Please use this identifier to cite or link to this item: http://hdl.handle.net/1822/43192

TitleAssessment of different genetic algorithms for pavement management systems
Author(s)Moreira, André Vilaça
Oliveira, Joel
Costa, L.
Fwa, Tien F.
KeywordsPavement management system
Genetic algorithms
Multi-objective optimization
Constraint handling
Penalty function
Issue dateJul-2016
PublisherResearch Publishing
CitationMoreira A. V., Oliveira J. R. M., Costa L., Fwa T. F. Assessment of different genetic algorithms for pavement management systems, 8th International Conference on Maintenance and Rehabilitation of Pavements and Technological Control, doi:10.3850/978-981-11-0449-7-082-cd, 2016
Abstract(s)As road administrations keep seeking for innovative ways to improve the means to manage their road assets, the continuous progresses of Pavement Management Systems (PMSs) towards a consistent and effective utility play an important role. An optimization methodology to support decision making is a key aspect of any PMS. In this paper, two genetic algorithms based optimization approaches are addressed. One comprises a multi-objective solver which uses the non-dominated sorting genetic algorithm II (NSGA-II). The other consists in using a genetic algorithm to optimize a single-objective function that is obtained after combining together the multiple objectives through the augmented Tchebycheff method with infinite norm. Objective functions and constraints are related with the pavement quality over time and the total costs of maintenance and rehabilitation (M&R) strategies. For each algorithm, three different constraint handling methods are analysed and compared; (1) a posteriori implementation; (2) constraint function; (3) penalty function. The results showed that, regardless specific modifications to the default algorithmsâ options, the multi-objective solver with a posteriori constraints or with a penalty function are the approaches more likely to provide the best approximations to the optimal solutions.
TypeconferencePaper
URIhttp://hdl.handle.net/1822/43192
ISBN9789811104497
DOI10.3850/978-981-11-0449-7-082-cd
ISSN978-981-11-0449-7
Peer-Reviewedyes
AccessrestrictedAccess
Appears in Collections:C-TAC - Comunicações a Conferências Internacionais

Files in This Item:
File Description SizeFormat 
2407-Mairepav_Moreira_et_al.pdf480,19 kBAdobe PDFView/Open    Request a copy!

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu Currículo DeGóis