☆ 4.7 Article

Self-organizing data-driven prediction model of ship maneuvering fast-dynamics

OCEAN ENGINEERING (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Marine

Online modeling and prediction of maritime autonomous surface ship maneuvering motion under ocean waves

Lijia Chen et al.

Summary: This paper focuses on the development of Maritime Autonomous Surface Ships (MASS) and addresses the challenges in ship motion prediction. By utilizing a mathematical model and the least squares support vector machine (LSSVM) identification algorithm, an offline black-box identification model is established for MASS motion prediction. Additionally, an error-based online modeling method is proposed for adaptive prediction of MASS motion under ocean waves.

OCEAN ENGINEERING (2023)

Add to Collection

Article Engineering, Marine

Math-data integrated prediction model for ship maneuvering motion

Qi Dong et al.

Summary: In this paper, a math-data integrated prediction (MDIP) model is proposed for accurate motion prediction in ship maneuvering. The model combines mathematical and data-driven modules, and validates the effectiveness of order selection and math-data integration in enhancing ship motion prediction accuracy.

OCEAN ENGINEERING (2023)

Add to Collection

Article Automation & Control Systems

Nonlinear Identification for 4-DOF Ship Maneuvering Modeling via Full-Scale Trial Data

Chunyu Song et al.

Summary: This research presents a 4-DOF ship maneuvering modeling based on full-scale trial data and proposes a new multi-innovation least squares algorithm for identifying nonlinear innovations in ship maneuvering motion. The design scheme shows significant computational advantages, higher accuracy, and faster identification speed.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

Add to Collection

Article Engineering, Marine

On neural network identification for low-speed ship maneuvering model

Kouki Wakita et al.

Summary: This study proposes a system identification method for generating a low-speed maneuvering model using recurrent neural networks (RNNs) and free running model tests. The aim is to achieve automatic berthing control. By reducing the impact of noise in the training data and conducting manual random maneuver tests, an accurate berthing maneuver model was obtained. The experimental results demonstrate that the proposed method using a neural network model accurately represents low-speed maneuvering motions.

JOURNAL OF MARINE SCIENCE AND TECHNOLOGY (2022)

Add to Collection

Article Engineering, Marine

Recurrent neural networks for nonparametric modeling of ship maneuvering motion

Lizhu Hao et al.

Summary: This paper presents a model based on recurrent neural network (RNN) for predicting ship maneuvering motion. The model takes input of rudder orders, propeller speed, and past velocities, and shows good generalization performance. The concept of uncertainty is proposed for further analysis.

INTERNATIONAL JOURNAL OF NAVAL ARCHITECTURE AND OCEAN ENGINEERING (2022)

Add to Collection

Article Engineering, Marine

Identification modeling and prediction of ship maneuvering motion based on LSTM deep neural network

Yan Jiang et al.

Summary: This paper introduces a novel system identification scheme to obtain a MIMO model of ship maneuvering motion using LSTM deep neural network, which shows better generalization performance and robustness to noise. The study successfully demonstrates the mapping between ship motion dynamics and LSTM computation, and establishes an equivalent model with improved accuracy in predicting ship maneuvering motion.

JOURNAL OF MARINE SCIENCE AND TECHNOLOGY (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Autonomous Pilot of Unmanned Surface Vehicles: Bridging Path Planning and Tracking

Ning Wang et al.

Summary: In this paper, an autonomous pilot framework for unmanned surface vehicles (USVs) in congested waters is proposed. The framework integrates path planning and tracking, and utilizes a combination of genetic algorithms and deep reinforcement learning for optimal policy generation. Comprehensive validations and comparisons demonstrate the effectiveness and superiority of the framework in various real-world geographies.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2022)

Add to Collection

Article Engineering, Marine

Nonparametric modeling of ship maneuvering motion based on self-designed fully connected neural network

Hong-Wei He et al.

Summary: A self-designed fully connected neural network is proposed for nonparametric modeling of ship maneuvering motion by using Bayesian optimization and Gaussian process. The method is validated on the KVLCC2 ship using experimental data, showing high prediction accuracy and strong generalization ability.

OCEAN ENGINEERING (2022)

Add to Collection

Article Engineering, Marine

A Novel Parameter Identification Algorithm for 3-DOF Ship Maneuvering Modelling Using Nonlinear Multi-Innovation

Baigang Zhao et al.

Journal of Marine Science and Engineering (2022)

Add to Collection

Article Engineering, Electrical & Electronic

An Unscented Kalman Filter Online Identification Approach for a Nonlinear Ship Motion Model Using a Self-Navigation Test

Jian Zheng et al.

Summary: This paper proposes a method for online parameter identification of nonlinear ship motion systems using an unscented Kalman filter (UKF) combined with rolling wavelet denoising. The proposed navigation identification framework improves the accuracy and control effectiveness of ship motion system identification.

MACHINES (2022)

Add to Collection

Article Engineering, Marine

Predicting Ship Trajectory Based on Neural Networks Using AIS Data

Tamara A. Volkova et al.

Summary: Creating an autonomously moving vessel involves accurately determining the vessel's coordinates, predicting its trajectory, estimating motion trends, and calculating course corrections. Reading satellite signals is the most accurate way to determine vessel coordinates, and using artificial neural networks to create a correction system on non-maneuvering routes is feasible.

JOURNAL OF MARINE SCIENCE AND ENGINEERING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Data-Driven Performance-Prescribed Reinforcement Learning Control of an Unmanned Surface Vehicle

Ning Wang et al.

Summary: The article introduces a novel self-learning-based model-free solution, DPRLC, for optimal control and prescribed tracking accuracy of USVs in complex marine environments. The scheme utilizes data-driven performance-prescribed reinforcement learning to convert constrained tracking errors into constraint-free stabilization for controller synthesis optimization. Theoretical analysis proves the effectiveness and superiority of the DPRLC scheme in guaranteeing prescribed tracking accuracy while minimizing costs.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Add to Collection

Article Engineering, Ocean

Identification of coupled response models for ship steering and roll motion using support vector machines

Yan Jiang et al.

Summary: The study uses support vector machines and least squares support vector machines to train response models for ship steering and roll motion, demonstrating good prediction ability and generalization performance through comparison with experimental data.

APPLIED OCEAN RESEARCH (2021)

Add to Collection

Article Automation & Control Systems

Finite-Time Unknown Observer-Based Interactive Trajectory Tracking Control of Asymmetric Underactuated Surface Vehicles

Ning Wang et al.

Summary: A finite-time unknown observer-based interactive trajectory tracking control scheme was proposed for an asymmetric underactuated surface vehicle. The philosophy of interactive trajectory, featuring freely prescribed surge and yaw dynamics, was innovatively established for the first time, contributing to a family of uniformly trackable trajectories. The closed-loop system stability was guaranteed by combining Lyapunov approach with cascade analysis, proving that tracking errors globally asymptotically converge to zero.

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY (2021)

Add to Collection

Article Engineering, Ocean

Numerical simulation of 6-degrees-of-freedom motions for a manoeuvring ship in regular waves

Ryosuke Suzuki et al.

Summary: In this study, the authors proposed a numerical simulation method to estimate 6 degrees of freedom motions of a manoeuvring ship in regular waves. The method is applicable to general manoeuvres and short waves, and can be used for both blunt and slender ships.

APPLIED OCEAN RESEARCH (2021)

Add to Collection

Article Automation & Control Systems

Extreme Learning-Based Monocular Visual Servo of an Unmanned Surface Vessel

Ning Wang et al.

Summary: This article presents an extreme learning-based monocular visual-servo scheme for maneuvering an unmanned surface vessel (USV) in the face of unmatched visual-servo uncertainties and unknown dynamics/disturbances. By utilizing the backstepping philosophy and adaptive compensating identifier, the scheme accelerates fast-dynamics identification and demonstrates remarkable performance and superiority on a prototype USV.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Reinforcement Learning-Based Optimal Tracking Control of an Unknown Unmanned Surface Vehicle

Ning Wang et al.

Summary: This article introduces a novel reinforcement learning-based optimal tracking control scheme for an unmanned surface vehicle in the presence of complex unknowns. By utilizing neural network approximators and an actor-critic reinforcement learning framework, the scheme effectively identifies complex unknowns and establishes an optimal control strategy and cost function.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Ship Model Identification with Genetic Algorithm Tuning

Anna Miller

Summary: The proposed method focuses on tuning a linearized plant model based on real measurements, speeding up the model identification process and improving the model's fit with experimental data. Through reducing standard deviations of model coefficients and eliminating output signal oscillations, the method enhances the mapping of ship dynamics.

APPLIED SCIENCES-BASEL (2021)

Add to Collection

Article Engineering, Civil

A Neural-Network-Based Sensitivity Analysis Approach for Data-Driven Modeling of Ship Motion

Xu Cheng et al.

IEEE JOURNAL OF OCEANIC ENGINEERING (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Dynamics-Constrained Global-Local Hybrid Path Planning of an Autonomous Surface Vehicle

Ning Wang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Nonlinear systems modelling based on self-organizing fuzzy neural network with hierarchical pruning scheme

Hongbiao Zhou et al.

APPLIED SOFT COMPUTING (2020)

Add to Collection

Article Engineering, Marine

Kernel-based support vector regression for nonparametric modeling of ship maneuvering motion

Zihao Wang et al.

OCEAN ENGINEERING (2020)

Add to Collection

Article Engineering, Marine

System identification of ship dynamic model based on Gaussian process regression with input noise

Yifan Xue et al.

OCEAN ENGINEERING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Modelling of a surface marine vehicle with kernel ridge regression confidence machine

David Moreno-Salinas et al.

APPLIED SOFT COMPUTING (2019)

Add to Collection

Article Engineering, Marine

Data-driven uncertainty and sensitivity analysis for ship motion modeling in offshore operations

Xu Cheng et al.

OCEAN ENGINEERING (2019)

Add to Collection

Article Engineering, Marine

A real-time ship roll motion prediction using wavelet transform and variable RBF network

Jian-Chuan Yin et al.

OCEAN ENGINEERING (2018)

Add to Collection

Article Automation & Control Systems

Data-Driven Modeling Using Improved Multi-Objective Optimization Based Neural Network for Coke Furnace System

Ridong Zhang et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2017)

Add to Collection

Article Computer Science, Artificial Intelligence

Improvements on parsimonious extreme learning machine using recursive orthogonal least squares

Yong-Ping Zhao et al.

NEUROCOMPUTING (2016)

Add to Collection

Article Automation & Control Systems

Multi-innovation auto-constructed least squares identification for 4 DOF ship manoeuvring modelling with full-scale trial data

Guoqing Zhang et al.

ISA TRANSACTIONS (2015)

Add to Collection

Article Automation & Control Systems

Large Tanker Motion Model Identification Using Generalized Ellipsoidal Basis Function-Based Fuzzy Neural Networks

Ning Wang et al.

IEEE TRANSACTIONS ON CYBERNETICS (2015)

Add to Collection

Review Engineering, Marine

Introduction of MMG standard method for ship maneuvering predictions

H. Yasukawa et al.

JOURNAL OF MARINE SCIENCE AND TECHNOLOGY (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Constructive multi-output extreme learning machine with application to large tanker motion dynamics identification

Ning Wang et al.

NEUROCOMPUTING (2014)

Add to Collection

Article Engineering, Marine

Manoeuvring simulation of catamaran by using implicit models based on support vector machines

Weilin Luo et al.

OCEAN ENGINEERING (2014)

Add to Collection

Article Engineering, Marine

Black-box modeling of ship manoeuvring motion based on feed-forward neural network with Chebyshev orthogonal basis function

Xin-Guang Zhang et al.

JOURNAL OF MARINE SCIENCE AND TECHNOLOGY (2013)

Add to Collection

Article Engineering, Marine

On-line prediction of ship roll motion during maneuvering using sequential learning RBF neural networks

Jian-chuan Yin et al.

OCEAN ENGINEERING (2013)

Add to Collection

Article Automation & Control Systems

Data-Driven Interval Type-2 Neural Fuzzy System With High Learning Accuracy and Improved Model Interpretability

Chia-Feng Juang et al.

IEEE TRANSACTIONS ON CYBERNETICS (2013)

Add to Collection

Article Computer Science, Artificial Intelligence

Parameter estimation of fuzzy neural network controller based on a modified differential evolution

Hung-Ching Lu et al.

NEUROCOMPUTING (2012)

Add to Collection

Article Engineering, Marine

Estimating maneuvering coefficients using system identification methods with experimental, system-based, and CFD free-running trial data

Motoki Araki et al.

OCEAN ENGINEERING (2012)

Add to Collection

Article Computer Science, Artificial Intelligence

A Generalized Ellipsoidal Basis Function Based Online Self-constructing Fuzzy Neural Network

Ning Wang

NEURAL PROCESSING LETTERS (2011)

Add to Collection

Article Computer Science, Artificial Intelligence

AN ONLINE SELF-ORGANIZING SCHEME FOR PARSIMONIOUS AND ACCURATE FUZZY NEURAL NETWORKS

Ning Wang et al.

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS (2010)

Add to Collection

Article Computer Science, Artificial Intelligence

A fast and accurate online self-organizing scheme for parsimonious fuzzy neural networks

Ning Wang et al.

NEUROCOMPUTING (2009)

Add to Collection

Article Engineering, Ocean

System identification for nonlinear maneuvering of large tankers using artificial neural network

G. Rajesh et al.

APPLIED OCEAN RESEARCH (2008)

Add to Collection

Article Computer Science, Artificial Intelligence

An on-line algorithm for creating self-organizing fuzzy neural networks

G Leng et al.

NEURAL NETWORKS (2004)

Add to Collection

Article Automation & Control Systems

Dynamic fuzzy neural networks - A novel approach to function approximation

SQ Wu et al.

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS (2000)

Add to Collection

© Peeref 2019-2024. All rights reserved.