Support　Vector　Machines　(SVM)　based　system　identification　is　proposed　to　determine　the　hydrodynamic　coefficients　in　the　mathematical　model　of　ship　manoeuvring　motion.　To　reduce　the　complexity　of　the　mathematical　model,　sensitivity　analysis　is　performed.　Particle　Swarm　Optimization　(PSO)　is　employed　to　obtain　the　optimal　regularization　factor　in　SVM.　Combined　with　free　model　tests,　the　hydrodynamic　coefficients　are　identified　by　using　the　optimized　SVM.　Comparison　between　the　prediction　results　and　the　test　results　demonstrates　the　validity　of　the　modeling　method　proposed.