A review on railway track buckling prediction methods

Railway track buckling has long been a significant challenge in railway track engineering. Various methods have been developed to predict and/or prevent this phenomenon, with the aim of enhancing safety, efficiency, and sustainability of railway operations. This review discusses several relevant aspects, including the theoretical foundations in understanding railway track buckling behaviour, techniques for measuring and evaluating critical track parameters, and maintenance strategies aimed at optimising the structural stability of the track. Despite the progress in these approaches in the prediction and prevention of track buckling, challenges remain due to the complex dynamics involved in this phenomenon; field tests can be dangerous and impractical to scale, analytical or numerical methods have assumptions and can be computationally inefficient. An emerging trend in railway track buckling prediction is the integration of machine learning (ML) and artificial intelligence (AI) in accelerating predictions of buckling risks. Addressing these challenges can enhance the predictive capabilities of advanced track buckling prediction methods, improving railway safety and efficiency