The paper presents the Fault Detection and Diagnosis (FDD) approach for water networks developed within the Waternomics project. In particular, the FDD system developed is based on the hydraulic modeling of the water network (done using the EPANET software) that is used to the train a Anomaly Detection With fast Incremental ClustEring (ADWICE) algorithm which in turns is applied to real time data of water flow and pressure monitored in the network to infer performance and detect leaks and operation anomalies. The developed FDD system is particularly useful when more than one parameter needs to be considered at the same time to determine if an anomaly or fault is in place in a complex water network. For a first evaluation, simulated training scenarios have been developed and tested for Linate airport (Milan – Italy) water network and the results are presented in this paper. WATERNOMICS is an EU FP7 research project and the key problem addressed is the lack of water information, management and decision support tools that present meaningful and personalized information about usage, price, and availability of water in an intuitive and interactive way to end users. On average water networks in EU have leakages and inefficiencies that results in 20-30% water losses. As such, new technologies and leakages detection methods are needed to solve this issue, to make the EU more sustainable and in this context the FDD method presented can be helpful.