Dealing with disruptions in railway track inspection using risk-based machine learning

Abstract

Unplanned track inspections can be a direct consequence of any disruption to the operation of on-board track geometry monitoring activities. A novel response strategy to enhance the value of the information for supplementary track measurements is thus established to construct a data generation model. In this model, artificial (synthetic) data is assigned on each measurement point along the affected track segment over a short period of time. To effectively generate artificial track measurement data, this study proposes a NARX (nonlinear autoregressive with exogenous variables) model, which incorporates short-range memory dependencies in the dependent variable and integrates interdependent effects from external factors. Nonlinearities in the proposed model have been determined using an artificial neural network that allowed fast computation of a mapping function in line with the needs of effective disruption management. The risk of over fitting the data generation model, which reflected its generalisation ability, has been effectively managed through risk aversion concept. For the model evaluation, the deviation of track longitudinal level has been taken as a case study, predicted using its degradation rate and track alignment and gauge as exogenous variables. Simulation results on two datasets that are statistically different showed that the data generation model for disrupted track measurements is reliable, accurate, and easy-to-use. This novel model is an essential breakthrough in railway track integrity prediction and resilient operation management.

Introduction to the novel model of preoperative Multi - Domain Risk Stratification (pMDRS)

“…However, risk is varied in different surgeries (Kristensen et al 2014), and individual scores do not predict reliable risk in older comorbid patients (Pang et al 2021). Therefore, the ability of these scores in predicting overall risk is limited in complex patients (Graebner et al 2023), and there is ongoing need for a comprehensive risk model.…”

Railway Track Fault Detection Using Selective MFCC Features from Acoustic Data

“…Machine-learning- and deep-learning-based systems have achieved good results in a variety of applications due to recent advancements in these techniques [ 13 ]. As railway derailment directly affects human life and the economy, this motivated us to design a system to improve the performance of railway track detection using a machine-learning-based approach [ 14 , 15 ]. Image-processing-based approaches are utilized predominantly, along with other sensors, for railway track detection [ 16 ].…”