Detection and identification of faults in a District Heating Network

District Heating Networks (DHNs) are composed of numerous pipes that can be threatened by faults that affect DHN operation and management. Thus, reliable diagnostic methodologies are essential to identify DHN health state and hinder DHN malfunctioning and performance deterioration. To this purpose, a novel diagnostic approach that couples a DHN simulation model with an optimization algorithm for detecting and identifying both thermal and hydraulic faults, i.e., water leakages, anomalous heat and pressure losses, is presented in this paper. In the current paper, the novel diagnostic approach is challenged at evaluating the health state of the DHN of the campus of the University of Parma, where different faults are artificially implanted, by using a digital twin of the DHN. The faulty datasets account for both single and multiple faults, as well as different fault types and causes. The novel diagnostic approach proves to correctly detect and identify all simulated faults, by also correctly estimating their magnitude even in the most challenging scenarios.