A Two-Stage Physical-Informed Neural Network Approach for High-Speed Railway Track Geometry Irregularity Maintenance

To enhance the reliability and long-term stability of track structures, it is essential to intelligently upgrade maintenance methods. Track geometry irregularity (TGI) plays a critical role in line maintenance, as its acquisition and control efficiency directly impact maintenance effectiveness. The Chord-reference system (CR-system) is widely used for measuring TGI data, but these measurements often exhibit amplification or reduction at different wavelengths, making them unsuitable for precise track fine-tuning maintenance. In addition, traditional maintenance scheme design algorithm suffers from low solution efficiency when faced with large-scale decision variables. Therefore, we propose a two-stage physical-informed neural network (TS-PINN) approach for high-speed railway TGI Maintenance. In the first stage, we systematically introduce a PINN for TGI measurement (PINN-M) based on the classic CR-system principle, which can effectively rectify the measured TGI data into the real TGI data within a specific wavelength range. In the second stage, we propose a PINN for track fine-tuning (PINN-F) maintenance scheme design, which rectifies the real TGI data into maintenance scheme that meets specific track parameter constraints. By incorporating early stopping (ES) mechanism and shared network, we realize the automated design of maintenance schemes with specified Track Quality Index (TQI) targets using rapid measured TGI data. Case results show that the proposed approach has good robustness, can significantly reduce maintenance costs, and improve the efficiency of TGI maintenance.