Abstract:

Urban water distribution networks are complex and strategic structures whose maintenance is of utmost importance both to preserve the environment and to avoid wasting a precious resource such as water, and to prevent serious service disruptions for end users. Various research efforts have been directed towards defining data-driven or machine-learning-based approaches for estimating the degradation and predictive maintenance of hydraulic structures such as valves, pipelines, and various technological devices. However, these approaches have typically been used in very specific and narrow contexts, thus losing generality. The AQUA-PREDICT research project aims to define a software architecture and propose a methodological approach that facilitates and guides the design and development of generic applications in the context of predictive maintenance of urban water distribution networks. The architecture will provide layers and abstraction components through which to structure an application in an Edge/Cloud continuum and IoT sensor environment, where Artificial Intelligence algorithms and tools will be used for prediction functionalities.