Extreme learning machine model for water network management
- 187 Downloads
A novel failure rate prediction model is developed by the extreme learning machine (ELM) to provide key information needed for optimum ongoing maintenance/rehabilitation of a water network, meaning the estimated times for the next failures of individual pipes within the network. The developed ELM model is trained using more than 9500 instances of pipe failure in the Greater Toronto Area, Canada from 1920 to 2005 with pipe attributes as inputs, including pipe length, diameter, material, and previously recorded failures. The models show recent, extensive usage of pipe coating with cement mortar and cathodic protection has significantly increased their lifespan. The predictive model includes the pipe protection method as pipe attributes and can reflect in its predictions, the effect of different pipe protection methods on the expected time to the next pipe failure. The developed ELM has a superior prediction accuracy relative to other available machine learning algorithms such as feed-forward artificial neural network that is trained by backpropagation, support vector regression, and non-linear regression. The utility of the models provides useful inputs when planning and budgeting for watermain inspection, maintenance, and rehabilitation.
KeywordsWater pipe network Pipe failure Extreme machine learning Management tool
The authors would like to thank the district of Scarborough for their contribution in the data collection phase and funding by the Natural Sciences and Engineering Research Council of Canada and the Canada Research Chairs program.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- 8.Atieh, M., Taylor, G., Sattar, A. M., & Gharabaghi, B. (2017). Prediction of flow duration curves for ungauged basins. Journal of Hydrology. Volume 545, February 2017, Pages 383–394, DOI: 10.1016/j.jhydrol.2016.12.048.
- 12.Ertugrul O, Kaya M (2014) A detailed analysis on extreme learning machine and novel approaches based on ELM. American Journal of Computer Science and Engineering 1(5):43–50Google Scholar
- 13.Gazendam, E., Gharabaghi, B., Ackerman, J., & Whiteley, H. (2016). Integrative neural networks models for stream assessment in restoration projects. Journal of Hydrology, 536 (2016) 339-350. DOI: 10.1016/j.jhydrol.2016.02.057.
- 14.Lian C, Zeng Z, Yao W, Tang H (2014) Ensemble of extreme learning machine for landslide displacement prediction based on time series analysis. Neural Comput & Applic 24(1). doi: 10.1007/s00521
- 32.Walker H (1931) Studies in the history of the statistical method. Williams & Wilkins Co., Baltimore, MD, pp 24–25Google Scholar
- 33.Folkman S (2012) Water main break rates in the USA and Canada: a comprehensive study, report, Utah State University buried structures laboratory, April 2012.Google Scholar
- 41.Asnaashari A, McBean E, Gharabaghi B, Pourrajab R, Shahrour I (2010) Survival rate analyses of watermains: a comparison of case studies for Canada and Iran. Journal of Water Management Modeling 18(30):499–508Google Scholar
- 43.Rostum J (2000) Master of Science Dissertation. In: Statistical modeling of pipe failures in water networks. Norwegian University of Science and Technology, Trondheim, NorwayGoogle Scholar
- 44.Lei J (1997) Statistical approach for describing lifetimes of water mains - case Trondheim Municpality. STF22 A97320, SINTEF, Trondheim.Google Scholar
- 45.Wang Y, Moselhi O, Zayed T (2009) Study of the suitability of existing deterioration models for water mains. Journal of Performance of Constructed Facilities, ASCE 23(1):40–46Google Scholar
- 47.Sattar AMA, El-Beltagy M (2017) Stochastic Solution to the Water Hammer Equations Using Polynomial Chaos Expansion with Random Boundary and Initial Conditions. J Hydraul Eng 143(2):04016078Google Scholar
- 48.Ebtehaj I, Sattar AMA, Bonakdari H, Zaji AH (2017) Prediction of scour depth around bridge piers using self-adaptive extreme learning machine. J Hydroinf 19(2):207–224Google Scholar