Preliminary study on runway pavement friction decay using data mining

Surfaces of airport pavements are subject to the friction decay phenomenon. A recurrent problem for the runways is representedby the deposits of vulcanized rubber of aircraft tires. This happens mainly in the touch-down areas during landing operations, andthe loss of grip compromises the safety of both take-off and landing operations. This study moves from the International CivilAviation Organization and the Italian Civil Aviation Authority provisions concerning runway friction measurement and reportingto a better way to analyze friction data. Being data mining the computational process of discovering patterns in a large data sets,data mining techniques are very helpful to reach this target. Unsupervised and supervised classification methods to analyzefriction data detected by Grip Tester Trailer were employed. First, K-means and Subtractive Clustering were applied to dividedata into a certain number of clusters representing the different areas of consumption. In a second time two differentClassification and Regression Trees models, CART and GCHAID, were employed to split the data points of the runway intonodes. At the end of the process scatterplots were built and better visualized through non-linear regressions. The decay curvesobtained were of service to compare the results achieved using data mining techniques versus the International Civil AviationOrganization and the Italian Civil Aviation Authority provisions in order to find out the best way to analyze friction data. Thefinal goals are to assure an optimum scheduling of the Airport Pavement Management System, as well as users safety.