Estimation of the hydrodynamic coefficients from captive model test results by using support vector machines

Abstract A novel method of artificial intelligence technology, support vector machines (SVM) is proposed for estimation of the hydrodynamic coefficients in the mathematical models of ship manoeuvring motion from captive model test results, including oblique towing test and pure sway test results. By analyzing the captive model test results, SVM is used to identify the hydrodynamic coefficients, which are obtained from the expansion of the inner product of a linear kernel function. To get rid of the influence of parameter drift in the estimation of the hydrodynamic coefficients from pure sway test results, an equivalent transformation is made for the hydrodynamic mathematical model. The hydrodynamic forces under different operating conditions are predicted by using the identified hydrodynamic mathematical model. Comparison between the predicted hydrodynamic forces and the test results shows that the identified hydrodynamic mathematical model has good generalization performance and SVM is an effective method for estimating the hydrodynamic coefficients from captive model test results.