Identification modeling of ship maneuvering motion based on local Gaussian process regression. (1st January 2023)

• Record Type: Journal Article
• Authors: Ouyang, Zi-Lu; Chen, Gang; Zou, Zao-Jian
• Is Part Of: Ocean engineering. Volume 267(2023)
• Publication Date: 2023-01-01
• Subjects: Ship maneuvering -- Nonparametric modeling -- Local Gaussian process regression -- Clustering analysis -- k-means algorithm; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2022.113251
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: A fast and accurate nonparametric modeling method based on local Gaussian process regression (LGPR) is proposed for the identification modeling and prediction of ship maneuvering motion. The training dataset collected from the free-running model tests of ship maneuvering is automatically divided into a number of clusters according to the similarity criterion by clustering analysis using k-means algorithm. Utilizing the data in each cluster, the corresponding local nonparametric model is identified. The computational cost of training and prediction based on LGPR is reduced compared to that based on the classic Gaussian process regression (CGPR) using the whole training dataset. Taking the KVLCC2 tanker and an unmanned surface vehicle (USV) as study objects, the nonparametric models are identified based on the experimental data of zigzag maneuvers of the KVLCC2 model and random maneuver of the USV. Using the identified models, the zigzag maneuvers of the KVLCC2 model and the random maneuver of the USV, which are not involved in the training data, are predicted. The results show that LGPR has higher computational efficiency than CGPR with acceptable prediction accuracy. Highlights: A fast and accurate nonparametric modeling method based on local Gaussian process regression (LGPR) is proposed. The method is applied in modeling and prediction of ship maneuvering by using measured test data for training and validation. The training dataset is automatically divided into some clusters according to similarity criterion by clustering analysis. Utilizing the data in each cluster, the corresponding local nonparametric model is identified. The computational cost of training and prediction is largely reduced compared with classic Gaussian process regression.