Multi-gene GP and GA-FIS models to deal with scaling problem in the ANFIS model for estimating roughness coefficient in erodible channels

Document Type : Article

Author

Department of Civil Engineering, Faculty of Engineering, Environmental Hazard Institute, Golestan University, Golestan, Iran

Abstract

Estimation of the roughness coefficient is important for reliable hydraulic design in erodible channels. In this paper, the capability of multi-gene Genetic Programming (GP), a combined Genetic Algorithm and Fuzzy Inference System (GA-FIS) model, and Multi Regression (MR) methods are employed to estimate the roughness coefficient. These methods try to extract either an explicit or an implicit relationship between the roughness coefficient and input variables. In addition, traditional GP, widely used by researchers, and conventional empirical formulas are implemented to evaluate the models. Results show that the employed methods are more accurate than empirical methods. In addition, the effects of some other parameters, such as non-dimensional water depth and shear Reynolds number, are highlighted over the roughness coefficient while previously ignored in the empirical methods. Also, findings prove that the GA is a helpful tool to optimize a FIS compared with gradient-based models like ANFIS, while the scale of input variables is not in the same order. The R2 for multi-gene GP and GA-FIS are 0.8504 and 0.8842, respectively, while this value for the most accurate empirical method (Yalin, 1992) is 0.6286.

Keywords

References

References:
1. Sumer, B.M., Kozakiewicz, A., Fredse, J., et al. "Velocity and concentration profiles in sheet- flow layer of movable bed", Journal of Hydraulic Engineering, 122(10), pp. 549-558 (1996).
2. Ackers, P. and White, W.R. "Sediment transport: new approach and analysis", Journal of the Hydraulics Division, 99(hy11), pp. 2041-2060 (1973).
3. Simons, D.B. and Richardson, E.V. "Resistance to flow in alluvial channels", US Government Printing Office (1996).
4. Hammond, F.D., Heathershaw, A.D., and Langhorne, D.N. "A comparison between shields threshold criterion and the Henderson movement of loosely packed gravel in a tidal channel", Sedimentology, 31, pp. 51- 62 (1984).
5. Colosimo, C., Copertino, V.A., and Veltri, M. "Average velocity estimation in gravel-bed rivers", In Proc., 5th IAHR-APD Congress, pp. 1-15 (1986).
6. Wilson, K.C. "Mobile-bed friction at high shear stress", Journal of Hydraulic Engineering, 115(6), pp. 825-830 (1989).
7. Yalin, M.S., River Mechanics, Pergamon, First Edition (1992).
8. Shayya, W.H. and Sablani, S.S. "An artificial neural network for non-iterative calculation of the friction factor in pipeline flow", J. of Computers and Electronics in Agriculture, 21(3), pp. 219-228 (1998).
9. Abdeen, M.A.M. "Artificial neutral network model for predicting the impact changing water structures' locations on the hydraulic performance of branched open channel system", J. of Mechanics and Mechanical Engineering, 7(2), pp. 179-192 (2004).
10. Yang, H.C. and Chang, F.J. "Modelling combined open channel  flow by artificial neural networks", Hydrological Processes: An International Journal, 19(18), pp. 3747-3762 (2005).
11. Yuhong, Z. and Wenxin, H. "Application of artificial neural network to predict the friction factor of open channel flow", J. of Communications in Nonlinear Science and Numerical Simulation, 14(5), pp. 2373- 2378 (2009).
12. Zahiri, A. and Dehghani, A.A. "Flow discharge determination in straight compound channels using ANN", J. of World Academy of Science, Engineering and Technology, 58, pp. 12-15 (2009).
13. Bateni, S.M., Borghei, S.M., and Jeng, D.S. "Neural network and neuro-fuzzy assessments for scour depth around bridge piers", J. of Engineering Applications of Artificial Intelligence, 20(3), pp. 401-414 (2007).
14. Begum, S.A., Fujail, A.M., and Barbhuiya, A.K. "Artificial neural network to predict equilibrium local scour depth around semicircular bridge abutments", 6th SASTech, Malaysia, Kuala Lumpur (2012).
15. Ghazanfari-Hashemi, S., Etemad-Shahidi, A., Kazeminezhad, M.H., et al. "Prediction of pile group scour in waves using support vector machines and ANN", J. of Hydroinformatics, 13(4), pp. 609-620 (2011).
16. Kazeminezhad, M.H., Etemad-Shahidi, A., and Bakhtiary, A.Y. "An alternative approach for investigation of the wave-induced scour around pipelines", J. of Hydroinformatics, 12(1), pp. 51-65 (2010).
17. Zanganeh, M., Yeganeh-Bakhtiary, A., and Bakhtyar, R. "Combined particle swarm optimization and fuzzy inference system model for estimation of currentinduced scour beneath marine pipelines", J. of Hydroinformatics, 13(3), pp. 558-573 (2011).
18. Zanganeh, M., Yeganeh-Bakhtiary, A., and Yamashita, T. "ANFIS and ANN models for the estimation of wind and wave-induced current velocities at Joeutsu- Ogata coast", J. of Hydroinformatics, 18(2), pp. 371- 391 (2016).
19. Azamathulla, H.M. and Ahmad, Z. "An expert system for predicting Manning's roughness coefficient in open channels by using gene expression programming", J. of Neural Computing and Applications, 23(5), pp. 1343- 1349 (2013).
20. Roushangar, K., Saghebian, S.M., Kirca, V.S., et al. "Prediction of form roughness coefficient in alluvial channels using efficient hybrid approaches", J. of Soft Computing, 24(24), pp. 18531-18543 (2020).
21. Zanganeh, M. and Rastegar, A. "Estimation of roughness coefficient in erodible channels by ANNs and the ANFIS methods", Amirkabir Journal of Civil Engineering, 52(2), pp. 495-512 (2020).
22. Deo, O., Jothiprakash, V., and Deo, M.C. "Genetic programming to predict spillway scour", Int. J. of Tomography and Statistics, 8, pp. 32-46 (2008).
23. Azamathulla, H.M., Ghani, A.A., Zakaria, N.A., et al. "Genetic programming to predict ski-jump bucket spillway scour", J. of Hydrodynamics, Ser. B., 20(4), pp. 477-484 (2008).
24. Guven, A. and Kisi, O. "Estimation of suspended sediment yield in natural rivers using machine-coded linear genetic programming", J. of Water Resources Management, 25(2), pp. 691-704 (2011).
25. Azamathulla, H.M., Ghani, A.A., Zakaria, N.A., et al. "Genetic programming to predict bridge pier scour", J. of Hydraulic Engineering, 136(3), pp. 165-169 (2009).
26. Azamathulla, H.M., Guven, A., and Demir, Y.K. "Linear genetic programming to scour below submerged pipeline", Ocean Engineering, 38(8), pp. 995-1000 (2011).
27. Najafzadeh, M. and Barani, G.A. "Comparison of group method of data handling based genetic programming and back propagation systems to predict scour depth around bridge piers", Scientia Iranica, 18(6), pp. 1207-1213 (2011).
28. Koc, M.L., Balas, C.E., and Koc, D._I. "Stability assessment of rubble-mound breakwaters using genetic programming", J. of Ocean Engineering, 111, pp. 8-12 (2016).
29. Hermanovsky, M., Havl_Icek, V., Hanel, M., et al. "Regionalization of runoff models derived by genetic programming", Journal of Hydrology, 547, pp. 544- 556 (2017).
30. Assimi, H., Jamali, A., and Nariman-zadeh, N. "Sizing and topology optimization of truss structures using genetic programming", J. of Swarm and Evolutionary Computation, 37, pp. 90-103 (2017).
31. Zanganeh, M. "Simultaneous optimization of clustering and fuzzy IF-THEN rules parameters by the genetic algorithm in fuzzy inference system-based wave predictor models", J. of Hydroinformatics, 19(3), pp. 385-404 (2017).
32. Zanganeh, M. "Improvement of the ANFIS-based wave predictor models by the particle swarm optimization", J. of Ocean Engineering and Science, 5(1), pp. 84-99 (2020).
33. Koza, J.R. "Genetic programming: on the programming of computers by means of natural selection", 1, MIT press (1992).
34. Searson, D.P., Leahy, D.E., and Willis, M.J. "GPTIPS: an open source genetic programming toolbox for multigene symbolic regression", In Proceedings of the International Multiconference of Engineers and Computer Scientists, 1, pp. 77-80 (2010).
35. Zanaganeh, M., Mousavi, S.J., and Shahidi, A.F.E. "A hybrid genetic algorithm-adaptive network-based fuzzy inference system in prediction of wave parameters", Engineering Applications of Artificial Intelligence, 22(8), pp. 1194-1202 (2009).
36. Chiu, S.L. "Fuzzy model identification based on cluster estimation", J. of Intelligent Fuzzy Systems, 2, pp. 267-278 (1994).
37. Jang, J.S.R. "ANFIS adaptive-network-based fuzzy inference systems", IEEE Trans System Man Cybern, 23(3), pp. 665-685 (1993).
38. Chipperfield, A., Fleming, P., Pohlheim, H., et al. Genetic algorithm toolbox for use with MATLAB (1994). 
Scientia Iranica
Volume 30, Issue 6
Transactions on Civil Engineering (A)
November and December 2023
Pages 1925-1941

Files

History

  • Receive Date: 07 April 2022
  • Revise Date: 21 June 2022
  • Accept Date: 18 January 2023

Share

How to cite

Statistics