Search

BACKGROUND: The use of indwelling closed thoracic drainage tubes in the wedge resection of the lungs is of great significance to postoperative recovery. However, there are potential risks. OBJECTIVE: To explore the design feasibility and application effect of triple-buffer-system-fixed small-diameter (18 F) thoracic closed drainage tubes following lung wedge resection. METHODS: A total of 136 patients with indwelling thoracic drainage tubes following pulmonary wedge resection were recruited, with 70 patients allocated to the control group and 66 to the experimental group. The drainage tube in the experimental group was fixed with the triple-buffer system, while that in the control group was fixed using the conventional lifting platform method. The incidence of unplanned extubation, the indwelling time of the drainage tube and the time and material costs, as well as information regarding any subcutaneous emphysema and skin tension blisters, were recorded following the operation. The pain and degree of comfort were assessed using a chi-square test and a rank sum t -test to compare the differences between the two groups. RESULTS: There were no statistically significant differences in terms of age, gender and sweating between the two groups. Compared with the control group, the unplanned extubation rate of the experimental group was lower ( χ 2 = 8.513; P = 0.004), the indwelling time of the drainage tube was shorter (t = 2.108; P = 0.037), the cumulative material cost was lower (t = 3.778; P < 0.001), the time cost was also lower (Z = 2.717; P = 0.008), the degree of comfort was higher (Z = 2.752; P = 0.006), and the degree of pain was lower (Z = 4.019; P < 0.001). The incidence of subcutaneous emphysema was significantly lower in the experimental group than in the control group ( χ 2 = 8.513; P = 0.004). CONCLUSION: The use of the triple-buffer system to fix small-diameter (18 F) thoracic closed drainage tubes can reduce the unplanned extubation rate, indwelling time of the drainage tube and the incidence of adverse reactions. [ABSTRACT FROM AUTHOR]

Autonomous railway inspection with unmanned aerial vehicles (UAVs) has huge advantages over traditional inspection methods. As a prerequisite for UAV‐based autonomous following of railway lines, it is quite essential to develop intelligent railway track detection algorithms. However, there are no existing algorithms currently that can efficiently adapt to the demand for the various forms and changing inclination angles of railway tracks in the UAV aerial images. To address the challenge, this paper proposes a novel anchor‐adaptive railway track detection network (ARTNet), which constructs a dual‐branch architecture based on projection length discrimination to realize full‐angle railway track detection for the UAV aerial images taken from arbitrary viewing angles. Considering the potential capacity imbalance of the two branches that can be caused by the uneven distribution of railway tracks in the dataset, a balanced transpose co‐training strategy is proposed to train the two branches coordinately. Moreover, an extra customized transposed consistency loss is designed to guide the training of the network without increasing any computational complexity. A set of experiments have been conducted to verify the feasibility and superiority of the ARTNet. It is demonstrated that our approach can effectively realize full‐angle railway track detection and outperform other popular algorithms greatly in terms of both detection accuracy and reasoning efficiency. ARTNet can achieve a mean F1 of 76.12 and run at a speed of 50 more frames per second. [ABSTRACT FROM AUTHOR]

A safe and stable operation power system is very important for the maintenance of national industrial security and social economy. However, with the increasing complexity of the power grid topology and its operation, new challenges in estimating and evaluating the grid structure performance have received significant attention. Complex network theory transfers the power grid to a network with nodes and links, which helps evaluate the system conveniently with a global view. In this paper, we employ the complex network method to address the cascade failure process and grid structure performance assessment simultaneously. Firstly, a grid cascade failure model based on network topology and power system characteristics is constructed. Then, a set of performance evaluation indicators, including invulnerability, reliability, and vulnerability, is proposed based on the actual functional properties of the grid by renewing the power-weighted degree, medium, and clustering coefficients according to the network cascade failure. Finally, a comprehensive network performance evaluation index, which combines the invulnerability, reliability, and vulnerability indicators with an entropy-based objective weighting method, is put forward in this study. In order to confirm the approach's efficacy, an IEEE-30 bus system is employed for a case study. Numerical results show that the weighted integrated index with a functional network could better evaluate the power grid performance than the unweighted index with a topology network, which demonstrates and validates the effectiveness of the method proposed in this paper. [ABSTRACT FROM AUTHOR]

Glutathione S-transferases (GSTs) are important type-II detoxification enzymes that protect DNA and proteins from damage and are often used as protein tags for the expression of fusion proteins. In the present work, octa-aminopropyl caged polyhedral oligomeric silsesquioxane (OA–POSS) was prepared via acid-catalyzed hydrolysis of 3-aminopropyltriethoxysilane and polymerized on the surface of graphene oxide (GO) through an amidation reaction. Glutathione (GSH) was then modified to GO–POSS through a Michael addition reaction to obtain a GSH-functionalized GO–POSS composite (GPG). The structure and characteristics of the as-prepared GPG composite were characterized using scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FT-IR), thermogravity analysis, and surface charge analysis. The specific binding interactions between glutathione and GST gave GPG favorable adsorption selectivity towards GST, and other proteins did not affect GST adsorption. The adsorption behavior of GST on the GPG composite conformed to the Langmuir isotherm model, and the adsorption capacity of GST was high up to 364.94 mg g−1 under optimal conditions. The GPG-based solid-phase adsorption process was applied to the extraction of GST from a crude enzyme solution of pig liver, and high-purity GST was obtained via SDS-PAGE identification. [ABSTRACT FROM AUTHOR]

At present, China's academic circles have made some research results on the hidden dropout of junior middle school students, but they have not formed a relatively mature theory. Based on Durkheim's "social integration" theory, this paper studies hidden dropout from the perspective of class sociology and puts forward the influencing mechanism of "class integration" of junior middle school students' hidden dropout behavior. By class observation, this paper obtains the hidden dropout theoretical model of the interaction between individuals and class organization. [ABSTRACT FROM AUTHOR]

• A robustness index considering cascading failures caused by failed units is proposed. • Robustness improvement by structure adjustment is studied for fixed characteristics. • TS with directed and undirected edge swap operators is designed to solve the problem. • A case study of structure adjustment for improving robustness in the HST is performed. • Robustness of the optimized HST is greatly enhanced and hardly affected by failures. To enhance the ability of a high-speed train (HST) to provide services under various adverse conditions, this paper studies robustness improvement of the HST by adjusting its structure. We model the HST as an interdependent machine-electricity-communication network (IMECN) composed of a machine network (MN), an electricity network (EN) and a communication network (CN), and propose a robustness metric of the IMECN subject to node failures considering failure propagation. Then, a robustness optimization model is constructed for structure adjustment. A Tabu search algorithm with directed and undirected edge exchange operators is designed to solve this problem. A case study on a practical HST is used to verify the feasibility and effectiveness of the proposed method. The results show that robustness of the IMECN is significantly improved by structure adjustment. Furthermore, most nodes have little effect on robustness, and impact of failures on any node is minimized after optimization. In addition, in terms of topology, nodes with low and high degrees in the MN and CN reconnect with those with a similar degree, their clustering coefficients become larger, and closeness of all nodes in the subnetworks increases. Finally, adjusting the structures leads to a slight difference of loads in the EN and CN. [ABSTRACT FROM AUTHOR]

Reliability assessments of mechatronic systems, considering covariates, are becoming more complex not just as a result of the integration of more diverse technologies into such systems but also because of increasing complexities in system topology; but traditional reliability assessment models with covariates tend to ignore the influence of system topology. This paper addresses such an exclusion and proposes a novel methodology dedicated to the analysis and quantification of system reliability using system topology and multiple covariates. There are essentially two new aspects contributing to the overall methodology. Firstly, using network theory, the system topology is abstracted as a network; in which network nodes represent a mechatronic system's minimum maintenance units, and the connections between them are regarded as edges. Secondly, the resultant topological network is combined with the inherent properties of the minimum maintenance units to construct the system baseline hazard function and considering the associated multi covariates from the perspective of failure propagation to provide a foundation for assessing system reliability. To validate the proposed methodology, by way of a case study, it was applied to the reliability assessment of a traction power supply system for a high‐speed train. The results, compared with three other assessment approaches, suggest that the proposed methodology provides for significantly more accurate assessments while requiring less computational resources. Furthermore, it can be flexibly extended to many other mechatronic systems. [ABSTRACT FROM AUTHOR]

The interdependent network is particularly vulnerable to attacks on high degree nodes; therefore, the improvement of its robustness under intentional attacks has become an important topic. In this paper, we put forward a new metric to quantify the robustness of interdependent networks against intentional attacks and develop an improved simulated annealing algorithm (ISAA) to maximize this metric by optimizing the allocation of intra-links in subnetworks. Based on the comparison between the ISAA and existing algorithms, it is found that the algorithm presented in this paper is more effective to enhance the robustness of an interdependent scale-free network (ISFN). By applying the ISAA to ISFNs with different coupling preferences, there is a key finding that the robustness of the optimized ISFN is significantly stronger than that of the original ISFN. In particular, for cases of disassortative and random couplings, no sudden collapse occurs in optimized ISFNs. According to the analysis of the degree and the clustering coefficient, we find that the subnetwork of the optimized ISFN exhibits an onion-like structure. In addition, the ISFN whose robustness is enhanced to resist the attacks on high degree nodes is still robust to the intentional attacks concerning the betweenness and PageRank. [ABSTRACT FROM AUTHOR]

This paper analyzes the relation of arrival-departure tracks and the platforms of various types of stations, and the minimum dwelling time and adjacent train arrival interval to avoid contact of the boarding and alighting passengers. It constructs an integrated model of high-speed train rescheduling and the arrival-departure tracks utilization planning, taking the minimum dwelling time at stations, train tracking interval, minimum train running time in sections, and the arrival-departure tracks occupation as the constraints. The genetic algorithm based on the tabu search strategy is utilized to address the problem. A comparison is conducted between the computational results based on the classical genetic algorithm and the designed algorithm, revealing a 18.92% reduction in total calculation time consumption and a 1.11% improvement in accuracy. The proposed method can provide decision support for train dispatching work in epidemic situations. [ABSTRACT FROM AUTHOR]

Wheelset bearing fault diagnosis is essential to guarantee safe rail system operation. However, real-time monitoring signals of high-speed trains are nonstationary under variable conditions. Additionally, wheelset bearings operate in a normal state most of the time, and therefore, only normal data are available for training in practice. Under such a scenario of variable operating conditions and lacking labelled data, it is still necessary to timely detect the possible abnormal states of wheelset bearings. Currently, one-class classification is a suitable approach for real-time anomaly detection, but its accuracy is affected by the linear relationship of network nodes. Concerning this issue, this paper presents a novel method named scale-independent shrinkage broad learning to detect the abnormal states of wheelset bearings in real time. First, scaled rotation regularization is presented to convert the output constraint into the node distance constraint. Then, the variance-guided mapping mechanism is constructed to solve the linear relationship between nodes. Meanwhile, the optimal network mapping parameters are generated iteratively according to a so-called high-polymerization strategy, with which new output weights are formed after the feedback calculation. This method eliminates the linear correlation of node features during the iteration and realizes one-class classification detection of abnormal states. Finally, wheelset bearing data collected from a test rig of a Chinese rolling stock company are utilized to demonstrate the feasibility and effectiveness of the proposed approach in variable conditions. [ABSTRACT FROM AUTHOR]

• A high-speed train is modeled as an interdependent network. • A robustness metric is proposed based on network theory and practical factors. • Assessment and optimization models of resilience are constructed. • The tabu search algorithm is developed to solve the optimization problem. • The optimal repair strategy of failed units in the high-speed train is analyzed. High-speed trains (HSTs) are used to transport passengers to destinations efficiently and safely. However, when HST units fail, strategies for repairing them are not available. Hence, to optimize repair strategies, an interdependent network is used to model an HST, and a metric of resilience based on network theory is introduced. Based on practical factors, an interdependent machine–electricity–communication network (IMECN) and related cascading failure models are developed. Comprehensive robustness metrics for the IMECN and nodes are proposed considering the topology of networks and functional features of nodes. Accordingly, a resilience optimization model of the IMECN subject to disturbances is formulated and solved using a tabu search (TS) algorithm. Finally, a real-world HST is considered to analyze the optimal repair strategy for different numbers of failed nodes. Analysis results show that the recovery process under the optimal repair strategy has at most three stages. When a few nodes and less than half of the nodes fail, the highest and lowest resilience levels of the IMECN are achieved, respectively. Moreover, the characteristics of the preferentially repaired node in terms of importance, vulnerability, network type, and interdependency are analyzed. Results indicate that the optimal repair strategy is not necessarily determined by topological metrics. [ABSTRACT FROM AUTHOR]

• A high-speed train is modeled based on network theory. • A multi-objective optimization model for identifying critical elements is proposed. • A novel importance metric of critical elements is designed. • The proposed model is verified by a practical high-speed train. • Critical nodes, intra-links and inter-links for a high-speed train are identified. This paper proposes a multi-objective optimization-based approach to identify critical elements, including units and interactions within and between systems, in a high-speed train (HST). In the framework, network theory is used to model the HST as an interdependent machine-electricity-communication network (IMECN) composed of a machine network (MN), an electricity network (EN) and a communication network (CN). Cascading failure models for the subnetworks and IMECN, and topological and functional metrics for robustness are developed. We then formulate a multi-objective optimization model for maximizing the impact of the failure of critical elements on the topological and functional robustness of the IMECN and minimizing their number. We use NSGA-II to solve the optimization problem. Considering a practical HST as a case study, we apply the multi-objective optimization framework to search the groups of critical nodes, intra-links and inter-links. The results show that critical nodes, intra-links and inter-links of the IMECN are within the MN and CN. In particular, end nodes of the critical intra-links and inter-links may also be critical, and the critical elements of subnetworks tend to also be critical for the IMECN. In addition, we find that the critical nodes, intra-links and inter-links are not related to their topological importance. [ABSTRACT FROM AUTHOR]

[Display omitted] • A multi-objective model is proposed to design guidance information system. • The model is designer-friendly due to simultaneous optimization of signage location and information allocation plans. • The model produces cost-effective GIS plans for underground spaces. • The model improves wayfinding efficiency by satisfying potential information demand in underground spaces. Guidance information systems (GISs) are widely used for pedestrian navigation in underground spaces. We investigate GIS design methods in this paper. First, the information demand and potential information locations are abstracted based on the network discretization of underground spaces. Second, a multiobjective GIS design (MOGISD) model that focuses on economic costs and wayfinding is developed, and a dynamic solution evaluation-based heuristic algorithm is proposed to determine the optimal GIS design plan. To obtain a GIS plan that can achieve a perfect match between demand and information, a three-dimensional microscopic pedestrian-information interaction model that considers both human and information factors is formulated. Finally, to evaluate the effectiveness of the MOGISD model, we use the model to design a GIS plan for the underground floor of a multimodal transportation hub. The results show that the proposed method produces cost-effective GIS design plans contributing to high-efficiency wayfinding. The MOGISD model is designer-friendly due to the simultaneous optimization of signage location and information allocation plans. [ABSTRACT FROM AUTHOR]

• The M-LSCSFN for an HSEMU system describes system structure and functions. • The layer reliability is calculated based on MPs using specific operators. • The M-LSCSFN reliability is estimated with the layer reliability. • The HSEMU system reliability is evaluated in terms of the M-LSCSFN reliability. • A practical case is shown to demonstrate the proposed method. This paper proposes a new reliability assessment method for a high-speed electric multiple unit (HSEMU) system based on the expanded multi-state flow network. An HSEMU system is abstracted as a multi-layer multi-source multi-commodity multi-state flow network (M-LSCSFN), where minimum maintenance units (MMUs) and three types of connections form nodes and edges in different layers, and functional characteristics are regarded as network parameters. In the M-LSCSFN, multi layers describe different types of connections and their relationships; multi-source and multi-commodity reflect system features; whereas multi-state flow indicates the dynamic realization of system functions. Considering that an HSEMU system can be divided into multiple independent holistic functions, each holistic function has a corresponding sub-M-LSCSFN, and each layer of this sub-M-LSCSFN is a multi-source multi-commodity multi-state flow network (M-SCSFN). In order to assess system reliability, layer reliability (i.e. , the M-SCSFN reliability) is first defined as the probability that the amounts of each commodity transmitted successfully from source nodes to sink nodes will not be less than the required demands. A corresponding algorithm is proposed to calculate layer reliability in terms of minimal paths (MPs) using the quick inclusion-exclusion technique (QIE). The sub-M-LSCSFN reliability is subsequently calculated based on the layer reliability and the conditional relationships among different layers. Based on these, the HSEMU system reliability is defined as the ability of a system to complete specified multiple functions under stated conditions for a specified period of time, and can be evaluated using the reliability of sub-M-LSCSFNs via the proposed operator. Finally, a case study of the "Fuxing" HSEMU system is analyzed to demonstrate the applicability of the proposed method and algorithm the effectiveness of the proposed method is demonstrated in an HSEMU system reliability assessment case study. [ABSTRACT FROM AUTHOR]

• The high-speed railway network is modeled as a three-layer network. • Network-specific characteristics are considered in performance evaluation instead of pure complex network analysis. • Railway stations are prioritized and compared within different layers of the network. • The current physical rail network in China is generally sufficient to satisfy the requirements of its transportation accessibility. • Management implications are provided to facilitate the rail network planning, transportation organization and operations. High-speed railways, as dominant transportation patterns, constitute a large-scale complex network. Network performance is critical for high-level transportation services in transportation management. However, existing studies generally adopt pure topological indicators to evaluate performance in a single network and without considering the specific characteristics of rail transportation. This paper modeled the high-speed railway as a three-layer network including topological, functional, and service layers and assessed the integrated network performance from the view of transportation accessibility. In addition, the rail stations were prioritized and their performances in different layers were compared to analyze whether the total integrated performance was restricted by its connection abilities, functional capacities, and transportation service level. Finally, a case study of the high-speed rail network in China and comparisons with other traditional evaluation methods were conducted to verify the feasibility and superiority of the model. The findings of this study enable to provide management implications for rail transportation planning, organization, and operations. [ABSTRACT FROM AUTHOR]

With excessive passenger demand and uneven distribution of passenger flow, long-distance subway lines face oversaturated conditions during peak hours, leading to potential safety problems for subway systems. To improve travel efficiency and reduce safety problems, this study proposes a method of constructing a passenger flow control jointly optimized train timetable for an oversaturated subway line under a short-turning operation pattern. Considering the time-dependent and dynamic characteristics of passenger demand, an integer nonlinear programming model is formulated to minimize the total passenger waiting time. To solve the problem, the tabu search algorithm and the IBM ILOG CPLEX solver are combined to seek the approximate optimal solution. Finally, a series of numerical experiments are conducted on the Beijing Fangshan line to demonstrate the effectiveness of the proposed model and approach, which shows that the method of jointly optimizing the train timetable and passenger flow control can drastically decrease the total passenger waiting time and reduce congestion. • A congested subway line under a short-turning operation pattern is considered. • Two types of passenger flow control and boarding strategies are investigated. • Passenger flow control jointly optimized train timetable model is formulated. • Tabu search algorithm with CPLEX solver is designed to search the solutions. • Real-world case study to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Illegal transshipment of maritime ships is usually closely related to illegal activities such as smuggling, human trafficking, piracy plunder, and illegal fishing. Intelligent identification of illegal transshipment has become an important technical means to ensure the safety of maritime transport. However, due to different geographical environments, legal policies and regulatory requirements in each sea area, there are differences in the movement characteristics and geographical distribution of illegal transshipment behavior in different time and space. Moreover, in areas with dense traffic flow, normal navigation behavior can easily be identified as illegal transshipment, resulting in a high rate of misidentification. This paper proposes a hybrid rule-based and data-driven approach to solve the problem of missing identification in fixed threshold methods and introduces a traffic density feature to reduce the misidentification rate in dense traffic areas. The method is both interpretable and adaptable through unsupervised clustering to get suitable threshold distribution combination for regulatory sea areas. The evaluation results in two different sea areas show that the proposed method is applicable. Compared with other widely used identification methods, this method identifies more illegal transshipment events, which are highly suspicious, and gives warning much earlier. The proposed method can even filter out misidentification events from compared methods' results, which account for more than half of the total number. [ABSTRACT FROM AUTHOR]

The state monitoring of the railway track line is one of the important tasks to ensure the safety of the railway transportation system. While the defect recognition result, that is, the inspection report, is the main basis for the maintenance decision. Most previous attempts have proposed intelligent detection methods to achieve rapid and accurate inspection of the safety state of the railway track line. However, there are few investigations on the automatic generation of inspection reports. Fortunately, inspired by the recent advances and successes in dense captioning, such technologies can be investigated and used to generate textual information on the type, position, status, and interrelationship of the key components from the field images. To this end, based on the work of DenseCap, a railway track line image captioning model (RTLCap for short) is proposed, which replaces VGG16 with ResNet-50-FPN as the backbone of the model to extract more powerful image features. In addition, towards the problems of object occlusion and category imbalance in the field images, Soft-NMS and Focal Loss are applied in RTLCap to promote defect description performance. After that, to improve the image processing speed of RTLCap and reduce the complexity of the model, a reconstructed RTLCap model named Faster RTLCap is presented with the help of YOLOv3. In the encoder part, a multi-level regional feature localization, mapping, and fusion module (MFLMF) are proposed to extract regional features, and an SPP (Spatial Pyramid Pooling) layer is employed after MFLMF to reduce model parameters. As for the decoder part, a stacked LSTM is adopted as the language model for better language representation learning. Both quantitative and qualitative experimental results demonstrate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Accurately diagnosing the faults of wheelset bearings in high-speed trains is critical for ensuring the safety of train operation. In recent years, deep learning methods have made significant progress in this area. However, collecting enough labeled data in high-speed operation would be highly impracticable. In addition, the harsh operating environment of wheelset bearings, coupled with fluctuations in loads due to passenger flow, weather conditions, and other factors, makes it challenging to identify the fault signatures submerged in background noise. To address these issues, this paper proposes a semi-supervised fault diagnosis method based on autocorrelation and an improved flow Gaussian mixture model. First, the autocorrelations of raw bearing vibration signals are calculated to reduce the impact of noise while highlighting the discriminative fault signatures. Second, an improved flow Gaussian mixture model is established, preserving its simplicity and interpretability, to handle the constraints of bearing fault diagnosis with limited labeled samples under variable loads. Finally, the proposed method is tested by using a bearing dataset collected from an industrial railway wheelset bearing test rig. The results demonstrate that the proposed method outperforms the five state-of-the-art methods in terms of diagnostic accuracy and robustness. • A semi-supervised method is proposed for high-speed train wheelset bearing fault diagnosis with limited labeled samples under variable loads. • Autocorrelation is used to pre-process the raw vibration signals while providing an input to the model. • An improved flow Gaussian mixture model with a simple structure and interpretability is used to diagnose the bearing faults under variable loads. • The effectiveness of the method is verified on a railway wheelset bearing dataset. [ABSTRACT FROM AUTHOR]

Spatiotemporal information on individual trajectories in urban rail transit is important for operational strategy adjustment, personalized recommendation, and emergency command decision-making. However, due to the lack of journey observations, it is difficult to accurately infer unknown information from trajectories based only on AFC and AVL data. To address the problem, this paper proposes a spatiotemporal probabilistic graphical model based on adaptive expectation maximization attention (STPGM-AEMA) to achieve the reconstruction of individual trajectories. The approach consists of three steps: first, the potential train alternative set and the egress time alternative set of individuals are obtained through data mining and combinatorial enumeration. Then, global and local potential variables are introduced to construct a spatiotemporal probabilistic graphical model, provide the inference process for unknown events, and state information about individual trajectories. Further, considering the effect of missing data, an attention mechanism-enhanced expectation-maximization algorithm is proposed to achieve maximum likelihood estimation of individual trajectories. Finally, typical datasets of origin-destination pairs and actual individual trajectory tracking data are used to validate the effectiveness of the proposed method. The results show that the STPGM-AEMA method is more than 95% accurate in recovering missing information in the observed data, which is at least 15% more accurate than the traditional methods (i.e., PTAM-MLE and MPTAM-EM). [ABSTRACT FROM AUTHOR]

Hydrogen has been advocated as a promising energy carrier for railway systems, but its limited energy density may introduce mileage anxiety into the transportation system. Motivated by nonstop power exchange design, this article proposes a novel facility planning model under energy transfer conditions and natural endowments, such as photovoltaic resources in geographical locations, to optimize the overall system benefit. The supply, consumption, and replenishment mechanisms of multienergy forms (hydrogen energy, photovoltaic, electric energy) are designed on both vehicle and ground sides of the power exchange system. The optimal facility location and allocation of photovoltaic hydrogen plants, movable tank shifting devices, and train cars are collaboratively decided. A Lhasa–Xining railway case study is applied by conducting sensitivity analyses on significant parameters. Various insights hold the promise to promote policies and strategies for integrating transportation and power systems in a real-world application. It is demonstrated that energy cost reduction, solar power generation improvement, and energy-carrier capacity expansion help solve the mileage anxiety problem in nonstop power exchange systems. [ABSTRACT FROM AUTHOR]

• The main accident causes at the macro level are not applicable to specific scenes. • The distribution of accident causes concentrates with the refinement of the scene. • A data-driven Bayesian network construction approach is proposed. • The significant causes in various specific scenes can be accurately identified. As the freight railway system is a typical complex system, freight railway accidents have various and complex accident scenes. A Data-Driven Bayesian Network (DDBN) with random variables representing scene elements, accident causes, and accident consequences as nodes, and conditional dependencies between nodes as edges is proposed to identify the most significant accident causes in various and complex specific accident scenes. First, an unsupervised-supervised method is designed to define the states of nodes in the DDBN, considering the characteristics of the data involving both continuous and discrete states. Second, a greedy algorithm is proposed to mine the causal sequence between nodes, and the direction of edges in DDBN is established accordingly. Then, an NB-K2-MLE approach is proposed to generate the structure and parameters of the DDBN from data. Finally, a risk calculation function based on DDBN is proposed to calculate the risk of various accident causes in specific scenes. In empirical analysis based on real accident data, the inference accuracy of DDBN reached 87.92 %, with precision and recall exceeding 70 %. More importantly, the research results indicate that the distribution of accident causes will concentrate with the refinement and specific of the scene, and the main accident causes at the macro level cannot be fully applicable to accident prevention in specific scenes. The DDBN constructed in this study can provide data support for the determination of the significant accident causes and the development of targeted accident prevention strategies in various and complex specific scenes. [ABSTRACT FROM AUTHOR]

Remaining useful life prediction (RUL) is a critical procedure in the application of prognostics and health management for devices or systems. It is difficult to predict the RUL in a time‐varying external environment. Specifically, many mechanical systems typically experience various operating conditions, which have impacts on the degradation process and degradation rate. In particular, the linear degradation modeling of the Wiener process‐based RUL prediction method has attracted considerable attention recently. However, the dependency of degradation rate and operating conditions is generally ignored in the current degradation modeling, which leads to inaccurate issues in the RUL prediction. Therefore, to solve the above issues, a novel RUL prediction method based on the Wiener process considering parameter dependence is proposed in this paper. At first, a linear Wiener process degradation model considering parameter dependence is constructed to describe the dependency of the drift coefficient and operating conditions. Secondly, the probability density function of RUL is derived under the concept of first hit time. After that, the collaboration between the Bayesian update and expectation maximization algorithm is introduced to update and estimate the model parameters. Finally, the validity and applicability of the proposed method are verified by a numerical simulation and three case studies of bearings. [ABSTRACT FROM AUTHOR]

The normal operation of a integrated hub station is of great significance for the safe operation of the entire city's transportation network. Accurately monitoring the passenger flow operation status of the station is the fundamental basis for achieving scientific management and control of passenger flow. In response to the urgent need for accurate and real-time detection of passenger flow in station passageways, a Yolov7-based improved Deep-Sort algorithm is proposed to detect and track bi-directional passenger flow in the passageways of integrated hub stations. Based on the Yolov7 detection algorithm, the SimAM attention mechanism was introduced to improve the accuracy of detecting passenger flow in the passageways. On the basis of the Deep-Sort tracking algorithm, the Kalman Filter (KF) method was optimized to make the tracking box of the target more accurate. Meanwhile, the Fast-ReID method was used to improve the long-term tracking of targets, thereby improving the value of IDF1. This algorithm can help to achieve real-time and accurate detection and tracking of bi-directional passenger flow in station passageways. In the event of an abnormal situation, the station staff can react rapidly to improve the station's operational safety. [ABSTRACT FROM AUTHOR]

• A semi-automatic model is developed for hazard and accident cause identification. • We explore and analyze the semantic relationship between the hazards of marine accidents. • The importance of both hazards and accident causes is calculated and ranked. • We gain accident causes distribution in 40 different accident scenarios by using topic model. In the past decades, marine accidents brought the serious loss of life and property and environmental contamination. With the accumulation of marine accident data, especially accident investigation reports, compared with subjective reasoning based on expert experience, data-driven methods for analysis and accident prevention are more comprehensive and objective. This paper aims to develop a content-aware corpus-based model for the analysis of marine accidents to mine the accident semantic features. The general research framework is established to combine accident data, expert prior knowledge, and semi-automated natural language processing (NLP) technology. The NLP models are optimized, fused, and applied to the case study of ship collision accidents. The results show that the proposed model can accurately and quickly extract hazards, accident causes, and scenarios from the accident reports, and perform semantic analysis for the latent relationships between them to extend the accident causation theory. This study can provide a powerful and innovative analysis tool for marine accidents for maritime traffic safety management departments and relevant research institutions. [ABSTRACT FROM AUTHOR]

Boron (B) deficiency is detrimental to Glycine max (L.) Merr., which is one of the leading oil crops. In this study, physiological analysis of soybean seedlings under B deficiency and control after 12 h, 24 h, 72 h and 8 days was carried out, and the roots were subjected to transcriptome sequencing analysis. The results showed that under B deficiency, the plant height, SPAD and chlorophyll fluorescence value of soybean seedlings decreased significantly, indicating that B stress significantly inhibited plant growth and photosynthesis. RNA-seq revealed a total of 5126 DEGs (Differentially Expressed Genes), and nine DEGs co-existed at the four-time points, among which GLYMA_03G130600 regulates transcription factor ORG3, which is related to plant growth. GO analysis revealed a total of annotated 4018 DEGs, among which the terms plasma membrane, extracellular, enzyme activity, ion transport metabolic process and oxidoreductase activity were significantly enriched at the four time points, which might hinder the growth of soybean and accelerate senescence. KEGG analysis showed that at level 1, the DEGs were mainly enriched in photosynthesis-related, phenylpropanoid biosynthesis, nitrogen metabolism and plant hormone signal transduction. At level 2 of secondary metabolism, the DEGs were mainly enriched in energy metabolism and amino acid metabolism pathways, which indicates that B stresses mainly affect photosynthesis, hormone regulation and amino acid metabolism of soybean, thus affecting plant growth. The above results give deeper insight into the soybean response to B deficiency and lay the foundation for further studies of the molecular mechanism of soybean response to boron deficiency. [ABSTRACT FROM AUTHOR]

Remaining useful life prediction (RUL) is a key component in the application of prognostics and health management associated with devices or systems. But such RUL predictions are cumbersome owing to complexities from external effects and internal degradation mechanisms within systems. Specifically, it is common for degradation processes to comprise distinct multiple stages rather than just one uniform stage in many mechanical systems. In particular, the two‐stage degradation modeling for RUL prediction based on the Wiener process with linear drift has received significant attention in recent years. However, negative effects of measurement errors and stochasticity of the degradation states are generally excluded from current degradation modeling, which causes inaccuracy problems that can impact system maintenance schedules and operational efficiency. Therefore, to solve such problems, measurement errors are considered in this paper and a two‐stage degradation model is proposed, in which an adaptive term is also characterized by the Wiener process. The transition probability density function (TPDF) of the degradation state at the two‐stage changing point is derived and an analytical solution for the RUL is obtained under the concept of the first hit time (FHT). A Kalman filter and smoothing algorithm are introduced to estimate variables, and the expectation maximization (EM) algorithm is applied to update and estimate model parameters. Finally, the effectiveness and applicability of the proposed model in RUL predictions are verified through numerical simulation and a case study of bearings. [ABSTRACT FROM AUTHOR]

More and more passengers prefer to travel by subway system, and congestion is inevitable in the routine operation of subway stations. To alleviate congestion, junctions with chamfer zone (JCZs) are built in subway stations. The main intention of this work is to investigate the improvement of walking efficiency by the chamfer zone. Firstly, the specific walking behaviors of pedestrians in JCZs are investigated, and the principle of detour behavior is proposed. Secondly, a walking model considering the detour behavior is developed for pedestrians traversing the JCZ, and model parameters are calibrated by the Response Surface Methodology (RSM). Then, the influences of chamfer geometry on walking speed, walking time and time headways are simulated and analyzed. Results indicate that the walking efficiency will be improved by about 7.1% when the chamfer length is 1 meter. The interference among pedestrians is lower, and most time headways fall within the range of 0.1 ∼ 0.3 s, which means pedestrians walk steadily in the JCZ. Finally, the walking parameters of pedestrians in JCZs and corners are compared in various scenarios, and the matching correlation between chamfer length and turning angle is obtained. [ABSTRACT FROM AUTHOR]

At present, the interest in non-Pd hydrogen permeation membranes mainly focuses on group 5 B metals (Nb, V, Ta) and their alloys. To solve the problem of easy oxidation and weak dissociation of hydrogen molecules, a "Pd catalytic layer" needs to be deposited on the membrane surface. Due to its limited stability towards sulfur, issues of irreversible poisoning by sulfur compounds must be addressed. To this end, Pd-, Pd 65 Ag 35 -, Pd 90 Cu 10 -, Pd 80 Au 20 -, and Pd 55 Ag 35 Au 10 -coated Nb 30 Hf 35 Co 35 membranes were firstly synthesised by magnetron sputtering, and their hydrogen permeation behaviour in pure H 2 and/or in different H 2 /H 2 S mixtures for up to 1000 ppm at 673 K were evaluated. At these conditions, the permeabilities of the Pd-coated membranes decrease rapidly with increasing the H 2 S concentration and cannot recover after removal of H 2 S from the feed mixtures. In comparison, the Pd–Ag-containing membrane greatly increases the pure H 2 permeability, whereas the membrane doped with Au can effectively improve the response to H 2 S. Specifically, the Pd 65 Ag 35 -coated membrane shows the highest pure H 2 permeability, but it loses maximum permeability value on exposure to H 2 /H 2 S feed mixtures. In contrast, Pd 80 Au 20 -containing membranes exhibit good tolerance of H 2 S poisoning and displayed a high fractional recovery (∼83%) of initial H 2 permeability. The degradation of permeability for Pd- or Pd 65 Ag 35 -coated membranes after the H 2 S exposure can be ascribed to the deterioration of the structure caused by the possible formation of bulk Pd 4 S, which has been corroborated with EDS analysis, XRD, and XPS after testing. Finally, to improve both permeability and chemical tolerance, a Pd 55 Ag 35 Au 10 -coated membrane was successfully fabricated, and it possesses excellent comprehensive performance with respect to the permeability and H 2 S response. At 120 ppm H 2 S in the feed, the H 2 flux equals ca. 43% of its original value at 673 K and can be stable for at least 166 h. Bulk sulfides did not form on the membrane surface after the testing. This paper not only developed a new type of group 5 B alloy membrane with improved resistance to corrosion by H 2 S, but also further confirmed the feasibility of improving H 2 S corrosion resistance by adjusting the catalytic layer type or composition of the outermost coating. Some novel Nb 30 Hf 35 Co 35 self-supported membranes were successfully developed by regulating the type or composition of the outermost catalytic film. Correspondingly, the compositional region suitable for hydrogen permeation with improved resistance to corrosion by H 2 S has been identified. Especially, Pd 55 Ag 35 Au 10 -coated membrane possesses excellent comprehensive performance with respect to the permeability and H 2 S response. At 120 ppm H 2 S in the feed, the H 2 flux equals ca. 43% of its original value at 673 K and can be stable for at least 166 h. Bulk sulfides did not form on the membrane surface after the testing. The first-principles calculations showed that doping alloying elements, especially gold, inhibit the formation of palladium sulphide (e.g., Pd 4 S), thus providing more activating active sites for hydrogen adsorption and dissociation. This could be the main reason for the improvement of hydrogen permeability of PdAuAg-coated composite membranes in an H 2 S atmosphere. [Display omitted] • A new way to design hydrogen permeable alloys with improved H 2 S corrosion resistance is proposed. • A novel Pd 55 Ag 35 Au 10 -coated Nb 30 Hf 35 Co 35 self-supported membrane were successfully developed. • The PdAgAu catalytic layer showed promising resistance to sulfur poisoning. • Adjusting the type or composition of the catalytic layer can alleviate H 2 S poisoning. [ABSTRACT FROM AUTHOR]

• The underground space is partitioned into cells with different size. • Guidance demand is treated as heterogeneous over the underground space. • An accurate interaction model for evacuees and signs is proposed. • A location set covering model for EGSS design is proposed. • We combine advantages of analytical and simulation methods to design EGSS. Emergency guidance signage systems (EGSSs) are widely used to guide crowd evacuation in underground spaces. However, the absence of signs often reduces the evacuation efficiency. Current methods for EGSS design suffer from challenges associated with complex evacuee-signage interactions, guidance demand determination and numerous potential sign locations. The present article investigates a discrete approach to EGSS design. To this end, a cell-based discretization method is proposed to abstract the guidance demand and potential sign locations. To design an EGSS that can efficiently convey guidance information to evacuees, an interaction model, which is determined by the cognitive capabilities of moving evacuees and the characteristics of signs, is proposed for analyzing the guidance relationship between evacuees and signs with different locations and orientations. An EGSS design model is formulated to recommend the optimal number, location, and installation orientation of signs, and a wayfinding simulation model is proposed to validate the obtained design plan. Finally, a real-world case study is used to demonstrate the effectiveness and advantages of the proposed methods. [ABSTRACT FROM AUTHOR]

Rail surface defects (RSDs) are a major problem that reduces operation safety. Unfortunately, the existing RSD detection systems have very limited accuracy. Current image processing methods are not tailored for the railway track and many fully convolutional networks (FCN)‐based methods suffer from the blurry rail edges (RE). This paper proposes a new rail boundary guidance network (RBGNet) for salient RS detection. First, a novel architecture is proposed to fully utilize the complementarity between the RS and the RE to accurately identify the RS with well‐defined boundaries. The newly developed RBGNet injects high‐level RS object information into shallow RS edge features by a progressive fused way for obtaining fine edge features. Then, the system integrates the refined edge features with RS features at different high‐level layers to predict the RS precisely. Second, an innovative hybrid loss consisting of binary cross entropy (BCE), structural similarity index measure (SSIM), and intersection‐over‐union (IoU) is proposed and equipped into the RBGNet to supervise the network and learn the transformation between the input and ground truth. The input and ground truth then further refine the RS location and edges. Conveniently, an image‐based model for RSD detection and quantification is also developed and integrated for an automatic inspection purpose. Finally, experiments conducted on the complex unmanned aerial vehicle (UAV) rail dataset indicate the system can achieve a high detection rate with good adaptation capability in complicated environments. [ABSTRACT FROM AUTHOR]

Split pins (SPs), as essential fasteners in the pantograph-catenary system, play a critical role in maintaining the structural stability of the catenary support device (CSD) in high-speed railroad. Unfortunately, impact and vibration generated by the interaction between catenary system and high-speed running vehicles will progressively damage SPs, including but not limited to the loose, breakage, and missing of SPs. Current image processing technologies have limited accuracy. Traditional convolutional neural network (CNN)-based systems that directly learn deep features are inefficient in detecting subtle defects (such as fractured and loose SPs). This study presents a novel SP inspection system based on an innovative destruction and reconstruction learning (DRL). In the DRL, a novel cross stage partial network (CSPNet)-based classifier is firstly developed to alleviate the impact of redundant semantic information and optimize gradient regression process. Then, "destruction" in the DRL stream means these partitioned sub-regions in an input image are shuffled by a region shuffling mechanism (RSM); this guides the classifier to pay more attention to the distinguishable regions in the destroyed and original images for a purpose of correct recognition. For "reconstruction", a newly developed position reconstruction network (PRN) is utilized to restore the original spatial distribution of the sub-regions by modeling the semantic correlation among the sub-regions. The proposed DRL can injects more discriminative details to the classifier by jointly training the classification network and PRN. Finally, comprehensive experiments are conducted on CSD datasets captured from real railroad lines, and the results demonstrate that the proposed approach outperforms existing state-of-the-art models yet keeps a reasonable inference speed. [ABSTRACT FROM AUTHOR]

• Accident semantic network framework and a conceptual model of accident risk control chain can provide great help for the study of accidents. • A method for acquiring and constructing key contents based on semantic analysis is elaborated. • A management matrix is established to serve safety decision. • It provides suggestions for the actual operation management of urban rail transit. Although the occurrence of urban rail transit operation accidents threatens the safety of people's lives and property, there is little research on how to systematically mine the knowledge behind accident data in China, and there is also lack of methods to support the safety management strategy of urban rail transit operation. To address these shortcomings, this study proposes a comprehensive analysis method that combines qualitative and quantitative analysis of urban rail operation accident factors and safety management strategies based on accident data, which can provide reference for systematic analysis of such accidents in the future and will help urban rail safety researchers and decision makers to take effective safety management measures. The new contributions of the method are as follows: (1) a semantic network framework for accidents and a conceptual model of accident risk control chain are proposed; (2) a method for acquiring and constructing key contents based on semantic analysis is elaborated, and indicators for evaluating the influence degree of key item and the influence possibility of entries are proposed; (3) a management matrix is established to serve safety decision making based on indicators for the degree of attention that key item of accidents should receive. In order to explain the application of the comprehensive analysis method, 910 urban rail transit operation safety accident cases are analyzed in detail, and suggestions for the actual operation management of urban rail transit are proposed in the light of the actual situation of urban rail transit operation in China. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis and continual learning techniques for train transmission systems are becoming more appealing to ensure the operation safety and reliability of trains. However, existing related methods have the following limitations. 1) They build separate fault diagnosis networks for each key component in train transmission systems, which not only brings burdensome work for training and managing diagnosis networks but also ignores the influence of fault propagation and interaction between adjacent components. 2) They rely on enough class-incremental samples for continual learning to obtain the growth diagnosis ability, but the accumulations of incremental fault samples are long-period processes, leading to belated network evolution and hysteretic performance enhancement. To overcome the above-mentioned limitations, an evolvable system-level fault diagnosis framework is proposed for train transmission systems. In the proposed framework, a novel graph neural network is first constructed based on component spatial relationships, which is able to effectively learn and capture the interaction between components and integrate fault diagnosis tasks into a unified framework. Then, an anhysteretic evolution learning mechanism is developed to avoid lengthy waiting for new fault sample accumulations, in which over-fitting due to insufficient incremental fault sample is addressed by employing prototype-based classifiers and diagnostic knowledge is transferred and captured by maintaining and generating prototypes. The effectiveness of the proposed diagnosis framework is verified by taking a case study of fault diagnosis for subway train transmission systems, and its superiority is demonstrated by comparison with some stage-of-the-art diagnosis methods. [ABSTRACT FROM AUTHOR]

This paper is devoted to applying fuzzy risk-ranking analysis for the railway train operational risk assessment. Specifically, a new risk-ranking approach of dynamic VlseKriterijuska Optimizacija I Komoromisno Resenje (VIKOR) combined with Type-2 intuitionistic fuzzy set (Type-2 IFS) theory is proposed under different stages, which can be better employed to rank the risk of system components considering the calculation uncertainty, expert preference, and information indeterminacy based on the hybrid index system of quantitative and qualitative information. A specific case is performed to validate the proposed approach. Based on the results, a comparative analysis between the proposed approach and the static risk assessment is presented, which shows the effectiveness and feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Greening of the railway energy supply chain is an irreversible trend, and photovoltaics (PVs) provide the most suitable type of renewable energy to integrate with railways. The integration of variable and uncertain PV power generation with the dynamic loads on a railway increases the flexibility needed to maintain load-generation balance. A new evolutionary model of a railway energy supply system (RESS) for railway PV integration systems (RPISs) is proposed by constructing a three-in-one "traction-storage-information integrated station" (TSIIS). A flexibility evaluation approach is proposed to estimate the system flexibility of both the individual TSIIS and the banded featured microgrid group through energy storage capacity configuration and dynamic scheduling via a multileader multifollower Stackelberg game. Finally, the Lanzhou-Xinjiang Railway is taken as an example to calculate the emission reduction and flexibility. The results show that through application of the storage configuration and scheduling strategy to the TSIIS network, the flexibility index of the Lanzhou-Xinjiang Railway increased by 8.40%, which promoted a corresponding decrease in carbon dioxide emissions and increase in PV permeability. In addition, with the gradual construction of PV and energy storage systems, an RPIS can basically achieve self-consistent energy utilization, offering environmental benefits and strong flexibility. [ABSTRACT FROM AUTHOR]

Corridor with corner may be the potential bottleneck in subway station, and walking behavior of passengers around corner is random. In this study, walking process of passenger around corner is divided into five phases according to field survey, i.e., pre-turning straight-going, ready-turning, turning, distance-adjusting and post-turning straight-going. An advanced social force model is proposed to model the turning behavior of passenger around corner, taking visual angle, walking preference and steering force into consideration. To improve walking efficiency, the influences of geometry of facility, walking preference of passengers and arrival rate of passenger flow are investigated. Results show when angle of corner is less than 120°, the walking speed slows down sharply and walking time extends. To improve the walking efficiency, passengers can be guided to walk in lines orderly. The maximum of throughput can be obtained with proper arrival rate. Once the volume of passengers exceeds the facility capacity, effects of "stop-and-go" and "faster is slower" will occur around corner. • Analyzing and demonstrating the walking process of passengers around corner. • Modeling movement of turning passengers with advanced social force model. • Verifying the proposed model with controlled experiments. • Quantifying arrival rate and corner angle influencing on walking efficiency. [ABSTRACT FROM AUTHOR]

To segment railway track regions in real-time for intrusion detection and improving security, this paper proposes an efficient railway track region segmentation network (ERTNet) based on the encoder–decoder architecture. Firstly, to ensure the lightweight of the encoder, depthwise convolution and the channel shuffle are utilized to construct sandglass-type feature extraction unit. Secondly, a feature-matching-based cross-fusion decoder is utilized to fuse deep and shallow feature maps. Thirdly, the knowledge distillation is employed with large-scale Deeplab v3+ as the teacher model to improve performance. Additionally, a loss function is proposed to penalize pixel points with large offsets. Finally, the ERTNet is validated on the self-built dataset, achieving an MIoU (Mean Intersection over Union) of 92.4% , which is 5.22% improvement over the benchmark model. ERTNet achieves a balance between segmentation accuracy and computational efficiency, requiring only 0.5 M parameters and 0.92 G FLOPs (Floating Point Operations). [Display omitted] • Visual perception is utilized to identify foreign object intrusion into railroad. • Deep learning based ERTNet model is proposed for track region pixel extraction. • ERTNet is built with lightweight neural network and cross-fusion decoder. • Optimizing training modes with knowledge distillation and new loss function. • ERTNet fits real-time needs and helps to improve the safety of rail construction. [ABSTRACT FROM AUTHOR]

• A new GDM method is developed based on incomplete PFPRs. • The sufficient conditions for the missing elements to be expressible are presented. • The missing elements in unrepresentable incomplete PFPRs are estimated. • The weights of decision-makers are determined based on the consensus degree. Completing the Pythagorean fuzzy preference relations (PFPRs) based on additive consistency may exceed the defined domain. Therefore, we develop a group decision-making (GDM) method with incomplete PFPRs. Firstly, sufficient conditions for the expressibility of estimated preference values in PFPRs based on additive consistency are presented. Next, the correction algorithm is developed to correct the inexpressible elements in incomplete PFPRs. Then, a GDM method based on incomplete PFPRs is proposed to determine the objective weights of decision-makers. Finally, an example of subway station safety management during COVID-19 is selected to illustrate the applicability of the developed GDM method. The results show that the developed GDM method effectively identifies the crucial risk factor in subway station safety management and has better performance in terms of computational time complexity than the multiplicative consistency method. [ABSTRACT FROM AUTHOR]

The condition monitoring of railway track line is one of the fundamental tasks to ensure the safety of the railway transportation system. Railway track line is mainly made up of tracks, fasteners, bolts, backing plates, and so on. Given the requirements for rapid and accurate inspection, an innovative and intelligent method for multi-component identification and common defect detection of railway track line is investigated based on instance segmentation. More specifically, a railway track line image (RTL-I) dataset is constructed and annotated manually in this paper. After that, based on the work of YOLACT and YOLACT++, combined with prior knowledge, a railway track line image segmentation model (RTLSeg for short) is proposed. Firstly, taking the characteristics of the objects in the RTL-I dataset, preset anchors are redesigned and a feature enhanced module is introduced in the prediction head to improve the detection and segmentation accuracy of the model. Secondly, to strengthen the internal information propagation within the model, PaFPN (path aggregation feature pyramid network) is applied instead of FPN in RTLSeg. Thirdly, with the help of CoordConv, Coord-Protonet is presented to add position awareness explicitly to the model for more robust and higher quality prototype masks. Finally, to further improve the model performance, the attention mechanism is explored and a novel spatial attention-guided bounding box branch is employed in the enhanced prediction head. Both quantitative and qualitative experimental results show that the proposed method is feasible in detecting and segmenting multi-component and common defects of railway track line, and outperforms the compared baseline models. In particular, RTLSeg is able to achieve 91.35 bbox mAP and 91.60 mask mAP with the customized dataset. Meanwhile, the average inference speed reaches 13.07 fps. The average detection accuracy and recall are 100% and 99.83%, respectively. Furthermore, the effectiveness of each optimized part of the proposed RTLSeg model is demonstrated by additional ablation study. • Pixel-level multi-component inspection of railway track line based on image instance segmentation is investigated for the first time. • Based on YOLACT and YOLACT++, a railway track line image segmentation model (RTLSeg for short) is proposed, which achieves better detection and segmentation performance than the compared baseline models, and is more suitable for the scenario of the railway track line. • The proposed RTLSeg model enables accurate and fast detection of railway track line components and common defects at the pixel level. [ABSTRACT FROM AUTHOR]

Considering the complexity of the urban rail transit system (URTS), it is necessary to systematically identify the critical factors and their relationships to avoid or prevent urban rail transit accidents. In response to the problems few previous studies have modeled networks for the whole system components of URTS and have focused too much on the identification of specific component states or behaviors without quantitative analysis of inter-component relationships. This paper proposed a risk network construction and analysis method based on complex network theory to identify the critical accident causative factors and their relationships of the URTS system. Firstly, the accident is defined as the combination of a sequence of risk incidents occurring in a certain order and their resulting consequences, and the definitions of risk point and risk incident were given. Secondly, a risk network construction and analysis method based on the combination of accident reports and complex network theory was proposed to obtain the critical factors and their relationships in the process of the accident. At last, this paper constructed the urban rail transit risk point set containing 39 risk points, built the risk network based on 201 accident reports of URTS in China and analyzed the critical risk points and risk relationships. The results show that this study can provide a new perspective for identifying the critical causative factors of URTS accidents and their relationships for practical application in risk analysis and accident prevention. • The new definitions of risk points and incidents are put forward. • A critical risk analysis framework are proposed by complex network theory. • Critical risk points and relationships are identified in the urban rail transit system by the risk network. [ABSTRACT FROM AUTHOR]

• The improved brute-force search transforms the energy-saving operation problem into optimal turning point solution. • Considering the speed limit, a more reasonable energy-saving turning point is obtained by adding a constant speed section. • The energy-saving effect of improved brute-force search is better than GA and PSO algorithms in Guangzhou Metro Line 7. Rail train operation energy consumption mainly focuses on train traction energy consumption. Reducing train traction energy consumption in rail transit operation is significant to developing a green and low-carbon economy and reducing operation costs. The rail train operation energy-saving optimization framework is developed considering the utilization of regenerative braking energy. Firstly, three objectives of punctual arrival, fixed-point parking and minimum energy consumption are provided by train operation strategy analysis. Secondly, the improved brute-force search is developed to solve train operation energy-saving multi-objective problems. The running time, speed, distance, power, and energy consumption of operation intervals are calculated. Finally, Guangzhou Metro Line 7 is taken as an example to verify the effectiveness of the developed optimization model. The results show that the improved brute-force search method effectively finds a more energy-saving turning point under constant interval operation time and has a better energy-saving effect than two other heuristic algorithms. [ABSTRACT FROM AUTHOR]

Potential safety hazards (PSHs) along the track needs to be inspected and evaluated regularly to ensure a safe environment for high-speed railroad operations. Other than track inspection, evaluating potential safety hazards in the nearby areas often requires inspectors to patrol along the track and visually identify potential threads to the train operation. The current visual inspection approach is very time-consuming and may raise safety concerns for the inspectors, especially in remote areas. Using the unmanned aerial vehicle (UAV) has great potential to complement the visual inspection by providing a better view from the top and ease the safety concerns in many cases. This study develops an automatic PSH detection framework named YOLARC (You Only Look at Railroad Coefficients) using UAV imagery for high-speed railroad monitoring. First, YOLARC is equipped with a new backbone having multiple available receptive fields to strengthen the multi-scale representation capability at a granular level and enrich the semantic information in the feature space. Then, the system integrates the abundant semantic features at different high-level layers by a light weighted feature pyramid network (FPN) with multi-scale pyramidal architecture and a Protonet with residual structure to precisely predict the track areas and PSHs. A hazard level evaluation (HLE) method, which calculates the distance between identified PSH and the track, is also developed and integrated for quantifying the hazard level. Experiments conducted on the UAV imagery of high-speed railroad dataset show the proposed system can quickly and effectively turn UAV images into useful information with a high detection rate and processing speed. [ABSTRACT FROM AUTHOR]

Turning junction of subway station is bottleneck being prone to congestion. Speeds of passengers fluctuate in these zones, which will diminish walking efficiency of the passengers and level of service (LOS) of facility. This paper explores the correlation between junction width and walking efficiency of passengers in subway station. Firstly, walking trajectories of passengers at junctions are abstracted from video footages with object detection and tracking algorithm. The parameters of walking behaviors of passengers in conditions with various junction widths are measured. With the calibrated turning social force model (TSFM), walking processes of passengers are simulated, and the optimal widths of junctions are estimated. Results show that the farther away from the inner turning boundary edge (TBE) is, the earlier the individual starts to turn. When junction width is more than 3 m, the walking efficiency will not be higher with junction widening during peak hours. The optimal width of junction is 5.41 m in the passenger-merging scenario with mean arrival rate of 1.67 ped ⋅ s−1. • Abstracting passengers' trajectories based on deep learning algorithm. • Turning trajectory is symmetrical to the turning center. • Exploring the correlation between junction width and walking efficiency. • Turning angular speed of passenger is calibrated to be 29.6 degree/s. • In merging flow scenario with 1.67 ped/s, the passage should be about 5.41 m wide. [ABSTRACT FROM AUTHOR]

• We provide a rail wheel tread defect detection framework based on improved YOLOv3 model to classify four tread defect types. • The improved YOLOv3 model transforms into the regression problem of the prediction frame and carries out multi-scale prediction for wheel tread defect detection. • Compared with the other detection methods, the improved YOLOv3 model maintains the detection speed, improves the detection accuracy and meets the real-time requirement. The rail wheel is the key device of the rail vehicle. When the vehicle running conditions worsen or emergency braking, the rail train will have severe sliding friction and collision on the track, resulting in scratches, peeling, and scratches on the wheel tread. The traditional wheel defect detection technology can not realize automatic classification and accurate defect positioning. Thus, an improved YOLOv3 framework for rail wheel surface defect detection is developed. The classification detection of four types of wheel tread defects is realized, and the average accuracy of mean average precision (mAP) is 0.92. Compared with the other detection methods, the experimental results show that the improved YOLOv3 model not only maintains the detection speed but also improves the detection accuracy and meets the real-time requirement. [ABSTRACT FROM AUTHOR]

Tramway has the advantages of reliable operation, energy-saving, and environmental protection, which is an important way to alleviate traffic pressure. Energy consumption optimization of tramway operation is significant in reducing the operation cost. Therefore, the energy consumption optimization model of tramway operation based on the improved PSO algorithm is developed. Firstly, the energy consumption model of the tramway is established based on the energy-saving operation strategy. Then, the competition mechanism-based particle swarm optimization (CM-PSO) algorithm is developed to improve energy-saving performance. Finally, the Guangzhou Haizhu tramway is taken as an example to illustrate the effectiveness of the developed method. The results show that the developed model effectively reduces the tramway operation energy consumption and performs better than the previous methods. • The energy-saving effect of the CM-PSO algorithm is better than other methods. • The operation strategy reduces energy consumption under operation time constraints. • The turning points between different work conditions are found. [ABSTRACT FROM AUTHOR]

Prediction of passenger flow distribution in urban rail transit stations can provide important data support for passenger flow organization and passenger travel guidance. However, complex station space structure and simulation-based passenger flow data bring challenges to accurate analysis and prediction of the passenger flow inside the station. This paper proposes a temporal graph attention convolutional neural network model (TGACN) to predict the passenger flow volume and density in key areas of the station. Firstly, considering the topological structure of key areas and the characteristics of passenger flow and flow trend in the station, a multi-graph generation method for continuous space in stations is designed, including geographic neighborhood graph and semantic neighborhood graph, to represent the static and dynamic correlation between nodes. Secondly, a new method of spatio-temporal feature fusion is proposed, which takes multi-graph as input to optimize the extraction and expression of spatial and temporal correlation. Finally, the TGACN is verified by passenger flow data set, which is constructed based on real-time video monitoring data of a transit station in Guangzhou. Experiments demonstrate that the TGACN can obtain the spatio-temporal correlation from passenger flow data, and the prediction results are better than the existing baseline models. • A prediction model for multipoint passenger flow in station is proposed. • Geographical graph is constructed to measure the spatial correlation between nodes. • Semantic graph is constructed to measure the correlation of passenger flow state. • Effective spatial information screening is realized by dimensionality reduction. [ABSTRACT FROM AUTHOR]

Long-term axle temperature prediction plays a significant role in train condition assessment and daily maintenance. However, most of methods make predictions for short-term conditions. In this paper, a method named GA-GRGAT is introduced that uses GAT and GAN to forecast the long-term axle temperature. In the proposed method, a GRGAT framework is used as a spatiotemporal fusion in temperature prediction. The GAN network with the GRGAT framework is used to construct a temporal conditional sequence after analyzing the periodic variation of the axle temperature, which can fuse the historical axle temperature information to improve the long-term prediction accuracy of the GA-GRGAT model. Our method in Python software and using the actual high-speed trains datasets in spring and summer. We using MAE, RMSE, MAPE, PCC to evaluate the accuracy of prediction. The accuracy of the GA-GRGAT is more than 90% on long-term predictions (1 day), and more than 80% on super long-term predictions (2 week). The GA-GRGAT method outperforms and is more accurate than the classical forecasting methods such as GRU, GOAMLP, DCNN, SVR and HA. In addition, the cost time of the proposed method is less than 5 min, which meets the requirements of high accuracy and long time. [ABSTRACT FROM AUTHOR]