Parameter Identification of Ship Maneuvering Models Using Recursive Least Square Method Based on Support Vector Machines

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.

Prediction of Economic Operation Index Based on Support Vector Machine

“…e predictor can be regarded as the "feature extractor" of the omen, so the lower limit of the number of hidden nodes can be defined as the class of the omen. e main defects of the neural network economic operation index prediction method are the structure selection problem and the local minimum point problem [17].…”

System identification of Vessel Manoeuvring Models

“…The uncertainty can be reduced by instead using model test data as in Araki et al (2012), He et al (2022), Xue et al (2021), Miller (2021) and Luo et al (2016). The uncertainty can be further reduced by using simulated data as in Shi et al (2009), Zhu et al (2017), Wang et al (2021) Luo et al (2016) the potential of new methods with the benefit that the true model is known, but one also has to remember that the objective is to identify real objects, not its mathematical model (Miller, 2021). Black-box modeling was used in He et al (2022), using neural network, and in Xue et al (2021), using gaussian process.…”

“…Unscented Kalman filter (UKF), which has been proposed as an improvement to the EKF in handling nonlinear systems, was used in Revestido Herrero and Velasco González (2012). Support vector regression (SVR) has been investigated in Zhu et al (2017), Wang et al (2021) and Luo et al (2016). A genetic algorithm was used in Miller (2021) for the system identification of model test performed on a lake.…”

Fast and Precise Generic Model for Position-Based Trajectory Prediction of Inland Waterway Vessels

“…It is noted that the methods are sensitive to noise and initial conditions. To cope up with initial conditions, the authors in [7] use recursive least square (RLS) in combination with Support Vector Machine (SVM), assuming there are no disturbances acting on the system. In [5], the authors develop an approach to identify parameters under disturbances using SVM.…”