An effective approach for VARANS-VOF modelling interactions of wave and perforated breakwater using gradient boosting decision tree algorithm
Dang, B.-L.; Nguyen-Xuan, H.; Wahab, M.A. (2023). An effective approach for VARANS-VOF modelling interactions of wave and perforated breakwater using gradient boosting decision tree algorithm. Ocean Eng. 268: 113398. https://dx.doi.org/10.1016/j.oceaneng.2022.113398
In: Ocean Engineering. Pergamon: Elmsford. ISSN 0029-8018; e-ISSN 1873-5258, meer
In this paper, we propose a systematic and time-efficient approach to calibrate 2D VARANS-VOF models for simulation of wave interaction with porous plate in numerical wave tank. To reach this goal, we develop a data-driven approach in combination with numerical and experimental data to figure out the optimal empirical coefficient associated with linear and non-linear drag force coefficients (α, β). Advanced gradient boosting decision trees algorithms (GBDT) are adopted to capture the accuracy of the prediction model. Although only limited samples, for instance 72 samples are generated and chosen to train and test the prediction model, the GBDT model is able to identify the trend in non-linear influence of model parameters. The advantage of GBDT algorithm can obviously be seen through the regression analysis with very high regression coefficient (R2 > 0.99). The developed model is subsequently employed for a large range of considered parameters as input features of the models to predict the possible hydrodynamics characteristics. The smallest mean squared error between predicted and experimental results, which is 0.00204, is found and used to determine the best performing combination of these model parameters. The numerical model together with selected values of empirical coefficients is then validated using available experimental data in literature. The free surface elevations in front of and behind the structure from the numerical model are nearly identical with the experimental data.
Alle informatie in het Integrated Marine Information System (IMIS) valt onder het VLIZ Privacy beleid
