Assessment and Prediction of Water Supply Network Reliability under Information Shortage Using Artificial Neural Networks
Publication: ASCE Inspire 2023
ABSTRACT
The paper is dedicated to application of artificial intelligence in the form of neural networks (ANN) to such critical infrastructure as urban water supply systems (WSS) that inherently are gray boxes as the information about their layout, structure, interconnection of its elements, their properties (and the properties of various loads and impacts on them) is incomplete and vague. For training the ANN, a dataset was used, consisting of 1,240 observations characterizing each pipeline of the Kamyshlov city WSS. The multilayer perceptron was chosen as the most suitable for modeling purposes because it had the highest performance at the stages of training, control, and testing. The convergence between the real and predicted values of the output parameters is quite satisfactory. As a result of the sensitivity analysis of the simulated ANN model, important conclusions about WSS reliability were obtained.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Bubtiena, A. M., Elshafie, A. H., and Jafaar, O. (2011). “Application of artificial neural networks in modeling water networks.” 7th International Colloquium on Signal Processing and its Applications: IEEE, 50–57.
Dawood, T., Elwakil, E., Novoa, H. M., and Delgado, J. F. G. (2020a). “Artificial intelligence for the modeling of water pipes deterioration mechanisms.” Autom. Constr., 120(103398), 1–12.
Dawood, T., Elwakil, E., Novoa, H. M., and Delgado, J. F. G. (2020b). “Toward urban sustainability and clean potable water: Prediction of water quality via artificial neural networks.” J. Cleaner Prod., 291.
Fan, X., Wang, X., Zhang, X., and Yu, X. (2021). “Machine learning based water pipe failure prediction: The effect of engineering, geology, climate and socio-economic factors.” Reliab. Eng. Syst. Saf., 219(2).
Jenny, H., Wang, Y., Garcia Alonso, E., and Minguez, R. (2020). “Using Artificial Intelligence for Smart Water Management Systems.” ADB Briefs., 143.
Kapelan, Z., Weisbord, E., and Babovic, V. (2020). “Solutions for the Water Sector.” IWA Network., 1–16.
Kutyłowska, M. (2017a). “Prediction of Availability Indicator of Water Pipes Using Artificial Intelligence” 9th Conference on Interdisciplinary Problems in Environmental Protection and Engineering EKO-DOK, 17.
Kutyłowska, M. (2017b). “Prediction of Failure Frequency of Water-Pipe Network in the Selected City.” Period. Polytech., Civ. Eng., 61(3).
Kutyłowska, M. (2016). “Prediction of water conduits failure rate – comparison of support vector machine and neural network.” Ecol. Chem. Eng., 23(2),147–160.
Liu, W., Chen, Z., and Hu, Y. (2022). “XGBoost algorithm-based prediction of safety assessment for pipelines.” Int. J. Press. Vessels Pip., 197(3).
Moradi, S., Zayed, T., and Golkhoo, F. (2019). “Review on computer aided sewer pipeline defect detection and condition assessment.” Infrastructures., 4 (1).
Robles-Velasco, A., Cortés, P., Munuzuri, J., and Onieva, L. (2019). “Prediction of pipe failures in water supply networks using logistic regression and support vector classification.” Reliab. Eng. Syst. Saf., № 196.
Information & Authors
Information
Published In
ASCE Inspire 2023
Pages: 733 - 741
History
Published online: Nov 14, 2023
ASCE Technical Topics:
- Analysis (by type)
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Design (by type)
- Education
- Engineering fundamentals
- Infrastructure
- Infrastructure resilience
- Neural networks
- Practice and Profession
- Sensitivity analysis
- Structural behavior
- Structural design
- Structural engineering
- Structural reliability
- Training
- Water and water resources
- Water management
- Water supply
- Water supply systems
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.