Parameter identification of ship maneuvering models using recursive least square method based on support vector machines

• Autorzy: Zhu M. , Hahn A. , Wen Y. , Bolles A.

Identyfikatory

DOI

10.12716/1001.11.01.01

• Języki publikacji: EN

Abstrakty

EN

Determination of ship maneuvering models is a tough task of ship maneuverability prediction. Among several prime approaches of estimating ship maneuvering models, system identification combined with the full-scale or free- running model test is preferred. In this contribution, real-time system identification programs using recursive identification method, such as the recursive least square method (RLS), are exerted for on-line identification of ship maneuvering models. However, this method seriously depends on the objects of study and initial values of identified parameters. To overcome this, an intelligent technology, i.e., support vector machines (SVM), is firstly used to estimate initial values of the identified parameters with finite samples. As real measured motion data of the Mariner class ship always involve noise from sensors and external disturbances, the zigzag simulation test data include a substantial quantity of Gaussian white noise. Wavelet method and empirical mode decomposition (EMD) are used to filter the data corrupted by noise, respectively. The choice of the sample number for SVM to decide initial values of identified parameters is extensively discussed and analyzed. With de-noised motion data as input-output training samples, parameters of ship maneuvering models are estimated using RLS and SVM-RLS, respectively. The comparison between identification results and true values of parameters demonstrates that both the identified ship maneuvering models from RLS and SVM-RLS have reasonable agreements with simulated motions of the ship, and the increment of the sample for SVM positively affects the identification results. Furthermore, SVM-RLS using data de-noised by EMD shows the highest accuracy and best convergence.

Słowa kluczowe

EN

ship manoeuvering; recursive least square method; ship manoeuvering model; ship maneuverability prediction; support vector machine; SVM; empirical mode decomposition; EMD; computational fluid dynamics CFD; extended Kalman filter (EKF)

• Wydawca: Faculty of Navigation, Gdynia Maritime University
• Czasopismo: TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
• Rocznik: 2017
• Tom: Vol. 11, no. 1
• Strony: 23--29
• Opis fizyczny: Bibliogr. 20 poz., rys., tab.

Twórcy

autor

Zhu M.

• Carl-von-Ossietzky University of Oldenburg, Oldenburg, Germany

autor

Hahn A.

• Carl-von-Ossietzky University of Oldenburg, Oldenburg, Germany

autor

Wen Y.

• School of Navigation, Wuhan University of Technology, Hubei, China

autor

Bolles A.

• Institute of Information Technology, Oldenburg, Germany

Bibliografia

• 1 Skjetne,  S.,  Smogeli,  V.,  &  Fossen,  T.  I.  2004.  Modeling,  identification, and adaptive maneuvering of Cybership  II: A complete design with experiments. IFAC Conference  on Control & Application in Marine System (pp.203‐208).  Ancona, Italy. 
• 2 Xu, F., Xiao, T., et al. 2014. Identification of Nomoto models  with integral sample structure for identification. The 33rd  Chinese  Control  Conference  (pp.6721‐6725).  Nanjing,  China
• 3 Åstrom,  K.,  &  Kållstrom,  C.  1976.  Identification  of  ship  steering dynamics. Automatica, 9‐22. 
• 4 Barford,  L.  A.,  Fazzio,  R.  S.,  &  Smith,  D.  R.  1992.  An  introduction  to  wavelets.  Hewlett‐Packard  Labs,  Bristol,  UK, Tech. Rep. HPL‐92‐124, 1–29.
• 5 Fossen, T. I. 2011. Handbook of Marine Craft Hydrodynamics  and Motion Control. Wiley.
• 6 Jiang, Z., Yan, W., Jin, X., & Gao, J. 2012. Identification of an  Underactuated  Unmanned  Surface  Vehicle.  JOURNAL  OF NORTHWESTERN POLYTECHNICAL UNIVERSITY,  699‐705. 
• 7 Ljung, L. 2002. Recursive identification algorithms. Circuits,  Systems, and Signal Processing, 57‐68.
• 8 Luo, W. L., & Zou, Z. J. 2009. Parametric Identification of  Ship  Maneuvering  Models  by  Using  Support  Vector  Machines. Journal of Ship Research, 19‐30. 
• 9 Luo, W., & Cai, W. 2014. Modeling of ship maneuvering  motion  using  optimized  support  vector  machines.  Intelligent  Control  and  Information  Processing  (ICICIP),  2014  Fifth  International  Conference  on  (pp.  476  ‐ 478).  Dalian: IEEE.
• 10 Perera, L. P., Oliveira, P., & Guedes Soares, C. 2015. System  Identification  of  Nonlinear  Vessel  Steering.  Journal  of  Offshore Mechanics and Arctic Engineering, 31302‐31307. 
• 11 Rajesh,  G.,  &  Bhattacharyya,  S.  K.  2008.  System  identification  for  nonlinear  maneuvering  of  large  tankers  using  artificial  neural  network.  Applied  Ocean  Research, 256‐263. 
• 12 Sutulo,  S.,  &  Guedes,  Soares,  C.  2014.  An  algorithm  for  offline identification of ship manoeuvring mathematical  models from free‐running tests. Ocean Engineering, 10‐25. 
• 13 Shi, C., Zhao, D., Peng, J., & Shen, C. 2009. Identification of  Ship  Maneuvering  Model  Using  Extended  Kalman  Filters.  TransNav,  the  International  Journal  on  Marine  Navigation and Safety of Sea Transportation, 105‐110. 
• 14 Vapnik, V. 2000. The nature of statistical learning theory. New  York: Springer. 
• 15 Wang, X., Zou, Z. J., & Yin, J. 2013. Modular Parameter  Identification for Ship Manoeuvring Prediction Based on  Support  Vector  Machines.  The  Twenty‐third  (2013)  International Offshore and Polar Engineering (pp. 834‐839).  Anchorage,  Alaska,  USA:  the  International  Society  of  Offshore and Polar Engineers
• 16 Wang, Y.‐H., Yeh, C.‐H., Young, H.‐W. V., Hu, K., & Lo, M.T.  2014.On  the  computational  complexity  of  the empirical  mode  decomposition  algorithm.  Physical  A:  Statistical Mechanics and its Applications, 159‐167.
• 17 XU, F., CHEN, Q., ZOU, Z.‐J., & YIN, J.‐C. 2014. Modeling  of underwater vehicles’ maneuvering motion by using  integral sample structure for identification. JOURNAL  OF SHIP MECHANICS, 211‐220. 
• 18 Xu,  F.,  Zou,  Z.  J.,  Yin,  J.  C.,  &  Cao,  J.  2012.  Parametric  identification and sensitivity analysis for Autonomous  Underwater  Vehicles  in  diving  plane.  Journal  of  Hydrodynamics, 744‐751. 
• 19 Zhang, X. G., & Zou, Z. J. 2011. Identification of Abkowitz  model  for  ship  manoeuvring  motion  using  ε‐support  vector regression. Journal of Hydrodynamics, 353‐360. 
• 20 Zhang,  X.‐G.,  &  Zou,  Z.‐J.  2013.  Estimation  of  the  hydrodynamic  coefficients  from  captive  model  test  results  by  using  support  vector  machines.  Ocean  Engineering, 25‐31. 

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017)