Pipe Failure Rate Prediction In Water Distribution Networks Using RCNN-SVR and FCMR Methods

Subject Areas : Article frome a thesis

mehdi momeni regh abadi ¹ , Ahmad Ravanbakhsh ² , Amir Robati ³

1 - Department of Civil Engineering, Kerman Branch, Islamic Azad University, Kerman, Iran
2 - Department of Civil Engineering, Kerman Branch, Islamic Azad University, Kerman, Iran
3 - Department of Civil Engineering, Kerman Branch, Islamic Azad University, Kerman, Iran

Received: 2021-03-11 Accepted : 2021-09-01 Published : 2024-01-21

Keywords: Water distribution network, Fuzzy, Artificial Intelligence, pipe burst, burst rate,

Abstract :

Abstract
Introduction: It is essential to optimize repair, reconstruction and rehabilitation programs of urban water distribution networks for the correct use of limited water resources. The aim of the present study is to implement and compare two artificial intelligence methods to predict the burst rate of water pipes.
Methods: In this article, dataset of the pipe bursts in Joopar water network from 2012 to 2017 has been collected. The parameters for predicting of pipe failure includes: material, age, diameter, water pressure and installation depth, and the correlation coefficient of these parameters with the failure rate has been investigated. In order to predict the failure rate, convolution neural network with support vector machine (RCNN-SVR) and fuzzy regression based on c mean clustering (FCMR) have been used. To compare the performance of these two methods, the criteria such as Root-Mean Squared Error (RMSE), Index Of Agreement (IOA), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R²) have been used.
Findings: According to the evaluations, RCNN-SVR method compared to FCMR method shows excellent results. Also, the correlation between age and failure rate in asbestos pipes is high and in polyethylene pipes this value is positive but low. The correlation coefficient between pressure and failure rate is also positive for both pipe types.

References:

1.        ASCE. 2017. 2017 Report Card for America’s Infrastructure, Drinking Water. American Society of Civil Engineers.

2.        Watson, T. G., C. D. Christian, A. J. Mason, M. H. Smith, and R. Meyer. 2004. Bayesian-Based Pipe Failure Model. Journal of Hydroinformatics 6(4):259–64.

3.        Pelletier, Geneviève, Alain Mailhot, and Jean-Pierre Villeneuve. 2003. Modeling Water Pipe Breaks—Three Case Studies. Journal of Water Resources Planning and Management 129(2):115–23.

4.       Asnaashari, A., 2007. Water pipeline failure modeling: statistical, artificial neural network and survival modeling, PhD. Thesis, University of Science and Technology of Lille.

5.       Soltani, J and Mohammad Rezapour Tabari, M., 2011. Determination of Effective Parameters in Pipe Failure Rate in Water Distribution System Using the Combination of Artificial Neural Networks and Genetic Algorithm. Journal of water and wastewater. [In Persian].

6.        Dridi, Leila, Alain Mailhot, Marc Parizeau, and Jean-Pierre Villeneuve. 2009. Multiobjective Approach for Pipe Replacement Based on Bayesian Inference of Break Model Parameters. Journal of Water Resources Planning and Management 135(5):344–54.

7.       Roozbahani, A., 2012. Risk-based decision making model for urban water systems management . PhD. Thesis, University of Tehran. [In Persian].

8.       Randall-Smith, M., A. Russell, and R. Oliphant. 1992. Guidance Manual for the Structural Condition Assessment of the Trunk Mains. Swindon, UK: Water Research Centre.

9.        Kutyłowska, Małgorzata. 2019. Application of MARSplines Method for Failure Rate Prediction. Periodica Polytechnica Civil Engineering 63(1):87–92.

 

10.    Achim, D., F. Ghotb, and K. J. McManus. 2007. Prediction of Water Pipe Asset Life Using Neural Networks. Journal of Infrastructure Systems 13(1):26–30.

11.   Kutylowska, M. 2017. Regression Methods for Predicting Rate and Type of Failures of Water Conduits. Ecological Chemistry and Engineering A 24 (2): 193–205.

12.    Kutyłowska, M. 2019. Forecasting Failure Rate of Water Pipes. Water Science and Technology: Water Supply 19(1):264–73.

13.    Rajani, B., and S. Tesfamariam. 2007. Estimating Time to Failure of Cast-Iron Water Mains. Proceedings of the Institution of Civil Engineers: Water Management 160(2):83–88.

14.    Christodoulou, Symeon, Pooyan Aslani, and Annie Vanrenterghem. 2003. A Risk Analysis Framework for Evaluating Structural Degradation of Water Mains in Urban Settings, Using Neurofuzzy Systems and Statistical Modeling Techniques. Pp. 681–89 in World Water and Environmental Resources Congress.

15.    Tabesh, M., J. Soltani, R. Farmani, and D. Savic. 2009. Assessing Pipe Failure Rate and Mechanical Reliability of Water Distribution Networks Using Data-Driven Modeling. Journal of Hydroinformatics 11(1):1–17.

16.    Berardi, L., O. Giustolisi, Z. Kapelan, and D. A. Savic. 2008. Development of Pipe Deterioration Models for Water Distribution Systems Using EPR. Journal of Hydroinformatics 10(2):113–26.

17.    Konstantinou, Charalampos, and Ivan Stoianov. 2020. A Comparative Study of Statistical and Machine Learning Methods to Infer Causes of Pipe Breaks in Water Supply Networks. Urban Water Journal 17(6):534–48.

18.    Snider, Brett, and Edward A. McBean. 2020. Improving Urban Water Security through Pipe-Break Prediction Models: Machine Learning or Survival Analysis. Journal of Environmental Engineering 146(3).

19.    Zhou, Xiao, Zhenheng Tang, Weirong Xu, Fanlin Meng, Xiaowen Chu, Kunlun Xin, and Guangtao Fu. 2019. Deep Learning Identifies Accurate Burst Locations in Water Distribution Networks. Water Research 166.

20.   Zhang Youshan, Guo Liangdong, Li Qi, and Li Junhui. 2019. Electricity consumption forecasting method based on mpso-bp neural network model. PROCEEDINGS OF THE 2019 4TH INTERNATIONAL CONFERENCE ON ELECTRICAL ELECTRONICS ENGINEERING AND COMPUTER SCIENCE (ICEEECS 2016), 50:674-678, 2019.

21.   Vapnik V., 1995. The nature of statistical learning theory, Springer-Verlag, New-York.

22.    Vapnik, Vladimir N. 1999. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks 10(5): 988–99.

23.   Vapnik V., 1998. The support vector method of function estimation, In Nonlinear Modeling: advanced black-box techniques, Suykens J.A.K., Vandewalle J. (Eds.), Kluwer Academic Publishers, Boston, pp.55-85.

24.    Hathaway, Richard J., and James C. Bezdek. 1993. Switching Regression Models and Fuzzy Clustering. IEEE Transactions on Fuzzy Systems 1(3):195–204.

25.    Bezdek, James C., Robert Ehrlich, and William Full. 1984. FCM: The Fuzzy c-Means Clustering Algorithm. Computers and Geosciences 10(2–3):191–203.

26.   Bezdek, J.C., 1981. Pattern Recognition with Fuzzy Objective Function Algorithm, New York: Plenum Press.

27.   Dave, R.N., 1992. Boundary detection through fuzzy clustering. IEEE International Conference on Fuzzy Systems. pp. 127-134.

28.    Ali, Ameer M.; Karmakar, Gour C. and Dooley, Laurence S. 2008. Review on Fuzzy Clustering Algorithms. Journal of Advanced Computations, 2(3) pp. 169–181.