An evolutionary fuzzy system to support the replacement policy in water supply networks: The ranking of pipes according to their failure risk

In this study, an evolutionary fuzzy system is proposed to predict unexpected pipe failures in water supply networks. The seeks underpin the decisions of management companies regarding maintenance and replacement plans pipes. On one hand, logic provides high degrees interpretability over other black box models, which requested engineering application where have social consequences. genetic algorithm helps optimize parameters that govern model, specifically, for two purposes: (i) selection variables; (ii) optimization membership functions. Data from a real network are used evaluate accuracy developed system. Several graphs depict ranking pipes according their risk failure against length be replaced support choice most successful model. fact, results demonstrate annual 6.75% makes it possible prevent 41.14% failures.