Evolutionary Algorithms for Optimizing Bridge Deck Rehabilitation

Bridges are vital links in infrastructure road networks and require frequent maintenance and repair to keep them functional throughout their service lives. However, with most existing bridges being old and the funds available for repair being limited, the prioritization of bridges for repair, the allocation of the limited funds, and the selection of appropriate repair methods become complex optimization decisions. This is still true even when considering only one bridge component (e.g., deck) within a large network of bridges. In this paper, an integrated bridge deck management system is formulated with detaile d life cycle cost analysis. The system’s implementation on a spreadsheet program is briefly highlighted. Five evolutionary algorithms namely; genetic algorithms, memetic algorithms, particle swarm, ant colony systems, and shuffled frog leaping are then int roduced and applied to optimize maintenance and repair decisions for various problems with different numbers of bridges. Based on the results obtained, the benefits of both the model formulation and the use of evolutionary algorithms are discussed, and the most suitable algorithm is selected for the proposed bridge deck management system. This paper contributes not only to the development of advanced management systems that can be adapted to various infrastructure types, but also to the implementation of ne w techniques for large scale optimization.

[1]  John O Sobanjo,et al.  FLORIDA DOT PROJECT-LEVEL BRIDGE MANAGEMENT MODELS , 2003 .

[2]  Marja-Kaarina Söderqvist,et al.  FINNISH PROJECT LEVEL BRIDGE MANAGEMENT SYSTEM , 1999 .

[3]  Lucio Soibelman,et al.  Computing in Civil Engineering (2005) , 2005 .

[4]  Yi Jiang,et al.  The development of performance prediction and optimization models for bridge management systems , 1990 .

[5]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[6]  Bernd Freisleben,et al.  A Genetic Local Search Approach to the Quadratic Assignment Problem , 1997, ICGA.

[7]  Hugh Hawk.  BRIDGIT deterioration models , 1995 .

[8]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[9]  Kevin E Lansey,et al.  Optimization of Water Distribution Network Design Using the Shuffled Frog Leaping Algorithm , 2003 .

[10]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[11]  Pablo Moscato,et al.  On Evolution, Search, Optimization, Genetic Algorithms and Martial Arts : Towards Memetic Algorithms , 1989 .

[12]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[13]  Tarek Hegazy,et al.  Bridge Deck Management System with Integrated Life-Cycle Cost Optimization , 2004 .

[14]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[15]  Ayaho Miyamoto,et al.  Development of a bridge management system for existing bridges , 2001 .