A Three-Stage Decision-Making Method Based on Machine Learning for Preventive Maintenance of Airport Pavement

Abstract

The goal of preventative maintenance (PM) decision-making on airport pavements is to deploy the appropriate maintenance countermeasures at the correct time. This paper proposed a three-stage method for maintenance based on machine learning, which further refined the PM decision-making process. First, a pavement maintenance level model was developed using the PCA and PSO algorithm optimized SVM model. The model was then used to separate pavement maintenance into three categories: daily, PM, and major. Second, the DBSCAN and OPTICS were utilized to further divide the PM requirements finely. In order to implement the scientific decision-making of PM, suitable maintenance procedures were ultimately chosen based on the predominant damage kinds of the pavement units. The results showed that, when compared to the original SVM model, the classification accuracy of the PCA-PSO-SVM model was greatly improved, with total accuracy and accuracy of each class increasing by 10%, 41.7%, 4.6%, and 7.8%, respectively. When clustering the airport pavement performance dataset, OPTICS outperformed the DBSCAN technique. Four groups of PM demands were discovered by visualizing the best grouping levels after dimensionality reduction.