Automatic Train Research Articles

Robust Fuzzy Predictive Control for Automatic Train Regulation in High-Frequency Metro Lines

This paper addresses the robust automatic train regulation problem in high-frequency metro lines with fuzzy passenger arrival rate. Due to the uncertainty of passenger demand, the passenger arrival rate is assumed to be represented by fuzzy variables. A nonlinear state-space model is formulated to describe the characteristic of metro train operation. To satisfy the real-time requirement of train regulation, a fuzzy constrained predictive control approach is designed to optimize a cost function at each decision epoch subject to safety constraints on the control input. Based on the Lyapunov stability theory and model predictive control method, sufficient conditions for the existence of corresponding state feedback control law are given in a set of linear matrix inequalities. Moreover, for reducing delays caused by the uncertain disturbance, the robust train regulation strategy is designed to guarantee that the practical train timetable tracks the nominal one with respect to certain disturbance attenuation level. The effectiveness of the proposed approach is validated by a number of experiments under real running circumstances of Beijing Metro Yizhuang Line of China.

A Train-Centric Communication-Based New Movement Authority Proposal for ETCS-2

Railway accidents inevitably happen around the world although the latest automatic train protection (ATP) or similar train control systems have been widely used. To increase the safety of train control systems, we propose a new train protection solution called movement authority plus (MA+). MA+ is designed to be overlaid onto a current train control system, e.g., European Train Control System Level 2 (ETCS-2), to form a parallel control system. Its system structure and working principles are presented. Redundant train-distance measurement strategies are adopted to ensure its availability. Safety performance of the overall system is evaluated and it is compared with ETCS-2. Benefit from the real-time information exchange between on-board MA+ units and that between them and switch announcement units, MA+ works based on the moving block principle. We calculate the minimum train headway distance required by MA+ and compare it with that required by ETCS-2. The results prove the feasibility of the proposed MA+ solution, i.e., MA+ is able to protect train safety when ETCS-2 fails, and would not interrupt its normal work.

Q-Learning of Straightforward Gait Pattern for Humanoid Robot Based on Automatic Training Platform

In this paper, an oscillator-based gait pattern with sinusoidal functions is designed and implemented on a field-programmable gate array (FPGA) chip to generate a trajectory plan and achieve bipedal locomotion for a small-sized humanoid robot. In order to let the robot can walk straight, the turning direction is viewed as a parameter of the gait pattern and Q-learning is used to obtain a straightforward gait pattern. Moreover, an automatic training platform is designed so that the learning process is automated. In this way, the turning direction can be adjusted flexibly and efficiently under the supervision of the automatic training platform. The experimental results show that the proposed learning framework allows the humanoid robot to gradually walk straight in the automated learning process.

Range-Doppler Based CFAR Ship Detection with Automatic Training Data Selection

Ship detection is an essential maritime security requirement. Current state-of-the-art synthetic aperture radar (SAR) based ship detection methods employ fully focused images. The time-consuming processing efforts required to generate these images make them generally unsuitable for real time applications. This paper proposes a novel real time oriented ship detection strategy applicable to range-compressed (RC) radar data acquired by an airborne radar sensor during linear, circular and arbitrary flight tracks. A constant false alarm rate (CFAR) detection threshold is computed in the range-Doppler domain using suitable distribution functions. Detection in range-Doppler has the advantage that principally even small ships with a low radar cross section (RCS) can be detected if they are moving fast enough so that the ship signals are shifted to the exo-clutter region. In order to determine a robust threshold, the ocean statistics have to be described accurately. Bright target peaks in the background ocean data bias the statistics and lead to an erroneous threshold. Therefore, an automatic ocean training data extraction procedure is proposed in the paper. It includes (1) a novel target pre-detection module that removes the bright peaks from the data already in time domain, (2) clutter normalization in the Doppler domain using the remaining samples, (3) ocean statistics estimation and (4) threshold computation. Various sea clutter models are investigated and analyzed in the paper for finding the most suitable models for the RC data. The robustness and applicability of the proposed method is validated using real linearly and circularly acquired radar data from DLR’s (Deutsches Zentrum für Luft- und Raumfahrt) airborne F-SAR system.

Intelligent Safe Driving Methods Based on Hybrid Automata and Ensemble CART Algorithms for Multihigh-Speed Trains.

Considering both the tracking safety of multi-HSTs and the operational efficiency of a single HST, intelligent safe driving methods (ISDMs) are proposed to obtain better speed-distance curves by integrating hybrid automata (HA) with data mining algorithms in this paper. To begin with, an intelligent safe distance controller is established by using HA to ensure the tracking safety of multi-HSTs' operation in real time. Then, data-driven intelligent driving methods based on ensemble algorithms (Bagging or Adaboost.R) and classification and regression tree (CART) are proposed to discover the potential driving rules from the field driving data. Furthermore, because of the continuous rise of HST's operation mileage, the driving data collected from HST has increased tremendously compared with the subways. So, an iterative pruning error minimization algorithm is designed to reduce the redundancy of the driving data and improve the computational speed of the learning process. Finally, compared with the automatic train operation (ATO) method, the energy consumption of B-CART, A-CART, and S-A-CART algorithms can be decreased by 3.32%, 3.80%, and 4.30%, respectively.

Multi-Objective Hybrid Optimization Algorithm Using a Comprehensive Learning Strategy for Automatic Train Operation

Aiming at the problem of easy-to-fall-into local convergence for automatic train operation (ATO) velocity ideal trajectory profile optimization algorithms, an improved multi-objective hybrid optimization algorithm using a comprehensive learning strategy (ICLHOA) is proposed. Firstly, an improved particle swarm optimization algorithm which adopts multiple particle optimization models is proposed, to avoid the destruction of population diversity caused by single optimization model. Secondly, to avoid the problem of random and blind searching in iterative computation process, the chaotic mapping and the reverse learning mechanism are introduced into the improved whale optimization algorithm. Thirdly, the improved archive mechanism is used to store the non-dominated solutions in the optimization process, and fusion distance is used to maintain the diversity of elite set. Fourthly, a dual-population evolutionary mechanism using archive as an information communication medium is designed to enhance the global convergence improvement of hybrid optimization algorithms. Finally, the optimization results on the benchmark functions show that the ICLHOA can significantly outperform other algorithms for contrast. Furthermore, the ATO Matlab/simulation and hardware-in-the-loop simulation (HILS) results show that the ICLHOA has a better optimization effect than that of the traditional optimization algorithms and improved algorithms.

Theoretical Study in Estimating Mineral Compositions From Spectral Measurements With a Bayesian Approach

Summary We propose a systematic Bayesian method for inferring the mineral composition of rock samples from transmission Fourier-transform infrared spectroscopy (FTIR) measurements. Currently available FTIR inversion methodologies depend on measuring pure minerals, using them within least-squares approaches with a hand-tuned noise model, and implementing ad hoc post-processing of the obtained solution. Within the proposed data-driven framework, we replaced these previous inversion approaches with the automatic training and estimation steps. In this approach, the linear operator, comparable with the FTIR spectral standards (FTIR spectra of end-members or pure minerals), is estimated or trained on a calibration set of rock samples for which the mineral composition has been accurately determined by other means in the laboratory. With this linear operator, we then quantify the spectral-noise covariance matrix from the calibration set, which forms the basis of our estimation of the Bayesian posterior uncertainty on a mineral-composition estimate. This quantification of uncertainty in mineral estimation is a novel feature that can be used as a reliability measure. The uncertainty also describes the correlation between estimates of mineral-weight fractions, indicating which pairs of minerals cannot be independently estimated. Our Bayesian model also addresses the uncertainty propagated from the estimated linear operator and thus captures a possible mismatch of the model parameter from the true operator (i.e., semiblindness of the model). We demonstrate the advantages of our approach by performing experiments with synthetic data.

Improved Prediction on Heart Transplant Rejection Using Convolutional Autoencoder and Multiple Instance Learning on Whole-Slide Imaging.

Heart transplant rejection is one major threat for the survival of patients with a heart transplant. Endomyocardial biopsies are effective in showing signs of heart transplant rejection even before patients have any symptoms. Manually examining the tissue samples is costly, time-consuming and error-prone. With recent advances in deep learning (DL) based image processing methods, automatic training and prediction on heart transplant rejection using whole-slide images expect to be promising. This paper develops an advanced pipeline for quality control, feature extraction, clustering and classification. We first implement a stacked convolutional autoencoder to extract feature maps for each tile; we then incorporate multiple instance learning (MIL) with dimensionality reduction and unsupervised clustering prior to classification. Our results show that utilizing unsupervised clustering after feature extraction can achieve higher classification results while preserving the capability for multi-class classification.

Neural Network Training System for Marker Encoding

In this paper, we propose a training system for visual markers that provides the generation and subsequent recognition (under real-world conditions) of stylized images that contain information encoded by a sequence of bits. New types of neural network layers that make the recognition process tolerant to external noise are developed. The training process is based on the end-to-end principle, which enables automatic training for the intermediate stages of the model. The experimental results that demonstrate the performance of the system in encoding and decoding artificial markers are presented.

Automatic land-water classification using multispectral airborne LiDAR data for near-shore and river environments

Rapid mapping of near-shore and coastal regions has become an indispensable task for the local authority to serve the purpose of coastal management and post-disaster monitoring. Aerial photogrammetry and satellite remote sensing have been utilized to fulfill such a task in the last few decades. Airborne LiDAR can further compensate the drawbacks of these image capturing approaches as a result of the direct geo-referenced 3D point cloud. The recent introduction of multispectral airborne LiDAR, such as the Teledyne Optech Titan, can potentially enhance the capability of water mapping, minimize the involvement of manual intervention and reduce the use of supplementary information or ancillary data. This study demonstrates the use of multispectral airborne LiDAR data for automatic land-water classification under different coastal and inland river environments. Two automatic training data selection methods are proposed. The first method utilizes Gaussian mixture model (GMM) to split preliminarily the land and water region based on the elevation/intensity histogram, and the second method is developed based on the use of scan line intensity-elevation ratio (SLIER). Subsequently, various LiDAR-derived feature sets, particularly based on the multispectral LiDAR intensity, are constructed in order to serve as an input for the log-likelihood classification model. Two optional post-classification enhancements can be implemented to further adjust the misclassified data points. The proposed workflow was evaluated with four Optech Titan datasets collected for different near-shore and river environments that are located nearby Lake Ontario, Ontario, Canada. Our experimental work demonstrated that the multispectral LiDAR intensity data was capable of enhancing the classification capability, where an overall accuracy better than 96% was achieved in most of the cases.

High-Throughput Automatic Training System for Spatial Working Memory in Free-Moving Mice.

Efficient behavioral assays are crucial for understanding the neural mechanisms of cognitive functions. Here, we designed a high-throughput automatic training system for spatial cognition (HASS) for free-moving mice. Mice were trained to return to the home arm and remain there during a delay period. Software was designed to enable automatic training in all its phases, including habituation, shaping, and learning. Using this system, we trained mice to successfully perform a spatially delayed nonmatch to sample task, which tested spatial cognition, working memory, and decision making. Performance depended on the delay duration, which is a hallmark of working memory tasks. The HASS enabled a human operator to train more than six mice simultaneously with minimal intervention, therefore greatly enhancing experimental efficiency and minimizing stress to the mice. Combined with the optogenetic method and neurophysiological techniques, the HASS will be useful in deciphering the neural circuitry underlying spatial cognition.

A hierarchical ensemble learning framework for energy-efficient automatic train driving

Railway transportation plays an important role in modern society. As China's massive railway transportation network continues to grow in total mileage and operation density, the energy consumption of trains becomes a serious concern. For any given route, the geographic characteristics are known a priori, but the parameters (e.g., loading and marshaling) of trains vary from one trip to another. An extensive analysis of the train operation data suggests that the control gear operation of trains is the most important factor that affects the energy consumption. Such an observation determines that the problem of energy-efficient train driving has to be addressed by considering both the geographic information and the trip parameters. However, the problem is difficult to solve due to its high dimension, nonlinearity, complex constraints, and time-varying characteristics. Faced with these difficulties, we propose an energy-efficient train control framework based on a hierarchical ensemble learning approach. Through hierarchical refinement, we learn prediction models of speed and gear. The learned models can be used to derive optimized driving operations under real-time requirements. This study uses random forest and bagging - REPTree as classification algorithm and regression algorithm, respectively. We conduct an extensive study on the potential of bagging, decision trees, random forest, and feature selection to design an effective hierarchical ensemble learning framework. The proposed framework was testified through simulation. The average energy consumption of the proposed method is over 7% lower than that of human drivers.

Energy-Efficient Train Operation Strategy with Speed Profiles Selection for an Urban Metro Line

In the daily operations of a metro system, physical trains track the speed profiles which are embedded in the automatic train operation (ATO) system, and the speed profile plays a key role in determining both energy consumption and travel time. With consideration of the real-world operational environment and uncertain levels of passenger demand, this study specifically proposes an integer programming model with respect to energy consumption to generate a robust operational strategy which determines the speed profile choice on each segment. Because of the computational complexity of the proposed model, a heuristic algorithm is designed, which combines a genetic algorithm (GA) and a nomadic algorithm (NA), to find a good solution in acceptable computational time. Finally, numerical experiments based on the Beijing Yizhuang metro line are implemented to verify the effectiveness and efficiency of this approach.

Modelling relationships between socioeconomy, landscape and water flows in Mediterranean agroecosystems: a case study in Adra catchment (Spain) using Bayesian networks

In Mediterranean areas, the co-evolution between social and natural systems has given rise to heterogeneous and complex systems of interactions called agroecosystems, in which strong relationships between socioeconomy, landscape and water flows have been identified. In this context, water resources management is a prominent area of research, particularly in semi-arid conditions, where a special set of challenges requires novel tools to deal with uncertainty, multiple sources of information and expert knowledge. In this paper, Bayesian Networks are proposed as a means to model the relationships between socioeconomy, landscape and water flows in a Mediterranean agroecosystem, studying its behaviour under two scenarios of change in land use trends: maintenance of traditional Mediterranean agriculture, and agricultural intensification through the development of greenhouses. Results show that an increase in the area of traditional agriculture would lead to better control of runoff and increased primary productivity, measured as green water flows. By contrast, agricultural intensification of the territory would provoke an increase in evaporation and water losses. Due to the versatility of Bayesian networks, results can be expressed not only as probabilities, but also using other metrics that can be computed from them. Accordingly, Sensitivity Analysis to Evidence, Sensitivity Analysis to Parameters and the Kullback–Leibler divergence were carried out. Bayesian Networks have demonstrated their ability to deal with uncertainty inherent to natural systems, combining expert knowledge, data from regional datasets and Geographical Information Systems, and automatic training algorithms giving robust and proper results.

Fast Lane Detection Based on Deep Convolutional Neural Network and Automatic Training Data Labeling

Fast Lane Detection Based on Deep Convolutional Neural Network and Automatic Training Data Labeling

Evaluating the Overall Accuracy of Additional Learning and Automatic Classification System for CT Images

A large number of images that are usually registered images in a training dataset are required for creating classification models because training of images using a convolutional neural network is done using supervised learning. It takes a significant amount of time and effort to create a registered dataset because recently computed tomography (CT) and magnetic resonance imaging devices produce hundreds of images per examination. This study aims to evaluate the overall accuracy of the additional learning and automatic classification systems for CT images. The study involved 700 patients, who were subjected to contrast or non-contrast CT examination of brain, neck, chest, abdomen, or pelvis. The images were divided into 500 images per class. The 10-class dataset was prepared with 10 datasets including with 5000–50,000 images. The overall accuracy was calculated using a confusion matrix for evaluating the created models. The highest overall reference accuracy was 0.9033 when the model was trained with a dataset containing 50,000 images. The additional learning for manual training was effective when datasets with a large number of images were used. The additional learning for automatic training requires models with an inherent higher accuracy for the classification.

Classification of Metro Facilities with Deep Neural Networks

Metro barrier-detection has been one of the most popular research fields. How to detect obstacles quickly and accurately during metro operation is the key issue in the study of automatic train operation. Intelligent monitoring systems based on computer vision not only complete safeguarding tasks efficiently but also save a great deal of human labor. Deep convolutional neural networks (DCNNs) are the most state-of-the-art technology in computer vision tasks. In this paper, we evaluated the effectiveness in classifying the common facility images in metro tunnels based on Google’s Inception V3 DCNN. The model requires fewer computational resources. The number of parameters and the computational complexity are much smaller than similar DCNNs. We changed its architecture (the last softmax layer and the auxiliary classifier) and used transfer learning technology to retrain the common facility images in the metro tunnel. We use mean average precision (mAP) as the metric for performance evaluation. The results indicate that our recognition model achieved 90.81% mAP. Compared with the existing method, this method is a considerable improvement.

Efficient Real-Time Control Design for Automatic Train Regulation of Metro Loop Lines

This paper systematically investigates the efficient real-time control design for automatic train regulation (ATR) of metro loop lines subjected to frequent minor disruptions. To describe the dynamic evolution of the trains periodically operating on the loop line, a train traffic model related to the departure time is proposed based on a state-space equation, where the number of the station increases from circle to circle. Under the frequent minor disruptions, a dynamic optimal control model is developed to determine the ATR strategy to improve the punctuality and the regularity of the metro operation with the safety and control constraints. To solve the formulated optimal control model with the updated information, a real-time control algorithm based on a model predictive control approach is designed, which splits the original optimization problem into a set of convex quadratic programming problems, which can be numerically calculated efficiently and satisfy the real-time control requirement. Numerical examples are given to illustrate the effectiveness of the proposed method.

High-speed trains automatic operation with protection constraints: a resilient nonlinear gain-based feedback control approach

This paper addresses the control design for automatic train operation of high-speed trains with protection constraints. A new resilient nonlinear gain-based feedback control approach is proposed, which is capable of guaranteeing, under some proper non-restrictive initial conditions, the protection constraints control raised by the distance-to-go &#x0028 moving authority &#X0029 curve and automatic train protection in practice. A new hyperbolic tangent function-based model is presented to mimic the whole operation process of high-speed trains. The proposed feedback control methods are easily implementable and computationally inexpensive because the presence of only two feedback gains guarantee satisfactory tracking performance and closed-loop stability, no adaptations of unknown parameters, function approximation of unknown nonlinearities, and attenuation of external disturbances in the proposed control strategies. Finally, rigorous proofs and comparative simulation results are given to demonstrate the effectiveness of the proposed approaches.

Система автоматической прицепки локомотива к составу поезда

Система автоматической прицепки локомотива к составу поезда