• Smart Structures and Systems
• /
• v.26 no.2
• /
• pp.175-184
• /
• 2020

Conventional Monte Carlo simulation-based methods for seismic risk assessment of water networks often require excessive computational time costs due to the hydraulic analysis. In this study, an Artificial Neural Network-based surrogate model was proposed to efficiently evaluate the flow-based system reliability of water distribution networks. The surrogate model was constructed with appropriate training parameters through trial-and-error procedures. Furthermore, a deep neural network with hidden layers and neurons was composed for the high-dimensional network. For network training, the input of the neural network was defined as the damage states of the k-dimensional network facilities, and the output was defined as the network system performance. To generate training data, random sampling was performed between earthquake magnitudes of 5.0 and 7.5, and hydraulic analyses were conducted to evaluate network performance. For a hydraulic simulation, EPANET-based MATLAB code was developed, and a pressure-driven analysis approach was adopted to represent an unsteady-state network. To demonstrate the constructed surrogate model, the actual water distribution network of A-city, South Korea, was adopted, and the network map was reconstructed from the geographic information system data. The surrogate model was able to predict network performance within a 3% relative error at trained epicenters in drastically reduced time. In addition, the accuracy of the surrogate model was estimated to within 3% relative error (5% for network performance lower than 0.2) at different epicenters to verify the robustness of the epicenter location. Therefore, it is concluded that ANN-based surrogate model can be utilized as an alternative model for efficient seismic risk assessment to within 5% of relative error.

• Journal of Korean Society of Water and Wastewater
• /
• v.33 no.5
• /
• pp.353-366
• /
• 2019

This research proposes an optimal flushing operation technique in an effort to prevent secondary water pollutions and accidents in aged pipes, and to improve the cleaning effect of unidirectional flushing. Water flow directions were analyzed using EPANET 2.0, while flushing and air scouring experiments in forward and reverse directions were performed in the field. In 42 experiments, average residual chlorine concentration and turbidity were improved after cleaning compared to before cleaning. It was found that even when the same cleaning method was used, further improvement of cleaning effect was possible by applying air injection and reverse direction cleaning techniques. By means of one-way ANOVA(Analysis of variance), it was also possible to statistically verify the need of actively utilizing air injection and reverse direction cleaning. Based on correlation between turbidity and TSS, the total amount of suspended solids removal was estimated for 874 flushing operations and 194 air scouring operations. The result showed that air scouring used more discharge water than flushing by an average of $4.9m^3$ yet with larger amounts of suspended solids removal by an average of 145.9 g. The result of analysis on turbidity values from 887 flushing operations showed low cleaning effect of unidirectional flushing for the pipes with diameters over 300 mm. In addition, the turbidity values measured during cleaning showed an increasing tendency as pipe age increased. The methodology and results of this research are expected to contribute to the efficient maintenance and improvement of water quality in water distribution networks. Follow-up research involving the measurement of water quality at regular time intervals during cleaning would allow a more accurate comparison of discharge water quality characteristics and cleaning effects between different cleaning methods. To this end, it is considered necessary to develop a standardized manual that can be used in the field and to provide relevant trainings.