Risk-Informed Support Vector Machine Regression Model for Component Replacement—A Case Study of Railway Flange Lubricator

The railway-rolling stock wheel flange lubricator protects the wheels and railhead by lubricating their contacts. Failed or missing lubricators can lead to excessive wear, flats, cracks, rolling contact fatigue, rail damage, derailment accidents. In extreme cases, worn due nonlinear conditions may fire hazards, particularly in underground infrastructure. addition, location of present accessibility issues prolong diagnosis failure. This study therefore proposes an adaptive risk-based support vector regression (SVR) machine with a Gaussian kernel function that accurately proactively predict wear loss from small data set. While most fail owing loss, others premature failure modes such as cracks fatigue. risk-informed feature evaluates rates associated failures other than balanced determination optimised replacement frequency. proposed model was applied validated case for London train. findings showed maintenance inspection lubricator, balance between safety organisational resource constraints, average every 4000 km train operations.