摘要：This paper presents a Model Predictive Control (MPC) strategy taking into account system and component reliability for drinking water networks. The objective is to deal from an availability point of view with a closed-loop system combining a deterministic part related to the system dynamics and a stochastic part related to the actuators and system reliability. The main contribution of this work consists in integrating the reliability assessment computed on-line using a Dynamic Bayesian Network (DBN) into the MPC algorithm.
关键词：ReliabilityModel Predictive ControlDynamic Bayesian NetworkDrinking Water Networks
