An ensemble classifier to predict track geometry degradation. (May 2017)

• Record Type: Journal Article
• Authors: Cárdenas-Gallo, Iván; Sarmiento, Carlos A.; Morales, Gilberto A.; Bolivar, Manuel A.; Akhavan-Tabatabaei, Raha
• Is Part Of: Reliability engineering & system safety. Volume 161(2017)
• Page Start: 53
• Page End: 60
• Publication Date: 2017-05
• Subjects: Railroad maintenance -- Defects -- Gamma process -- Logistic regression -- Support vector machines -- Classification -- Ensemble algorithms; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2016.12.012
• Languages: English
• ISSNs: 0951-8320

Abstract

Abstract: Railway operations are inherently complex and source of several problems. In particular, track geometry defects are one of the leading causes of train accidents in the United States. This paper presents a solution approach which entails the construction of an ensemble classifier to forecast the degradation of track geometry. Our classifier is constructed by solving the problem from three different perspectives: deterioration, regression and classification. We considered a different model from each perspective and our results show that using an ensemble method improves the predictive performance. Abstract : Highlights: We present an ensemble classifier to forecast the degradation of track geometry. Our classifier considers three perspectives: deterioration, regression and classification. We construct and test three models and our results show that using an ensemble method improves the predictive performance.