|
|
Publications
Xu, H.T. and Guedes Soares, C. (2022), “Adaptive nonlinear vessel steering modelling using time-sequence incremental and decremental LS-SVM”, Trends in Maritime Technology and Engineering, Guedes Soares, C. & Santos T.A. (Eds.), Taylor and Francis, London, UK, Vol. 1, pp. 601-612.
In this paper, an adaptive nonlinear vessel steering model is proposed. A time-sequence Least square support vector machine (LS-SVM) based on incremental and decremental updating algorithm is proposed to estimate the parameters dynamically. The proposed method is different from the online estimations method based on a sliding data window, which usually needs to train the model when a new sample is observed during each time step. It usually indicates an expensive and time-costing operation for training SVM. In the presented method, the parameters can update in an incremental and decremental way, which avoid the training operation. The validation is carried out based on the maneuvering tests using a free-running ship model. The obtained parameters agree well with the analytical values. The effect of the length of the training set is also discussed. The size of training set plays a trade-off on the stable and response speed of the system. The proposed method can dynamically estimate the parameters with a good accuracy and fast response. It can be used for designing a dynamic model-based control system for vehicles.
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
|