Determination of Pipe Diameters for Pressurized Irrigation Systems Using Linear Programming and Artificial Neural Networks

Abstract

Pressurized irrigation systems are widespread among other alternatives in Mediterranean countries. Since the initial investment costs of pressurized irrigation systems are quite high, it is crucial to determine design parameters such as pipe diameter. Most of the current optimization techniques for pipe diameter selection are based on linear, non-linear, and dynamic programming models. The ultimate aim of these techniques is to produce solutions to problems with less cost and computation time. In this study, a novel approach for determining pipe diameter was proposed
using Artificial Neural Networks (ANN) as an alternative to existing models. For this purpose, three pressurized irrigation systems were investigated. Different ANN architectures were created and tested using hydrant level parameters of the irrigation systems, such as irrigated area per hydrant, hydrant discharge, pipe length, and hydrant elevation. Different training algorithms, transfer functions, and hidden neuron numbers were tried to determine the best ANN model for each irrigation system. Using multilayer feed-forward ANN architecture, the highest coefficients of determination were found to be 0.97, 0.93, and 0.83 for irrigation systems investigated. It was concluded that pipe diameters could be determined by using artificial neural networks in the planning of pressurized irrigation systems. 

Keywords

• Machine learning
• Optimization techniques
• Irrigation water management
• Network performance analysis
• Hydraulic parameters

References

1. Ait-Kadi M, Abdellaoui R, Oulhaj A & Essafi B (1990). Design of large scale collective sprinkler irrigation projects for an on demand operation: a holistic approach. In Proceedings 14th International Congress on Irrigation and Drainage, Rio de Janeiro, Brazil. (Vol. 1, No. D, pp. 59-78).
2. Alandí PP, Álvarez JO & Martín-Benito JT (2007). Optimization of irrigation water distribution networks, layout included. Agricultural water management, 88(1-3), pp.110-118. doi: 10.1016/j.agwat.2006.10.004
3. Alperovits E & Shamir U (1977). Design of optimal water distribution systems. Water resources research, 13(6), pp.885-900. doi: 10.1029/WR013i006p00885
4. Arsene C T, Gabrys B & Al-Dabass D (2012). Decision support system for water distribution systems based on neural networks and graphs theory for leakage detection. Expert Systems with Applications, 39(18), 13214-13224. doi:10.1016/j.eswa.2012.05.080
5. Beale M H, Hagan M T & Demuth H B (2014). Neural Network Toolbox User’s Guide (pp. 18–19). Natick, MA: The MathWorks Inc.
6. Calejo M J, Lamaddalena N, Teixeira J L & Pereira L S (2008). Performance analysis of pressurized irrigation systems operating on-demand using flow-driven simulation models. Agricultural water management, 95(2), pp.154-162. Doi: 10.1016/j.agwat.2007.09.011
7. Cantos W P & Juran I (2019). Infrastructure aging risk assessment for water distribution systems. Water Supply, 19(3), 899-907. Doi: 10.2166/ws.2018.139
8. Cunha M D C & Sousa J (1999). Water distribution network design optimization: simulated annealing approach. Journal of water resources planning and management, 125(4), pp.215-221. Doi: 10.1061/(ASCE)0733-9496(2001)127:1(69)

9. Czapczuk A & Dawidowicz J (2018). The Application of RBF Neural Networks for the Assessment of the Water Flow Rate in the Pipework. In 2018 2nd International Conference on Artificial Intelligence: Technologies and Applications (ICAITA 2018). Atlantis Press.
10. da Conceicao Cunha M & Ribeiro L (2004). Tabu search algorithms for water network optimization. European Journal of Operational Research, 157(3), pp.746-758. Doi: 10.1016/S0377-2217(03)00242-X
11. Dawidowicz J (2018). A Method for Estimating the Diameter of Water Pipes Using Artificial Neural Networks of the Multilayer Perceptron Type. In 2018 2nd International Conference on Artificial Intelligence: Technologies and Applications (ICAITA 2018). Atlantis Press. Doi: 10.2991/icaita-18.2018.13
12. Dawidowicz J, Czapczuk A & Piekarski J (2018). The application of artificial neural networks in the assessment of pressure losses in water pipes in the design of water distribution systems. Rocznik Ochrona Środowiska, (20), 292-308.
13. Garg V K & Bansal R K (2015). Comparison of neural network back propagation algorithms for early detection of sleep disorders. In 2015 International Conference on Advances in Computer Engineering and Applications (pp. 71-75). IEEE. Doi: 10.1109/ICACEA.2015.7164648
14. Geem Z W, Kim J H & Loganathan G V (2002). Harmony search optimization: application to pipe network design. International Journal of Modelling and Simulation, 22(2), pp.125-133. Doi: 10.1080/02286203.2002.11442233
15. Heaton J (2015). Introduction to Neural Networks for Java: Feedforward Backpropagation Neural Networks. Retrieved from http://www.heatonresearch.com/node/707.
16. Labye Y (1981). Iterative discontinuous method for networks with one or more flow regimes. In Proceedings of the international workshop on systems analysis of problems in irrigation, drainage and flood control. New Delhi, vol. 30, pp. 31-40.
17. Lamaddalena N (1997). Integrated simulation modeling for design and performance analysis of on-demand pressurized irrigation systems. Technical University of Lisbon, PhD, Dissertation. Portugal.
18. Lamaddalena N & Sagardoy J A (2000). Performance analysis of on-demand pressurized irrigation systems. No. 59. Food & Agriculture Org.
19. Lansey K E & Mays L W (1989). Optimization model for water distribution system design. Journal of Hydraulic Engineering, 115(10), pp.1401-1418. Doi: 10.1061/(ASCE)0733-9429(1989)115:10(1401)
20. Lertworasirikul S & Tipsuwan Y (2008). Moisture content and water activity prediction of semi-finished cassava crackers from drying process with artificial neural network. Journal of Food Engineering, 84(1), 65–74. doi:10.1016/j.jfoodeng.2007.04.019.
21. Maier H R, Simpson A R, Zecchin A C, Foong W K, Phang K Y, Seah H Y & Tan C L (2003). Ant colony optimization for design of water distribution systems. Journal of water resources planning and management, 129(3), pp.200-209. Doi: 10.1061/(ASCE)0733-9496(2003)129:3(200)
22. Moreno J J M, Pol A P, Abad A S & Blasco B C (2013). Using the R-MAPE index as a resistant measure of forecast accuracy. Psicothema, 25(4), pp.500-506. Doi: 10.7334/psicothema2013.23
23. Mounce S R & Machell J (2006). Burst detection using hydraulic data from water distribution systems with artificial neural networks. Urban Water Journal, 3(1), 21-31. Doi: 10.1080/15730620600578538
24. Nazghelichi T, Aghbashlo M & Kianmehr M H (2011). Optimization of an artificial neural network topology using coupled response surface methodology and genetic algorithm for fluidized bed drying. Computers and Electronics in Agriculture, 75(1), 84–91. doi:10.1016/j.compag.2010.09.014. Doi: 10.1016/j.compag.2010.09.014
25. Omid M, Mahmoudi A & Omid M H (2009). An intelligent system for sorting pistachio nut varieties. Expert Systems with Applications, 36(9), 11528–11535. doi:10.1016/j.eswa.2009.03.040. Doi: 10.1016/j.eswa.2009.03.040
26. Pakalapati H, Tariq M A & Arumugasamy S K (2019). Optimization and modelling of enzymatic polymerization of ε-caprolactone to polycaprolactone using Candida Antartica Lipase B with response surface methodology and artificial neural network. Enzyme and microbial technology, 122, pp.7-18. Doi: 10.1016/j.enzmictec.2018.12.001
27. Priddy K L & Keller P E (2005). Artificial Neural Networks: An Introduction. Bellingham, Washington, USA: SPIE Tutorial Texts in Optical Engineering.
28. Schaake John C & Fu Hsiung L (1969). Linear programming and dynamic programming application to water distribution network design. MIT Hydrodynamics Laboratory.
29. Shirzad A & Safari M J S (2019). Pipe failure rate prediction in water distribution networks using multivariate adaptive regression splines and random forest techniques. Urban Water Journal, 16(9), 653-661. Doi: 10.1080/1573062X.2020.1713384
30. Sigtia S & Dixon S (2014). Improved music feature learning with deep neural networks. In 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6959-6963). IEEE.
31. Simpson A R, Dandy G C & Murphy L J (1994). Genetic algorithms compared to other techniques for pipe optimization. Journal of water resources planning and management, 120(4), pp.423-443.
32. Ucar M K, Nour M, Sindi H & Polat K (2020). The Effect of Training and Testing Process on Machine Learning in Biomedical Datasets. Mathematical Problems in Engineering, 2020. Doi: 10.1155/2020/2836236
33. Wang W & Paliwal J (2006). Generalisation Performance of Artificial Neural Networks for Near Infrared Spectral Analysis. Biosystems Engineering, 94(1), 7–18. doi:10.1016/j.biosystemseng.2006.02.001. Doi: 10.1016/j.biosystemseng.2006.02.001