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.

Template-based knowledge reuse method for generating high-speed railway virtual construction scenes

Virtual construction has become an important approach to the high-quality development of high-speed railways,but existing methods have problems such as low efficiency in generating virtual construction scenes and the inability to reuse construction knowledge.To support the rapid visual representation of multiple types of construction processes and construction methods,a template-based knowledge reuse method is proposed.The method includes using a component-based modeling mode to build body structure models of a high-speed railway project and generate a 3D scene;decomposing the construction process and building a construction process knowledge base;establishing joint linkage models of construction machinery and forming a construction method knowledge template;and fusing multiple types of information according to a time sequence to visualize the construction process.Based on the template-based knowledge reuse method,a prototype system was developed,and virtual construction experiments were carried out.The results show that this method achieves the reuse of construction knowledge at different levels including construction machinery level,construction method level,and work site level.Compared with animation software for virtual construction,this method improves the production efficiency by 87%.Moreover,this method can provide a multilevel knowledge reuse scheme for diversified virtual construction.