Maintenance optimization of infrastructure networks using genetic algorithms

Markov-chain models are used for predicting the performance of infrastructure facilities because of their ability to capture the time-dependence and uncertainty of the deterioration process, maintenance operations, and initial condition, as well as their practicality for network level analysis.

Abstract

This paper presents an approach to determining the optimal set of maintenance alternatives for a network of infrastructure facilities using genetic algorithms. Optimal maintenance alternatives are those solutions that minimize the life-cycle cost of an infrastructure network while fulfilling reliability and functionality requirements over a given planning horizon. Genetic algorithms are applied to maintenance optimization because of their robust search capabilities that resolve the computational complexity of large-size optimization problems. In the proposed approach, Markov-chain models are used for predicting the performance of infrastructure facilities because of their ability to capture the time-dependence and uncertainty of the deterioration process, maintenance operations, and initial condition, as well as their practicality for network level analysis. Data obtained from the Ministére des Transports du Québec database are used to demonstrate the feasibility and capability of the proposed approach in programming the maintenance of concrete bridge decks.