Railway safety and efficiency increasingly rely on precise train positioning. The integration of the Global Navigation Satellite System (GNSS) into railway control systems aims to reduce dependence on track-side infrastructure. While GNSS has significantly improved train localization, challenges such as the susceptibility to jamming remain. To address this, this paper introduces an Inertial Navigation System (INS)-aided train positioning system based on deep integration, exploring its performance through semi-physical experiments and simulations. Experimental results demonstrate that the proposed solution is able to reduce the positioning error by 63.47 %, and the velocity error by 58.47 % under jamming conditions. The study highlights the potential of deep integration for improving the resilience of GNSS-based train control systems, especially in the face of Radio Frequency (RF) jamming threats.

Global Navigation Satellite Systems (GNSSs) are vulnerable to both unintentional interference and intentional attacks, making it difficult to meet the stringent safety requirements of railway train control systems. The growing threat to information security posed by spoofing attacks has received limited attention. This study investigates the impact of GNSS spoofing attacks on train positioning, emphasizing their detrimental effects on the accuracy and availability of train location report functions for train operation control. To explore the antispoofing performance of typical GNSS-based train positioning schemes, specific approaches, and system architectures are designed under two GNSS-alone and two GNSS-integrated train positioning schemes. Field data are utilized to establish spoofing attack scenarios for GNSS-based train positioning, with which the anti-spoofing capabilities of different train positioning schemes are evaluated. Experimental results indicate that under specific conditions, the GNSS-integrated positioning schemes demonstrate superior GNSS spoofing suppression capabilities. Results of the tests present valuable guidance for designers and manufacturers in developing more advanced and resilient train positioning solutions and equipment for the next generation of train control systems, thereby promoting the applications of GNSS technology in railway systems.

In view of class imbalance in data-driven modeling for Prognostics and Health Management (PHM), existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train control equipment. A virtual sample generation solution based on Generative Adversarial Network (GAN) is proposed to overcome this shortcoming. Aiming at augmenting the sample classes with the imbalanced data problem, the GAN-based virtual sample generation strategy is embedded into the establishment of fault prediction models. Under the PHM framework of the on-board train control system, the virtual sample generation principle and the detailed procedures are presented. With the enhanced class-balancing mechanism and the designed sample augmentation logic, the PHM scheme of the on-board train control equipment has powerful data condition adaptability and can effectively predict the fault probability and life cycle status. Practical data from a specific type of on-board train control system is employed for the validation of the presented solution. The comparative results indicate that GAN-based sample augmentation is capable of achieving a desirable sample balancing level and enhancing the performance of correspondingly derived fault prediction models for the Condition-based Maintenance (CBM) operations.