Archard model guided feature engineering improved support vector regression for rail wear analysis. (July 2022)

• Record Type: Journal Article
• Authors: Wang, Jinlong; Su, Yi; Alagu Subramaniam, N.; Pang, John Hock Lye
• Is Part Of: Engineering failure analysis. Volume 137(2022)
• Publication Date: 2022-07
• Subjects: Rail wear analysis -- Measurement data outliers -- Physics model guided feature engineering -- Support Vector Regression; System failures (Engineering) -- Periodicals; Fracture mechanics -- Periodicals; Reliability (Engineering) -- Periodicals; Pannes -- Périodiques; Rupture, Mécanique de la -- Périodiques; Fiabilité -- Périodiques; Fracture mechanics; Reliability (Engineering); System failures (Engineering); Periodicals; Electronic journals; 620.112
• DOI: 10.1016/j.engfailanal.2022.106248
• Languages: English
• ISSNs: 1350-6307

Abstract

Highlights: A physics model is applied to generate new features for the SVR model improvement when the raw data contains outliers. A long-term rail wear degradation modelling and prediction approach is realized based on a 14-year in-field dataset. A two-peak characteristic of rail wear was observed across the cant height value range. Rail service time length is the most important factor for rail wear prediction. Abstract: This paper applied Archard wear law in feature engineering for the improvement of Support Vector Regression (SVR) performance and realized the rail steel wear behavior prediction. The actual complex rail wear multidimensional degradation information was obtained from field maintenance records over a decade and the hidden data outliers raised the modelling challenges. We applied pre-process technologies including feature importance analysis, physical model guided feature generation and outlier detection to build up the SVR based robust nonlinear regression analysis framework. Individual railway parameters' effects on the wear process were investigated and revealed through model interpretation-based post analysis. This work provides a practical approach to deploying machine learning algorithms for rail service maintenance data analysis and treatment of data outliers.