A Nondestructive Evaluation Technique to Measure Axial Stress in Continuous Welded Rails

Abstract

AbstractContinuous welded rails (CWR) are track segments welded together and widely used in many rail networks worldwide. Compared to mechanically jointed rails, CWR provide smoother ride to the passengers, require less maintenance, increase the life cycle of the tracks, and can be traveled at higher speeds. However, CWR are prone to buckling during the warm seasons as the rise in the steel temperature induces excessive compressive loads. To prevent such instability issues, axial stress or the so-called rail neutral temperature are determined in order to take proper safety measures. This article presents some results of in-situ measurements relative to a nondestructive evaluation method to determine axial stress and rail neutral temperature (i.e., the temperature at which the axial stress is zero). The technique builds upon a parametric modal analysis of the track under varying boundary conditions and axial stresses, using a finite element model tested in the field. The modal analysis results were used to create a database which was then fed into a machine learning algorithm to predict the axial stress. The estimated neutral temperatures by this technique appeared to be in good agreement with the recorded measurements from strain gages bonded (after a cumbersome distressing procedure) on the CWR.KeywordsContinuous welded railsFinite element analysisRail neutral temperatureNondestructive evaluationMachine learning