“…Despite the significant progress of vibration-based RULE, related applications for automated RULE in railway vehicle wheels using on-board measurements remain scarce [ 11 , 12 , 13 , 14 ], while the considered wheels possess severe faults in their treads, such as cracks and spalling. The methods of these studies fall under the category of the prediction-based RULE with the majority relying on statistical models, which incorporate a Wiener process model integrated with a linear, power-law, or exponential deterministic function according to the considered defect [ 11 , 12 , 13 ], whereas only the study in [ 14 ] utilizes an AI/ML model via the Neural Basis Expansion Analysis for Time Series (N-BEATS). The vibration signals RMS is employed as the selected feature for RULE in [ 11 , 12 , 13 ], where statistical models are also employed and the obtained results indicate adequate agreement between the RMS evolution and the selected deterministic function representing wheel degradation.…”