Application of artificial neural networks to the technical condition assessment of water supply systems

• Autorzy: Kamiński K. , Kamiński W. , Mizerski T.

Identyfikatory

DOI

10.1515/eces-2017-0003

Warianty tytułu

PL

Zastosowanie sztucznych sieci neuronowych do oceny stanu technicznego sieci wodociągowej

• Języki publikacji: EN

Abstrakty

EN

The paper explains a method for discerning the parts of a water supply system in need of renovation. The results are based on technical data collected over the last twenty one years, concerning more than two hundred sections of both renovated and nonrenovated pipelines. In the study, an appropriately prepared data set was used for training an artificial neural network (ANN) in the form of a multilayer perceptron (MLP). Further comparison between the responses of the trained MLP and the decisions made by human experts showed satisfactory consistency, although 15% of the database records produced certain discrepancies. The presented method can help create an expert system capable of supporting failure-free operation of a water distribution system.

Słowa kluczowe

EN

water supply system; pipeline renovation; multilayer perceptron

PL

system zaopatrzenia w wodę; renowacja rurociągu; perceptron wielowarstwowy

• Wydawca: Towarzystwo Chemii i Inżynierii Ekologicznej
• Czasopismo: Ecological Chemistry and Engineering. S
• Rocznik: 2017
• Tom: Vol. 24, nr 1
• Strony: 31--40
• Opis fizyczny: Bibliogr. 30 poz., wykr., tab., rys.

Twórcy

autor

Kamiński K.

• Faculty of Process and Environmental Engineering, Lodz University of Technology, ul. Wólczańska 213, 90-924 Łódź, Poland, phone [phone]

autor

Kamiński W.

• Faculty of Process and Environmental Engineering, Lodz University of Technology, ul. Wólczańska 213, 90-924 Łódź, Poland, phone [phone]

autor

Mizerski T.

• Company of Water Supply and Sewage Disposal Ltd., ul. Wierzbowa 52, 90-133 Łódź, Poland

Bibliografia

• [1] Hotloś H. Ilościowa ocena wpływu wybranych czynników na parametry i koszty eksploatacyjne sieci wodociągowych (Quantitative effect assessment of selected factors on indicators and operating costs of water-pipe networks). Wrocław: Ofic Wyd Politechniki Wrocławskiej; 2007. http://www.dbc.wroc.pl/Content/4273/Hotlos.pdf.
• [2] Ladopoulos EG. Non-linear real-time expert water management telematics system for leaks control. Water Res. 2013;40:476:482. DOI: 10.1134/S0097807813040076.
• [3] Hoang TH, Mouton A, Lock K, De Pauw N, Goethals PLM. Integrating data-driven ecological models in an expert-based decision support system for water management in the Du river basin (Vietnam). Environ Monit Assess. 2013;185:631-642. DOI: 10.1007/s10661-012-2580-6.
• [4] Cretescu I, Craciun I, Benchea RE, Kovács Z, Iavorschi A, Sontea V, et al. Development of an expert system for surface water quality monitoring in the context of sustainable management of water resources. Environ Eng Manage J. 2013;12:1721-1734. http://omicron.ch.tuiasi.ro/EEMJ/pdfs/vol12/no8/20_769_Cretescu_13.pdf.
• [5] Nicklow J, Reed P, Savic D, Dessalegne T, Harrell L, Chan-Hilton A, et al. State of the art for genetic algorithms and beyond in water resources planning and management. J Water Resources Plann Manage. 2010;136:412-432. DOI: 10.1061/(ASCE)WR.1943-5452.0000053.
• [6] Tchorzewska-Cieslak B. Matrix method for estimating the risk of failure in the collective water supply system using fuzzy logic. Environ Protect Eng. 2011;38:111-118. http://epe.pwr.wroc.pl/2011/3_2011/12tchorzewska.pdf.
• [7] Kolasa-Więcek A. Use of artificial neural networks in predicting direct nitrous oxide emissions from agricultural soils. Ecol Chem Eng S. 2013;20:419-428. DOI: 10.2478/eces-2013-0030.
• [8] Olawoyin R. Application of backpropagation artificial neural network prediction model for the PAH bioremediation of polluted soil. Chemosphere. 2016;161:145-150. DOI: 10.1016/j.chemosphere.2016.07.003.
• [9] Wu Y, Wang J. A novel hybrid model based on artificial neural networks for solar radiation prediction. Renew Energy. 2016;89:268-284. DOI: 10.1016/j.renene.2015.11.070.
• [10] Selami D, Karadeniz A, Demir NM. Using steepness coefficient to improve artificial neural network performance for environmental modeling. Pol J Environ Stud. 2016;25:1467-1477. DOI: 10.15244/pjoes/61958.
• [11] Wang Y, Yu T-Y. Novel tornado detection using an adaptive neuro-fuzzy system with S-band polarimetric weather radar. J Atmosph Oceanic Technol. 2015;32:195-208. DOI: 10.1175/JTECH-D-14-00096.1.
• [12] Kaur G. Neural networks to identify tornadic/nontornadic circulations based on various radar attributes. Intern J Sci Eng Res. 2013;4:1124-1126. http://www.ijser.org/researchpaper%5CNeural-Networks-toidentify-Tornadic-NonTornadic-Circulations-based-on-various-radar-attributes.pdf.
• [13] Liu Y, Xia J, Shi C-X, Hong Y. An improved cloud classification algorithm for China’s FY-2C multi-channel images using artificial neural network. Sensors. 2009;9:5558-5579. DOI: 10.3390/s90705558.
• [14] Kuril S, Saini I, Saini BS. Cloud classification for weather information by artificial neural network. International J Appl Phys Math. 2013;3:28-30. DOI: 10.7763/IJAPM.2013.V3.167.
• [15] Asadollahfardi G, Zangooei H, Aria SH. Predicting PM2.5 concentrations using artificial neural networks and Markov chain, a case study Karaj City. Asian J Atmosph Environ. 2016;10:67-79. DOI: 10.5572/ajae.2016.10.2.067.
• [16] Kaminski W, Tomczak E. An integrated neural model for drying and thermal degradation of selected products. Drying Technol. 1999, 17:7-8, 1291-1301. DOI: 10.1080/07373939908917615.
• [17] Kolasa-Więcek A. Exploitation of water resources of the Opole province - forecasting with the use of artificial neural networks. Ecol Chem Eng S. 2010;17:363-371. http://tchie.uni.opole.pl/freeECE/S_17_3/KolasaWiecek_17(S3).pdf.
• [18] Korus I, Piotrowski K. Neural network model prediction of chromium separation in polyelectrolyteenhanced ultrafiltration. Ecol Chem Eng A. 2014;21:377-385. DOI: 10.2428/ecea.2014.21(3)31.
• [19] Sentas A, Psilovikos A, Psilovikos T, Matzafleri N. Comparison of the performance of stochastic models in forecasting daily dissolved oxygen data in dam-Lake Thesaurus. Desalin Water Treatm. 2016;57:11660-11674. DOI: 10.1080/19443994.2015.1128984.
• [20] Lee JHW, Huang Y, Dickman M, Jayawardena AW. Neural network modelling of coastal algal blooms. Ecol Modelling. 2003;159:179-201. DOI: 10.1016/S0304-3800(02)00281-8.
• [21] Wei B, Sugiura N, Maekawa T. Use of artificial neural network in the prediction of algal blooms. Water Res. 2001;35:2022-2028. DOI: 10.1016/S0043-1354(00)00464-4.
• [22] Możejko J, Gniot R. Application of neural networks for the prediction of total phosphorus concentrations in surface waters. Pol J Environ Stud. 2008;17:363-368. http://www.pjoes.com/pdf/17.3/363-368.pdf.
• [23] Kutyłowska M. Neural network approach for failure rate prediction. Eng Failure Anal. 2015;47:41-48. DOI: 10.1016/j.engfailanal.2014.10.007.
• [24] Kutyłowska M. Prediction of water conduits failure rate - comparison of support vector machine neural network. Ecol Chem Eng A. 2016;23:147-160. DOI: 10.2428/ecea.2016.23(2)11.
• [25] Rojek I, Studziński J. Sieci neuronowe w lokalizacji awarii w sieci wodociągowej (Application of neuronal networks for localization of a failure in the water supply network). Studia i Materiały Informatyki Stosowanej. 2012;9:29-34. http://repozytorium.ukw.edu.pl/handle/item/3539.
• [26] Cieżak W, Siwoń Z, Cieżak J. Zastosowanie sztucznych sieci neuronowych do prognozowania szeregów czasowych krótkotrwałego poboru wody w wybranych systemach wodociągowych (Artificial neural networks for predicting time series of water demand in selected municipal water supply systems). Ochrona Środ. 2006:39-44. http://www.os.not.pl/docs/czasopismo/2006/Ciezak_1-2006.pdf.
• [27] Muszyński K. Metoda sztucznych sieci neuronowych w prognozowaniu bieżącym zapotrzebowania na wodę w Krakowie (Artificial neural network method in current prediction of water demand in Krakow), Rozprawa doktorska (PhD Thesis). Kraków: Politechnika Krakowska im. Tadeusza Kościuszki; 2012. https://suw.biblos.pk.edu.pl/downloadResource&mId=979033.
• [28] Dawidowicz J. Ocena średnic przewodów wodociągowych za pomocą sieci neuronowych Kohonena (Evaluation of water pipe diameters using Kohonen neural networks). J Civil Eng, Environ Architect. 2015;62:43-64. DOI: 10.7862/rb.2015.4.
• [29] Kamiński W, Strumiłło P, Tomczak E. Zastosowanie sztucznej inteligencji w rozwiązywaniu wybranych problemów ochrony atmosfery (Application of artificial intelligence systems for solving some environmental problems). Łódź: PAN Oddział w Łodzi; 2005.
• [30] Osowski S. Sieci neuronowe w ujęciu algorytmicznym (An algorithmic approach to neural networks). Warszawa: WNT; 1996.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).