Below the Data Range Prediction of Soft Computing Wave Reflection of Semicircular Breakwater

Abstract

Coastal defenses such as the breakwaters are important structures to maintain the navigation conditions in a harbor. The estimation of their hydrodynamic characteristics is conventionally done using physical models, subjecting to higher costs and prolonged procedures. Soft computing methods prove to be useful tools, in cases where the data availability from physical models is limited. The present paper employs adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) models to the data obtained from physical model studies to develop a novel methodology to predict the reflection coefficient (K _r) of seaside perforated semicircular breakwaters under low wave heights, for which no physical model data is available. The prediction was done using the input parameters viz., incident wave height (H _i), wave period (T), center-to-center spacing of perforations (S), diameter of perforations (D), radius of semicircular caisson (R), water depth (d), and semicircular breakwater structure height (h _s). The study shows the prediction below the available data range of wave heights is possible by ANFIS and ANN models. However, the ANFIS performed better with R ² = 0.9775 and the error reduced in comparison with the ANN model with R ² = 0.9751. Study includes conventional data segregation and prediction using ANN and ANFIS.

Keywords

Semicircular breakwater / Wave reflection / Below the data range / Artificial neural network / Adaptive neuro-fuzzy inference system

References

[1] Al-hmouz A, Shen J, Al-Hmouz R, Yan J. Modeling and simulation of an adaptive neuro-fuzzy inference system (ANFIS) for mobile learning. IEEE Trans Learn Technol, 2012, 5(3): 226-237

[2] Azmathulla HMD, Ghani Ab A. ANFIS-based approach for predicting the scour depth at culvert outlets. J Pipeline Syst Eng Pract, 2011, 2(1): 35-40

[3] Chiu S. Fuzzy model identification based on cluster estimation. J Intell Fuzzy Syst, 1994, 2(3): 267-278

[4] Chiu S (1996) Method and software for extracting fuzzy classification rules by subtractive clustering. North American Fuzzy Information Processing Society Conf. (NAFIPS'96), Berkeley, 19–22. https://doi.org/10.1109/NAFIPS.1996.534778

[5] Dattatri J. Waves off Mangalore harbour-west coast of India. J Waterw Port Coast Ocean Eng, ASCE, 1993, 99(2): 39-57

[6] Deo MC. Artificial neural networks in coastal and ocean engineering. Indian J Mar Sci, 2010, 39(4): 589-596

[7] Dhinakaran G, Sundar V, Sundaravadivelu R, Graw KU. Effect of perforations and rubble mound height on wave transformation characteristics of surface piercing semicircular breakwaters. Ocean Eng, 2009, 36: 1182-1198

[8] Erdik T, Savci ME, Sen Z. Artificial neural network for predicting maximum wave runup on rubble mound structures. Expert Syst Appl, 2009, 36(3): 6403-6408

[9] Goyal R, Singh K, Hegde AV. Quarter circular breakwater : prediction and artificial neural network. Mar Technol Soc J, 2014, 48: 1-7

[10] Harish N, Mandal S, Rao S, Patil SG. Particle Swarm Optimization based support vector machine for damage level prediction of non-reshaped berm breakwater. Appl Soft Comput, 2015, 27: 313-321

[11] Hiremath S, Patra SK (2010) Transmission rate prediction for cognitive radio using adaptive neural fuzzy inference system. Proc IEEE Ind Inf Syst Conf Mangalore, India, p 92–97

[12] Issacson M. Measurement of regular wave reflection. J Waterway Port Coastal Ocean Eng ASCE, 1991, 117(6): 553-569

[13] Jabbari E, Talebi O. Using artificial neural networks for estimation of scour at the head of vertical wall breakwater. J Coast Res, 2011, SI 64(ICS2011): 521-526

[14] Jain P, Deo MC (2008) Artificial neural networks for coastal and ocean studies. 12th Int Conf Int Assoc Comput Methods Adv Geomech, Goa, India, p 1655–1663

[15] Janardhan P, Harish N, Rao S, Shirlal KG. Performance of variable selection method for the damage level prediction of reshaped berm breakwater. Aquat Procedia, 2015, 4: 302-307

[16] Jang JR. ANFIS : adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern, 1993, 23(3): 665-685

[17] Karsoliya S. Approximating number of hidden layer neurons in multiple hidden layer BPNN. Architecture Int J Eng Trends Technol, 2012, 6: 714-717

[18] Kim DH, Kim YJ, Hur DS. Artificial neural network based breakwater damage estimation considering tidal level variation. Ocean Eng, 2014, 87: 185-190

[19] Kudumula SR, Mutukuru MRG. Experimental studies on low crested rubble mound, semicircular breakwaters and vertical wall system. Int J Ocean Climate Syst, 2013, 4(3): 213-226 http://journals.sagepub.com/doi/abs/10.1260/1759-3131.4.3.213

[20] Kundapura S, Hegde AV, Wazerkar AV (2019) Beyond the data range approach to soft compute the reflection coefficient for emerged perforated semicircular breakwater, In: Murali K, Sriram V, Samad A, Saha N (eds) Proceedings of the Fourth International Conference in Ocean Engineering (ICOE2018). Lecture Notes in Civil Engineering, vol 23. Springer, p 281–292

[21] Lee A, Kim SE, Suh KD. Estimation of stability number of rock armor using artificial neural network combined with principal component analysis. Procedia Eng, 2015, 116: 149-154

[22] Mandal S, Patil S, Hegde AV (2009) Wave transmission prediction of multilayer floating breakwater using neural network. Proc 3rd International Conference in Ocean Engineering, ICOE-2009, IIT Madras, Chennai, p 574–585

[23] Mohammady S. Optimization of adaptive neuro-fuzzy inference system based urban growth model. City Territ Archit, 2016, 3(10): 1-15

[24] Mohan RU, Sood YR, Jarial RK. Subtractive clustering fuzzy expert system for engineering applications. Procedia Comput Sci, 2015, 48(C): 77-83

[25] Nishanth N (2008) Hydrodynamic performance characteristics of semicircular breakwaters. Master Thesis, National Insitutute of Technology Karnataka, Surathkal, Mangaluru, India, Appendix 5–13

[26] Panchal FS, Panchal M. Review on methods of selecting number of hidden nodes in artificial neural network. Int J Comput Sci Mob Comput, 2014, 3(11): 455-464

[27] Patil SG, Mandal S, Hegde AV, Alavandar S. Neuro-fuzzy based approach for wave transmission prediction of horizontally interlaced multilayer moored floating pipe breakwater. Ocean Eng, 2011, 38: 186-196

[28] Raju B, Hegde AV, Chandrashekar O. Computational intelligence on hydrodynamic performance characteristics of emerged perforated quarter circle breakwater. Procedia Eng, 2015, 116: 118-124

[29] Ratrout NT. Subtractive clustering-based K -means technique for determining optimum time-of-day breakpoints. J Comput Civ Eng, 2011, 25(5): 380-387

[30] Sooraj M (2009) Sliding stability and hydrodynamic performance of emerged semicircular breakwater, Master Thesis, NITK, Surathkal, Mangaluru, India, AppendixII, 96–102

[31] Sreejith KU (2015) Sliding stability and hydrodynamic performance of emerged semicircular breakwater, Master Thesis, NITK, Surathkal, Mangaluru, India, Appendix 95–104

[32] Tiwari S, Babbar R, Kaur G. Performance evaluation of two ANFIS models for predicting water quality index of river Satluj (India). Adv Civil Eng, 2018, 2018: 8971079

[33] Vishal K (2010) Hydrodynamic performance characteristics of one side and two side perforated semicircular breakwater. Master Thesis, NITK, Surathkal, Mangaluru, India, Appendix I, 79–83

[34] Yagci O, Mercan DE, Cigizoglu HK, Kabdasli MS. Artificial intelligence methods in breakwater damage ratio estimation. Ocean Eng, 2005, 32: 2088-2106

[35] Zanuttigh B, Mizar S, Briganti R. A neural network for the prediction of wave reflection from coastal and harbor structures. Coast Eng, 2013, 80: 49-67

[36] Zhou Q, Wang F, Zhu F. Estimation of compressive strength of hollow concrete masonry prisms using artificial neural networks and adaptive neuro-fuzzy inference systems. Constr Build Mater, 2016, 125: 417-426