Kernel-based support vector regression for nonparametric modeling of ship maneuvering motion

Abstract System identification is crucial to predict the maneuverability of the ship. In this work, ε-support vector regression (ε-SVR) is implemented to identify hydrodynamic derivatives of Abkowitz maneuver model. A proposed technique, batch learning, is implemented with the addition of Gaussian white noise to reconstruct the samples and alleviate the parameter drift in the system identification of the ship maneuvering model. The predicted results are compared with results obtained from Planar Motion Mechanism (PMM) test. Standard maneuvers, 35° turning circle, 10°/10° and 20°/20° zigzags, are simulated and compared with the predicted model by ε-SVR. The presented results show that the proposed batch learning technique with Gaussian white noise is an effective technique, which improves the accuracy and robustness of ε-SVR in system identification. The results obtained from the predicted model match well with the those obtained from PMM results, which shows its excellent generalization performance. The developed model is applied to understand control requirements for vessels under different conditions.

Download Full-text

Parameter Identification of Ship Maneuvering Model Based on Support Vector Machines and Particle Swarm Optimization

Journal of Offshore Mechanics and Arctic Engineering ◽

10.1115/1.4032892 ◽

2016 ◽

Vol 138 (3) ◽

Cited By ~ 22

Author(s):

Weilin Luo ◽

C. Guedes Soares ◽

Zaojian Zou

Keyword(s):

Particle Swarm Optimization ◽

Support Vector Machines ◽

Difference Method ◽

Particle Swarm ◽

Support Vector ◽

Ship Maneuvering ◽

Swarm Optimization ◽

Hydrodynamic Derivatives ◽

Vector Machines ◽

Maneuvering Motion

Combined with the free-running model tests of KVLCC ship, the system identification (SI) based on support vector machines (SVM) is proposed for the prediction of ship maneuvering motion. The hydrodynamic derivatives in an Abkowitz model are determined by the Lagrangian factors and the support vectors in the SVM regression model. To obtain the optimized structural factors in SVM, particle swarm optimization (PSO) is incorporated into SVM. To diminish the drift of hydrodynamic derivatives after regression, a difference method is adopted to reconstruct the training samples before identification. The validity of the difference method is verified by correlation analysis. Based on the Abkowitz mathematical model, the simulation of ship maneuvering motion is conducted. Comparison between the predicted results and the test results demonstrates the validity of the proposed methods in this paper.

Download Full-text

Parametric Identification of Ship Maneuvering Models by Using Support Vector Machines

Journal of Ship Research ◽

10.5957/jsr.2009.53.1.19 ◽

2009 ◽

Vol 53 (01) ◽

pp. 19-30 ◽

Cited By ~ 9

Author(s):

W. L. Luo ◽

Z. J. Zou

Keyword(s):

Support Vector Machines ◽

Predictive Ability ◽

Parametric Identification ◽

Inner Product ◽

Support Vector ◽

Identification Algorithm ◽

Hydrodynamic Coefficients ◽

Ship Maneuvering ◽

Vector Machines ◽

Maneuvering Motion

System identification combined with free-running model tests or full-scale trials is one of the effective methods to determine the hydrodynamic coefficients in the mathematical models of ship maneuvering motion. By analyzing the available data, including rudder angle, surge speed, sway speed, yaw rate, and so forth, a method based on support vector machines (SVM) to estimate the hydrodynamic coefficients is proposed for conventional surface ships. The coefficients are contained in the expansion of the inner product of a linear kernel function. Predictions of maneuvering motion are conducted by using the parameters identified. The results of identification and simulation demonstrate the validity of the identification algorithm proposed. The simultaneous drift and multicollinearity are diminished by introducing an additional ramp signal to the training samples. Comparison between the simulated and predicted motion variables from different maneuvers shows good predictive ability of the trained SVM.

Download Full-text

Nonparametric modeling of ship maneuvering motion based on Gaussian process regression optimized by genetic algorithm

Ocean Engineering ◽

10.1016/j.oceaneng.2021.109699 ◽

2021 ◽

Vol 238 ◽

pp. 109699

Author(s):

Zi-Lu Ouyang ◽

Zao-Jian Zou

Keyword(s):

Genetic Algorithm ◽

Gaussian Process ◽

Gaussian Process Regression ◽

Nonparametric Modeling ◽

Ship Maneuvering ◽

Maneuvering Motion

Download Full-text

Recurrent neural networks for nonparametric modeling of ship maneuvering motion

International Journal of Naval Architecture and Ocean Engineering ◽

10.1016/j.ijnaoe.2022.100436 ◽

2022 ◽

pp. 100436

Author(s):

Lizhu Hao ◽

Yang Han ◽

Chao Shi ◽

Ziying Pan

Keyword(s):

Neural Networks ◽

Recurrent Neural Networks ◽

Nonparametric Modeling ◽

Ship Maneuvering ◽

Maneuvering Motion

Download Full-text

Modified grey wolf optimizer-based support vector regression for ship maneuvering identification with full-scale trial

Journal of Marine Science and Technology ◽

10.1007/s00773-021-00858-2 ◽

2021 ◽

Author(s):

Xiufeng Zhang ◽

Yao Meng ◽

Zhaochun Liu ◽

Jinxin Zhu

Keyword(s):

Support Vector Regression ◽

Full Scale ◽

Support Vector ◽

Grey Wolf Optimizer ◽

Grey Wolf ◽

Ship Maneuvering

Download Full-text

Blind Prediction of Ship Maneuvering by Using Support Vector Machines

29th International Conference on Ocean, Offshore and Arctic Engineering: Volume 4 ◽

10.1115/omae2010-20723 ◽

2010 ◽

Cited By ~ 2

Author(s):

Wei-lin Luo ◽

Zao-jian Zou

Keyword(s):

Support Vector Machines ◽

Black Box ◽

Support Vector ◽

Nonlinear Functions ◽

Ship Maneuvering ◽

Vector Machines ◽

Turning Test ◽

Yaw Moment ◽

Rudder Angle ◽

Maneuvering Motion

Support Vector Machines (SVM) based system identification is applied to predict ship maneuvering motion. Different from the prediction methods based on the explicit mathematical model of ship maneuvering motion, the black-box model of ship maneuvering motion is constructed and used to predict ship maneuvering motion. With the rudder angle and the variables of maneuvering motion as inputs and the hydrodynamic forces as outputs, the complicated nonlinear functions in the Abkowitz model are identified; and the surge force, sway force and yaw moment are predicted blindly by using the functions identified. Taking turning test as example, with the rudder angle as inputs and the maneuverability parameters of turning circles as outputs, the input-output mappings are identified and the maneuverability parameters such as the advance, the transfer and the tactical diameter are also predicted blindly by using the identified mappings.

Download Full-text