Random-Forest Machine Learning Approach for High-Speed Railway Track Slab Deformation Identification Using Track-Side Vibration Monitoring

High-speed railways (HSRs) are established all over the world owing to their advantages of high speed, ride comfort, and low vibration noise. A ballastless track slab is a crucial part HSR, its working condition directly affects safe operation train. With increasing train time, slabs suffer from various defects such as warping arching well interlayer disengagement defect. These will eventually lead deformation thus jeopardize operation. Therefore, it important monitor identify defects. This paper proposes method for monitoring using fiber optic sensing technology an intelligent identifying random-forest model. The results show that track-side can effectively capture signals caused by vibration, deformation, noise, environmental vibration. proposed algorithm effectively, recognition rate reach 96.09%. provides new methods identification.