Comparison of MLP and RBF Neural Networks in the Task of Classifying the Diameters of Water Pipes

• Autorzy: Gvishiani Zurab , Dawidowicz Jacek

Identyfikatory

DOI

10.54740/ros.2022.036

• Języki publikacji: EN

Abstrakty

EN

Hydraulic calculations of water distribution systems are currently performed using computer programs. In addition to the basic calculation procedure, modules responsible for evaluating the obtained calculation results are introduced more and more often into the programs. This article presents the results of research on artificial neural networks with a radial base function (RBF) and a multilayer perceptron (MLP), aimed at determining whether they can be used to model the relationship between the variables describing the computational section of the water distribution system and the diameter of the water pipe. The classification capabilities of the RBF and MLP networks were analyzed according to the number of neurons in the hidden layer of the network. A comparative analysis of RBF networks with multilayer perceptron (MLP) networks was performed. The results showed that the MLP networks have much better classification properties and are better suited for the task of assessing the selected diameters of the water pipes.

Słowa kluczowe

EN

water distribution system; hydraulic calculation; selection of diameter; water pipe; artificial neural network; radial basis function; multilayer perceptron

• Wydawca: Politechnika Koszalińska
• Czasopismo: Rocznik Ochrona Środowiska
• Rocznik: 2022
• Tom: Tom 24
• Strony: 505--519
• Opis fizyczny: Bibliogr. 18 poz., rys.

Twórcy

autor

Gvishiani Zurab

• Faculty of Civil Engineering, Georgian Technical University, Georgia

• https://orcid.org/0000-0001-5134-0089

autor

Dawidowicz Jacek

• Faculty of Civil Engineering and Environmental Sciences, Bialystok University of Technology, Poland

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

Bibliografia

• Bishop, C.M. (1995). Neural Networks for Pattern Recognition. Oxford: Oxford Univ. Press.
• Bridle, J.S. (1990). Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition, In: Neurocomputing: Algorithms, Architectures and Applications (227-236). Berlin, Heidelberg: Springer-Verlag.
• 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.
• 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.
• Hartigan, J.A., Wong, M.A. (1979). Algorithm AS 136: K-Means Clustering Algorithm. Applied Statistics, 28, 100-108.
• Konar, A. (2006). Computational intelligence: principles, techniques and applications. Springer Science & Business Media. New York.
• Lansey, K., Mays, L.W. (2000). Hydraulics of water distribution systems. In: Mays LW (ed) Water distribution systems handbook. New York: McGraw-Hill.
• Lingireddy, S., Brion G.M. (2005). Artificial neural networks in water supply engineering. In: Lingireddy S, Brion GM (eds) Artificial neural networks in water supply engineering, (1-9). Cincinnati: ASCE.
• 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.
• Rutkowski, L. (2008). Computational intelligence: methods and techniques. New York: Springer Science & Business Media.
• 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).