Automatic Train Research Articles

Integrated train timetabling and rolling stock rescheduling for a disturbed metro system: A hybrid deep reinforcement learning and adaptive large neighborhood search approach

For a metro line with high density and short trip time, the original train timetable and rolling stock circulation face infeasible risks under unexpected disturbances. This paper focuses on integrated train timetabling and rolling stock rescheduling for a disturbed metro system to reduce the negative impact. The problem is formulated as a multi-objective master model, in which required operational constraints and dispatching strategies are taken into account. To satisfy the real-time requirement, an innovative solution framework consisting of an independent rescheduling process and a cooperative rescheduling process is proposed. In the independent rescheduling process, the master model is decomposed into a series of submodels in the unit of train service. The submodel can be transformed into a Markov Decision Process (MDP) with well-defined fundamental elements (i.e., state, action, and reward function). Based on the MDP, a hierarchical policy is developed by introducing deep reinforcement learning to generate the initial solution, including the lower-level policy for train timetable and the higher-level policy for flexible rolling stock circulation. In the cooperative rescheduling process, the selfishness of agents that appears after the model decomposition is overcome by an adaptive large neighborhood search algorithm, which can improve the solution quality. Finally, two sets of numerical experiments are conducted to demonstrate the performance of the proposed solution framework. The experimental results show that a near-optimal solution can be obtained in a short time, which is better than the currently used practical rules in the automatic train supervision system, especially during peak hours. Furthermore, the effects of different parameter settings are analyzed.

An Automatic Train Operation Based Real-Time Rescheduling Model for High-Speed Railway

With the continuous development of the Automatic Train Operation (ATO) system in high-speed railways, automatic driving is progressively supplanting manual operations, ushering in a new era of predictability and reliability for high-speed railway transport. Concurrently, the advent of the ATO system provides a notable impact on real-time rescheduling during disruptions, as it equips dispatchers with precise insights into train operation statuses. This paper is dedicated to a thorough analysis of how the transition to automatic driving in train operations influences the real-time rescheduling model. Based on the distinctive impact of the ATO system on real-time rescheduling, we have proposed a mixed-integer linear programming model that combines train re-timing, reordering, and the minimization of passenger delays. To validate the effectiveness of our model, we present several experiments conducted using data from the Beijing–Shanghai high-speed railway line. The results unequivocally demonstrate that our ATO-based model significantly mitigates train delay time, demonstrating its practical value in optimizing high-speed railway operations.

Fault Diagnosis of Analog Circuits Based on The Sailfish Algorithm Optimized SKELM

In view of the long training time for the optimization of the network model parameters of the SELM and the uncertainty of the model generalization ability, this paper proposes an analog circuit fault diagnosis model based on the sailfish algorithm to optimize the stacked kernel extreme learning machine(SKELM). This model introduces a kernel function to build a multi-layer KELM, which can improve the generalization ability and learning speed of the feedforward neural network. The weights of each layer of SKELM are obtained through the automatic encoder training based on the KELM. Since KELM-AE does not need to set initial parameters, the training speed is improved. However, the kernel parameters and regularization coefficients of KELM-AE are set manually, so the sailfish optimizer (SFO) is used to optimize these two parameters, and then the optimal SKELM model is built through layer by layer training. Finally, the Leap frog filter circuit is used as the simulation experiment circuit, and further compared with the optimized SELM. The results show that KELM-AE has strong generalization ability, and it can map fault features to high-dimensional feature space through nonlinear mapping without extracting fault features separately, thus improving the classification accuracy.

GSOANR-based multi-objective train trajectory optimization

ABSTRACT Railway transport is an important mode of transportation in China, UK, and worldwide. It is expected to play an even more important role in transportation decarbonization in shifting more passenger trips and freight transportations to railway. It is strategically important to reduce the energy consumption and improve the overall energy efficiency of the railway systems. The introduction of automatic train operation (ATO) systems in electrified railway systems makes it possible to achieve energy consumption reduction while satisfying other railway operation criteria such as the need for passenger comfort, train punctuality, and safety. Although energy saving of railway systems has attracted substantial interest in recent years, ATO systems are not environmentally friendly as expected and there is a lack of a set of energy saving performance measures for railway system planning and operation. In this paper, the features of ATO systems are incorporated into the problem formulation, and a modified GSO algorithm with adaptive neighbourhood range (namely the GSOANR algorithm) is proposed as the solver of the problem. The proposed method is applied to the trajectory planning of a 58-km-long route between Heishan North Station and Fuxin Station of the Beijing-Shenzhen Line in China, and the results confirm that the train operation trajectory generated by the GSOANR algorithm-based optimization method can reduce the electrical energy consumption by about 5.6% compared with the results generated by the standard GSO algorithms, confirming the efficacy of the proposed energy-saving measures and the effectiveness of the novel optimization method, and the referential significance for the study of the train trajectory optimization.

Reliability-aware failure recovery for cloud computing based automatic train supervision systems in urban rail transit using deep reinforcement learning

As urban rail transit construction advances with information technology, modernization, information, and intelligence have become the direction of development. A growing number of cloud platforms are being developed for transit in urban areas. However, the increasing scale of urban rail cloud platforms, coupled with the deployment of urban rail safety applications on the cloud platform, present a huge challenge to cloud reliability.One of the key components of urban rail transit cloud platforms is Automatic Train Supervision (ATS). The failure of the ATS cloud service would result in less punctual trains and decreased traffic efficiency, making it essential to research fault tolerance methods based on cloud computing to improve the reliability of ATS cloud services. This paper proposes a proactive, reliability-aware failure recovery method for ATS cloud services based on reinforcement learning. We formulate the problem of penalty error decision and resource-efficient optimization using the advanced actor-critic (A2C) algorithm. To maintain the freshness of the information, we use Age of Information (AoI) to train the agent, and construct the agent using Long Short-Term Memory (LSTM) to improve its sensitivity to fault events. Simulation results demonstrate that our proposed approach, LSTM-A2C, can effectively identify and correct faults in ATS cloud services, improving service reliability.

Accurate energy barriers for catalytic reaction pathways: an automatic training protocol for machine learning force fields

We introduce a training protocol for developing machine learning force fields (MLFFs), capable of accurately determining energy barriers in catalytic reaction pathways. The protocol is validated on the extensively explored hydrogenation of carbon dioxide to methanol over indium oxide. With the help of active learning, the final force field obtains energy barriers within 0.05 eV of Density Functional Theory. Thanks to the computational speedup, not only do we reduce the cost of routine in-silico catalytic tasks, but also find an alternative path for the previously established rate-limiting step, with a 40% reduction in activation energy. Furthermore, we illustrate the importance of finite temperature effects and compute free energy barriers. The transferability of the protocol is demonstrated on the experimentally relevant, yet unexplored, top-layer reduced indium oxide surface. The ability of MLFFs to enhance our understanding of extensively studied catalysts underscores the need for fast and accurate alternatives to direct ab-initio simulations.

On the Effectiveness of Correlation Reception and Nonlinear Processing in a Receiver of Continuous Automatic Train Signaling Signals

On the Effectiveness of Correlation Reception and Nonlinear Processing in a Receiver of Continuous Automatic Train Signaling Signals

A deformability-based biochip for precise label-free stratification of metastatic subtypes using deep learning

Cellular deformability is a promising biomarker for evaluating the physiological state of cells in medical applications. Microfluidics has emerged as a powerful technique for measuring cellular deformability. However, existing microfluidic-based assays for measuring cellular deformability rely heavily on image analysis, which can limit their scalability for high-throughput applications. Here, we develop a parallel constriction-based microfluidic flow cytometry device and an integrated computational framework (ATMQcD). The ATMQcD framework includes automatic training set generation, multiple object tracking, segmentation, and cellular deformability quantification. The system was validated using cancer cell lines of varying metastatic potential, achieving a classification accuracy of 92.4% for invasiveness assessment and stratifying cancer cells before and after hypoxia treatment. The ATMQcD system also demonstrated excellent performance in distinguishing cancer cells from leukocytes (accuracy = 89.5%). We developed a mechanical model based on power-law rheology to quantify stiffness, which was fitted with measured data directly. The model evaluated metastatic potentials for multiple cancer types and mixed cell populations, even under real-world clinical conditions. Our study presents a highly robust and transferable computational framework for multiobject tracking and deformation measurement tasks in microfluidics. We believe that this platform has the potential to pave the way for high-throughput analysis in clinical applications, providing a powerful tool for evaluating cellular deformability and assessing the physiological state of cells.

A Distributed Multiparticle Precise Stopping Control Model Based on the Distributed Model Predictive Control Algorithm for High-Speed Trains

Abstract The fixed-point stopping of high-speed trains in stations is generally accomplished through manual operation in China. This situation often leads to a failure to stop at fixed-point signs and causes a fluctuation in the longitudinal acceleration due to the lack of experience of the drivers. To achieve precise, stable, and automatic stopping, a distributed multiparticle precise stopping control model based on the distributed model predictive control (MPC) algorithm is developed in this paper. A two-level hierarchical control structure for the subcontroller of each vehicle is adopted to bring itself to a controlled stop. In the upper control of subcontroller, the MPC algorithm is designed in turn based on the multiparticle mechanism model of the train. In the lower control of subcontroller, the target input from the upper control is converted and distributed. The controlled object, a comprehensive numerical computing model including the spatial dynamic model of the train and its electropneumatic blending braking model, is established and controlled by the corresponding subcontroller and employed to verify the performance of the controller. The influence of the model control parameters on the stopping performance is discussed, and the optimal combination of control parameters is selected. The proposed control model using the optimization parameters is tested and verified through the comprehensive numerical computing model. The results indicate that the stopping error is 0.0075 m, which is much less than the accuracy requirements for fixed-point stopping. The computing time of each subcontroller in real-time is stable at 0.09 s. The coupler impact force between two adjacent vehicles can also be effectively inhibited and eliminated. Its control performance outperforms a proportional–integral–derivative (PID) algorithm. The proposed precise stopping model and comprehensive numerical computing model provide references for the application and algorithm optimization of automatic train operation technology in high-speed trains.

FARM: A fully automated rice mapping framework combining Sentinel-1 SAR and Sentinel-2 multi-temporal imagery

Rice farming exemplifies intensive agriculture, demanding significant inputs to achieve optimal yields. Thus, accurate and precise mapping of rice cultivation is vital for effective agricultural management and food security. However, such studies have been limited by the challenges of obtaining optical cloud-free data and dealing with radar data's speckle noise. Identifying crops using a single data source poses many difficulties. Additionally, acquiring sufficient representative training samples that accurately reflect diverse phenological patterns is challenging for large-scale monitoring and rice cultivation classification. To address these challenges, this study proposed a fully automated rice-mapping framework (FARM) that combines the strengths of time-series synthetic aperture radar (SAR) and optical satellite imagery for large-scale rice mapping without manual sample collection. First, an object-based, fully automatic training sample generation strategy is introduced. The phenology constraint rule, based on time-series SAR satellite images and specific rice-flooding features, is used to extract rice sample objects. Second, the extracted rice sample objects, adhering to phenological rules, serve as training samples for paddy rice extraction by integrating multiple random forest (RF) classifiers, referred to as the multi-RF method, where each RF is individually built using images acquired during each phenological phase of the growing season. Furthermore, the study explored the availability of the method in early-season rice identification by transferring the training samples acquired by the FARM to a new year. The proposed FARM approach was then validated under different cropping conditions at three study sites in China and two sites in other countries. The results showed that the FARM framework proved to be more effective than other methods at all five study sites, achieving average overall accuracies (OA) ranging from 89.67%−97.00%. In addition, when transferring the training samples from 2021 to other years (2020/2022), the OAs of site A, site B and site C were high during the heading period, with accuracies of 97.57%, 84.28% and 89.27%, respectively. These results demonstrated that, first, the FARM framework exhibits high efficiency and accuracy in different study areas without the need for extensive fieldwork to collect training samples. Second, the method has good performance in the early-season rice mapping of the new year and can be used to perform timely and accurate rice identification and monitoring tasks. The method shows great potential in obtaining large-area automatic rice mapping results in a timely and accurate manner. The latest release of FARM can be viewed at https://feature-selected.users.earthengine.app/view/farm, and the code is available on GitHub at the link https://github.com/gactyxc/FARM.git.

Key technologies and applications of intelligent dispatching command for high-speed railway in China

PurposeThe intelligent Central Traffic Control (CTC) system plays a vital role in establishing an intelligent high-speed railway (HSR) system. As the core of HSR transportation command, the intelligent CTC system is a new HSR dispatching command system that integrates the widely used CTC in China with the practical service requirements of intelligent dispatching. This paper aims to propose key technologies and applications for intelligent dispatching command in HSR in China.Design/methodology/approachThis paper first briefly introduces the functions and configuration of the intelligent CTC system. Some new servers, terminals and interfaces are introduced, which are plan adjustment server/terminal, interface for automatic train operation (ATO), interface for Dynamic Monitoring System of Train Control Equipment (DMS), interface for Power Supervisory Control and Data Acquisition (PSCADA), interface for Disaster Monitoring, etc.FindingsThe key technologies applied in the intelligent CTC system include automatic adjustment of train operation plans, safety control of train routes and commands, traffic information data platform, integrated simulation of traffic dispatching and ATO function. These technologies have been applied in the Beijing-Zhangjiakou HSR, which commenced operations at the end of 2019. Implementing these key intelligent functions has improved the train dispatching command capacity, ensured the safe operation of intelligent HSR, reduced the labor intensity of dispatching operators and enhanced the intelligence level of China's dispatching system.Originality/valueThis paper provides further challenges and research directions for the intelligent dispatching command of HSR. To achieve the objectives, new measures need to be conducted, including the development of advanced technologies for intelligent dispatching command, coping with new requirements with the development of China's railway signaling system, the integration of traffic dispatching and train control and the application of AI and data-driven modeling and methods.

Fully automatic training sample collection for detecting multi-decadal inland/seaward urban sprawl

Accurate and timely monitoring of urban sprawl using remote sensing provides valuable insights for urban management and sustainable development. While existing studies have explored methods for large-scale monitoring of urban sprawl, most of them rely on the collection of manually labeled training samples for supervised classification. Additionally, previous studies generally focused on inland urban sprawl, neglecting the process of urban sprawl towards sea areas, known as seaward urban sprawl, which has profound ecological implications for coastal ecosystems. Here we develop a fully automatic algorithm for detecting urban sprawl, named Fully Automatic Detection of Urban Sprawl (FADUS), using the time-series Landsat imagery without manually collecting training samples or existing urban maps for reference. FADUS automatically generates initial samples through a sequential binary unsupervised clustering technique and then updates them by removing the spectral outliers to obtain a high-quality training set for subsequent supervised classification. A tidal module is included in FADUS to avoid pseudo-urban changes caused by tidal fluctuations so that both inland and seaward urban sprawl can be detected. By applying the algorithm to 75 coastal cities in China, the most rapidly urbanizing region in the world, we uncovered a neglected but dramatic seaward urban sprawl process that has converted sea areas to urban space since 1985. Our results indicate that 9904.36 km2 of coastal wetlands and nearshore seawater areas have been converted to land area, of which 44.83% is currently covered by built-up area. With our method, the fully automatic detection of urban dynamics is now possible for both coastal and inland cities worldwide. Our derived map of seaward urban sprawl in China provides valuable references for coastal land-cover change monitoring, wetland protection and restoration, and integrated coastal management.

Прогноз случайных процессов, при наличии единичных возмущений в интеллектуальных транспортных системах

Forecasting random perturbations allows improving the control quality in intelligent transport systems and ensuring the efficient operation of diagnostic systems. Several works are known where extrapolator models based on Chebyshev polynomials orthogonal on equidistant points are presented. These models use a predictive polynomial whose coefficients are computed using the least squares criterion. Additionally, an analysis of forecast errors for random stationary input signals has been conducted. At the same time, in the case of non-stationary input signals, singular perturbations may occur, the influence of which on the extrapolator leads to significant forecast errors.
 This article presents an example of the occurrence of additive perturbations that arise in automatic train control systems. An analytical expression has been derived, and calculations of forecast error magnitudes in the presence of singular perturbations have been conducted. The analysis of the calculation results allows determining the influence of extrapolator parameters on the forecast error magnitude, highlighting the necessity of detecting singular perturbations, and excluding their influence on the forecast error magnitude.
 The article discusses an algorithm for detecting singular perturbations and their exclusion during the forecasting process. The conclusion is drawn about the effectiveness of using extrapolators for random perturbations with the exclusion of singular perturbations in intelligent systems for automatic train control in subway transportation.

Simultaneous object detection and segmentation for patient-specific markerless lung tumor tracking in simulated radiographs with deep learning.

Real-time tumor tracking is one motion management method to address motion-induced uncertainty. To date, fiducial markers are often required to reliably track lung tumors with X-ray imaging, which carries risks of complications and leads to prolonged treatment time. A markerless tracking approach is thus desirable. Deep learning-based approaches have shown promise for markerless tracking, but systematic evaluation and procedures to investigate applicability in individual cases are missing. Moreover, few efforts have been made to provide bounding box prediction and mask segmentation simultaneously, which could allow either rigid or deformable multi-leaf collimatortracking. The purpose of this study was to implement a deep learning-based markerless lung tumor tracking model exploiting patient-specific training which outputs both a bounding box and a mask segmentation simultaneously. We also aimed to compare the two kinds of predictions and to implement a specific procedure to understand the feasibility of markerless tracking on individualcases. We first trained a Retina U-Net baseline model on digitally reconstructed radiographs (DRRs) generated from a public dataset containing 875 CT scans and corresponding lung nodule annotations. Afterwards, we used an independent cohort of 97 lung patients to develop a patient-specific refinement procedure. In order to determine the optimal hyperparameters for automatic patient-specific training, we selected 13 patients for validation where the baseline model predicted a bounding box on planning CT (PCT)-DRR with intersection over union (IoU) with the ground-truth higher than 0.7. The final test set contained the remaining 84 patients with varying PCT-DRR IoU. For each testing patient, the baseline model was refined on the PCT-DRR to generate a patient-specific model, which was then tested on a separate 10-phase 4DCT-DRR to mimic the intrafraction motion during treatment. A template matching algorithm served as benchmark model. The testing results were evaluated by four metrics: the center of mass (COM) error and the Dice similarity coefficient (DSC) for segmentation masks, and the center of box (COB) error and the DSC for bounding box detections. Performance was compared to the benchmark model including statistical testing forsignificance. A PCT-DRR IoU value of 0.2 was shown to be the threshold dividing inconsistent (68%) and consistent (100%) success (defined as mean bounding box DSC > 0.6) of PS models on 4DCT-DRRs. Thirty-seven out of the eighty-four testing cases had a PCT-DRR IoU above 0.2. For these 37 cases, the mean COM error was 2.6 mm, the mean segmentation DSC was 0.78, the mean COB error was 2.7 mm, and the mean box DSC was 0.83. Including the validation cases, the model was applicable to 50 out of 97 patients when using the PCT-DRR IoU threshold of 0.2. The inference time per frame was 170 ms. The model outperformed the benchmark model on all metrics, and the comparison was significant (p < 0.001) over the 37 PCT-DRR IoU > 0.2 cases, but not over the undifferentiated 84 testingcases. The implemented patient-specific refinement approach based on a pre-trained baseline model was shown to be applicable to markerless tumor tracking in simulated radiographs for lungcases.

An improved single-stage convolutional neural network for rail transit obstacle detection

Obstacles that intrude into the rail area can lead to serious rail accidents, so obstacle detection technology is an essential guarantee for the safe operation of fully automatic trains. To meet the high-performance requirements of onboard obstacle detection, an efficient feature-aware convolutional neural network (EFA-Net) is proposed in this paper. The multi-scale aware feature pyramid network (MA-FPN) is designed as feature fusion network to extract multi-scale context information. In the detection head, the dynamic awareness block is used to refine the features. A joint representation branch and the generalized focal loss function are introduced to optimize the training effect. The experiments are based on the dataset of real-world rail transit environment. The results show that EFA-Net can achieve a detection accuracy of 90.4% mAP at a detection speed of 20.4 frames per second, and the lightweight design significantly reduces the computational complexity of the proposed model. Compared with other classical detectors, EFA-Net has the best comprehensive performance.

THE UTILIZATION OF AUTOMATIC PLASTIC SEAL PRESS MACHINES TO IMPROVE PRODUCT PACKAGING QUALITY OF BREAD ENTREPRENEURS IN SINGOSARI, MALANG

Micro, Small, and Medium Enterprises (UMKM) are one of the driving forces of the economy in a local area and a booster for the community's welfare. One of the obstacles often faced by the bread entrepreneurs in Singosari District, Malang Regency, is the lack of quality product packaging that still uses manual tools and is not optimal in creating marketing content. This community service aims to provide automatic plastic seal press machines and training on marketing content creation for micro-business actors in the bread entrepreneurs so that it is expected to increase partners' competitiveness. The stages of community service were observation and coordination, providing machines, handing over machines, holding training, and evaluation. The results of the community service activities showed that the training participants were enthusiastic and actively participated during the training. The quality of product packaging after using a plastic seal press machine has also improved, evidenced by a tighter and well-protected packaging seal. The copywriting training has also broadened the participants' knowledge about strategies for creating product marketing content by utilizing applications available on Android.

Real-Time Video Smoke Detection Based on Deep Domain Adaptation for Injection Molding Machines

Leakage with smoke is often accompanied by fire and explosion hazards. Detecting smoke helps gain time for crisis management. This study aims to address this issue by establishing a video smoke detection system, based on a convolutional neural network (CNN), with the help of smoke synthesis, auto-annotation, and an attention mechanism by fusing gray histogram image information. Additionally, the study incorporates the domain adversarial training of neural networks (DANN) to investigate the effect of domain shifts when adapting the smoke detection model from one injection molding machine to another on-site. It achieves the function of domain confusion without requiring labeling, as well as the automatic extraction of domain features and automatic adversarial training, using target domain data. Compared to deep domain confusion (DDC), naïve DANN, and the domain separation network (DSN), the proposed method achieves the highest accuracy rates of 93.17% and 91.35% in both scenarios. Furthermore, the experiment employs t-distributed stochastic neighbor embedding (t-SNE) to facilitate fast training and smoke detection between machines by leveraging domain adaption features.

A Microservices-Based Approach to Designing an Intelligent Railway Control System Architecture

The symmetry between customer expectations and operator goals, on one hand, and the digital transition of the railways, on the other hand, is one of the main factors affecting green transport sustainability. The European Train Control System (ETCS) was created to improve interoperability between different railway signaling systems and increase safety and security. While there are a lot of ETCS Level 2 deployments all over the world, the specifications of ETCS Level 3 are under development. ETCS Level 3 is expected to have a significant impact on automatic train operation, protection, and supervision. In this paper, we present an innovative control system architecture that allows the incorporation of artificial intelligence (AI)/machine learning (ML) applications. The architecture features control function virtualization and programmability. The concept of an intelligent railway controller (IRC) is introduced as being a piece of cloud software responsible for the control and optimization of railway operations. A microservices-based approach to designing the IRC’s functionality is presented. The approach was formally verified, and some of its performance metrics were identified.

Layered mixed-precision training: A new training method for large-scale AI models

How to efficiently and quickly train large-scale AI models has become a hot topic in recent deep learning. Mixed-precision training is an effective technique to speed up training and reduce memory usage. At present, the automatic mixed-precision training method mainly uses half-precision (FP16) for the matrix operations of forward and backward propagation of the entire model and accumulates the FP32 weight copies to avoid rounding errors. However, this method is not optimized for each layer individually, leading to poor convergence in large-scale model training because different layers have different data patterns. Therefore, this paper proposes a layered mixed-precision training method, which can flexibly adjust training precisions according to the contribution of each layer to the training effect. Applying the layered mixed-precision method, the ResNet model achieves a 1.9× speedup compared to the baseline and a lower percentage of accuracy loss. In addition, this paper combines the layered mixed-precision method with distributed training strategies. Combining data parallel training, the model achieves a 3.74× speedup by using four Tesla V100 GPUs. The applicability of the layered mixed-precision method in model parallel training has been verified. Combining optimized pipeline parallel training, the model achieves a 3.26× speedup by using three Tesla V100 GPUs.

Parameter Adaptive Research of Automatic Train Control Algorithm Based on Sliding Mode PID

In existing urban rail systems, most trains are operated by automatic control, which places high demands on the control effectiveness of automatic train operation (ATO). In this study, a train operation model considering the response delay is firstly constructed. Subsequently, by analyzing and comparing the existing mainstream research methods, neural network and sliding mode control techniques were selected and incorporated into the speed control of the train. Among them, the dynamic sliding mode technique, is used to optimize the PID control effect of ATO. Single neuron and back propagation (BP) neural network algorithms are applied to the selection of PID control parameters. The study selects the difference between the actual speed of the control train and the target speed as the control objective. Through continuous optimization and iteration of the control parameters, the control accuracy of the train operation was improved. Finally, this study validates and simulates different model control methods using the actual operation data of urban rail transit. The results show that the sliding mode PID control model optimized with BP neural network performs better in terms of error distribution, average error value, and control effect variance under different simulation scenarios, showing good tracking ability and robustness. The related research results are expected to be applied to the initial selection of rail vehicle control parameters, dynamic adaptive operation control, and other fields, providing practical help to rail operators and rail signaling companies.