Comparison of Artificial Neural Networks and Genetic Algorithms for Predicting Liquid Sloshing Parameters

Abstract

This paper develops a numerical code for modelling liquid sloshing. The coupled boundary element-finite element method was used to solve the Laplace equation for inviscid fluid and nonlinear free surface boundary conditions. Using Nakayama and Washizu’s results, the code performance was validated. Using the developed numerical mode, we proposed artificial neural network (ANN) and genetic algorithm (GA) methods for evaluating sloshing loads and comparing them. To compare the efficiency of the suggested methods, the maximum free surface displacement and the maximum horizontal force exerted on a rectangular tank’s perimeter are examined. It can be seen from the results that both ANNs and GAs can accurately predict η _max and F _max.

Keywords

Sloshing loads / Fluid structure interactions / Potential flow analysis / Artificial neural network / Genetic algorithm

References

[] Ahn Y, Kim Y, Kim SY. Database of model-scale sloshing experiment for LNG tank and application of artificial neural network for sloshing load prediction. Marine Structures, 2019, 66: 66-82,

[] Cetin EC, Lee J, Kim S, Kim Y. Prediction of extreme sloshing pressure using different statistical models. Journal of Advanced Research in Ocean Engineering, 2018, 4(4): 185-194

[] Chen J, Lin Y, Zhou HJ, Xia ZM, Zhuo SJ. Optimization of ship’s subdivision arrangement for offshore sequential ballast water exchange using a non-dominated sorting genetic algorithm. Ocean Engineering, 2010, 37: 978-988,

[] Chen X, Diez M, Kandashamy M, Zhang Z, Campana E, Stern F. High-fidelity global optimization of shape design by dimensionality reduction, metamodels and deterministic particle swarm. Engineering Optimization, 2014 Abingdon, UK Taylor & Francis 473-494

[] Forrest S (1993) Genetic Algorithms: principles of natural selection applied to computation. Science 261

[] Gran S. Statistical distributions of local impact pressures. Norweg Marit Res, 1981, 8(2): 2-13

[] Graupe D (2007) Principles of Artificial Neural Networks. World Scientific Publisher, Advanced Series on Circuits and Systems 6. https://doi.org/10.1142/8868

[] Grazcyk M, Moan T. A probabilistic assessment of design sloshing pressure time histories in LNG tanks. Ocean Engineering, 2008, 35: 834-855,

[] Harries S, Abt C. CAESES—The HOLISHIP platform for process integration and design optimization. A Holistic Approach to Ship Design, 2019 Berlin/Heidelberg, Germany Springer 276-291

[] Jin Y, Liu X, Qiu W, Hou C. Time-varying sliding mode controls in rigid spacecraft attitude tracking. Chinese Journal of Aeronautics, 2008, 21: 352-360,

[] Ketabdari MJ, Saghi H. Numerical analysis of trapezoidal storage tank due to liquid sloshing phenomenon. Iranian Journal of Marine Science and Technology, 2012, 18(61): 33-39

[] Ketabdari MJ, Saghi H. Parametric study for optimization of storage tanks considering sloshing phenomenon using coupled BEM–FEM. Applied Mathematics and Computation, 2013, 224: 123-139,

[] Ketabdari MJ, Saghi H. Numerical study on behavior of the trapezoidal storage tank due to liquid sloshing impact. International journal of Computational Methods, 2013, 10(6): 1-22,

[] Kuzniatsova M, Shimanovsky A. Definition of rational form of lateral perforated baffle for road tanks. Procedia Engineering, 2016, 134: 72-79,

[] Li HT, Jing L, Zong Z, Chen Z. Numerical studies on sloshing in rectangular tanks using a tree-based adaptive solver and experimental validation. Ocean Engineering, 2014, 82: 20-31,

[] Mizumura K. Application of Kalman filtering to ocean data. Journal of Waterway, Port, Coastal. And Ocean. Engineering, ASCE, 1984, 110(3): 334-343

[] Nakayama T, Washizu K. Bauerjee PK, Mukherjee S. Boundary element analysis of nonlinear sloshing problems. Published in Developments in Boundary Element Method-3, 1984 New York Elsevier Applied Science Publishers

[] Núñez J, Cruchaga M, Tampier G. Wave analysis based on genetic algorithms using data collected from laboratories at different scales. European Journal of Mechanics-B/Fluids, 2022, 95: 231-239,

[] Saghi H. The pressure distribution on the rectangular and trapezoidal storage tanks’ perimeters due to liquid sloshing phenomenon. International Journal of Naval Architecture and Ocean Engineering, 2016, 8(12): 153-168,

[] Saghi H, Lakzian E. Optimization of the rectangular storage tanks for the sloshing phenomena based on the entropy generation minimization. Energy, 2017, 128: 564-574,

[] Saghi H, Mikkola T, Hirdaris S. The influence of obliquely perforated dual baffles on sway induced tank sloshing dynamics. Proceedings of the institution of Mechanical Engineerings, Part M: Journal of Engineering for the Maritime Environment, 2021, 235(4): 905-920

[] Saltari F, Pizzoli M, Gambioli F, Jetzschmann C, Mastroddi F. Sloshing reduced-order model based on neural networks for aeroelastic analyses. Aerospace Science and Technology, 2022, 127: 107708,

[] Sclavounos P, Yu M (2018) Artificial Intelligence machine Learning in marine Hydrodynamics. Proceedings of the International Conference on Ocean, Offshore and Arctic Engineering, Madrid, Spain

[] Talebitooti R, Shojaeefard MH, Yarmohammadisatri S. Shape design optimization of cylindrical tank using b-spline curves. Computers & Fluids, 2015, 109: 100-112,

[] Volpi S, Gaul N, Diez M, Song H, Iema U, Campana E, Choi K, Stern F. Development and validation of a dynamic metamodel based on stochastic radial basis functions and uncertainty quantification. Struct. Multidiscip Optim, 2015, 51: 347-368,

[] Wu CH, Faltinsen OM, Chen BF. Numerical study of sloshing liquid in tanks with baffles by time-independent finite difference and fictitious cell method. Computers & Fluids, 2012, 63: 9-26,

[] Yen PH, Jan CD, Lee YP, Lee HF. Application of Kalman filter to short-term tide level prediction. Journal of Waterway, Port, Coastal and Ocean Engineering, ASCE, 1991, 122(5): 226-231,

[] Zhang C. Application of an improved semi-Lagrangian procedure to fully nonlinear simulation of sloshing in non-wall-sided tanks. Applied Ocean Research, 2015, 51: 74-92,

[] Zhao Y, Chen HC. Numerical simulation of 3D sloshing flow in partially filled LNG tank using a coupled level-set and volume-of-fluid method. Ocean Engineering, 2015, 104: 10-30,