Multi-Innovation Gradient Iterative Locally Weighted Learning Identification for A Nonlinear Ship Maneuvering System

Wei-wei BAI; Jun-sheng REN; Tie-shan LI

doi:10.1007/s13344-018-0030-0

Citation: Wei-wei BAI, Jun-sheng REN and Tie-shan LI. Multi-Innovation Gradient Iterative Locally Weighted Learning Identification for A Nonlinear Ship Maneuvering System[J]. China Ocean Engineering, 2018, 32(3): 288-300. doi: 10.1007/s13344-018-0030-0 shu

Multi-Innovation Gradient Iterative Locally Weighted Learning Identification for A Nonlinear Ship Maneuvering System

Navigation College, Dalian Maritime University, Dalian 116026, China

Corresponding author: Wei-wei BAI, baiweiwei_dl@163.com Tie-shan LI, tieshanli@126.com
Received Date: 2017-10-24
Accepted Date: 2018-02-02
Available Online: 2018-01-01
Fund Project: This work was financially supported in part by the National High Technology Research and Development Program of China (863 Program, Grant No. 2015AA016404), the National Natural Science Foundation of China (Grant Nos. 51109020, 51179019 and 51779029), and the Fundamental Research Program for Key Laboratory of the Education Department of Liaoning Province (Grant No. LZ2015006).

Figures(27) / Tables(13)

This paper explores a highly accurate identification modeling approach for the ship maneuvering motion with full-scale trial. A multi-innovation gradient iterative (MIGI) approach is proposed to optimize the distance metric of locally weighted learning (LWL), and a novel non-parametric modeling technique is developed for a nonlinear ship maneuvering system. This proposed method's advantages are as follows: first, it can avoid the unmodeled dynamics and multicollinearity inherent to the conventional parametric model; second, it eliminates the over-learning or under-learning and obtains the optimal distance metric; and third, the MIGI is not sensitive to the initial parameter value and requires less time during the training phase. These advantages result in a highly accurate mathematical modeling technique that can be conveniently implemented in applications. To verify the characteristics of this mathematical model, two examples are used as the model platforms to study the ship maneuvering.
- multi-innovation gradient iterative (MIGI),
- locally weighted learning (LWL),
- identification,
- nonlinearship maneuvering,
- full-scale trial
1. [1]
  Abkowitz, M.A., 1980. Measurement of hydrodynamic characteristics from ship maneuvering trials by system identification, SNAME Transactions, 33(88), 283–318.
2. [2]
  Aha, D.W., 1997. Lazy learning, Artificial Intelligence Review, 11, 1–5.
3. [3]
  Atkeson, C.G. and Schaal, S., 1995. Memory-based neural networks for robot learning, Neurocomputing, 9(3), 243–269.
4. [4]
  Bai, W.W., Ren, J.S., Li, T.S. and Li, R.H., 2017. Locally optimal-based LWL identification modeling for ship manoeuvring motion, Journal of Harbin Engineering University, 38(5), 676–683. (in Chinese)
5. [5]
  Cleveland, W.S. and Loader, C., 1995. Smoothing by Local Regression: Principles and Methods, AT&T Bell Laboratories, Murray Hill NY.
6. [6]
  Daafouz, J. and Bernussou, J., 2001. Parameter dependent Lyapunov functions for discrete time systems with time varying parametric uncertainties, Systems & Control Letters, 43(5), 355–359.
7. [7]
  Ding, F. and Chen, T.W., 2007. Performance analysis of multi-innovation gradient type identification methods, Automatica, 43(1), 1–14.
8. [8]
  Fossen, T.I., 2011. Handbook of Marine Craft Hydrodynamics and Motion Control, John Wiley and Sons, New York.
9. [9]
  Haddara, M.R. and Wang, Y., 1999. Parametric identification of manoeuvring models for ships, International Shipbuilding Progress, 46(445), 5–27.
10. [10]
  Jia, X.L. and Yang, Y.S., 1999. Ship Motion Mathematical Model, Dalian Maritime University Press, Dalian, China. (in Chinese)
11. [11]
  Jia, Z.J. and Song, Y.D., 2017. Barrier function-based neural adaptive control with locally weighted learning and finite neuron self-growing strategy, IEEE Transactions on Neural Networks and Learning Systems, 28(6), 1439–1451.
12. [12]
  Kaneko, H. and Funatsu, K., 2016. Ensemble locally weighted partial least squares as a just-in-time modeling method, AIChE Journal, 62(3), 717–725.
13. [13]
  Leung, H., Huang, Y.S. and Cao, C.X., 2004. Locally weighted regression for desulphurisation intelligent decision system modeling, Simulation Modelling Practice and Theory, 12(6), 413–423.
14. [14]
  Ljung, L. and Sööderström, T., 1986. Theory and Practice of Recursive Identification, Cambridge MIT Press, Cambridge.
15. [15]
  Luo, W.L. and Zou, Z.J., 2010. Blind prediction of ship maneuvering by using support vector machines, Proceedings of the 29th International Conference on Ocean, Offshore and Arctic Engineering (OMAE2010), Shanghai, China, Paper No. OMAE2010-20723.
16. [16]
  Luo, W.L. and Zhang, Z.C., 2016. Modeling of ship maneuvering motion using neural networks, Journal of Marine Science and Application, 15(4), 426–432.
17. [17]
  Ma, J.L., Chan, J.C.W. and Canters, F., 2014. Robust locally weighted regression for superresolution enhancement of multi-angle remote sensing imagery, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4), 1357–1371.
18. [18]
  Moreira, L. and Guedes Soares, C., 2012. Recursive neural network model of catamaran manoeuvring, International Journal of Maritime Engineering, 154, A-121–A-130.
19. [19]
  Ogawa, A. and Kasai, H.,1978. On the mathematical model of manoeuvring motion of ships, International Shipbuilding Progress, 25(292), 306–319.
20. [20]
  Schaal, S. and Atkeson, C.G., 1994. Robot juggling: an implementation of memory-based learning, Control Systems Magazine, 14(1), 57–71.
21. [21]
  Schaal, S., Atkeson, C.G. and Vijayakumar, S., 2002. Scalable techniques from nonparametric statistics for real time robot learning, Applied Intelligence, 17(1), 49–60.
22. [22]
  Sutulo, S. and Guedes Soares C., 2014. An algorithm for offline identification of ship manoeuvring mathematical models from free-running tests, Ocean Engineering, 79, 10–25.
23. [23]
  Uzunoglu, E., Silva, S.R.E., Guedes Soares, S., Marón, A. and Gutierrez, C., 2016. The effect of asymmetric cross-sections on hydrodynamic coefficients of a C11 type container vessel, Ocean Engineering, 113, 264–275.
24. [24]
  Xu, L. and Ding, F., 2017. Recursive least squares and multi-innovation stochastic gradient parameter estimation methods for signal modeling, Circuits, Systems, and Signal Processing, 36(4), 1735–1753.
1. [1]
  Wen-bo DONG , Li ZHOU , Shi-feng DING , Ai-ming WANG , Jin-yan CAI . Two-Staged Method for Ice Channel Identification Based on Image Segmentation and Corner Point Regression. China Ocean Engineering, 2024, 38(2): 313-325. doi: 10.1007/s13344-024-0026-x
2. [2]
  毕春伟 , 赵云鹏 , 董国海 . Numerical Study on the Hydrodynamic Characteristics of Biofouled Full-Scale Net Cage. China Ocean Engineering, 2015, (3): 401-414.
3. [3]
  Tae Ho KIM , Duck Jong JANG , Kyong Uk YANG , Sun Chol NA , Dae An KIM . Comparison Between Full-Scale and Model Experiments of Oil Fences. China Ocean Engineering, 2009, (4): 657-668.
4. [4]
  Zheng-jie LI , Qi-yin DING , Hu-wei CUI , Nan ZHAO . Research on the Ultimate Strength of a Hull Bottom Full-Scale Stiffened Plate Under Axial Compression and Lateral Pressure. China Ocean Engineering, 2025, 39(1): 1-12. doi: 10.1007/s13344-025-0001-1
5. [5]
  Shu-huan SUI , Xue-liang ZHAO , Xin-rui CHEN , Wen-ni DENG , Kan-min SHEN . Full-Scale Numerical Simulation of the Local Scour Under Combined Current and Wave Conditions Based on Field Data. China Ocean Engineering, 2023, 37(6): 1032-1043. doi: 10.1007/s13344-023-0086-3
6. [6]
  WU Wen-hua , LV Bai-cheng , YUE Qian-jin , ZHANG Yan-tao , LIN Yang . Research on Analytical Method of Fatigue Characteristics of Soft Yoke Mooring System Based on Full-Scale Measurement. China Ocean Engineering, 2017, (2): 230-237. doi: 10.1007/s13344-017-0027-0
7. [7]
  . Experimental Study and System Identification of Hydrodynmnic Force Acting on Heave Damping Plate. China Ocean Engineering, 2008, (1): -.
8. [8]
  陈立 , 马骏 , 赵德有 , 邬君 . Curvature of Flexibility Matrix for Damage Identification in Legs of Jacket Platforms. China Ocean Engineering, 2008, (4): 547-559.
9. [9]
  Abtahi Seid Farhad , Alishahi Mohammad Mehdi , Yazdi Ehsan Azadi . Identification of Pitch Dynamics of An Autonomous Underwater Vehicle Using Sensor Fusion. China Ocean Engineering, 2019, 33(5): 563-572. doi: 10.1007/s13344-019-0054-0
10. [10]
  . Modal Identification of Offshore Platforms Using Statistical Method Based on ERA. China Ocean Engineering, 2005, (2): -.
11. [11]
  . Experimental Study and System Identification of Hydrodynamic Force Acting on Heave Damping Plate. China Ocean Engineering, 2008, (1): -.
12. [12]
  胡家顺 , 冯新 , 李昕 , 周晶 . Condition Identification Based on Vibration Measurements for Free Spanning Submarine Pipelines. China Ocean Engineering, 2008, (4): 561-574.
13. [13]
  M. M. Ettefagh . Damage Identification of A TLP Floating Wind Turbine by Meta-Heuristic Algorithms. China Ocean Engineering, 2015, (6): 891-902.
14. [14]
  . A Study on the Maneuvering Motion of a Low Speed Submersible. China Ocean Engineering, 1997, (4): -.
15. [15]
  张铭钧 , 吴娟 , 褚振忠 . Multi-Fault Diagnosis for Autonomous Underwater Vehicle Based on Fuzzy Weighted Support Vector Domain Description. China Ocean Engineering, 2014, (5): 599-616.
16. [16]
  王雪刚 , 邹早建 , 余龙 , 蔡韡 . System Identification Modeling of Ship Manoeuvring Motion in 4 Degrees of Freedom Based on Support Vector Machines. China Ocean Engineering, 2015, (4): 519-534.
17. [17]
  Wen-long YANG , Shu-qing WANG . Modal Parameters Identification of A Real Offshore Platform From the Response Excited by Natural Ice Loading. China Ocean Engineering, 2020, 34(4): 558-570. doi: 10.1007/s13344-020-0050-4
18. [18]
  Jian-cheng LENG , Jin-yong MA , Zong-heng FAN , Wan-dong QIAN , Hui-yu FENG . Modal Parameter Identification Method of Jacket Platform Structure Based on AFDD and Optimized FBFFT. China Ocean Engineering, 2023, 37(3): 393-407. doi: 10.1007/s13344-023-0033-3
19. [19]
  Qi-wang WENG , Jian-min YANG , Qiong-wen LIANG , Jing-hang MAO , Xiao-xian GUO . System Identification and Parameter Self-Tuning Controller on Deep-Sea Mining Vehicle. China Ocean Engineering, 2023, 37(1): 53-61. doi: 10.1007/s13344-023-0005-7
20. [20]
  S. Sakthivel MURUGAN , V. NATARAJAN , K. MAHESWARAN . Analysis of EMD Algorithm for Identification and Extraction of An Acoustic Signal in Underwater Channel Against Wind Driven Ambient Noise. China Ocean Engineering, 2014, (5): 645-657.

Get Citation

PDF

XML

Metrics

PDF Downloads(55)
Abstract views(15526)
HTML views(600)
Cited By(0)

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142