Virtual sample generation for model-based prognostics and health management of on-board high-speed train control system

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.

Flexible Optimal Model and Algorithm for Track Utilization in High-speed Railway Stations

Track utilization is the most important technical operation in high-speed railway stations.It is an effective way to take flexible man-agement based on dispatchers’decision preferences into consideration for making track utilization plans to relieve the influence caused by unmeasurable unstructured factors.Thus,based on the flexible management concept and taking the flexible optimal for track utilization in high-speed railway stations as the object,time and space occupation safety trajectories of arrival routes,departure routes and tracks are all analysed.Then,taking the following constraints into consideration-minimum safety time intervals for var-ious routes and tracks occupation,space-time arc occupation and decision-makers’preferences-a flexible optimal model for track utilization in high-speed railway stations is established to maximize its balance and robustness and to minimize its volatility at the same time.Further,a flexible optimal solution based on a simulated annealing algorithm is designed to make a safety track utilization plan in high-speed railway stations integrating the dispatchers’decision preference.The results from the experiments show that the proposed methodology can effectively make satisfied safety track utilization plans based on decision-makers’preferences,which can improve its balance and robustness level significantly.Meanwhile,its volatility can be reduced as much as possible caused by flexible management based on artificial intervention to ensure the relative stability of the plan.