Integrated airport pavement management using a hybrid approach of Markov Chain and supervised multi-objective genetic algorithms

ABSTRACT

An airport pavement management system is of great significance in terms of allocating budget and resources as well as preserving the level of serviceability and safety. In order to provide a more accurate, reliable, and applicable plan for airport pavement management, the combination and interrelation of four crucial affecting factors should be considered: pavement age, traffic load frequency, weather conditions, as well as maintenance actions effects. These factors have not been comprehensively studied enough neither within the deterioration modelling, which is the core of airport pavement management, nor through the decision-making procedure. The Markov Chain method is used for deterioration modelling. The data required to build up Markov Chain deterioration models are collected through questionnaires filled by experts. Having built up deterioration models, the second version of Non-Dominated Sorting Genetic Algorithms (NSGA-II) is applied to solve pavement management problems, i.e. providing a pavement maintenance activity plan over the planning horizon through a supervised manner considering both pavement conditions and monetary resources as objective functions. Finally, the proposed plan maintains a minimum acceptable level of airport pavement conditions over the planning horizon minimizing budget.

KEYWORDS:

• Airport pavement management
• Markov Chains
• genetic algorithms

Acknowledgements

The authors would like to thank the personnel of Mehrabad and Imam Khomeini Airports, Tehran, Iran, for their assistance regarding completing questionnaires and providing valuable comments.

Disclosure statement

No potential conflict of interest was reported by the authors.