|
|
Publications
Xu, H.T. and Guedes Soares, C. (2023), Data-driven parameter estimation of nonlinear ship manoeuvring model in shallow water using Truncated Least Squares Support Vector Machines, Journal of Marine Science and Engineering, Vol. 11, 1865
A data-driven method, truncated LS-SVM, is proposed to estimate the nondimensional hydrodynamic coefficients of a nonlinear manoeuvring model. Experimental data obtained in a shallow water towing tank is used in the study. To validate the accuracy and robustness of the proposed truncated LS-SVM, different sizes of the test data are chosen as the training set, and the identified nondimensional hydrodynamic coefficients are presented, as well as the corresponding parameter uncertainty and confidence intervals. The validation has been carried out using reference data, and statistical measures, such as the correlation coefficient, centred RMS difference and standard deviation, are employed to quantify the similarity. The results show that the Truncated LS-SVM method is capable of modelling problems with a large-scale training set, and using a large scaled training set can diminish the parameter uncertainty and provide a more convincing result.
If you did not manage to obtain a copy of this paper: Request a copy of this article
For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications
|