Train Operation Research Articles

Characteristics of Sudden Change in Aerodynamic Load of High-Speed Train Caused by Wind Barrier and Its Buffer Measure

When high-speed trains (HSTs) rapidly enter or exit the wind barrier area of the bridge, the quick change in the operating environment can lead to sudden changes in train aerodynamic loads, resulting in the deterioration of their aerodynamic performance and adversely affecting safe and stable operation. In this paper, the effects of wind barrier porosity, crosswind speed, and train speed on the sudden change in the aerodynamic load of the HST induced by wind barriers are analyzed, and the reasons for the sudden change from a flow field perspective are given. Additionally, the influences of the buffer structure with three lengths of 45 m, 90 m, and 135 m on the sudden change in the aerodynamic load of HSTs are studied. The results show that the lower the porosity of the wind barrier, the higher the crosswind speed, and the lower the speed of trains entering and exiting the wind barrier area, resulting in a greater degree of sudden change in the aerodynamic load of the HST. The buffer structure measuring 90 m in length is considered the most suitable, as it can significantly alleviate the sudden change in the aerodynamic load and effectively enhance the safety of train operations.

Transforming Farming: A Review of AI-Powered UAV Technologies in Precision Agriculture

The integration of unmanned aerial vehicles (UAVs) with artificial intelligence (AI) and machine learning (ML) has fundamentally transformed precision agriculture by enhancing efficiency, sustainability, and data-driven decision making. In this paper, we present a comprehensive overview of the integration of multispectral, hyperspectral, and thermal sensors mounted on drones with AI-driven algorithms to transform modern farms. Such technologies support crop health monitoring in real time, resource management, and automated decision making, thus improving productivity with considerably reduced resource consumption. However, limitations include high costs of operation, limited UAV battery life, and the need for highly trained operators. The novelty of this study lies in the thorough analysis and comparison of all UAV-AI integration research, along with an overview of existing related works and an analysis of the gaps. Furthermore, practical solutions to technological challenges are summarized to provide insights into precision agriculture. This paper also discusses the barriers to UAV adoption and suggests practical solutions to overcome existing limitations. Finally, this paper outlines future research directions, which will discuss advances in sensor technology, energy-efficient AI models, and how these aspects influence ethical considerations regarding the use of UAVs in agricultural research.

Turbulence correlation between moving trains and anemometer towers: Theoretical analysis, field measurements and simulation

A precise command of railway operations according to the measured instantaneous wind speed on an anemometer tower along a railway line is the development trend, whose challenges lie in the unknown transfer relation(s) between wind speed fluctuations on a moving train and an anemometer tower, i.e. the turbulence correlation between them. To address this issue, in the current work, the cross-correlation functions of wind speed fluctuations at the moving train and anemometer tower are derived, and an empirical formula of the coherence functions is obtained. The turbulence correlation is inversely related to the separation distance from the anemometer tower to the line, and there is little correlation when this distance is longer than double the longitudinal turbulence length scale. Field measurements of wind characteristics were carried out on an anemometer tower and a moving vehicle, and the turbulence correlation and its expression were validated. Three methods are proposed and compared to evaluate the instantaneous wind speed at the anemometer tower and moving train with this correlation. The methods based on the cross-spectral density and coherence function can accurately simulate the correlation, and the latter performance is slightly better (its simulation of the frequency domain correlation is 52.9% better than the former); the method based on solely independent and identically distributed random phases cannot fully simulate the correlation. From this, the effects of the correlation on train operations are studied and analysed in detail. Our analysis shows that neglecting this correlation leads to conservative estimates: wind speed differences between the anemometer tower and the moving train are at least 18.1% greater, and the safety and economic assessments of train operations in crosswinds are underestimated by at least 32.0%. Considering the correlation can reduce the (excess) safety risk/margin and is an inevitable development of adapting to the detailed assessment of the crosswind stability of vehicles. The quantitative description and simulation of the correlation presented in this work point to the critical importance of wind speed monitoring systems for the detailed crosswind assessment, and provide a theoretical basis for further research work on the crosswind stability of vehicles under true/realistic turbulent flow wind.

Discrete Element Analysis of the Dynamic Mechanical Characteristics of Ballasted Track on Bridges Under Train Loading

The operation and service performance of ballasted track on bridges face significant challenges due to high-speed railway train operations. To investigate the mechanical characteristics of ballasted track on bridges, field experiments were conducted. A coupling model of ballasted track on a simply-supported girder bridge was established using the coupling method of discrete element and multi-flexible body dynamics and analyzes the changes in ballast bed settlement deformation, stiffness and energy with increasing load cycles. The findings reveal that dynamic loading alters the original contact state of ballast particles, displaying notable anisotropy vertically and longitudinally and isotropy horizontally. The vibration of ballast particles on bridges is more pronounced than on the subgrade, with vibration acceleration under the sleeper at 150[Formula: see text]mm depth on the bridge being 2.89 times that on the subgrade foundation. As the system stabilizes, the interlocking effect among granular ballast particles strengthens, reducing mutual sliding and increasing ballast bed stiffness by approximately 7.8–9.5% compared to the initial state, while total energy and dissipated energy gradually decrease. It is recommended to monitor the quality of ballast particles under the sleeper of ballasted tracks on bridges, implement vibration mitigation measures, or periodically replace ballast particles.

A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems

A main circuit ground fault (MCGF) is a typical system fault in an electrical traction drive system (ETDS). When two or more MCGFs occur, it will cause serious accidents. Therefore, it is particularly important to detect and handle MCGFs in a timely manner. To improve the efficiency of train operation and ensure driving safety, this paper proposes a hybrid data-driven MCGF diagnosis method. First, the voltage signals related to the fault are selected according to the mechanism analysis of the MCGF, and then the initial feature variables are constructed according to these voltage signals. Secondly, the initial feature variables of different types of MCGF are analyzed in the time and frequency domains by wavelet transform, and four feature indicators are calculated. Finally, the fault feature indicators are trained by random forest to obtain a model for subsequent fault diagnosis. After comparative experiments using various machine learning methods, it was found that the RF used in the proposed method has a better diagnostic effect, and the correct isolation rate exceeds 99%.

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

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

Physics-guided fault diagnosis method for proton exchange membrane fuel cells based on LSTM neural network

In this paper, we propose a novel hybrid method for fault diagnosis of Proton Exchange Membrane Fuel Cells (PEMFCs) based on the combination of a physics-based model and a long short-term memory (LSTM) neural network. By incorporating the physics-based model in the fault diagnosis algorithm, we can access to several process variables not directly measured through sensors but related to the state of the PEMFC stack. The model estimates are subsequently combined with signals measured on the PEMFC stack and inputted to a LSTM neural network. The performance of the physics-guided LSTM is evaluated on an extensive dataset comprising a thousand hours of operation of a PEMFC stack under dynamic load profiles, proving the enhanced capability of the proposed fault diagnosis method in capturing complex fault patterns. Furthermore, the effectiveness of the proposed method in dealing with PEMFC aging is tested by using data from the initial phase of stack operation for algorithm training and reserving the data from the aged stack operation for the testing phase. The experimental results reveal that the proposed physics-guided LSTM method allows for a significant amelioration over purely data-driven LSTM.

Computing Unit and Data Migration Strategy under Limited Resources: Taking Train Operation Control System as an Example

There are conflicts between the increasingly complex operational requirements and the slow rate of system platform upgrading, especially in the industry of railway transit-signaling systems. We attempted to address this problem by establishing a model for migrating computing units and data under resource-constrained conditions in this paper. By decomposing and reallocating application functions, optimizing the use of CPU, memory, and network bandwidth, a hierarchical structure of computing units is proposed. The architecture divides the system into layers and components to facilitate resource management. Then, a migration strategy is proposed, which mainly focuses on moving components and data from less critical paths to critical paths and ultimately optimizing the utilization of computing resources. Specifically, the test results suggest that the method can reduce the overall CPU utilization by 27%, memory usage by 6.8%, and network bandwidth occupation by 35%. The practical value of this study lies in providing a theoretical model and implementation method for optimizing resource allocation in scenarios where there is a gap between resource and computing requirements in fixed-resource service architectures. The strategy is compatible for distributed computing architectures and cloud/cloud–edge-computing architectures.

Research on aerodynamic characteristics of high-velocity train bogies

The bogie is a critical component of high-velocity trains. As train velocity rises, the operational quality is increasingly influenced by aerodynamic forces. The aerodynamic characteristics of bogies significantly impact the safety of train operations. This article examines a real high-velocity train model, constructing a 3-group train model, and developing a mathematical model of high-velocity train operation on open lines. Using three-dimensional steady-state Navier–Stokes equations, the flow field characteristics, pressure spread, aerodynamic forces, and torque characteristics on the bogie and body of high-velocity locomotives operating at velocities of 200 km/h, 250 km/h, 300 km/h, and 350 km/h are calculated, with measurement spots set to study the trend of pressure variation with train velocity. The research findings indicate that pressure at the same location on the body surface rises with vehicle velocity, with a quadratic link between the two. The uneven pressure spread between two bogies of the same vehicle and between two axles of the same bogie indicates that aerodynamic forces can cause axle load transfer in high-velocity trains. The highest values of aerodynamic resistance and lift happen at the front bogie, and the resistance and lift of both a single carriage and the entire vehicle increase with velocity, following a quadratic relationship. The highest nodding torque of the train body occurs on one vehicle, while the highest nodding torque of the bogie occurs on the 6th bogie, with both torques increasing with velocity, also in a quadratic relationship.

Automatic measurement of stimulation to maximum negative dv/dt in V5 and V6 leads to confirm left bundle capture for conduction system pacing

Abstract Introduction Left bundle area conduction system pacing is obtained when the ventricular pacing lead is implanted into the right ventricular septum and captures the left bundle branch, demonstrated by right bundle branch morphology in the lead V1 and short stimulation to R-wave peak time (SRWPT) in leads V5 or V6. Manual measurements are challenging and result in significant variability. Maximum negative dv/dt in leads V5 and V6, occurring immediate after maximal lateral wall depolarization, represents the ideal measurement of synchronicity of left ventricular depolarization, as suggested by the guidelines. Objective To test feasibility of automatic algorithm to measure the maximum negative dV/dt in comparison to manual SRWPT measurement in V5 and V6. Method Data was collected from 7 patients with confirmed left bundle branch capture. Three trained operators manually measured SRWPT in leads V5 and V6 (Figure A). An algorithm capable of automatically measuring stimulation to maximum dv/dt was retrospectively applied to the same measured beats. Variability and correlation of measurements was compared between manual and automatic using the Bartlett Test for equal variance. Results In total, 137 individual beats were measured in the 2 leads by three operators resulting in 822 manual measurements. The mean variability of SRWPT in V5 and V6 was 2.9 ± 0.7 msec and 3.1 ± 1.1 msec, respectively (inter-operator correlation of 0.83). In contrast the stimulation to max negative dv/ dt mean variability in V5 and V6 was 1.3 ± 0.4 msec and 1.2 ± 0.5 msec, respectively (P < 0.001). The comparison of variation in measurement between manual and automatic measures are shown in a box and whisker plot in figure 2. Conclusion Manual measurement of SRWPT can be challenging resulting in higher variability compared to an automatic algorithm measuring max negative dv/dt. This study demonstrates the feasibility of automatic interval measurement in conduction system pacing; however, further studies are required to validate the reliability of such tool.Fig 1.Example ECG interval measurement

Research on frequency shift signal detection algorithm for jointless track circuits based on improved relaxation algorithm

The accuracy of ZPW-2000 frequency shift signal demodulation is related to the safety and efficiency of high-speed trains. This paper proposed a kind of ZPW-2000 frequency-shift signal detection algorithm based on improved Relaxation algorithm (ZFSD-IR) to address the issue of low accuracy in detecting ZPW-2000 frequency shift signal under strong noise interference, as the traditional fast Fourier transform (FFT) spectrum analysis methods are susceptible to fence effects and spectrum leakage effects. Firstly, the principle of ZPW-2000 jointless track circuit was analyzed, and then the ideal and simplified models of ZPW-2000 frequency shift signal were established, respectively. Finally, the simulation experiments were conducted on ZPW-2000 frequency shift signal detection under different sampling durations and signal-to-noise ratios (SNR). The effectiveness of the proposed algorithm was verified through comparative analysis with the traditional algorithms. The research results indicated that the ZFSD-IR algorithm has better accuracy in carrier-frequency and low-frequency estimation than traditional algorithms, and can achieve accurate detection of ZPW-2000 frequency shift signal under the lower SNR conditions. It has high detection accuracy and good anti-interference ability, ensuring the safe operation of high-speed trains.

Integral predictive sliding mode control for high-speed trains: A dynamic linearization and input constraint-based data-driven scheme

A control scheme with high reliability and excellent tracking performance is essential for the automatic operation of high-speed trains (HSTs). In this study, a novel discrete-time data-driven predictive sliding mode control (DDPSMC) scheme is proposed for multi-power unit HSTs. Initially, a nonlinear integral terminal sliding mode surface was designed to replace the traditional linear sliding mode function, thereby achieving a rapid system error convergence and alleviating chattering. Then, receding horizon optimization was integrated into predictive control, which allowed the predicted sliding mode state to follow the expected trajectory of a predefined continuous convergence law. This scheme enabled the system to obtain higher output error accuracy and explicitly handle input constraints. Moreover, to enhance robustness, a parameter update law and disturbance delay estimation algorithm were introduced to calculate the control gain and total uncertainty, respectively. Finally, a comparative test of the proposed control scheme was conducted using a CRH380A HST simulation experimental platform in a laboratory setting. Simulation results demonstrate that the velocity error range of each power unit of the HST under the proposed control scheme is within [−0.176 km/h, 0.152 km/h], while the control force and acceleration are within [−55.7 kN, 44.8 kN] and [−0.564 m/s2, 0.496 m/s2], respectively, with stable variation, and other performance indicators are also better than other comparison methods. These results satisfy the safety, stability, and punctuality requirements of the train.

Laboratory Experimental Investigation on the Structural Optimization of a Novel Coupled Energy Tunnel

Freezing damage to tunnels in cold regions has long posed a threat to the safe operation of high-speed trains and other means of transportation. Finding a reasonable and effective solution to this problem, while also considering green, low-carbon, energy-saving, and environmental protection measures, has garnered widespread attention. Herein, the concept of a novel coupled energy tunnel is proposed, which combines the technologies of an air curtain and ground source heat pump (GSHP). The aim is to effectively address the issue of freezing damage in tunnels located in cold regions, while ensuring traffic safety. First, the multifunctional experimental apparatus for testing the anti-freezing and insulation performance of a coupled energy tunnel was independently designed and developed for laboratory experiments. Second, single-factor experiments and orthogonal experiments are conducted, and the influences of five key factors (i.e., the air outlet hole diameter, air outlet hole spacing, circulating water temperature of the GSHP, wind speed at the tunnel model entrance, and airflow jet angle) on the internal temperature field of the tunnel model are discussed. Third, combined with range analysis and variance analysis, the ranking of importance for each key factor and the optimal scheme of the coupled energy tunnel are obtained as follows: wind speed at the tunnel model entrance D > circulating water temperature of GSHP C > airflow jet angle E > air outlet hole spacing B > air outlet hole diameter A, and the optimal scheme is A2B1C4D1E2, i.e., the air outlet hole diameter is 3 mm, the air outlet hole spacing is 10 mm, the circulating water temperature of GSHP is 50 °C, the wind speed at the tunnel model entrance is 1.5 m/s and the airflow jet angle is 45°. In conclusion, the research achievements presented in this paper can offer a new perspective for the structural design of tunnels in cold regions. Additionally, they contribute to the early achievement of a carbon dioxide emissions peak and carbon neutrality, and provide some valuable and scientific references for both innovators and practitioners.

Influence of trains meeting on the ventilation performance of equipment compartment with independent air duct in high-speed train: numerical and experimental study

AbstractDuring the train meeting events, train equipment compartments are exposed to the worst pressure changes, potentially affecting the ventilation performance of equipment, particularly for electrical facilities equipped with independent air ducts. In this paper, a two-step method is used for numerical computation: (1) obtaining the temporal and spatial transient node data of the flow field sections during the train-passing simulation and (2) using the data as the input data for the equipment compartment simulation. In addition, this paper also compares the difference in equipment ventilation between the single-train and train-passing scenarios in real vehicle tests. The results indicate that the primary factors influencing ventilation effectiveness are the aerodynamic compression and deceleration of airflow induced by the other train’s nose, as well as the instability of the external flow field in the wake of the other train. During train crossing, the air is forced into the air duct, with a maximum ratio of the airflow in-duct to the airflow out-duct reaching 3.2. The average mass flow falls below the rated mass flow for the converter. Compared to the rated air volume of converter, the maximum suppression rates obtained from testing and simulation are – 24.5% and – 16.8%, respectively. Compared to the single-train operation, the maximum suppression rates obtained from testing and simulation are – 15% and – 18%, respectively. These findings provide valuable insights into the design and operation of high-speed trains.

Identification of wheel surface cracks under high noise environment based on texture segmentation and combination descriptor

ABSTRACT The wheel is easy to produce defects after a long time of use. Train maintenance technicians must overhaul and maintain train wheels on time and regularly to ensure the safe operation of trains. The existing manual detection has disadvantages of low efficiency and strong subjectivity. Compared with other defect forms, the identification accuracy of wheel surface crack is low due to the high noise and weak features, this paper proposes a feature enhancement and identification method for wheel surface crack based on texture segmentation and combination descriptor. Firstly, a morphology-based texture segmentation method is proposed to separate cracks and noise. Then, the crack characteristics are enhanced by filtering. Finally, a crack diagnosis method based on combination descriptor is proposed, which is evaluated from two dimensions of crack morphology and distribution characteristics. In order to verify the effectiveness of the proposed method, the images of the wheel collected from the freight car workshop were used for verification, and the detection rate reached 93.78%. The experimental results show that the proposed method is more effective in the case of weak crack features and surface dirt, and can better adapt to the identification of surface cracks on wheel in complex engineering applications.

Adaptive feature fusion and disturbance correction for accurate remaining useful life prediction of rolling bearings

As a key component in the transmission system of high-speed trains, bearings need to withstand certain loads while rotating at high speeds. Once a failure occurs, it can directly affect the safety of train operations. Therefore, it is of great significance to establish a reliable remaining useful life model to ensure train operation safety. Addressing the problems of redundant features in the existing multi-feature fusion process, which affects diagnostic performance, and the spurious fluctuations in the fusion features, which cause inaccurate determination of the start fault time and lead to low prediction accuracy of remaining useful life, we propose a method based on adaptive feature fusion and the autoregressive integrated moving average model for rolling bearing prediction. Firstly, features from the time domain, frequency domain, and entropy are extracted. A feature selection mechanism with minimum redundancy is constructed to screen the optimal sensitive feature set. Secondly, based on adaptive feature fusion, the optimal sensitive feature set is dynamically fused, and the spurious fluctuations of the health index are corrected using linear regression and the 3σ principle. Next, a bottom-up time series segmentation method is employed to divide the health status of the Improved Health Indicators. Finally, a remaining useful life prediction model based on the autoregressive integrated moving average model is established. This study demonstrates that the proposed method effectively identifies features that are most sensitive to degradation trends, accurately determines the initial fault moment of bearings, and achieves effective prediction of the remaining useful life of bearings.

Research on fault diagnosis of mechanical component in high-speed train based on one-dimensional convolutional block residual channel attention

The yaw damper and the rolling bearing are key components to ensure the safe and reliable operation of high-speed trains. However, fault identification in these components remains challenging, with traditional feature extraction methods often suffering from low diagnostic accuracy. To address these issues, a one-dimensional convolutional block residual channel attention (1DCBRCA) method for fault diagnosis of high-speed train components is introduced. Firstly, the convolutional layer is constructed for feature extraction, and the convolution block attention module is utilized for adaptive feature optimization in both channel and space dimensions. Subsequently, a residual neural network model is established, with channel attention added after each residual block to focus on critical feature information, which is used for adjusting the weight parameters. Furthermore, the proposed method was validated through damper fault experiments and bearing fault experiments. Comparative analysis with state-of-the-art methods demonstrated that the proposed 1DCBRCA approach achieves higher diagnostic accuracy, confirming its potential to enhance fault diagnosis in high-speed train components.

Training and education of operating room nurses in robot-assisted surgery: a systematic review.

With the introduction of robot-assisted surgery, the role and responsibility of the operating room nurses have been expanded. The surgical team for robotic-assisted surgery depends on the ability of the operating room nurses to operate and handle the robotic system before, during, and after procedures. However, operating room nurses must acquire the necessary competencies for robotic-assisted surgery. We performed a systematic review using the databases MEDLINE and EMBASE to review the evidence on educating and training operating room nurses in robot-assisted surgery. Studies describing operating room nurses' training and team-training with operating room nurses for robot-assisted surgery were included. The Medical Education Research Study Quality Instrument (MERSQI) and the Newcastle-Ottawa Scale-Education (NOS-E) were used to evaluate the quality of the included studies. We identified 3351 potential studies and included 16 in the final synthesis. Nine studies focused on team-training in robot-assisted surgery: four focused solely on training for operating room nurses, and only three on operating room nurses as first assistants in robot-assisted surgery. Most studies examined team-training in RAS, including OR nurses, focused on emergency situations and conversion to an open procedure. Only a few studies addressed other competencies relevant to OR nurses in RAS. No randomized controlled trials were identified. Only a few studies used pre- and post-testing, and only one examined clinical outcomes. The quality assessment of the included studies was moderate to low, with a median MERSQI score of 10.3 and a median NOS-E score of 2. There is sparse research on the education of operating room nurses in robot-assisted surgery, and the literature emphasizes the training of surgeons. More research is needed to develop evidence-based training for operating room nurses in robot-assisted surgery.

Energy consumption analysis of trains based on multi-mode virtual coupling operation control strategies

Urban rail transit, as a main mode of travel, has always been concerned with the balanced relationship between energy consumption and transport efficiency. The advent of the virtually coupled train set (VCTS) has significantly enhanced the efficiency of existing railway lines. Both energy consumption and comfort during the operation of VCTS control technology have emerged as significant challenges for the development of VCTS since the inception of onsite testing. A review of the current research status of VCTS control systems has revealed that the majority of current formation control systems are focused on the safe operation of formation trains, the stability of train control systems, and safe train separation models. However, a case study has shown there is a strong correlation between train operating intervals, train control strategies, and train operating energy consumption. Therefore, it is necessary to design and plan the operation modes of formation trains for different train operation requirements. This paper presents four distinct control modes, developed through the integration of the most prevalent VCTS control strategies, operational modes, and operational requirements. The design of these control modes is guided by considerations of energy consumption, safety, and comfort during train operation. A case study of Beijing Subway Line 11 revealed a significant correlation between energy consumption, control mode, and safety under different control modes. In particular, the correlation between train running intervals and energy consumption in a high-precision tracking state provides valuable technical support for the future operation of VCTS technology in different periods, scenarios, and environments.

3D reconstruction and depth estimation method for local anomalies of rail surface based on multi-view stereo matching

Abstract Detecting rail surface anomalies has become crucial for ensuring the safety of train operations. However, manual detection methods are time-consuming and labor-intensive. Although traditional detection models based on one-dimensional signals or two-dimensional images can effectively identify the existence of defects, they are difficult to use to obtain local depth characteristic information, leading to difficulties in accurately assessing the extent of damage in abnormal regions. Rail track maintenance strategies are typically developed based on the detected different depth ranges of defects. To address this issue, this paper proposes a local depth estimation method based on the point cloud of the target rail surface reconstructed by PatchmatchNet. Firstly, according to the acquisition method of multi-view images and the sampling environment at the site, a practical data collection protocol is established for generating a multi-view dataset of rail surface. Next, dense point cloud of the target rail surface were reconstructed by PatchmatchNet. Subsequently, a method for estimating the local anomaly depth is developed based on the point cloud. Experimental results demonstrate that the proposed method achieves a minimum error of approximately 5.5% within a maximum depth range of 0.35mm, when compared to depth measurements obtained using a structured light camera. Finally, this paper presents a more comprehensive three-dimensional representation of the local abnormal physical structure, surpassing traditional one-dimensional and two-dimensional forms. This enhanced representation offers richer information for the effective determination of whether the anomalies constitute defects and aids in distinguishing true defects from other surface irregularities. Such advancement significantly improves the precision of defect assessment and supports the development of highly precise repair strategies.