Print Email Facebook Twitter Improving Subsurface Asset Failure Predictions for Utility Operators Title Improving Subsurface Asset Failure Predictions for Utility Operators: A Unique Case Study on Cable and Pipe Failures Resulting from Excavation Work Author Wijs, R. J.A. (Student TU Delft) Nane, G.F. (TU Delft Applied Probability) Leontaris, G. (TU Delft Applied Sciences) Van Manen, T. R.W. (Evides) Wolfert, A.R.M. (TU Delft Materials and Environment) Faculty Applied Sciences Date 2020-06-01 Abstract Utility operators must rely on predictive analyses regarding the availability of their subsurface assets, which highly depend on damage by increasing amounts of excavation work. However, straightforward use of standard statistical techniques, such as logistic regression or Bayesian logistic regression, does not allow for accurate predictions of these rare events. Therefore, in this paper, alternative approaches are investigated. These approaches involve weighting the likelihood as well as over-and undersampling the data. It was found that these data methods could substantially improve the accuracy of predicting rare failure events. More specifically, an application based on the real data of a Dutch water utility operator showed that undersampling and weighting improved the balanced accuracy, varying between 0.61 and 0.66, whereas the proposed methods resulted in failure predictions on between 38% and 58% of the validation data set. Hence, the proposed methods will enable utility operators to arrive at more accurate forecasts, enhancing their asset operation decision-making. Subject Cable and pipe networkExcavation workLogistic regressionNetwork operatorPredictive maintenanceRare-event dataSynthetic minority oversamplingWeighted sampling To reference this document use: http://resolver.tudelft.nl/uuid:cff03c37-2026-41d0-945c-124f0c8857d0 DOI https://doi.org/10.1061/AJRUA6.0001063 Embargo date 2021-04-01 ISSN 2376-7642 Source ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 6 (2) Part of collection Institutional Repository Document type journal article Rights © 2020 R. J.A. Wijs, G.F. Nane, G. Leontaris, T. R.W. Van Manen, A.R.M. Wolfert Files PDF RUENG_420_Proof.pdf 783.07 KB Close viewer /islandora/object/uuid:cff03c37-2026-41d0-945c-124f0c8857d0/datastream/OBJ/view