Refined evaluation methods for preventive maintenance of project-level asphalt pavement based on confusion-regression model

•Airport pavement preventive maintenance three-level evaluation index system is established.•PM decisions are considered as the binary classification problem.•The asphalt pavement decay model is developed based on PCI.•Project-level asphalt pavement PM timing was determined through confusion matrix....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Construction & building materials Jg. 403; S. 133105
Hauptverfasser: Li, Yan, Zou, Zhengbo, Zhang, Jiupeng, He, Yinzhang, Huang, Guojing, Li, Junbo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 03.11.2023
Schlagworte:
Airport pavement
Binary classification problem
Confusion matrix
K-S curve
Preventive maintenance
ROC curve
Airport pavement
Confusion matrix
ROC curve
K-S curve
Binary classification problem
Preventive maintenance
ISSN:0950-0618
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Airport pavement preventive maintenance three-level evaluation index system is established.•PM decisions are considered as the binary classification problem.•The asphalt pavement decay model is developed based on PCI.•Project-level asphalt pavement PM timing was determined through confusion matrix. Accurate evaluation of the performance of airport pavement can help managers make scientific and systematic preventive maintenance (PM) decisions, ensuring pavement safety and extending service life. To this end, firstly, this paper sorted out the pavement performance evaluation index system, based on which a multi-dimensional evaluation system for PM was proposed, including control indexes, macroscopic indexes, and microscopic indexes. Then, the pavement decay model based on the pavement condition index (PCI) was developed, and the regression model between PCI and International roughness index (IRI) and friction coefficient (μ) was established. Finally, by converting the PM decisions for project-level pavement into a binary classification problem in machine learning, the optimal maintenance thresholds and intervals for PM of each index were determined using receiver operating characteristic (ROC) curve and Kolmogorov-Smirnov (K-S) curve. The optimal threshold represents the threshold when the index can separate the binary classification problem (PM decisions) with maximum probability. Based on confusion-regression model, the pavement performance can be evaluated more comprehensively, and the timing of PM can be accurately determined. The model helps airport managers develop accurate PM plans to address future maintenance needs.
ISSN:0950-0618
DOI:10.1016/j.conbuildmat.2023.133105