Optimization of ANFIS Network Using Particle Swarm Optimization Modeling of Scour around Submerged Pipes

Abstract

In general, submerged pipes passing over the sedimentary bed of seas are installed for transmitting oil and gas to coastal regions. The stability of submerged pipes can be threatened with waves and coastal flows occurring at coastal regions. In this study, for the first time, the adaptive neuro-fuzzy inference system (ANFIS) is optimized using the particle swarm optimization (PSO) algorithm, and a meta-heuristic artificial intelligence model is developed for simulating the scour pattern around submerged pipes located in sedimentary beds. Afterward, six ANFIS-PSO models are developed by means of parameters affecting the scour depth. Then, the superior model is detected through sensitivity analysis. This model has the function of all input parameters. The calculated correlation coefficient and scatter index for this model are 0.993 and 0.047, respectively. The ratio of the pipe distance from the sedimentary bed to the submerged pipe diameter is introduced as the most effective input parameter. PSO significantly improves the performance of the ANFIS model. Approximately 36% of the scour depths simulated using the ANFIS model have an error less than 5%, whereas the value for ANFIS-PSO is roughly 72%.

Keywords

Adaptive neuro-fuzzy inference system (ANFIS) / Meta-heuristic model / Particle swarm optimization (PSO) / Scour around submerged pipes / Coastal regions

References

[1] Azamathulla HM, Ab Ghani A. Genetic programming to predict river pipeline scour. Pipeline Syst Eng Pract, 2012, 1(3): 127-132

[2] Azamathulla HM, Yusoff MAM, Hasan ZA. Scour below submerged skewed pipeline. Hydrology, 2014, 509: 615-620

[3] Azimi H, Shiri H. Ice-seabed interaction analysis in sand using a gene expression programming-based approach. Appl Ocean Res, 2020, 98: 102120

[4] Azimi H, Bonakdari H, Ebtehaj I, Talesh SHA, Michelson DG, Jamali A. Evolutionary Pareto optimization of an ANFIS network for modeling scour at pile groups in clear water condition. Fuzzy Sets Syst, 2017, 319: 50-69

[5] Azimi H, Bonakdari H, Ebtehaj I. Design of radial basis function-based support vector regression in predicting the discharge coefficient of a side weir in a trapezoidal channel. Appl Water Sci, 2019, 9(4): 78

[6] Azimi H, Bonakdari H, Ebtehaj I, Shabanlou S, Talesh SHA, Jamali A (2019b) A pareto design of evolutionary hybrid optimization of ANFIS model in prediction abutment scour depth. Sādhanā 44(7):169

[7] Bonakdari H, Ebtehaj I. Scour depth prediction around bridge piers using neuro-fuzzy and neural network approaches. Int J Civil Environ Eng, 2017, 11(6): 835-839

[8] Brørs B. Numerical modeling of flow and scour at pipelines. Hydraulic Eng, 1999, 125(5): 511-523

[9] Chiew YM. Effect of spoilers on wave-induced scour at submarine pipelines. Waterway Port Coastal Ocean Eng, 1993, 119(4): 417-428

[10] Dey S, Singh NP. Clear-water scour below underwater pipelines under steady flow. Hydraulic Eng, 2008, 134(5): 588-600

[11] Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory. In Micro Machine and Human Science, Proceedings of the Sixth International Symposium on IEEE, 39-43. https://doi.org/10.1109/MHS.1995.494215

[12] Etemad-Shahidi A, Yasa R, Kazeminezhad MH. Prediction of wave-induced scour depth under submarine pipelines using machine learning approach. Appl Ocean Res, 2011, 33(1): 54-59

[13] Fredsoe J, Hansen EA, Mao Y, Sumer BM. Three-dimensional scour below pipelines. Offshore Mechan Arctic Eng, 1988, 110(4): 373-379

[14] Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Systems, Man, Cybern 23(3):665–685. https://doi.org/10.1109/21.256541

[15] Moncada-M AT, Aguirre-Pe J. Scour below pipeline in river crossings. Hydraulic Eng, 1999, 125(9): 953-958

[16] Myrhaug D, Rue H. Scour below pipelines and around vertical piles in random waves. Coast Eng, 2003, 48(4): 227-242

[17] Najafzadeh M, Barani GA, Azamathulla HM (2014a) Prediction of pipeline scour depth in clear-water and live-bed conditions using group method of data handling. Neural Comput Applic 24(3–4):629–635. https://doi.org/10.1007/s00521-012-1258-x

[18] Najafzadeh M, Barani GA, Hessami Kermani MR. Estimation of pipeline scour due to waves by GMDH. Pipeline Syst Eng Pract, 2014, 5(3):

[19] Shabanlou S, Azimi H, Ebtehaj I, Bonakdari H. Determining the scour dimensions around submerged vanes in a 180 bend with the gene expression programming technique. J Mar Sci Appl, 2018, 17(2): 233-240

[20] Sumer M, Fredsoe J. Scour below pipelines in waves. Waterway Port Coastal Ocean Eng, 1990, 116(3): 307-323

[21] Sumer BM, Truelsen C, Sichmann T, Fredsøe J. Onset of scour below pipelines and self-burial. Coast Eng, 2001, 42(4): 313-335

[22] Teh TC, Palmer AC, Bolton MD, Damgaard JS. Stability of submarine pipelines on liquefied sea beds. Waterway Port Coastal Ocean Eng, 2006, 132(4): 244-251

[23] Wu Y, Chiew YM. Three-dimensional scour at submarine pipelines. Hydraulic Eng, 2012, 138(9): 788-795