Pipes age and corrosion are the main factors of leakage in water distribution networks. If we take Italy as an example, more than 40% of drinking water was lost in 2020 due to leaky aqueducts. According to the World Resources Institute, European countries will face water problems by 2040. Decrepit pipes can lead to environmental concerns, economical losses, and potential public health problems if water gets contaminated. Localizing leakage positions in an accurate way is often a big challenge. On the other side, replacing decrepit pipes is not an easy task and usually costly. An optimal solution to deal with water leakage is to use smart pipes where appropriate sensors monitoring the conditions of the pipes are incorporated in. Digitalization plays a crucial role here. By providing accurate information about the pipes, and use artificial intelligence techniques for data analysis, potential leakages and their corresponding positions can be detected in time, which allows to schedule a maintenance task as soon as possible.

In the SANDMAN project, Fraunhofer FOKUS has developed an AI based predictive maintenance solution for smart pipes able to detect potential leakages and their corresponding positions in time. The undertaken approach has two main goals. The first goal is to predict whether a pipe is leaky, using vibration sensor data. The second goal is to classify the location and size of a leak, once it was detected. These goals were achieved using extensive data preprocessing and deep learning Long Short-Term Memory (LSTM) networks. The implemented solution was validated in an experimental setup at the Italian company EKSO s.r.l in its factory facilities in Rozallo, Italy. The developed solution significantly contributes to the preservation of water resources, mitigates the effects of water scarcity, and minimizes the carbon footprint associated with water treatment and transportation.