Deep Hybrid Learning Based Fault Diagnosis for Data Communication Systems in Communication-Based Train Control Systems

Communication-based train control (CBTC) systems are automated train control systems based on continuous and bidirectional train-ground communications. CBTC is the direction of future train control systems. Complex channel condition and frequent handoff can severely affect urban rail CBTC train-ground communication performance, and consequently affect CBTC operation efficiency. Current research regarding CBTC does not consider the impact of train-ground communications on train control performance. This paper studies the joint optimization of communication and control in CBTC systems. With the objective to minimize the optimal operation profile tracking error and energy consumption, linear quadratic cost is defined as the control performance measure. In order to ensure train operation safety, the optimization model puts constraints on train control actions related to safety. Moreover, based on the stochastic channel characteristics and the real-time train position information, handoff decision and train control policy are jointly optimized using deep reinforcement learning. Extensive simulation results based on real-field channel measurements illustrate that the proposed optimization method can significantly improve the train control performance in CBTC systems, and CBTC systems need to sacrifice part of performance to ensure system safety.

Leaky waveguide has been adopted in communication based train control (CBTC) systems, as it can significantly enhance railway network efficiency, safety and capacity. Since CBTC systems have high requirements for the train ground communications, modeling the leaky waveguide channels is very important to design the wireless networks and evaluate the performance of CBTC systems. In the letter, we develop a finite-state Markov channel (FSMC) model for leaky waveguide channels in CBTC systems based on real field channel measurements obtained from a business operating subway line. The proposed FSMC channel model takes train locations into account to have a more accurate channel model. The overall leaky waveguide is divided into intervals, and an FSMC model is applied in each interval. The accuracy of the proposed FSMC model is illustrated by the simulation results generated from the model and the real field measurement results.

To meet the growing railway-transportation demand, researchers have designed a new train control system, communication-based train control (CBTC) system, to maximize the ability of train lines by reducing the headway of each train. However, wireless communications expose the CBTC system to new security threats. Due to the cyber-physical nature of the CBTC system, a jamming attack can damage the physical part of the train system by disrupting the communications. To address this issue, this chapter develops a secure framework to mitigate the impact of the jamming attack based on a security criterion. At the cyber layer, we apply a multi-channel model to enhance the reliability of the communications and develop a zero-sum stochastic game to capture the interactions between the transmitter and jammer. We present analytical results and use dynamic programming to find the equilibrium of the stochastic game. We investigate a special case study to obtain insight results, showing a strong inter-dependency between the physical and cyber layers. Finally, the experimental results are provided to evaluate the performance of the proposed secure mechanism.

Although there has been substantial research in system analytics for risk assessment in traditional methods, little work has been done for safety risk prediction in communication-based train control (CBTC) system, especially intelligently predicting risk caused by the uncertainty in the system operation. Risk prediction and assessment of hazards in train control systems are vital for the safety and efficiency of urban rail transit. In this paper, we propose an intelligent hazard-risk prediction model based on a deep recurrent neural network for a new communication-mode CBTC system. First, a train-to-train communication-based train control (T2T-CBTC) system is proposed to improve the drawback of CBTC in information-exchanging mode. Then we design a risk prediction feature selection and generation method and estimate a critical function feature in the T2T-CBTC system by statistical model checking. Finally, we construct our intelligent hazard-risk prediction model based on a deep recurrent neural network using a long-short-term memory (LSTM) network. The model had excellent risk prediction classification results and performance in our experiment, even for unbalanced data set. This model consistently outperforms the deep belief network trained in Accuracy, Precision, Recall and F1-score for the hazard-risk prediction problem. Specifically, the mean accuracy is 97.2% and mean F1-score is 93.9% in overall performance of model. The improvements of our model against DBN model are 8.2% for Precision, 7% for Recall and 8% for F1-score.

Communication-Based Train Control (CBTC) system is a critical signal system to ensure rail transit’s safe operation. Compared with the train-ground CBTC system, the train control system based on train-to-train (T2T) communication has the advantages of fast response speed, simple structure, and low operating cost. As the core part of the train control system based on T2T communication, the reliability of the data communication system (DCS) is of great significance to ensure the train’s safe and efficient operation. According to the T2T communication system requirements, this paper adopts Long-Term Evolution-Unlicensed (LTE-U) technology to design the DCS structure and establishes the reliability model of the communication system based on Deterministic and Stochastic Petri Nets (DSPN). Based on testing the real line’s communication performance parameters, the DSPN model is simulated and solved by π -tool, and the reliability index of the system is obtained. The research results show that the LTE-U-based T2T communication system designed in this paper meets the train control system’s needs for communication transmission. This paper’s reliability evaluation method can complete the reliability modeling of train control DCS based on T2T communication. The research in this paper will provide a strong practical and theoretical basis for the design and optimization of train control DCS based on T2T communication.

Communication-based train control (CBTC) system is an advanced train signalling and control technology which is developed using the moving block signalling (MBS) framework. The CBTC system has been shown to be capable of improving the operational efficiency, line capacity and safety of the railway operation. The main objective in implementing the MBS framework in CBTC system is to minimize the train headways through the utilization of an inter-train continuous communication system that determine and control the position of each train more precisely. One important challenge in such an implementation is the fulfillment of the necessary requirement of having highly accurate train localization method to ensure the safety of the short headway operation. This paper describes the results from experimental examination and application of a synchronization control strategy for the CBTC system using an unscented Kalman filter (UKF)-based sensor fusion approach as the localization method. In the proposed approach, the train localization task is performed using an UKF-based sensor fusion method which fuses measurement data from speed sensors and radio frequency identification tags. A synchronization control approach to ensure the safety movement of the train convoy in curved railway tracks under the MBS scheme is then proposed. The results presented in this paper show that the proposed localization and synchronization control methods can significantly improve the localization accuracy and reduce the inter-train headways.

In communication-based train control (CBTC) systems, as a train travels along a track, it changes its association from one access point (AP) to another, which is referred to as a handoff. Control parameters for handoff algorithms are often set based on desired system requirements, such as outage probability, without considering the effect of the underlying propagation characteristics of the channel on the system performance. Therefore, for typical CBTC systems, conservative safety margins are introduced in order to ensure safe operations leading to potentially sub-optimal system performance. In this paper, we propose a systematic procedure for selecting a control parameter, namely the threshold value, which determines when handoffs are triggered for received signal strength (RSS) based handoff algorithms. The proposed scheme leads to the selection of threshold values that increase the safety margin in addition to reducing the number of handoffs incurred, thereby enhancing the overall CBTC system performance. These enhancements are made possible with the integration of physics-based propagation models and network design that harnesses the propagation characteristics of the underlying wireless channels.

Communication-Based Train Control (CBTC) systems use wireless communication to confirm safe train operation for train-ground transmission. CBTC consists of four subsystems, and the Data Communication System (DCS) is one of the most important parts, which plays a vital role in train-ground transmission. Many devices are exposed to the environment in DCS, trains operation in bad weather easily leads to a series of hardware failures. When DCS occurs one mistake, it will threaten the efficiency of CBTC and even the safety of passengers. Since DCS occurs failures inevitably, it is necessary to analyze and identify the mistakes more quickly and accurately. This paper proposes a GAN-Bert based edge-to-edge model to identify DCS faults. Bidirectional Encoder Representations from Transformers (BERT) extracts text features from fault diagnosis with Masked Language Model(MLM) and Next Sentence Prediction(NSP). Meanwhile, Generative Adversarial Network (GAN) is used to perform DCS fault diagnosis. At the same time, edge-to-edge collaboration contributes to training a better model. We use raw DCS logs and compare prediction results between the GAN-Bert and Bert-only models. The simulation results represent that the GAN-Bert based model presents higher accuracy.

Communication-based train control (CBTC) systems use wireless local area networks (WLANs) to transmit train status and control commands. Since WLANs are not originally designed for applications with high mobility, random transmission delays and packet drops are inevitable, which could result in unnecessary traction, brakes or even emergency brakes of trains, loss of line capacity, and passenger satisfaction. In this paper, we study the packet drops introduced by random transmission errors and handovers in CBTC systems, analyze the impact of random packet drops on the stability and performances of CBTC systems, and propose two novel schemes to improve the performances of CBTC systems. Unlike the existing works that only consider a single train and study the communication issues and train control issues separately, we model the system to control a group of trains as a networked control system (NCS) with packet drops in transmissions. Extensive field test and simulation results are presented. We show that our proposed schemes can provide less energy consumption, better riding comfortability, and higher line capacity compared with the existing scheme.

Communication-based train control (CBTC) systems are automated train control systems using information technologies to ensure safe train control. With the adoption of wireless communication and computer network technologies, CBTC systems are facing increasingly serious security attacks. The Man-in-the-Middle (MitM) attack is one kind of attacks with strong concealment, with which attackers can gain control of the system and inflict serious train collision. This paper proposes a Bayesian game based defense scheme for CBTC systems under Man-in-the-middle attacks. We develop an attack detection method and active defense strategy to reduce the harm brought by MitM and improve the efficiency of the system under MitM attacks. Extensive simulation results show that the proposed defense scheme achieves great performance in defending against MitM attacks.

Intrusion detection plays a critical role in safeguarding computer networks from malicious activities and unauthorized access. Traditional machine learning (ML) models have been widely employed for intrusion detection, but their effectiveness can be limited due to the complex and evolving nature of network attacks. An efficient Convolutional Neural Network (CNN) that utilizes one-dimensional convolutions, batch normalization, and max pooling layers is designed to capture the attack patterns in network traffic data. By leveraging the inherent feature extraction capabilities of CNNs, the proposed architecture demonstrates improved performance in identifying network intrusions compared to traditional ML models. The effectiveness of the novel CNN architecture is evaluated by conducted comprehensive experiments on two benchmark intrusion detection datasets. The designed CNN performance was compared with four other ML models such as logistic regression, k-nearest neighbors, decision trees, and random forest. The experimental results revealed that the proposed CNN architecture outperformed the traditional ML models with highest accuracy of 97.68% and 97.39% and highest F1-score of 97.68% and 97.40% for. UNSW-NB15 and CICIDS2017 datasets, respectively. The proposed CNN architecture serves as a promising alternative to traditional ML models, offering improved performance in identifying and mitigating network attacks.

Small data, big challenges: Machine- and deep-learning strategies for data-limited drug discovery.

Communication-based train control (CBTC) systems use wireless local area networks (WLANs) for train-ground transmission. Transmission delays and packet drops may cause unnecessary tractions and brakes of trains, degradation of riding comfortability, rising of energy consumption and loss of the line's capacity. In this paper, We model the system to control a group of trains in CBTC as a networked control system (NCS) with transmission delays and packet drops. We study the delays and packet drops in CBTC, analyze their effects on train's control, and propose a method to improve the performance of CBTC. Extensive simulation results are presented. We show that our proposed method has a strong tolerance for transmission delays and packet drops, and outperforms the currently adopted scheme in different channel conditions.

Electromagnetic interference (EMI) is an important issue that needs to be considered for the safe operation of communication-based train control (CBTC) systems in railway environments. In this paper, two EMI scenarios are considered: the EMI of a wireless local area network (WLAN) at subway stations to CBTC systems and the interference of the CBTC system in tunnels to WLAN devices inside the train. To effectively solve those EMI problems, we introduce two hybrid wave propagation modeling techniques, where ray-tracing and finite-difference time-domain (FDTD) methods are hybridized for the first scenario and vector parabolic equation and FDTD methods are hybridized for the second scenario. The two hybrid models combine advantages of each individual method and achieve a better tradeoff between accuracy and efficiency. Based on our analysis, EMI-aware planning such as the optimization of WLAN antenna placement at subway stations can be pursued. The benefits that this approach can produce are demonstrated.

With the rapid development of wireless communications, passengers are able to surf the internet on the subway trains through mobile communication systems, even wireless local area networks (WLAN). That leads to communications-based train control (CBTC) systems interfered by WLAN equipments in the carriage due to working on the same frequency (2.4GHz frequency band). In this paper, we evaluate the interference from WLAN equipments for the spatial deployment for CBTC systems. To investigate the impact of the carriage to radio propagation, the test on the shielding effectiveness of the carriage is carried out and also verifies the simulation results based on ray-tracing method. Then, multiple spatial deployment scenarios for access points (APs) and mobile radios (MRs) of CBTC systems are investigated on anti-interference to WLAN equipments, respectively. From the analysis, the suggestions of the deployment for APs and MRs are provided.