Using fuzzy logic and expert system approaches in evaluating flexible pavement distress: Case study

Hari Krishan Koduru, Feipeng Xiao, Serji N. Amirkhanian, C. Hsein Juang

Research output: Contribution to journalArticlepeer-review

34 Scopus citations

Abstract

Fuzzy logic and expert system techniques are effective in evaluating the flexible pavement distress. Distress classification has usually been performed by visual inspection of the surface of the pavement or from the data gathered by automated distress measuring equipment. Consistency in this process can be increased and subjectivity is minimized by using an expert system. A methodology has been developed that uses fuzzy logic for the categorization of distresses. An expert system was developed in C language using fuzzy logic for reasoning. The objective of the developed methodology was to use automated techniques for quick, efficient, and consistent classification for flexible pavement distresses using data from the automated distress measuring system. The developed expert system has been designed to be used as a module within a pavement management system. This will help to completely automate pavement condition evaluation and strategy development for maintenance and rehabilitation of pavements, thus eliminating subjectivity and inconsistency in the process. According to the experts, mostly highway officials, the differences between the actual measured data and results from fuzzy logic expert system approaches were well within acceptable ranges.

Original languageEnglish
Article number003002QTE
Pages (from-to)149-157
Number of pages9
JournalJournal of Transportation Engineering
Volume136
Issue number2
DOIs
StatePublished - Feb 2010

Keywords

  • Case studies
  • Distress
  • Expert system
  • Flexible pavement
  • Fuzzy sets
  • Methodology
  • Pavement management system

Fingerprint

Dive into the research topics of 'Using fuzzy logic and expert system approaches in evaluating flexible pavement distress: Case study'. Together they form a unique fingerprint.

Cite this