A Bayesian machine learning approach for online detection of railway wheel defects using track-side monitoring

Abstract

Wheel condition assessment is of great significance to ensure the operation safety of trains and metro systems. This study is intended to develop a Bayesian probabilistic method for online and quantitative assessment of railway wheel conditions using track-side strain-monitoring data. The proposed method is a fully data-driven, nonparametric approach without the need of a physical model. To enable defect identification using only response measurement, the measured dynamic strain responses of rail tracks during the passage of trains are processed to elicit the normalized cumulative distribution function values representative of the effect of individual wheels, which in conjunction with the frequency points are used to formulate a probabilistic reference model in terms of sparse Bayesian learning. Through cleverly realizing sparsity by introducing hyper-parameters and their priors, the sparse Bayesian learning makes the resulting model to exempt from overfitting and generalize well on unseen data. Only the monitoring data in healthy state are needed in formulating the reference model. A novel Bayesian null hypothesis significance testing in terms of scale-invariant intrinsic Bayes factor, which does not suffer from the Jeffreys–Lindley paradox, is then pursued in the presence of new monitoring data collected from possibly defective wheel(s) to detect wheel defects and quantitatively assess wheel condition. The proposed method in fully Bayesian inference framework is verified by utilizing the real-world monitoring data acquired by a distributed fiber Bragg grating–based track-side monitoring system and comparing with the offline inspection results.

Bayesian approaches for evaluating wind‐resistant performance of long‐span bridges using structural health monitoring data

“…Sparse Bayesian learning (SBL) is a nonparametric machine learning approach in the Bayesian context that shares characteristics in common with support vector machine (SVM) but derives accurate prediction models utilizing fewer basis functions than a comparable SVM 31,37 . Its ability of sparse representation and accurate prediction is primarily due to the Bayesian setting where uncertainty is considered and “inactive” basis terms can be automatically pruned through introducing hyperparameters in prior distributions of the weight parameters 37 .…”

“…This means that the related basis functions ϕ i ( x ) are irrelevant and can be pruned from the model given in Equation 21. Thus, the SBL offers an automatic regularization approach to making sparsity come out through pruning irrelevant basis functions in the iteration process 31,37 …”

“…The Bayesian posterior distribution offers a lot more flexibility in the type of evidence and provides information more transparent to interpret. Although Bayesian approaches have been widely used in different engineering fields, 18–31 no study has been attempted on developing a Bayesian approach to probabilistically characterize the correlation between the wind speed and wind‐induced bridge response for wind‐resistant performance assessment.…”

A Hybrid Multi-Criteria Decision Making Model for Defect-Based Condition Assessment of Railway Infrastructure

“…The changes in the weights of railway components are evaluated based on the absolute deviation in the condition index (ADCI). The ADCI can be mathematically expressed using Equation (12):…”

“…The captured readings were sent to an online diagnosis system for analyzing the health condition status of inservice railway tracks. Ni and Zhang [12] introduced a Bayesian learning-based model for the online assessment of railway wheel conditions. The measured dynamic strain responses were studied to a normalized cumulative density function that modeled the patterns of healthy railway wheels.…”