Deep Learning for Water Quality Classification in Water Distribution Networks

2021 ◽  
pp. 153-164
Author(s):  
Essa Q. Shahra ◽  
Wenyan Wu ◽  
Shadi Basurra ◽  
Stamatia Rizou
Keyword(s):  
Water Quality ◽  
Deep Learning ◽  
Water Distribution ◽  
Distribution Networks ◽  
Water Distribution Networks ◽  
Quality Classification ◽  
Water Quality Classification

scholarly journals First Results in Leak Localization in Water Distribution Networks using Graph-Based Clustering and Deep Learning

2020 ◽  
Vol 53 (2) ◽  
pp. 16691-16696
Author(s):  
Luis Romero ◽  
Joaquim Blesa ◽  
Vicenç Puig ◽  
Gabriela Cembrano ◽  
Carlos Trapiello
Keyword(s):  
Deep Learning ◽  
Water Distribution ◽  
Distribution Networks ◽  
Water Distribution Networks ◽  
First Results ◽  
Leak Localization ◽  
Graph Based Clustering

scholarly journals Optimal Water Quality Sensor Placement by Accounting for Possible Contamination Events in Water Distribution Networks

Water ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 1999
Author(s):  
Malvin S. Marlim ◽  
Doosun Kang
Keyword(s):  
Water Quality ◽  
Water Distribution ◽  
Sensor Placement ◽  
Pso Algorithm ◽  
Distribution Networks ◽  
Fair Value ◽  
Water Distribution Networks ◽  
Optimization Approach ◽  
Protection Measure ◽  
Contamination Events

Contamination in water distribution networks (WDNs) can occur at any time and location. One protection measure in WDNs is the placement of water quality sensors (WQSs) to detect contamination and provide information for locating the potential contamination source. The placement of WQSs in WDNs must be optimally planned. Therefore, a robust sensor-placement strategy (SPS) is vital. The SPS should have clear objectives regarding what needs to be achieved by the sensor configuration. Here, the objectives of the SPS were set to cover the contamination event stages of detection, consumption, and source localization. As contamination events occur in any form of intrusion, at any location and time, the objectives had to be tested against many possible scenarios, and they needed to reach a fair value considering all scenarios. In this study, the particle swarm optimization (PSO) algorithm was selected as the optimizer. The SPS was further reinforced using a databasing method to improve its computational efficiency. The performance of the proposed method was examined by comparing it with a benchmark SPS example and applying it to DMA-sized, real WDNs. The proposed optimization approach improved the overall fitness of the configuration by 23.1% and showed a stable placement behavior with the increase in sensors.

Sign in / Sign up

Export Citation Format

Share Document