Identification method of nonlinear maneuver model for unmanned surface vehicle from sea trial data based on support vector machine

다국어 초록 (Multilingual Abstract)

In order to solve the difficulty of modeling the unmanned surface vehicle (USV) nonlinear maneuver model, a combination identification method of linear hydrodynamic coefficients and nonlinear hydrodynamic coefficients based on support vector machine (SVM) is proposed. The identification principle of USV hydrodynamic coefficients is briefly introduced and a regression algorithm of the SVM is derived for the USV maneuver model. Then, the linear hydrodynamic coefficients of the hull are identified by using a series of USV turning test data at small water-jet angles. And the large water-jet angle turning motion test data and the identified linear hydrodynamic coefficients are used to identify the nonlinear hydrodynamic coefficients for USV. The fourth-order Runge-Kutta method is used to design the USV maneuver simulation program, and a series of USV turning motion simulation experiments are carried out.
The simulation data is compared with the corresponding USV sea trial data. Through comparative analysis, it is shown that the USV maneuver mathematical model established in this paper can describe the maneuverability of the USV. It is feasible to use the combination method of SVM to identify the hydrodynamic coefficient of USV.

참고문헌 (Reference)

1 V. Vapnik, "Universal learning technology : support vector machines" 2 (2): 137-144, 2005

2 Y. Xue, "System identification of ship dynamic model based on Gaussian process regression with input noise" 216 : 107862-, 2020

3 G. Wu, "Study of the maneuverability and intelligent control for unmanned surface vehicle" Harbin Engineering University 2011

4 V. N. Vapnik, "Statistical Learning Theory" Wiley 1998

5 D. Hess, "Simulation of ship maneuvers using recursive neural networks" 2000

6 X. Cui, "Seafloor habitat mapping using multibeam bathymetric and backscatter intensity multi-features SVM classification framework" 174 : 107728-, 2021

7 J. A. K. Suykens, "Recurrent least squares support vector machines" 47 (47): 1109-1114, 2000

8 T. Perez, "Practical aspects of frequency domain identification of dynamic models of marine structures from hydrodynamic data" 38 (38): 426-435, 2011

9 W. Luo, "Parametric identification of ship maneuvering models by using support vector machines" 53 (53): 19-30, 2009

10 M. R. Haddara, "Parametric identification of maneuvering models for ships" 46 (46): 5-27, 1999

11 S. K. Bhattacharyya, "Parametric identification for nonlinear ship maneuvering" 50 (50): 197-207, 2006

12 F. Xu, "Parametric identification and sensitivity analysis for autonomous underwater vehicles in diving plane" 24 (24): 744-751, 2012

13 Y. T. Dai, "Parameter identification of ship vertical motions using improved particle swarm optimization" 44-50, 2010

14 W. Luo, "On the identification of coupled pitch and heave motions using support vector machine" 3316-3321, 2016

15 Y. T. Dai, "On the identification of coupled pitch and heave motions using opposition-based particle swarm optimization" 221-231, 2014

16 P. Wang, "Numerical and experimental study on the maneuverability of an active propeller control based wave glider" 104 : 102369-, 2020

17 X. R. Hou, "Nonparametric identification of nonlinear ship roll motion by using the motion response in irregular waves" 73 (73): 88-99, 2018

18 W. Luo, "Modeling of ship maneuvering motion using optimized support vector machines" 476-478, 2014

19 M. A. Abkowitz, "Measurement of hydrodynamic characteristic from ship maneuvering trials by system identification" 88 : 283-318, 1980

20 P. F. Xu, "Identification-based 3 DOF model of unmanned surface vehicle using support vector machines enhanced by cuckoo search algorithm" 197 : 106898-, 2020

21 X. Zhang, "Identification of Abkowitz model for ship manoeuvring motion using ε-support vector regression" 23 (23): 353-360, 2011

22 Y. Jiang, "Identification modeling and prediction of ship maneuvering motion based on LSTM deep neural network" 27 : 125-137, 2022

23 W. H. Sun, "Identification method of Hydrodynamic coefficients of ship structure nonlinear rolling motion based on Hilbert transform" Ludong University 2021

24 T. I. Fossen, "Handbook of Marine Craft Hydrodynamics and Motion Control" John Wiley and Sons 2011

25 H. Yasukawa, "Evaluations of wave-induced steady forces and turning motion of a full hull ship in waves" 24 : 1-15, 2018

26 W. Luo, "Elimination of simultaneous drift and sensitivity analysis in the hydrodynamic modeling of ship manoeuvring" 42 (42): 1358-1362, 2008

27 Y. P. Yan, "Calculation and hydrodynamic coefficient modeling of open-frame underwater robot" 42 (42): 1972-1986, 2021

28 S. Sutulo, "An algorithm for offline identification of ship maneuvering mathematical models from freerunning tests" 79 : 10-25, 2014

29 A. J. Smola, "A tutorial on support vector regression" 14 (14): 199-222, 2004

30 S. Adachi, "A new system identification method based on support vector machines" 34 (34): 181-186, 2001

31 G. N. Kouziokas, "A new W-SVM kernel combining PSOneural network transformed vector and Bayesian optimized SVM in GDP forecasting" 92 : 103650-, 2020

32 M. Mohammadi, "A comprehensive survey and taxonomy of the SVM-based intrusion detection systems" 178 : 102983-, 2021

33 K. Zheng, "A SVM based ship collision risk assessment algorithm" 202 : 107062-, 2020

34 B. J. Lyu, "A SR-UKF-based method to identify submarine hydrodynamic coefficients" 16 (16): 44-49, 2021