Ship dynamics model identification based on Semblance least square support vector machine

In recent years, with the rapid development of Maritime Autonomous Surface Ships (MASS) in the industry and academia, using system identification method to build the accurate ship dynamics model has become a hotspot in this area, which is critical to achieve precise and robust ship motion control for safety and adaptive navigation of MASS. Therefore, a non-parametric and robust two-phase system identification method is proposed. Firstly, the improved complete ensemble empirical mode decomposition is introduced to filter datasets collected from model-scale free-running model tests. Secondly, Semblance least square support vector machine (S-LS-SVM) is proposed for the ship dynamics modeling based on the LS-SVM with the state-of-the-art Semblance kernel function. Compared with the traditional method, the Root Mean Square Error (RMSE) of overall prediction on the test dataset improves by 20.82%, 7.68%, and 58.19% for surge, sway, and yaw speed of target ship model. According to maneuverability simulation, it is verified that this method has better generalization performance and higher accuracy for the prediction of the ship’s heading angle and trajectory.