Application and Optimization of Algorithms for Pressure Wave Evaluation Based on Measurement Data

Abstract

Leakages can occur in a district heating network, resulting in high economical damage. The propagating pressure wave resulting from large, spontaneous leakages reaches sensors at different locations in the network. This leads to pressure drops registered at each sensor at a different point in time. The time differences help to localize the leakage. Different algorithms are presented and applied in this paper to estimate the pressure drop time points based on non-uniform, time-discrete sensor signals. Five of the nine algorithms are self-developed with, e.g., parts of linear regression, whereas the other four algorithms have already been described in the literature, such as change-point detection. In this paper, several recorded events were investigated, and the algorithms were applied to real measurement data. After detection, leakage localization was performed to determine the affected exclusion area. A performance criterion was used as a measure to compare the algorithms. For practical application, the best-performing algorithm was identified. Furthermore, the events were classified according to how well they could be evaluated.

Leakages in District Heating Networks—Model-Based Data Set Quality Assessment and Localization

“…In Vahldiek’s paper [ 3 ], the data of several real events in cases of leakage within a DHN are evaluated. For each event, different algorithms are applied to detect the PDTP.…”

“…In [ 10 , 11 , 12 ], the presented evaluation of the pressure wave is divided into two steps: The determination of the PDTPs and the attribution to the EAs. The best suitable algorithm for the PDTP detection is presented in [ 3 ] and the required framework in [ 4 ]. In this paper, we borrow from these ideas, but an approach is proposed to combine these two steps.…”

“…In the case of a large, spontaneous leakage where a network shutdown is imminent, Figure 2 shows three very generic but still relevant steps with detection, localization, and separation. To secure safe network operation, the damaged network part has to be separated as fast as possible [ 3 ]. Two of these steps are already established in practice.…”

“…The replenishment is performed via the refill mass flow (green), but the available quantity for this is limited. The refill is necessary to maintain the prevailing pressure in the entire network and to keep the medium liquid due to the high supply temperature [ 3 ]. However, if the loss of medium is too large, it may be necessary to stop network operation.…”

“…After the evaluation, the model is also used to localize leakages directly within the network. In prior publications, there were two steps necessary: the determination of the PDTP [ 3 ] and the attribution to EA to separate the damaged network part [ 4 ]. With MoFoDatEv, both steps will be combined as a novelty and first results for artificial and real data will be shown.…”