Communication-based train control (CBTC) systems are automated train control systems using wireless communications. The normal operation of CBTC systems depends on a reliable data communication system. The existing CBTC data communication system are based on train-to-ground communication, which suffers from too many subsystem interfaces and makes ground equipment extremely complicated. In next generation CBTC systems, train-to-train communication is adopted with the advantages of higher efficiency and briefer system structure. Although train-to-train communication based CBTC systems has been implemented in urban rail systems. The data communication system reliability has not been studied before. In this paper, the next generation CBTC data communication system reliability is modeled with Deterministic and stochastic Petri nets (DSPNs). We design a next generation CBTC data communication system using LTE technologies, and set up laboratory test environment to test system performance. The performance data is converted as DSPN model parameters to evaluate system reliability. With the tested system performance measures, we evaluate the reliability of data communication scenarios, which includes the reconnection and handoff scenarios. Extensive simulation results are then given to illustrate the system reliability, which considers both the train to train communication link and train to ground communication link.

Rail transit is developing towards intelligence which takes lots of computation resource to perform deep learning tasks. Among these tasks, object detection is the most widely used, like track obstacle detection, catenary wear, and defect detection and looseness detection of train wheel bolts. But the limited computation capability of the train onboard equipment prevents running deep and complex detection networks. The limited computation capability of the train onboard equipment prevents conducting complex deep learning tasks. Cloud computing is widely utilized to make up for the insufficient onboard computation capability. However, the traditional cloud computing architecture will bring in uncertain heavy traffic load and cause high transmission delay, which makes it fail to complete real‐time computing intensive tasks. As an extension of cloud computing, edge computing (EC) can reduce the pressure of cloud nodes by offloading workloads to edge nodes. In this paper, we propose an edge computing‐based method. The onboard equipment on a fast‐moving train is responsible for acquiring real‐time images and completing a small part of the inference task. Edge computing is used to help execute the object detection algorithm on the trackside and carry most of the computing power. YOLOv3 is selected as the object detection model, since it can balance between the real‐time and accurate performance on object detection compared with two‐stage models. To save onboard equipment computation resources and realize the edge‐train cooperative interface, we propose a model segmentation method based on the existing YOLOv3 model. We implement the cooperative inference scheme in real experiments and find that the proposed EC‐based object detection method can accomplish real‐time object detection tasks with little onboard computation resources.

With the wide application of data-driven intelligence technology, the management efficiency and quality of urban rail transit improve considerably. However, due to data privacy and security protection, a large amount of data is still scattered among operators or rail transit departments in the form of data islands. The data barriers between urban rail departments severely hinder the intelligent development of urban rail transit systems. In this study, we design a distributed data-sharing system based on blockchain for urban rail transit system. Data production node in urban rail department, such as servers in data centers, wayside equipment, and onboard equipment, can share their data in a distributed way. Blockchain provides audit and check functions to guarantee data-sharing security. We explore the data-sharing incentive mechanism which has an impact on sharing willingness of data production nodes. To maximize the individual utility of nodes, we formulate an evolutionary game model for data nodes with bounded rationality to adapt their sharing strategies. The uniqueness and stability of the equilibrium of the game are also analyzed theoretically. Extensive experiments are conducted and illustrated that data production nodes can share their data efficiently and safely in our proposed data-sharing system. Our proposed evolutionary game model can determine the most effective data-sharing incentive mechanism.

Train-to-wayside (T2W) and train-to-train (T2T) communication modes may coexist in future train-centric communication-based train control (CBTC) systems. The feasibility of T2T communication in urban rail transit is analyzed first. Referring to the device-to-device (D2D) communication scenario in the general cellular network, this paper establishes a radio resource optimization model for the coexistence of train-to-train communication and train-to-wayside communication. With the aim of more efficient scheduling of radio time-frequency resources in the dedicated frequency band, we propose a Stackelberg game-based radio resource management algorithm based on the consideration of different service priorities of trains. The analysis and simulation results show that the proposed algorithm can effectively guarantee the performance of the system and improve the reliability of the CBTC system.

The safe operation of rail transit systems relies heavily on the efficient and reliable maintenance of their equipment, as any malfunction or abnormal operation may pose serious risks to transportation safety. Traditional manual inspection methods are often characterized by high costs, low efficiency, and susceptibility to human error. To address these limitations, this paper presents a rail transit equipment inspection system based on Edge Intelligence (EI) and 5G technology. The proposed system adopts a cloud–edge–end collaborative architecture that integrates Computer Vision (CV) techniques to automate inspection tasks; specifically, a fine-tuned YOLOv8 model is employed for object detection of personnel and equipment, while a ResNet-18 network is utilized for equipment status classification. By implementing an ETSI MEC-compliant framework on edge servers (NVIDIA Jetson AGX Orin), the system enhances data processing efficiency and network performance, while further strengthening security through the use of a 5G private network that isolates critical infrastructure data from the public internet, and improving robustness via distributed edge nodes that eliminate single points of failure. The proposed solution has been deployed and evaluated in real-world scenarios on Beijing Metro Line 6. Experimental results demonstrate that the YOLOv8 model achieves a mean Average Precision (mAP@0.5) of 92.7% ± 0.4% for equipment detection, and the ResNet-18 classifier attains 95.8% ± 0.3% accuracy in distinguishing normal and abnormal statuses. Compared with a cloud-centric architecture, the EI-based system reduces the average end-to-end latency for anomaly detection tasks by 45% (28.5 ms vs. 52.1 ms) and significantly lowers daily bandwidth consumption by approximately 98.1% (from 40.0 GB to 0.76 GB) through an event-triggered evidence upload strategy involving images and short video clips, highlighting its superior real-time performance, security, robustness, and bandwidth efficiency.