Parameter Identification of Ship Maneuvering Models Using Recursive Least Square Method Based on Support Vector Machines
Journal Title: TransNav, the International Journal on Marine Navigation and Safety of Sea Transportation - Year 2017, Vol 11, Issue 1
Abstract
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.
Authors and Affiliations
Man Zhu, Axel Hahn, Yuanqiao Wen, A. Bolles
Keywords
Related Articles
- EP ID EP193389
- DOI 10.12716/1001.11.01.01
- Views 138
- Downloads 0
New Learning Methods for Marine Oil Spill Response Training
In Finland the Regional Fire and Rescue Services (RFRS) are responsible for near shore oil spill response and shoreline cleanup operations. In addition, they assist in other types of maritime incidents, such as search an...
Development of Analytical Method for Finding the High Risk Collision Areas
The traffic condition has been analyzed by models that are based on Gas model and Obstacle Zone by Target (OZT) by using 1 year AIS data for Tsunami measure. By applying Gas model based method, it is possible to analyze...
Human Error in Pilotage Operations
Pilotage operations require close interaction between human and machines. This complex sociotechnical system is necessary to safely and efficiently maneuver a vessel in constrained waters. A sociotechnical system consist...
Sources of Error in Satellite Navigation Positioning
An uninterrupted information about the user’s position can be obtained generally from satellite navigation system (SNS). At the time of this writing (January 2017) currently two global SNSs, GPS and GLONASS, are fully op...
Ship Domain Model for Multi-ship Collision Avoidance Decision-making with COLREGs Based on Artificial Potential Field
A multi-ship collision avoidance decision-making and path planning formulation is studied in a distributed way. This paper proposes a complete set of solutions for multi-ship collision avoidance in intelligent navigation...