Neural Network Identification of Marine Ship Dynamics

Оськин, Д. А.; Dyda, Alexander A.; Markin, Vasily E.

doi:10.3182/20130918-4-jp-3022.00018

Cited by 13 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreira proposed an RNN maneuvering simulation model for turning circle and zigzag maneuvers, but this method also required a lot of training tests [16]. Oskin presented an RNN to identify a ship motion response model that neglects ship speed prediction [17]. On the basis of multiple tests, Bai used the locally weighted learning to predict maneuvering motion by using the black box structure.…”

Section: Introductionmentioning

confidence: 99%

Ship Maneuvering Prediction Using Grey Box Framework via Adaptive RM-SVM with Minor Rudder

Mei

Sun

Shi

et al. 2019

Polish Maritime Research

View full text Add to dashboard Cite

A grey box framework is applied to model ship maneuvering by using a reference model (RM) and a support vector machine (SVM) (RM-SVM). First, the nonlinear characteristics of the target ship are determined using the RM and the similarity rule. Then, the linear SVM adaptively fits the errors between acceleration variables of RM and target ship. Finally, the accelerations of the target ship are predicted using RM and linear SVM. The parameters of the RM are known and conveniently acquired, thus avoiding the modeling process. The SVM has the advantages of fast training, quick simulation, and no overfitting. Testing and validation are conducted using the ship model test data. The test case reveals the practicability of the RF-SVM based modeling method, while the validation cases confirm the generalization ability of the grey box framework.

show abstract

Section: Introductionmentioning

confidence: 99%

Ship Maneuvering Prediction Using Grey Box Framework via Adaptive RM-SVM with Minor Rudder

Mei

Sun

Shi

et al. 2019

Polish Maritime Research

View full text Add to dashboard Cite

show abstract

“…The black-box model has a potentially higher capability to express complex non-linear dynamics than the system-based method because the predetermined structure of mathematical models bounds the capability of the system-based method. Numerous studies had been done in the last decade: recursive neural network (RNN) [29,30]; locally weighted learning [31]; model reference and random forest [32].…”

Section: System-based Methodsmentioning

confidence: 99%

System Parameter Exploration of Ship Maneuvering Model for Automatic Docking / Berthing using CMA-ES

Miyauchi¹,

Maki²,

Umeda³

et al. 2021

Preprint

View full text Add to dashboard Cite

Accurate maneuvering estimation is essential to establish autonomous berthing control. The system-based mathematical model is widely used to estimate the ship's maneuver. Commonly, the system parameters of the mathematical model are obtained by the captive model test (CMT), which is time-consuming to construct an accurate model suitable for complex berthing maneuvers. System identification (SI) is an alternative to constructing the mathematical model. However, SI on the mathematical model of ship's maneuver has been only conducted on much simpler maneuver: turning and zig-zag. Therefore, this study investigates the SI on a mathematical model capable of berthing maneuver. The main contributions of this study are as follows: (i) construct the system-based mathematical model on berthing by optimizing system parameters with a reduced amount of model tests than the CMT-based scheme; (ii) Find the favorable choice of objective function and type of training data for optimization. Global optimization scheme CMA-ES explored the system parameters of the MMG model from the free-running model's trajectories. The berthing simulation with the parameters obtained by the proposed method showed better agreement with the free-running model test than parameters obtained by the CMT. Furthermore, the proposed method required fewer data amounts than a CMTbased scheme.

show abstract

“…A catamaran model using Recursive Neural Network (RNN) has demonstrated tactical circles and zigzag maneuvering assessment [39]. In addition, RNN is a network that is more flexible for ship dynamics with good perspectives to solve numerous problems in theory and applications in marine systems [40]. In facilitated the control action and steering of the ship, three algorithms were used to fulfill maneuvering tasks with assistance feedback and feed-forward controllers [41].…”

Section: Artificial Intelligencementioning

confidence: 99%

State of the Art Review on Autonomous Surface Vehicle Maneuvering Assessment

Jalal

Ayob

Rahman

et al. 2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

In the preliminary design stage, maneuvering assessment is a prerequisite based on IMO regulations. Traditionally, maneuvering assessment activities are conducted using physical boats and pilots. Such practice is tedious; requires more time to complete, suitable weather conditions, and costly. To overcome such obstacles in conducting maneuvering assessments, it may be hypothesized that simulation methods are more efficient. At present, the autonomous surface vehicle (ASV) is a hot topic within the maritime industry. Therefore, this paper shall review the state-of-the-art applications of ASV for maneuvering assessment. Also, the factors that contributed to the impact of ship maneuverability performance are discussed in this paper. Additionally, the safety aspect is also reviewed concerning COLREGS requirements.

show abstract

Neural Network Identification of Marine Ship Dynamics

Cited by 13 publications

References 1 publication

Ship Maneuvering Prediction Using Grey Box Framework via Adaptive RM-SVM with Minor Rudder

Ship Maneuvering Prediction Using Grey Box Framework via Adaptive RM-SVM with Minor Rudder

System Parameter Exploration of Ship Maneuvering Model for Automatic Docking / Berthing using CMA-ES

State of the Art Review on Autonomous Surface Vehicle Maneuvering Assessment

Contact Info

Product

Resources

About