Nonparametric modeling of ship maneuvering motion based on Gaussian process regression optimized by genetic algorithm. (15th October 2021)

• Record Type: Journal Article
• Authors: Ouyang, Zi-Lu; Zou, Zao-Jian
• Is Part Of: Ocean engineering. Volume 238(2021)
• Publication Date: 2021-10-15
• Subjects: Ship maneuvering -- Nonparametric modeling -- System identification -- Gaussian process regression -- Genetic algorithm -- Sliding time window; ANN Artificial Neural Network -- CFD Computational Fluid Dynamics -- GA Genetic Algorithm -- GPR Gaussian Process Regression -- LSSVM Least Squares Support Vector Machine -- MASS Maritime Autonomous Surface Ships -- MLE Maximum Likelihood Estimation -- RBF Radial Basis Function -- RMSE Root Mean Square Error -- SE Squared Exponential -- SVM Support Vector Machine -- SVR Support Vector Regression -- TRD Training Dataset -- VAD Validation Dataset; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2021.109699
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: A novel method, Gaussian process regression optimized by genetic algorithm (GA-GPR), is proposed for nonparametric modeling of ship maneuvering motion. A genetic algorithm with adaptive crossover and mutation operations is introduced for adjustment and optimization of hyperparameters in the kernel function. The sliding time window method is adopted to update the training samples to improve the adaptability of the model. Taking the Mariner vessel and the container ship KCS as study objects, the simulation data and the real measured data provided by SIMMAN 2020 workshop are employed to evaluate the proposed method. The prediction results of the proposed method and the traditional Gaussian process regression are compared and validated against available experimental data of zigzag and turning circle maneuvers. It shows that the proposed method has higher prediction accuracy and better generalization ability, indicating that the hyperparameters optimized by genetic algorithm make the model closer to the ship's dynamic characteristics. Highlights: A method based on Gaussian process regression optimized by GA is proposed for nonparametric modeling of ship maneuvering. GA with adaptive crossover and mutation operations is used to adjust and optimize the hyperparameters in kernel function. The sliding time window method is adopted for updating the training samples to improve the adaptability of the model. Case studies are carried out with training datasets from simulations for Mariner vessel and from experiments for KCS ship. The prediction results are validated against the experimental data of zigzag and turning circle maneuvers.