Forecasting Vertical Acceleration Railway Wagons - A comparative study

Advances in modern machine learning techniques has encouraged interest in the development of vehicle health monitoring (VHM) systems. These techniques are useful for the reduction of maintenance and inspection requirements of railway systems. The performance of rail vehicles running on a track is limited by the lateral instability and track irregularities of a railway wagon. In this study, a forecasting model has developed to investigate vertical acceleration behavior of railway wagons attached to a moving locomotive using different regression algorithms. Front and rear vertical acceleration conditions have predicted using ten popular learning algorithms. Different types of models can be built using a uniform platform to evaluate their performances. This study was conducted using ten different regression algorithms with five different datasets. Finally best suitable algorithm to predict vertical acceleration of railway wagons have suggested based on performance metrics of the algorithms that includes: correlation coefficient, root mean square (RMS) error and computational complexity.