Investigation of steering dynamics ship model identification based on PSO-LSSVR

According to the high-order nonlinearity and parameter uncertainty of the ship steering dynamics, it is difficult to establish the accurate mathematical model by using normal identification methods. To solve this problem, a new kind of Least Squares Support Vector Regression based on the Particle Swarm Optimization (PSO-LSSVR) is proposed. This method can select the parameters of LSSVR automatically without trial and error, thus ensure the accuracy of parameters optimization. Apply this method to the model identification of the ship steering dynamics, and compare the identification effect with the experimental reference data. The PSO-LSSVR is able to establish the system model effectively, the structure is simple and generalization ability is well.