Leakage detection of water distribution networks using integrated model of ant colony optimization (ACO) and step by step elimination method (SSEM)

Abstract

AbstractIntroduction: Conventional leak detection methods are costly and time-consuming, so attention has recently been drawn to methods that detect leakage by network modeling comprehensively.Methods: In these methods, the difference between the measured pressure and flow rate and those obtained by the model is minimized as a fitness function by calibrating the network and adjusting the nodal demands. It has been established by analysis that the fitness function in itself cannot be a good guide to achieving the minimum point. This drawback was solved by using the ACO method. In addition to the fitness, this method employs a parameter called heuristic guidance to improve its capabilities.Results: This research compared three ACO-based optimization methods. The first was ACO with fixed heuristic guidance already introduced in the literature. In the second method, the heuristic guidance varies by the values of the observed pressures and pressure decline versus the no-leak state. The third is studied and compared by integrating SSEM and ACO models. These methods were investigated on a network derived from the literature and the Birjand network.Conclusion: The results revealed that the methods proposed here achieved more precise results in a shorter time and with fewer iterations.

Keywords

• calibration
• optimization
• water distribution network
• leak detection
• aco