The Concept of Calculating the Water Distribution System as a Repeatable Process with Elements of Diagnostics Using Neural Modeling

• Autorzy: Dawidowicz Jacek

Identyfikatory

DOI

10.54740/ros.2022.035

• Języki publikacji: EN

Abstrakty

EN

Calculations of water distribution systems are most often performed many times because the correct solution from a technical point of view is rarely obtained after the first calculation run; hence, we can talk about a multistage calculation process. In connection with this, the calculation process of computer water distribution systems can be additionally supplemented with elements of process diagnostics. Diagnostic activities should be carried out using numerical algorithms, which can be a complement to classical hydraulic calculations of water distribution systems. The condition for reliable functioning of the diagnostic system formulated in this way is the efficient detection of computational irregularities. For this purpose, diagnostic problems were defined for the water pipes and the connection nodes in the water distribution system. The proposed diagnostic tests analyze the calculation results and indicate whether the solution is correct or, if irregularities are detected, suggest a way to solve the problem. Diagnostic tests are carried out using artificial neural networks.

Słowa kluczowe

EN

water distribution system; hydraulic calculation; process diagnostics; evaluation of calculation results; artificial neural network

• Wydawca: Politechnika Koszalińska
• Czasopismo: Rocznik Ochrona Środowiska
• Rocznik: 2022
• Tom: Tom 24
• Strony: 493--504
• Opis fizyczny: Bibliogr. 23 poz., rys.

Twórcy

autor

Dawidowicz Jacek

• Bialystok University of Technology, Poland

• https://orcid.org/0000-0003-1742-9463

Bibliografia

• Czapczuk, A., Dawidowicz, J., Piekarski, J. (2015). Artificial Intelligence Methods in the Design and Operation of Water Supply Systems. Rocznik Ochrona Srodowiska, 17, 1527-1544 (in Polish).
• Czapczuk, A., Dawidowicz, J., Piekarski, J. (2017). Application of Multilayer Perceptron for the Calculation of Pressure Losses in Water Supply Lines. Rocznik Ochrona Srodowiska, 19, 200-210.
• Damas, M, Salmeron, M., Ortega, J. (2000). ANNs and Gas for predictive controlling of water supply networks. In: Proceedings of the IEEE-INNSENNS international joint conference on neural networks (IJCNN2000). Como, Italy, 365-368.
• Dawidowicz, J. (2012). Expert System for Evaluation of Water Distribution System Created with an Inductive Inference. Rocznik Ochrona Srodowiska, 14, 650-659 (in Polish).
• Dawidowicz, J. (2018a). Evaluation of a pressure head and pressure zones in water distribution systems by artificial neural networks. Neural Computing & Applications, 30(8), 2531-2538. DOI: 10.1007/s00521-017-2844-8
• Dawidowicz, J. (2018b). A Method for Estimating the Diameter of Water Pipes Using Artificial Neural Networks of the Multilayer Perceptron Type. In: 2nd International Conference on Artificial Intelligence: Technologies and Applications (ICAITA 2018), (50-53). Atlantis Press. DOI: 10.2991/icaita-18.2018.13
• Dawidowicz, J., Czapczuk, A., Kruszynski, W. (2021). Kohonen Artificial Networks for the Verification of the Diameters of Water-pipes. Rocznik Ochrona Srodowiska, 23, 835-844. DOI: 10.54740/ros.2021.057
• Dawidowicz, J., Czapczuk, A., Piekarski, J. (2018a). The Application of Artificial Neural Networks in the Assessment of Pressure Losses in Water Pipes in the Design of Water Distribution Systems. Rocznik Ochrona Srodowiska, 20, 292-308.
• Dawidowicz, J., Kruszynski, W., Andraka, D., Czapczuk, A. (2018b). Assessing the Diameters of Water Pipes Using the k-Nearest Neighbours Method in the Calculations of Water Distribution Systems. Rocznik Ochrona Srodowiska, 20, 528-537.
• Isermann, R., Balle, P. (1997). Trends in the application of model-based fault detection and diagnosis of technical processes. Control engineering practice, 5(5), 709-719.
• Knapik, K., Bajer, J. (2010). Waterworks: a textbook for students of higher technical schools. Cracow: Publishing house of the Cracow University of Technology. (in Polish).
• Kościelny, J.M. (2004a). Models in the Diagnostics of Processes. In: Korbicz, J., Kowalczuk, Z., Kościelny, J.M., Cholewa, W. (eds) Fault Diagnosis (29-58). Berlin: Springer. DOI: 10.1007/978-3-642-18615-8_2
• Kościelny, J.M. (2004b). Process Diagnostics Methodology. In: Korbicz, J., Kowalczuk, Z., Kościelny, J.M., Cholewa, W. (eds) Fault Diagnosis (59-117). Berlin: Springer. DOI: 10.1007/978-3-642-18615-8_3
• Kwietniewski, M. (2009). GIS in water and sewage systems. Warsaw: Scientific Publishing House PWN (in Polish).
• Lansey, K, Mays, L.W. (2000). Hydraulics of water distribution systems. In: Mays L.W. (ed.) Water distribution systems handbook. New York: McGraw-Hill.
• Ormsbee, L.E. (2006). The history of water distribution network analysis: the computer age. In: Proceedings of the 8th annual water distribution systems analysis symposium, (1-6). USA, Cincinnati: ASCE.
• Palade, V., Bocaniala, C.D. (eds.). (2006). Computational intelligence in fault diagnosis. London: Springer Science & Business Media.
• Patan, K., Korbicz, J. (2004). Artificial Neural Networks in Fault Diagnosis. In: Korbicz, J., Kowalczuk, Z., Kościelny, J.M., Cholewa, W. (eds.) Fault Diagnosis (333-379). Berlin: Springer. DOI: 10.1007/978-3-642-18615-8_9
• Piasecki, A., Jurasz, J., Kaźmierczak, B. (2018). Forecasting daily water consumption : a case study in Torun, Poland. Periodica Polytechnica Civil Engineering, 62(3), 818-824.
• Rossman, L.A. (2000). EPANET 2 users manual. Cincinnati: U.S. Environmental Protection Agency, Office of Research and Development, National Risk Management Research Laboratory.
• Shamsi, U.M. (2005). GIS applications for water, wastewater, and stormwater systems. New York: CRC Press Inc., Taylor & Francis Group.
• Walski, M.T., Chase, D.V., Savic, D.A., Grayman, W.M., Beckwith, S., Koelle, E. (2003). Advanced water distribution modeling and management. Waterbury: Haestad Methods Solution Center, Haestad Press.
• Zhu, D., Zhang, T., Mao, G. (2002). Back-propagation artificial neural networks for water supply pipe line model. Tsinghua Sci. Technol., 7(5), 527-531.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).