The aim of this paper is to compare sorting and ranking methods for prioritization of rehabilitation interventions of sewers, taking into account risk, performance and cost. For that purpose multiple criteria decision-aid (MCDA) methods such as ELECTRE TRI for sorting and ELECTRE III for ranking are applied in a real case-study and the results obtained are compared. The case study is a small sanitary sewer system from a Portuguese utility located in the metropolitan area of Lisbon. The problem to investigate is the prioritization of the sewer candidates for rehabilitation. The decision maker (a panel group of specialists) has chosen five assessment measures: water level and maximum flow velocity (hydraulic performance indices), sewer importance and failure repair cost (collapse-related consequences of failure) and the risk of collapse. The results show that the outcomes from ELECTRE III are easier to understand than those from ELECTRE TRI method. Two different sets of weights were used, and the sorting and ranking results from both methods were found to be sensitive to them. ELECTRE TRI method is not straightforward as it involves technical parameters that are difficult to define, such as reference profiles and cut levels.

The research focuses on the analysis of transient cavitating flow in polyethylene pipes, which are characterized by a viscoelastic–rheological behaviour. A hydraulic transient solver incorporating the description of the rheological–mechanical behaviour of these pipes and the cavitating pipe flow has been developed. Both the discrete vapour cavity model and the discrete gas cavity model have been used to describe transient cavitating flow. These assume that discrete air cavities are formed at fixed pipe sections and consider a constant wave speed in the pipe reaches between the cavities. An experimental programme was conducted in a pipe-rig composed of a high-density polyethylene (HDPE) pipeline. Numerical results have been compared with collected data resulting in a good agreement. Effects related to the viscoelasticity of HDPE pipes and to the occurrence of vapour pressures during the transient events are also discussed.

Water utilities collect, store and manage vast data sets using many information systems (IS). For infrastructure asset management (IAM) planning those data need to be processed and transformed into information. However, information management efficiency often falls short of desired results. This happens particularly in municipalities where management is structured according to local government models. Along with the existing IS at the utilities' disposal, engineers and managers take their decisions based on information that is often incomplete, inaccurate or out-of-date. One of the main challenges faced by asset managers is integrating the several, often conflicting, sources of information available on the infrastructure, its condition and performance, and the various predictive analyses that can assist in prioritizing projects or interventions. This paper presents an overview of the IS used by Portuguese water utilities and discusses how data from different IS can be integrated in order to support IAM.

The current paper presents a hyper parameterization optimization process for a convolutional neural network (CNN) applied to pipe burst locations in water distribution networks (WDN). The hyper parameterization process of the CNN includes the early stopping termination criteria, dataset size, dataset normalization, training set batch size, optimizer learning rate regularization, and model structure. The study was applied using a case study of a real WDN. Obtained results indicate that the ideal model parameters consist of a CNN with a convolutional 1D layer (using 32 filters, a kernel size of 3 and strides equal to 1) for a maximum of 5000 epochs using a total of 250 datasets (using data normalization between 0 and 1 and tolerance equal to max noise) and a batch size of 500 samples per epoch step, optimized with Adam using learning rate regularization. This model was evaluated for distinct measurement noise levels and pipe burst locations. Results indicate that the parameterized model can provide a pipe burst search area with more or less dispersion depending on both the proximity of pressure sensors to the burst or the noise measurement level.