Multiple Trains Research Articles

MPC‐Bi‐LSTM based control strategy for connected and automated vehicles platoon oriented to cyberattacks

AbstractAny technological innovation will be accompanied by new challenges and risks, and the connected and automated vehicles (CAVs) are no exception. Among them, the argument that cooperating platoons may fall victim to cyberattacks through wireless communication has emerged as a significant issue. Therefore, this paper designs a communication topology anomaly response system (CTARS) to ensure platoon safety, which consists of a trigger module and a control module. The primary objective of the trigger module is to distinguish abnormal vehicle behavior based on time to collision (TTC) indicators, and the control module combines the model predictive control (MPC) and bidirectional long short‐term memory (Bi‐LSTM) to achieve accurate trajectory prediction of and optimal control, working in tandem with the trigger module. Subsequently, the real dataset HISTORIC is used to calibrate the multiple vehicle intelligent driver model (IDM) and train the trajectory prediction model. Furthermore, comparative simulations are conducted, encompassing various forms of cyberattacks, in order to examine the evolution characteristics of CAVs platoons (CAVP) and evaluate the performance of CTARS. The results demonstrate the remarkable effectiveness of CTARS in safeguarding the security of CAVP during cyberattacks, thus confirming its exceptional performance.

Dynamic Pricing and Capacity Optimization in Railways

Problem definition: Revenue management in railways distinguishes itself from that in traditional sectors, such as airline, hotel, and fashion retail, in several important ways. (i) Capacity is substantially more flexible in the sense that changes to the capacity of a train can often be made throughout the sales horizon. Consequently, the joint optimization of prices and capacity assumes genuine importance. (ii) Capacity can only be added in discrete “chunks” (i.e., coaches). (iii) Passengers with unreserved tickets can travel in any of the multiple trains available during the day. Further, passengers in unreserved coaches are allowed to travel by standing, thus giving rise to the need to manage congestion. Motivated by our work with a major railway company in Japan, we analyze the problem of jointly optimizing pricing and capacity; this problem is more-general version of the canonical multiproduct dynamic-pricing problem. Methodology/results: Our analysis yields four asymptotically optimal policies. From the viewpoint of the pricing decisions, our policies can be classified into two types—static and dynamic. With respect to the timing of the capacity decisions, our policies are again of two types—fixed capacity and flexible capacity. We establish the convergence rates of these policies; when demand and supply are scaled by a factor [Formula: see text], the optimality gaps of the static policies scale proportional to [Formula: see text], and those of the dynamic policies scale proportional to [Formula: see text]. We illustrate the attractive performance of our policies on a test suite of instances based on real-world operations of the high-speed “Shinkansen” trains in Japan and develop associated insights. Managerial implications: Our work provides railway administrators with simple and effective policies for pricing, capacity, and congestion management. Our policies cater to different contingencies that decision makers may face in practice: the need for static or dynamic prices and for fixed or flexible capacity. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0246 .

Automated Diagnosis for Colon Cancer Diseases Using Stacking Transformer Models and Explainable Artificial Intelligence.

Colon cancer is the third most common cancer type worldwide in 2020, almost two million cases were diagnosed. As a result, providing new, highly accurate techniques in detecting colon cancer leads to early and successful treatment of this disease. This paper aims to propose a heterogenic stacking deep learning model to predict colon cancer. Stacking deep learning is integrated with pretrained convolutional neural network (CNN) models with a metalearner to enhance colon cancer prediction performance. The proposed model is compared with VGG16, InceptionV3, Resnet50, and DenseNet121 using different evaluation metrics. Furthermore, the proposed models are evaluated using the LC25000 and WCE binary and muticlassified colon cancer image datasets. The results show that the stacking models recorded the highest performance for the two datasets. For the LC25000 dataset, the stacked model recorded the highest performance accuracy, recall, precision, and F1 score (100). For the WCE colon image dataset, the stacked model recorded the highest performance accuracy, recall, precision, and F1 score (98). Stacking-SVM achieved the highest performed compared to existing models (VGG16, InceptionV3, Resnet50, and DenseNet121) because it combines the output of multiple single models and trains and evaluates a metalearner using the output to produce better predictive results than any single model. Black-box deep learning models are represented using explainable AI (XAI).

Deterministic reinforcement learning for optimized formation control of virtually-coupled trains via performance index monitor

This article presents a deterministic reinforcement learning based optimized formation control for virtually-coupled trains using a novel designed performance index monitor, forming a new paradigm of artificial intelligence-based control for virtually-coupled trains. First, a reinforcement learning-based optimized formation control is designed using backstepping design and neural networks-based actor-critic framework, achieving steady formation separation among multiple trains and providing key theoretical basis to ”moving block with soft wall” (or virtually-coupled) mode, by online approximating the solutions of Hamilton–Jacobi–Bellman equations in both virtual position adjusting and actual speed regulating control signals. Second, a hysteretic-lag performance index monitor is designed to determine the time moments that enough knowledge has been obtained and insufficient knowledge is available in dynamical environments and switch the previously-mentioned reinforcement learning-based optimized formation control to deterministic reinforcement learning manner and vice versa. The idea of deterministic reinforcement learning lies in that as long as the convergences of actor and critic neural networks are observed, speaking equivalently, sufficient knowledge has been obtained provisionally, inner weight vectors of neural networks can be set as deterministic constant ones, achieving the human-like learning and control and reducing the computational amount. Rigorous closed-loop stability using deterministic reinforcement learning is also given using Lyapunov stability theorem. Finally, by utilizing the designed performance index monitor, the switching behavior between reinforcement learning and deterministic reinforcement learning is guaranteed to be finite during finite time of running duration. Simulation examples are given to verify the effectiveness of proposed control.

Event-Triggered Cooperative Model-Free Adaptive Iterative Learning Control for Multiple Subway Trains With Actuator Faults.

This article investigates the issue of speed tracking and dynamic adjustment of headway for the repeatable multiple subway trains (MSTs) system in the case of actuator faults. First, the repeatable nonlinear subway train system is transformed into an iteration-related full-form dynamic linearization (IFFDL) data model. Then, the event-triggered cooperative model-free adaptive iterative learning control (ET-CMFAILC) scheme based on the IFFDL data model for MSTs is designed. The control scheme includes the following four parts: 1) the cooperative control algorithm is derived by the cost function to realize cooperation of MSTs; 2) the radial basis function neural network (RBFNN) algorithm along the iteration axis is constructed to compensate the effects of iteration-time-varying actuator faults; 3) the projection algorithm is employed to estimate unknown complex nonlinear terms; and 4) the asynchronous event-triggered mechanism operated along the time domain and iteration domain is applied to lessen the communication and computational burden. Theoretical analysis and simulation results show that the effectiveness of the proposed ET-CMFAILC scheme, which can ensure that the speed tracking errors of MSTs are bounded and the distances of adjacent subway trains are stabilized in the safe range.

Virtual Coupling-Based H∞ Active Fault-Tolerant Cooperative Control for Multiple High-Speed Trains With Unknown Parameters and Actuator Faults

This paper investigates the cooperative control problem of multiple high-speed trains subject to unknown parameters and actuator faults. The cooperative operation of multiple high-speed trains is modeled as a coupled control system. On the basis of the virtual coupling technique, the H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> active fault-tolerant cooperative control scheme is established to guarantee the desired tracking performances and cooperative performances. The adaptive control technique is adopted to estimate the unknown Davis’ coefficients and the fault parameters and linear matrix inequalities are utilized to derive the control gain of the cooperative control protocols for the trains. Rigorous analysis is provided to corroborate the closed-loop stability of the cooperative train control system and numerical simulation is conducted to verify the effectiveness and feasibility of the proposed results.

Stochastic Linear Quadratic Optimal Control of Speed and Position of Multiple Trains on a Single-Track Line

Stochastic Linear Quadratic Optimal Control of Speed and Position of Multiple Trains on a Single-Track Line

A Prescriptive Machine Learning Approach to Mixed-Integer Convex Optimization

We introduce a prescriptive machine learning approach to speed up the process of solving mixed-integer convex optimization (MICO) problems. We solve multiple optimization instances and train a machine learning model in advance, which we use to solve new instances. Previous works have shown that the predictions of classification algorithms enable us to solve optimization problems much faster than commercial solvers. What distinguishes this paper from the previous work is that we use a prescriptive algorithm, Optimal Policy Trees (OPT), instead of classification algorithms. Whereas classification algorithms aim to predict the correct label and consider all other labels equally undesirable, a prescriptive approach takes into account all the available decision options and their counterfactuals. We first introduce an algorithm that is purely based on OPT and also its extension. We compare their performance with Optimal Classification Trees (OCT) on various MICO problems. Test problems include transportation optimization, portfolio optimization, facility location, and hybrid vehicle control. We also experiment on real-world instances taken from the Mixed Integer Programming Library. OPT-based methods have a significant edge on finding feasible solutions, whereas OCT-based methods have a slight edge on the degree of suboptimality. The proposed extension of the pure OPT algorithm improves on the suboptimality of the solutions the algorithm produces. History: Accepted by Andrea Lodi, Area Editor for Design &amp; Analysis of Algorithms–Discrete. Funding: The research was funded in part by a grant from OCP to MIT.

Integrating train service route design with passenger flow allocation for an urban rail transit line

Train service design problem considers many operating strategies, i.e., multiple service routes, multiple train compositions, and express/local modes. Incorporating multiple operating strategies, this study first formulates an integer linear programming model for integrating train service route design with the passenger flow allocation problem. Consistency between the two components is enforced by a set of linking constraints that consider the relationship between the number of transit trips assigned to a route and the capacity of a single train. To solve the proposed model on real-life instances, we develop an approach that utilizes the Alternating Direction Method of Multipliers (ADMM). This dualizes the linking constraints and decomposes the problem into two subproblems: a train service route design subproblem and a passenger flow allocation subproblem. The latter can be subdivided into a set of passenger group-specific subproblems and is solved by a label correcting algorithm. Through Lagrangian multipliers, the interplay between the train service route design and passenger flow allocation subproblems is explored. To address the nonlinearities that arise in ADMM, we describe a new linearization technique for the quadratic penalty terms in the two subproblems by exploiting the rolling update mechanism of ADMM. The proposed approach is tested on synthetic and real-life instances from an urban rail company in China. The numerical results show that the proposed ADMM approach provides objective values that are on average 7.63% better than the conventional sequential approach. We also demonstrate that ADMM provides smaller optimality gaps in general when compared to a Lagrangian relaxation approach.

Composite Motion Learning with Task Control

We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn decoupled motions for specific body parts from multiple reference motions simultaneously and directly by leveraging the use of multiple discriminators in a GAN-like setup. In this process, there is no need of any manual work to produce composite reference motions for learning. Instead, the control policy explores by itself how the composite motions can be combined automatically. We further account for multiple task-specific rewards and train a single, multi-objective control policy. To this end, we propose a novel framework for multi-objective learning that adaptively balances the learning of disparate motions from multiple sources and multiple goal-directed control objectives. In addition, as composite motions are typically augmentations of simpler behaviors, we introduce a sample-efficient method for training composite control policies in an incremental manner, where we reuse a pre-trained policy as the meta policy and train a cooperative policy that adapts the meta one for new composite tasks. We show the applicability of our approach on a variety of challenging multi-objective tasks involving both composite motion imitation and multiple goal-directed control. Code is available at https://motion-lab.github.io/CompositeMotion .

Optimisation of seat reservations on trains to minimise transfer distances

This paper introduces a novel optimisation problem motivated by the real-world application of transferring between trains. The driving idea is to minimise the walking distances of all transferring passengers by optimising the assignment of passengers to railcarriages in the seat reservation process. The focus of this work is on formalising and modelling the problem, which has not been studied before. It aims to provide a framework for future considerations. We present three versions of the problem with increasing difficulty: one-train-one-station, one-train-many-stations, and a general problem with multiple trains and stations. Since the simplest version of the problem is a pure assignment problem in the form of minimum-cost bipartite matching, our problem modelling and algorithmic solution approach remain closely related to maxflow problems as they represent a proven method for assignment problems. However, even the one-train-many-stations problem cannot be solved by transforming it into a standard maximum-flow problem. The main result shown is the NP-hardness of the general problem.

A decentralized data evaluation framework in federated learning

Federated Learning (FL) is a type of distributed deep learning framework in which multiple devices train a local model using local data, and the gradients of the local model are then sent to a central server that aggregates them to create a global model. This type of framework is ideal where data privacy is of utmost importance because the data never leave the local device. However, a major concern in FL is ensuring the data quality of local training data. Since there is no control over the local training data, ensuring that the local model is trained on clean data becomes challenging. A model trained on poor-quality data can have a significant impact on its accuracy. In this paper, we propose a decentralized approach using blockchain to ensure local model data quality. We use miners to validate each local model by checking its accuracy against a secret testing dataset. This is done using a smart contract that the miners invoke during the mining process. The local model is aggregated with the global model only if it passes a preset accuracy threshold. We test our proposed method on two datasets: the Brain Tumor Classification dataset from Kaggle, comprised of 7000 MRI images divided into two classes (Tumor/No Tumor), and the Medical MNIST dataset, which includes 58,954 images classified into six different classes: AbdomenCT, BreastMRI, ChestCT, Chest X-ray, Hand X-ray, and HeadCT. Our results show that our method outperforms the original FL approach in all experiments.

Comparative Analysis of Buried Pipe Under Heavy Train Loads

With rapid development of railway transportation and increasing demand of oil and gas in China, the heavy haul train load becomes an important factor that threaten the safe operation of pipe. The mechanical behavior of buried pipe subjected to heavy haul train load was investigated in this study. A finite element model was established to investigate the effect of train load. Finally, the multiple train loads were also discussed. Results show that the high stress area occurs under the train track. In the pipe segment below the track, the top of pipe is under compression and the bottom of pipe is under tension. The cross section of pipe is still circular. The maximum vertical and horizontal displacement are at the top and side of pipe. The maximum von Mises stress, axial strain, and displacement of pipe increase with the increase of train load. Under the multiple train loads, there are two high stress and high strain areas at the top and bottom of pipe. With the increase of multiple train loads, the maximum von Mises stress, axial strain, displacement and ovality increase.

Improving service qualities of cyclic line plans considering heterogeneous passenger origin-destination (OD) flow groups

ABSTRACT Cyclic train services provide huge conveniences to passengers. This work aims to fix one vital promise in major line planning studies that passengers were homogeneous. In fact, passengers’ rail travel expectations are heterogeneous. But those heterogeneities show common needs correlating with travel distances and defined station levels. Therefore, we cluster passenger heterogeneities into divided OD groups, extend service qualities, and add more train line factors to our line planning model. Cyclic line plan from this joint optimisation not only receives service quality improvements but also provides multiple train service types to match clustered OD groups. Moreover, we allow passengers to be served by different train service types, deliver a high level of direct services, and maintain the minimum operation cost. We compare concluded line plans with the results of the generic line planning model and the real-world line plan to show our solution advantages.

A Study on Generating Webtoons Using Multilingual Text-to-Image Models

Text-to-image technology enables computers to create images from text by simulating the human process of forming mental images. GAN-based text-to-image technology involves extracting features from input text; subsequently, they are combined with noise and used as input to a GAN, which generates images similar to the original images via competition between the generator and discriminator. Although images have been extensively generated from English text, text-to-image technology based on multilingualism, such as Korean, is in its developmental stage. Webtoons are digital comic formats for viewing comics online. The webtoon creation process involves story planning, content/sketching, coloring, and background drawing, all of which require human intervention, thus being time-consuming and expensive. Therefore, this study proposes a multilingual text-to-image model capable of generating webtoon images when presented with multilingual input text. The proposed model employs multilingual BERT to extract feature vectors for multiple languages and trains a DCGAN in conjunction with the images. The experimental results demonstrate that the model can generate images similar to the original images when presented with multilingual input text after training. The evaluation metrics further support these findings, as the generated images achieved an Inception score of 4.99 and an FID score of 22.21.

Study on strain characteristic function for performance evaluation of high-speed railway steel truss bridge

From the data collected by bridge health monitoring systems, various indicators can be derived to evaluate the structural, environmental, and loading conditions. These indicators provide a basis for decision-making of bridge operations managers and administrators. In this paper, a new monitoring indicator called the Statistical Steady-State Static Effect Characteristic Function is proposed for railway bridges. A digital twin (DT) finite element model is developed in this study, which allows for real-time analysis of the structural effects during train travel. Using this model, the strain effects on key components of a high-speed railway steel truss bridge under dynamic loading conditions caused by random trains are simulated. Based on the characteristics of the simulation results, an extraction algorithm for the statistical steady-state strain characteristic function of the high-speed railway steel truss bridge is proposed in this study. By simulating the strain effects under multiple random train travel events, the strain characteristic functions at different locations of the structure are extracted, demonstrating the applicability of the proposed algorithm. Finally, by comparing these strain characteristic functions, the distribution pattern in the structural configuration space is revealed, suggesting the potential of the function as an indicator for assessing inherent structural characteristics, monitoring structural condition, and identifying damage.

Modeling system dynamics of interacting cruising trains to reduce the impact of power peaks

Rail operators around the globe are striving to improve the efficiency, automation, safety, and sustainability of railway systems. Despite significant advances in technologies such as artificial intelligence and automated train operations (ATO), achieving these goals is challenging for complex rail networks when accounting for unpredictable factors that alter real-time operations. In this paper, we model railway traffic in a corridor as a string of interacting cruising trains, each subject to random speed variations that are described by a stochastic process. We simulate this dynamic system under assumptions that model human drivers and ATO systems, and compute performance measures focusing on energy consumption and the power peaks arising when multiple trains accelerate simultaneously. Different strategies to smooth these peaks are investigated, including the use of regenerative braking energy, potentially coupled with an electric energy storage, and a rule that uses fixed waiting times before re-acceleration. Our findings shed light on when and why these strategies can be effective at reducing energy consumption and/or shaving the peaks. They also show that employing a well-calibrated ATO controller in which vehicles exchange information about their location improves energy performance compared to a model of a human driven. Finally, a trade-off between energy performance and traffic regularity is exposed, i.e., strategies to reduce power peaks may slow rail traffic down, reducing capacity utilization.

Study on Characteristics of Electromagnetic Interference Caused by Metro Train Movement

With the rapid development of the urban power grid and metro system, their mutual influence has become more and more serious. The dc magnetic bias of the transformer caused by the metro becomes the main research direction. In this paper, the characteristics of dynamic electromagnetic coupling between metro trains and transmission lines are studied. First, the motion equation of the metro is written out according to the running law of the train, and three coupling relations are given according to the position of the train. The calculation method of dynamic induced voltage is deduced. Then the influence of parallel length and distance between the metro and transmission line on induced voltage is studied. The dynamic induction voltage increases first and then decreases with the increase of the parallel length of the metro and transmission line and decreases with the increase of the distance between them. It is proposed that the electromagnetic coupling of a single train has limited influence on the dc magnetic bias of transmission lines, but the influence of dynamic electromagnetic coupling cannot be ignored when multiple trains are running simultaneously.

Damage Detection of Spatial Track–Bridge System with Interlayer Connection Using High-Speed Train Response and Sensitivity Analysis

Bridge damage detection has attracted much attention recently. Most studies on damage detection of the high-speed railway (HSR) bridge neglect the effect of the interlayer connection between the railway track and bridge. This paper proposes a damage detection method for the HSR bridge using response-based sensitivity analysis of high-speed trains. The HSR bridge is modeled as a spatial track–bridge system, in which the fasteners, sleepers and track slabs are modeled as one viscoelastic layer. The responses of multiple vehicles are merged to overcome the critical issue that the length of response data recorded by a high-speed vehicle moving over the bridge is too short to perform the sensitivity analysis. Numerical studies demonstrate that the proposed method is capable to detect damages of the track–bridge system with different train speed, car-body mass, irregularity grade and the interlayer connection properties. By using the signal merging method and the averaged response from multiple train trips, the proposed method is robust to high speed and measurement noise. The damage on the bridge beam and the interlayer connection can be well-identified. It is also found that increasing the car-body mass, damping ratio of the track–bridge system, damping coefficient of interlayer connection could improve the efficiency of damage detection.

An Energy-Efficient Optimal Operation Control Strategy for High-Speed Trains via a Symmetric Alternating Direction Method of Multipliers

Train operation control is of great importance in reducing train operation energy consumption and improving railway operation efficiency. This paper investigates the design of optimal control inputs for multiple trains on a single railway line with several stations. Firstly, a distributed optimal control problem for multiple train operation is formulated to reduce the energy consumption and improve the punctuality of trains. Then, we propose an efficient algorithm based on the framework of the symmetric alternating direction method of multipliers to solve this optimization problem. Finally, numerical simulations show that the method can obtain the optimal train control sequence in fewer iterative steps compared to the alternating direction multiplier method, thus illustrating the effectiveness of the algorithm.