Comparison of Two Evolutionary Algorithms for Optimization of Bridge Deck Repairs

Most bridge management systems have been developed to support either network- or project-level decisions. Network-level decisions include the selection of bridges for repair while repair strategies are considered project-level decisions. This article introduces an integrated model for bridge deck repairs with detailed life cycle costs of both network-level and project-level decisions. Two evolutionary-based optimization techniques that are capable of handling large-size problems, namely genetic algorithms and shuffled frog leaping, are then applied on the model to optimize maintenance and repair decisions. Ten trial runs with different numbers of bridges were used to compare the results of both techniques. The results indicate that both techniques can be equally suitable, and that the key issue is determining the set of parameters that optimize performance. The best optimization strategy for this type of problem appears to be a year-by-year strategy coupled with the use of a preprocessing function to allocate repair funds first to critical bridges.

[1]  Yi Jiang,et al.  BRIDGE PERFORMANCE PREDICTION MODEL USING THE MARKOV CHAIN , 1988 .

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

[3]  Timothy L. Jacobs,et al.  Optimal long term scheduling of bridge deck replacement and rehabilitation , 1992 .

[4]  H. Adeli,et al.  Integrated Genetic Algorithm for Optimization of Space Structures , 1993 .

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

[6]  Hitoshi Furuta,et al.  Optimal Maintenance Planning of Reinforced Concrete Decks on Highway Network , 2001 .

[7]  John O Sobanjo.  A Neural Network Approach to Modeling Bridge Deterioration , 1997 .

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

[9]  Ayaho Miyamoto.  Development of a Bridge Management System (J-BMS) in Japan , 2001 .

[10]  Samer Madanat,et al.  OPTIMAL REHABILITATION TIMES FOR CONCRETE BRIDGE DECKS , 1993 .

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

[12]  Donald E. Grierson,et al.  A modified shuffled frog-leaping optimization algorithm: applications to project management , 2007 .

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

[14]  Donath Mrawira,et al.  Shuffled complex evolution algorithms in infrastructure works programming , 2004 .

[15]  Fazil T. Najafi,et al.  USER COSTS AT THE WORK ZONE , 2001 .

[16]  R Ellis,et al.  THE NEW ONTARIO BRIDGE MANAGEMENT SYSTEM , 1999 .

[17]  Donald E. Grierson,et al.  Comparison among five evolutionary-based optimization algorithms , 2005, Adv. Eng. Informatics.

[18]  Paul D Thompson,et al.  User Cost Model for Bridge Management Systems , 2000 .

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

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

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

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

[23]  Changqin Liu,et al.  Maintenance Strategy Optimization of Bridge Decks Using Genetic Algorithm , 1997 .