Abstract
This study explores a nonparametric identification scheme for a ship maneuvering mathematical model. To overcome the difficulty in setting support vector regression (SVR) hyperparameters, a modified grey wolf optimizer algorithm is proposed. The algorithm introduces a nonlinear convergence factor and an adaptive position update strategy to enhance the search ability, which contributes toward identifying optimal hyperparameters. Using these optimal hyperparameters, SVR can predict the state variables pertaining to ship motion with high precision. The prediction of the motion state variables of the vessel YUKUN is considered as an illustrative example to verify the algorithm’s generalization ability and robustness. The prediction results indicate that, compared with the SVR based on the firefly algorithm and the particle swarm optimization, the proposed scheme offers the advantages of robustness, fewer iterations, and smaller prediction errors.
Similar content being viewed by others
Abbreviations
- MGWO:
-
Modified grey wolf optimizer
- SVR:
-
Support vector regression
- FA:
-
Firefly algorithm
- SI:
-
System identification
- LS:
-
Least squares
- RPE:
-
Recursive prediction error
- EKF:
-
Extended Kalman filter
- ML:
-
Maximum likelihood
- NN:
-
Neural network
- SVM:
-
Support vector machine
- GA:
-
Genetic algorithm
- RBF:
-
Radial basis function
- RNN:
-
Recursive neural network
- LWL:
-
Locally weighted learning
- PSO:
-
Particle swarm optimization
- ABC:
-
Artificial bee colony
- DOF:
-
Degree of freedom
- LWR:
-
Local weighted regression
- \(u\) :
-
Surge velocity
- \(v\) :
-
Sway velocity
- \(r\) :
-
Yaw rate
- \(\dot{u}\) :
-
Surge acceleration
- \(\dot{v}\) :
-
Sway acceleration
- \(\dot{r}\) :
-
Yaw acceleration
- \(\delta\) :
-
Rudder angle
- \(\psi\) :
-
Heading angle
- \(\mathop{X}\limits^{\rightharpoonup}\) :
-
Position vector of grey wolf
- \(\mathop{D}\limits^{\rightharpoonup}\) :
-
Distance vector of grey wolf
- \(K\left({x}_{i},{x}_{j}\right)\) :
-
Kernel functions
- MaxAE:
-
Maximum absolute error
- MAE:
-
Mean absolute error
- EV:
-
Error variance
- MSE:
-
Mean square error
- CC:
-
Correlation coefficient
- OI:
-
Optimization iterations
References
Zhu M, Hahn A, Wen Y, Bolles A (2017) Parameter identification of ship maneuvering models using recursive least square method based on support vector machines. TransNav Int J Mar Navig Saf Sea Transp 11(1):23–29
Zhou WW, Blanke M (1986) Identification of a class of nonlinear state-space models using RPE techniques, 1986 25th IEEE Conference on Decision and Control, Athens, pp. 1637–1642
Shi C, Zhao D, Peng J, Shen C (2009) Identification of ship maneuvering model using extended kalman filters. TransNav 3(1):105–110
Åström KJ, Källström CG (1976) Identification of ship steering dynamics[J]. Automatica 12(1):9–22
Wang N, Er MJ, Han M (2015) Large tanker motion model identification using generalized ellipsoidal basis function-based fuzzy neural networks[J]. IEEE Trans Cybern 45(12):2732–2743
Luo WL, Zou ZJ (2009) Parametric identification of ship maneuvering models by using support vector machines. J Ship Res 53(01):19–30
Witkowska A, Śmierzchalski R (2008) Identifying ship parameters with the aid of genetic algorithm[J]. Prace Naukowe Politechniki Warszawskiej Elektronika 165:245–252
Zhang G, Zhang X, Pang H (2015) Multi-innovation auto-constructed least squares identification for 4 DOF ship manoeuvring modelling with full-scale trial data[J]. ISA Trans 58:186–195
Xie S, Chu X, Liu C et al (2020) Parameter identification of ship motion model based on multi-innovation methods[J]. J Mar Sci Technol 25(1):162–184
Yin J, Zou Z, Xu F (2013) On-line prediction of ship roll motion during maneuvering using sequential learning RBF neural networks [J]. Ocean Eng 61:139–147
Chiu FC, Chang TL, Go J, et al (2004) A recursive neural networks model for ship maneuverability prediction[C] Oceans' 04 MTS/IEEE Techno-Ocean' 04 (IEEE Cat. No. 04CH37600). IEEE, 3: 1211–1218
Bai W, Ren J, Li T (2019) Modified genetic optimization-based locally weighted learning identification modeling of ship maneuvering with full scale trial[J]. Futur Gener Comput Syst 93:1036–1045
Bai W, Ren J, Li T et al (2019) Grid index subspace constructed locally weighted learning identification modeling for high dimensional ship maneuvering system[J]. ISA Trans 86:144–152
Zhang X, Zou Z (2011) Identification of Abkowitz model for ship manoeuvring motion using ε-support vector regression[J]. J Hydrodyn 23(3):353–360
Wang Z, Zou Z, Soares CG (2019) Identification of ship manoeuvring motion based on nu-support vector machine[J]. Ocean Eng 183:270–281
Wang X, Zou Z, Yu L et al (2015) System identification modeling of ship manoeuvring motion in 4 degrees of freedom based on support vector machines[J]. China Ocean Eng 29(4):519–534
Wang XG, Zou ZJ, Hou XR et al (2015) System identification modelling of ship manoeuvring motion based on -support vector regression[J]. J Hydrodyn Ser B 27(4):502–512
Luo W, Soares CG, Zou Z (2016) Parameter identification of ship maneuvering model based on support vector machines and particle swarm optimization. J Offshore Mech Arctic Eng 138(3):031101
Zhu M, Hahn A, Wen YQ et al (2017) Identification-based simplified model of large container ships using support vector machines and artificial bee colony algorithm[J]. Appl Ocean Res 68:249–261
Hou XR, Zou ZJ (2015) SVR-based identification of nonlinear roll motion equation for FPSOs in regular waves[J]. Ocean Eng 109(15):531–538
Hou X, Zou Z, Xu F (2016) SVR-based Parameter Identification of Coupled Heave-pitch Motion Equations in Regular Waves. The 26th International Ocean and Polar Engineering Conference, Rhodes, pp 580–585
Mirjalili S, Mirjalili SM, Lewis A (2014) Grey Wolf optimizer. Adv Eng Softw 69:46–61
Tolouei K, Moosavi E (2020) Production scheduling problem and solver improvement via integration of the grey wolf optimizer into the augmented Lagrangian relaxation method. SN Appl Sci. https://doi.org/10.1007/s42452-020-03758-z
Merikhi B, Mirjalili SM, Zoghi M et al (2019) Radiation pattern design of photonic crystal LED optimized by using multi-objective grey wolf optimizer[J]. Photon Netw Commun 38(1):167–176
Ma X, Mei X, Wu W et al (2019) A novel fractional time delayed grey model with Grey Wolf Optimizer and its applications in forecasting the natural gas and coal consumption in Chongqing China[J]. Energy 178:487–507
Dewangan RK, Shukla A, Godfrey WW (2019) Three dimensional path planning using Grey wolf optimizer for UAVs[J]. Appl Intell 49(6):2201–2217
Panda M, Das B, Pati BB (2020) Global path planning for multiple AUVs using GWO[J]. Arch Control Sci 30(1):77–100
Bai W, Ren J, Li T (2018) Multi-innovation gradient iterative locally weighted learning identification for a nonlinear ship maneuvering system[J]. China Ocean Eng 32(3):288–300
Perera LP, Oliveira P, Soares CG (2016) System identification of vessel steering with unstructured uncertainties by persistent excitation maneuvers[J]. IEEE J Oceanic Eng 41(3):515–528
Acknowledgements
This work was supported by the National Natural Science Foundation of China (51779029) and Fundamental Research Funds for the Central Universities (3132019306). The authors sincerely thank all the crew members who completed the full-scale sea trial test. The authors gratefully acknowledge this support.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Zhang, X., Meng, Y., Liu, Z. et al. Modified grey wolf optimizer-based support vector regression for ship maneuvering identification with full-scale trial. J Mar Sci Technol 27, 576–588 (2022). https://doi.org/10.1007/s00773-021-00858-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00773-021-00858-2