Heavy-haul rail surface defect identification based on multi-sensor data fusion

Abstract Heavy-haul railways play a vital role in freight transportation, and the health of the rails directly impacts the safety and efficiency of railway operations. The heavy axle loads and long train compositions of heavy-haul trains make the rail surface susceptible to damage such as rail corrugation, spalling and abrasion, threatening operational safety. To address the issue, this paper proposes a multi-source data fusion method for identifying rail surface defects on heavy-haul railways. First, complete ensemble empirical mode decomposition with adaptive noise is used to decompose vibration signals and extract multi-dimensional vibration features. Next, dynamic time warping is applied to align rail profile data and extract key geometric features. Then, the vibration features and profile features are fused using Relief-F to select the most discriminative features. Finally, a support vector machine is utilized for defect identification. Experiment results show that the proposed method achieves high accuracy in identifying rail surface defects, with an accuracy of 96.4%.