With the advancement of digital technology, the collection of pavement performance data has become commonplace. The improvement of tools to extract useful information from pavement databases has become a priority to justify expenditures. This paper presents a case study of PaveMD, a tool that integrates multi-dimensional data structures with a data-driven fuzzy approach to identify good performing pavement sections. Combining this tool with an innovative paradigm where the focus is on repeating success can bring additional value to existing pavement databases. The case study shows that PaveMD can identify pavement sections that are performing well by comparing performance measures for the New Zealand context. In this paper, PaveMD’s development is described, and its implementation is showcased using data from the New Zealand Long-Term Pavement Performance (LTPP) database. It is recommended that this approach be further developed and extended to other infrastructure databases internationally.
Read full abstract