Real Time Leak Isolation in Pipelines Based on a Time Delay Neural Network

Navarro, A.E.; Begovich, O.; Delgado-Aguiñaga, J.A.; Sánchez, Juan Diego

doi:10.1109/ropec48299.2019.9057112

Cited by 5 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…k is a scaling factor that increases the variance of each univariate Gaussian with a constant factor: 3) Evaluation: As here only a small number (9 samples) of in-field leak experiments can be used as test data, we evaluate and report the average cross-entropy loss calculated over all leak experiments per hyperparameter k in Eq. (10). A map of the leak probability predictions for the best hyperparameter is then visualized.…”

Section: From Twhbc To Training a Gnb Classifiermentioning

confidence: 99%

See 1 more Smart Citation

Leak localization in Water Distribution Networks By Directly Fitting the Learning Parameters of a Gaussian Naive Bayes Classifier

Mazaev

Weyns

Vancoillie³

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Water supply companies around the globe are struggling to meet the needs of an ever-increasing population, while climate change contributes to more drought. At the same time, up to 30% of the total amount of treated drinking water in the water supply system is lost due to leaks. An important strategy to reduce leak losses is using hydraulic modeling to localize leaks in a expert-driven manner. In this paper, we present a hybrid leak localization approach combining both hydraulic modeling and machine learning-based classification. A Gaussian Naive Bayes classifier is trained to localize leaks based on simulated pressures and historical pressure measurements. The simulated pressures are obtained using a hydraulic model of the water supply system. In our methodology, learned parameters of the classifier are inferred directly from processing the simulated and measured pressures, without the need for explicit training. We demonstrate the effectiveness of our leak localization approach by using real leak experiments, achieved by opening hydrants at different locations in an operational water supply system. Stateof-the-art results are achieved, similar to an approach where explicit training is still needed.

show abstract

Section: From Twhbc To Training a Gnb Classifiermentioning

confidence: 99%

“…A main drawback using purely data-driven approaches for localizing leaks, is that usually the amount of data does not suffice to represent different leak scenarios. Recent examples can be found in Zhou et al [9] and Navarro et al [10].…”

Section: Introductionmentioning

confidence: 99%

Leak localization in Water Distribution Networks By Directly Fitting the Learning Parameters of a Gaussian Naive Bayes Classifier

Mazaev

Weyns

Vancoillie³

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

show abstract

“…A data-driven method, proposed in Arifin et al (2018), applies the concept of Kantorovich distance to detect and locate leaks from flow rates and pressure measurements. In Navarro et al (2019), a real time leak localization method using time delay neural networks and flow/pressure measurements is presented.…”

Section: Introductionmentioning

confidence: 99%

Clustering-Learning Approach to the Localization of Leaks in Water Distribution Networks

Romero-Ben

Blesa

Puig

et al. 2022

J. Water Resour. Plann. Manage.

View full text Add to dashboard Cite

Leak detection and localization in water distribution networks (WDNs) is of great significance for water utilities. This paper proposes a leak localization method that requires hydraulic measurements and structural information of the network. It is composed by an image encoding procedure and a recursive clustering/learning approach. Image encoding is carried out using Gramian angular field (GAF) on pressure measurements to obtain images for the learning phase (for all possible leak scenarios). The recursive clustering/learning approach divides the considered region of the network into two sets of nodes using graph agglomerative clustering (GAC) and trains a deep neural network (DNN) to discern the location of each leak between the two possible clusters, using each one of them as inputs to future iterations of the process. The achieved set of DNNs is hierarchically organized to generate a classification tree. Actual measurements from a leak event occurred in a real network are used to assess the approach, comparing its performance with another state-of-the-art technique, and demonstrating the capability of the method to regulate the area of localization depending on the depth of the route through the tree.

show abstract

Recognition Method of Pipeline Weld Defects Based on Auxiliary Classifier Generative Adversarial Networks

Lang

2022

IEEE Instrum. Meas. Mag.

View full text Add to dashboard Cite

Real Time Leak Isolation in Pipelines Based on a Time Delay Neural Network

Cited by 5 publications

References 9 publications

Leak localization in Water Distribution Networks By Directly Fitting the Learning Parameters of a Gaussian Naive Bayes Classifier

Leak localization in Water Distribution Networks By Directly Fitting the Learning Parameters of a Gaussian Naive Bayes Classifier

Clustering-Learning Approach to the Localization of Leaks in Water Distribution Networks

Recognition Method of Pipeline Weld Defects Based on Auxiliary Classifier Generative Adversarial Networks

Contact Info

Product

Resources

About