is based on adaptive particle swarm optimization (APSO) algorithm parameter optimization nonlinear active disturbance rejection controller (NLADRC). The method of population comparison, linear update of learning factors, and adaptive updating of inertia weight values addresses the premature convergence phenomenon that occurs during the parameter optimization of the traditional particle swarm algorithm. The APSO algorithm solves the problem that the parameters of the NLADRC are difficult to adjust. Compared with PID, NLADRC, and NLADRC based on traditional particle swarm optimization algorithms, the proposed control algorithm has higher tracking accuracy and more robust anti‐interference capability and provides better comfort.

Energy efficiency driving strategy with Connected-Driving Advisory System (C-DAS)

Energy efficiency in the railway sector is highly influenced by the driving strategy adopted by the driver taking into account the scheduled timings and TMS regulations. An efficient driving strategy combined with good regulation can reduce significantly operating costs, improve service quality and increase environment sustainability. The rail sector shows an increasing interest for energy saving algorithms, combined to Driver Advisory System (DAS) or Automatic Train Operation (ATO), integrated with TMS information. This document will deal with the energy aspect taking into account the Timetable programming and TMS regulation. In particular, it focuses on the definition of appropriate speed profiles in order to optimize TMS time constraints and on the study of a C-DAS architecture which can be applied immediately to the current infrastructure.

Intelligent Energy-Efficient Train Trajectory Optimization Approach Based on Supervised Reinforcement Learning for Urban Rail Transits

Artificial intelligence of things (AIoT)-enabled intelligent automatic train operation (iATO) is an urgently needed technology to expand the capability of ATO in addressing the real-time responsiveness and dynamic online challenges to energy-efficient train trajectory optimization (TTO) and its associated ride-comfort, punctuality, and safety issues in modern urban rail transit networks. This paper proposes a three-step supervised reinforcement learning-based intelligent energy-efficient train trajectory optimization (SRL-IETTO) approach for iATO by hybrid-integrating deep reinforcement learning (DRL) and supervised learning. First, multiple objectives are formulated based on real-time train operation and systematically integrated into the RL algorithm by a binary function-based goal-directed reward design method. Second, an IETTO model is established to handle uncertain disturbances in real-time train operation and generate optimal energy-efficient train trajectories online by optimizing energy efficiency and receiving supervisory information from trajectories of pre-trained TTO models. Finally, numerical simulations are implemented to validate the effectiveness of the SRL-IETTO using in-service subway line data. The results demonstrate the superiority and improved energy saving of the proposed approach, and confirm its adaptability to online trip time adjustments within the practical running time range under uncertain disturbances with less trip time error compared to other intelligent TTO algorithms.

CNN-based red blood cell detection and tracking with automatic train data generation

CNN-based red blood cell detection and tracking with automatic train data generation

COMPLEX METHOD FOR AUTOMATIC RECOGNITION OF NATURAL LANGUAGE AND EMOTIONAL STATE

Current trends in NLP emphasize universal models and learning from pre-trained models. This article explores these trends and advanced models of pre-service learning. Inputs are converted into words or contextual embeddings that serve as inputs to encoders and decoders. The corpus of the author's publications over the past six years is used as the object of the research. The main methods of research are the analysis of scientific literature, prototyping, and experimental use of systems in the direction of research. Speech recognition players are divided into players with huge computing resources for whom training on large unlabeled data is a common procedure and players who are focused on training small local speech recognition models on pre-labeled audio data due to a lack of resources. Approaches and frameworks for working with unlabeled data and limited computing resources are almost not present, and methods based on iterative training are not developed and require scientific efforts for development. The research aims to develop methods of iterative training on unlabeled audio data to obtain productively ready speech recognition models with greater accuracy and limited resources. A separate block proposes methods of data preparation for use in training speech recognition systems and a pipeline for automatic training of speech recognition systems using pseudo marking of audio data. The prototype and solution of a real business problem of emotion detection demonstrate the capabilities and limitations of owl recognition systems and emotional states. With the use of the proposed methods of pseudo-labeling, it is possible to obtain recognition accuracy close to the market leaders without significant investment in computing resources, and for languages with a small amount of open data, it can even be surpassed.