Optimal Number of Pressure Sensors for Real-Time Monitoring of Distribution Networks by Using the Hypervolume Indicator

Ferreira, Bruno; Carriço, Nelson; Covas, Dídia

doi:10.3390/w13162235

Cited by 16 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The WDN can be visualized in Figure 5 , showing the storage tank which contains the flow rate meter (using a blue square marker) and the location of the eight pressure sensors (using a yellow triangle marker). The process used for determining the optimal number and location of pressure sensors for WDN monitoring is presented in [ 4 , 32 ].…”

Section: Application: Results and Discussionmentioning

confidence: 99%

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

et al. 2023

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Application: Results and Discussionmentioning

confidence: 99%

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The WDN presents an average nodal pressure-head of 37.5 m and an average inlet flowrate of 31 L/s. For this study, it is assumed that eight pressure sensors are installed in the network (whose location was optimized using the multi-objective methodology presented in [27,28]), recording values on an hourly basis. The inlet flowrate of the storage tank is measured with the same time step.…”

Section: Case Study Descriptionmentioning

confidence: 99%

Comparison of model-based techniques for pipe burst location in water distribution networks

Ferreira

Antunes

Carriço

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The current paper compares the performance of three model-based techniques for the automatic location of pipe burst events in water distribution networks. The first technique is based on nodal pressure sensitivities, the second solves an inverse analysis problem and the third technique uses hydraulic simulation to train a classifier. A real case study is used and a set of artificial measurements is generated for a number of pipe burst scenarios, with fixed burst location and variable pressure and flowrate noise levels and burst sizes. The performance of each technique is assessed based on the determined burst distance to the real burst location. Obtained results are discussed and the most relevant conclusions are drawn.

show abstract

“…This is a reality in many Portuguese water utilities, as investment in sensors is carried out mainly to monitor water consumption and inlet pressure of DMA. Ideally (and in addition to the already installed sensors), an optimal number of pressure sensors should be established, for instance, based on the analysis of the hypervolume indicator [25], and whose location is optimally defined to carry out leak detection and location [26].…”

Section: Leak Locationmentioning

confidence: 99%

Leak detection and location in a real water distribution network using a model-based technique

Ferreira,

Carriço,

Covas

2022

Proceedings - 2nd International Join Conference on Water Distribution System Analysis (WDSA)& Computing and Control in the

View full text Add to dashboard Cite

This paper presents a practical application of a model-based approach for leak detection and location in a real water distribution network. The methodology is divided into three main steps: 1) identification of the DMA with the highest leakage volume; 2) hydraulic model update and 3) leak location by inverse analysis. The water distribution network is monitored through 14 flowrate and pressure sensors and data were available for 1.5 years. The methodology is applied 15 times, specifically to five weekdays in three different periods with high seasonal variation (summer, spring and winter). Regardless of the analysed period, obtained results point to the presence of a leak with ca. 4 m3/h in a specific area of the network. This approximate location is a starting point for the application of more precise leak location techniques using acoustic equipment.

show abstract

Optimal Number of Pressure Sensors for Real-Time Monitoring of Distribution Networks by Using the Hypervolume Indicator

Cited by 16 publications

References 48 publications

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

Hyperparameter Optimization of a Convolutional Neural Network Model for Pipe Burst Location in Water Distribution Networks

Comparison of model-based techniques for pipe burst location in water distribution networks

Leak detection and location in a real water distribution network using a model-based technique

Contact Info

Product

Resources

About