Ship Motion Prediction Research Articles

Neural-network-based modelling and analysis for time series prediction of ship motion

ABSTRACTThis paper presents a data-driven model for time series prediction of ship motion. Prediction based on past time series of data is a powerful function in modern ship support systems. For a large amount of ship sensor data, neural network (NN) is considered as a proper tool in modelling the prediction system. Efforts are made to compact the NN structure through sensitivity analysis, in which the importance of each input to the output is quantified and lower ranked inputs are eliminated. Further analysis about the impact of three different learning strategies, i.e. offline, online and hybrid learning on the NN, is conducted. The hybrid learning combining the advantages of both the offline learning and the online learning exhibits superior prediction performance. According to the long-term prediction ability of recurrent NN, multi-step-ahead prediction under the hybrid learning strategy is realised in a multi-stage prediction form. Experiments are carried out using collected ship sensor data on a vessel. The results show the feasibility of generating a data-driven model through modelling and analysis of the NN for ship motion prediction.

SPH simulation of ship behaviour in severe water-shipping situations

Fishing vessels, having relatively small freeboard, are prone to encounter a water-shipping event in severe sea states. The water impact and accumulated water effects could make fishing vessels be unstable and capsize in the worst-case scenario. Therefore securing the safety of fishing vessels under water-shipping situations is an important subject, but it is not easy to predict the water behaviour in water-shipping situations, where over-topping, water impact, largely deformed free-surface and strong coupling with ship motions appear compositely. In this paper, SPH simulations using GPU are applied to the prediction of 6DoF ship motions in severe water-shipping condition. Then the prediction accuracy of the SPH method is systematically investigated through comparisons with dedicated captive and free motion tests.

A predictive controller for joint pitch-roll stabilization

Reduction of roll and pitch motions is critical in improving the safety and operability of a ship. In this paper, a predictive controller for a ship equipped with two pairs of active fins is proposed for joint pitch-roll stabilization. The proposed controller is developed on the basis of ship motion and hydrodynamic force prediction (SMHFP). The SMHFP controller consists of a short-term predictor, a force estimator, and a fin angle allocator. The short-term predictor adopts an autoregressive (AR) approach and serves to forecast ship motions. Then, predicted ship motions are used in an external hydrodynamic force estimator to evaluate the expected stabilizing forces. Finally, the optimal attack angles for active fins are allocated based on external hydrodynamic forces forecasts. The control system of the stabilizing fins and SMHFP controller is integrated into the sea-keeping program. The program was developed based on a weakly nonlinear 2.5D method, which shows better efficiency and accuracy compared with conventional 2D and 3D methods. To evaluate the performance of the proposed controller, numerical simulations of the joint pitch-roll stabilization under various sea states were investigated on a ship model. The results suggest that the SMHFP controller shows satisfactory performance in reducing pitch and roll motions simultaneously.

A Study on the Feedforward Control Algorithm for Dynamic Positioning System Using Ship Motion Prediction

In the present study we verified performance of feed-forward control algorithm using short term prediction of ship motion information by taking advantage of developed numerical simulation model of FPSO motion. Up until now, various studies have been conducted about thrust control and allocation for dynamic positioning systems maintaining positions of ships or marine structures in diverse sea environmental conditions. In the existing studies, however, the dynamic positioning systems consist of only feedback control gains using a motion of vessel derived from environmental loads such as current, wind and wave. This study addresses dynamic positioning systems which have feedforward control gain derived from forecasted value of a motion of vessel occurred by current, wind and wave force. In this study, the future motion of vessel is forecasted via Brown`s Exponential Smoothing after calculating the vessel motion via a selected mathematical model, and the control force for maintaining the position and heading angle of a vessel is decided by the feedback controller and the feedforward controller using PID theory and forecasted vessel motion respectively. For the allocation of thrusts, the Lagrange Multiplier Method is exploited. By constructing a simulation code for a dynamic positioning system of FPSO, the performance of feedforward control system which has feedback controller and feedforward controller was assessed. According to the result of this study, in case of using feedforward control system, it shows smaller maximum thrust power than using conventional feedback control system.

Ship motion prediction using dynamic seasonal RvSVR with phase space reconstruction and the chaos adaptive efficient FOA

Affected by coupling effect of 6 DOF motions, especially by the chaos characteristic, variable periodicity and noise signal of ship motion time series, it is difficult to obtain precise forecasting results of ship motion. In order to improve the forecast precision, firstly, aiming at the chaos characteristics of ship motion time series, based on the theory of the space reconstruction, this paper, employed the G-P method to determine the embedding dimension m, selected the mutual information to calculate the delay time τ, and established a chaos system reconstruction method appropriate for ship motion prediction, for rebuilding the chaotic systems of ship motion time series; Then, directing at cycle variability of the ship motion time series under different working conditions, a dynamic seasonal adjustment mechanism(namely DSAM) was designed, in view of the ship motion time series contain noise signals, robust loss function was introduced to the SVR model, and a new dynamic seasonal robust v-support vector regression forecasting model, namely DSRvSVR, was proposed and used to simulate the built chaotic systems of ship motion time series; Thirdly, in order to obtain more appropriate parameters of the DSRvSVR model, considering with shortcomings of FOA, this paper designed adaptive efficient flight guidance law (AEFGL), establish global chaos perturbation mechanism (GCPM), and established a chaos adaptive efficient fruit fly optimization algorithm, namely CAEFOA; Finally, coupling the proposed PSR method, DSRvSVR model and CAEFOA, a hybrid forecasting approach for ship motion forecasting, namely PSR–DSRvSVR–CAEFOA, was established. Subsequently, the ship heave time series under four working conditions were used to conduct numerical example, to test forecast performance of the proposed PSR–DSRvSVR–CAEFOA approach and optimize performance of CAEFOA. Analysis results showed that the proposed hybrid forecasting approach receive better forecasting performance compared with classical prediction models selected in this paper, and the CAEFOA obtain higher optimization efficiency than FOA.

A precise computation method of transient free surface Green function

The transient free surface Green function (TFSGF) is of great importance in the prediction of unsteady ship motions with forward speed. In this numerical approach, the wave part of the TFSGF and its spatial derivatives are obtained by solving the fourth-order ordinary differential equations (ODEs) based on the semi-analytical Precise Integration Method (PIM). Theoretical derivations show that in fact the horizontal and vertical derivatives can be expressed by TFSGF, which means only one ODE needs to be solved. The stability and accuracy of this method is demonstrated by the comparison with other method as well as the analytical solutions. Additionally, the proposed method is applied to solve the radiation problem of a floating hemisphere at zero speed using the time domain Rankine–Green method. The numerical hydrodynamic coefficients show good agreement with the analytical solutions.

A hybrid AR-EMD-SVR model for the short-term prediction of nonlinear and non-stationary ship motion

Accurate and reliable short-term prediction of ship motions offers improvements in both safety and control quality in ship motion sensitive maritime operations. Inspired by the satisfactory nonlinear learning capability of a support vector regression (SVR) model and the strong non-stationary processing ability of empirical mode decomposition (EMD), this paper develops a hybrid autoregressive (AR)-EMD-SVR model for the short-term forecast of nonlinear and non-stationary ship motion. The proposed hybrid model is designed by coupling the SVR model with an AR-EMD technique, which employs an AR model in ends extension. In addition to the AR-EMD-SVR model, the linear AR model, non-linear SVR model, and hybrid EMD-AR model are also studied for comparison by using ship motion time series obtained from model testing in a towing tank. Prediction results suggest that the non-stationary difficulty in the SVR model is overcome by using the AR-EMD technique, and better predictions are obtained by the proposed AR-EMD-SVR model than other models.

Rankine Source Method for Ship–Ship Interaction Problems

A Rankine source method is extended and applied to ship–ship interaction problems. The method covers the nonlinear steady flow and linear seakeeping in the frequency domain. The nonlinear steady flow solution accounts for the nonlinear free-surface conditions, ship wave, and dynamic trim and sinkage. Periodic flow due to waves is linearized with respect to the wave amplitude, taking into account interactions with the nonlinear steady flow following Hachmann approach, which considers the steady perturbation potential as constant in the body-fixed reference frame. This is advantageous for the prediction of ship motions at moderate to high Froude numbers. In this context, a new formulation of the boundary condition for the multibody case is derived. Two examples are considered, overtaking in calm water and replenishment at sea. For a feeder vessel overtaken by a container ship, horizontal forces and yaw moment are computed and compared with reference data. As an example of replenishment operation, interaction between a frigate and a supply vessel is studied. Ship motions are computed for two relative positions and three forward speeds and compared with model test data for the largest forward speed. The Rankine source method proves as more accurate compared with a zero-speed freesurface Green function method. [DOI: 10.1115/1.4029316]

Short-Term Prediction of Ship Motion Based on EMD-SVM

Ship sailing at sea is affected by many factors, such as winds, waves and so on, which makes six degrees of freedom motions and thus influences the shipboard arms control, aircraft landing and other operations. In view of the non-linear and non-stationary features of ship motion in waves, a new method based on EMD (Empirical Model Decomposition) and SVM (Support Vector Machine) is presented to predict the ship motion. The EMD is used to decompose the ship motion time series data into several IMFs (intrinsic mode functions) and a residual trend term, which decreases the difficulty of prediction. As the IMF is relatively stationary, but also non-linear, these features are fit to be processed by using SVM. Then the decompositions are used as inputs into SVM to forecast ship motion. The simulation and comparison analysis show that the EMD-SVM prediction model can effectively forecast the ship motion in waves.

Real-Time Ship Motion Prediction Based on Time Delay Wavelet Neural Network

A wavelet neural network with time delay is proposed based on nonlinear autoregressive model with exogenous inputs (NARMAX) model, and the sensitivity method is applied in the selection of network inputs. The inclusion of delayed system information improves the network’s capability of representing the dynamic changes of time-varying systems. The implement of sensitivity analysis reduces the dimension of input as well as the dimension of networks, thus improving its generalization ability. The time delay wavelet neural network was implemented to real-time ship motion prediction, simulations are conducted based on the measured data of vessel “YUKUN,” and the results demonstrate that the feasibility of the proposed method.

An Application of the Improved Autoregressive Method for Two Vessels Roll Motion Prediction

It is of great significance and value to predict the roll of two ships, especially when one is replenishing for the other or in some other conditions. Autoregressive time series analysis method (AR) with Recursive least squares (RLS) theory is the mainstream currently and the effectiveness for the prediction of the motion attitudes have been fully validated. However, there are some differences between the prediction for the motion of two vessels and for that of one. The hydrodynamic interactions between two ships should be taken into consideration and be reflected in the application of the method. In order to solve this issue, this work firstly proposed a double ships autoregressive (DAR) method, which can determine the orders and the parameters of model in real-time with consideration of the interference between two ships and the DAR method was applied to forecast the roll motion between two ships. The simulative results of DAR method show the validity and veracity compared to real value and the advancement compared to the autoregressive (AR) method for single ship motion prediction.

Research on Ship Swaying Motion Prediction Based on Multi-Variable Chaotic Time Series Analysis

Wind and waves have particularly significant influence upon exertion of naval vessels battle effectiveness. It is urgently necessary to improve the ability of the Navy to carry out combat service in severe sea state normally. This paper aims to obtain the accurate prediction of ship motions with second level predictable time in real waves. According to the characteristics of the ship motion, the research on extremely short-time prediction of ship motion has been carried out based on multi-variable chaotic time series analysis, and the effectiveness of the prediction of ship motion in real wave is highly improved.

Application of method of fundamental solutions in solving potential flow problems for ship motion prediction

A novel panel-free approach based on the method of fundamental solutions (MFS) is proposed to solve the potential flow for predicting ship motion responses in the frequency domain according to strip theory. Compared with the conventional boundary element method (BEM), MFS is a desingularized, panel-free and integration-free approach. As a result, it is mathematically simple and easy for programming. The velocity potential is described by radial basis function (RBF) approximations and any degree of continuity of the velocity potential gradient can be obtained. Desingularization is achieved through collating singularities on a pseudo boundary outside the real fluid domain. Practical implementation and numerical characteristics of the MFS for solving the potential flow problem concerning ship hydrodynamics are elaborated through the computation of a 2D rectangular section. Then, the current method is further integrated with frequency domain strip theory to predict the heave and pitch responses of a containership and a very large crude carrier (VLCC) in regular head waves. The results of both ships agree well with the 3D frequency domain panel method and experimental data. Thus, the correctness and usefulness of the proposed approach are proved. We hope that this paper will serve as a motivation for other researchers to apply the MFS to various challenging problems in the field of ship hydrodynamics.

Experimental and Numerical Study of Stem Shape Influence on Speed Loss in Waves

This paper addresses prediction of ship motion and propulsion system behaviour to demonstrate the effect of waves in real sea states. For a 8000 t deadweight tanker, three different stem shapes are studied experimentally and numerically. Numerical simulations of speed loss were performed in time and frequency domain, generally agreeing well with experimental results. While a conventional bow with bulb and flare gave least calm water resistance, a bow without bulb and flare gave least total resistance in severe wave conditions.

Nonlinear Ship Motion Prediction Via a Novel High Precision RBF Neural Network

Nonlinear Ship Motion Prediction Via a Novel High Precision RBF Neural Network

Verification and validation of ShipMo3D ship motion predictions in the time and frequency domains

This paper compares frequency domain and time domain predictions from the ShipMo3D ship motion library with observed motions from model tests and sea trials. ShipMo3D evaluates hull radiation and diffraction forces using the frequency domain Green function for zero forward speed, which is a suitable approach for ships travelling at moderate speed (e.g., Froude numbers up to 0.4). Numerical predictions give generally good agreement with experiments. Frequency domain and linear time domain predictions are almost identical. Evaluation of nonlinear buoyancy and incident wave forces using the instantaneous wetted hull surface gives no improvement in numerical predictions. Consistent prediction of roll motions remains a challenge for seakeeping codes due to the associated viscous effects.

A Six Degrees of Freedom Ship Simulation System for Maritime Education

The title of this paper was changed from 'A Ship Simulation System for Maritime Education' to 'A Six Degrees of Freedom Ship Simulation System for Maritime Education' on 21/09/2012.The authors N Kodikara, C Keppitiyagama and R Rosa were added to the paper on 21/09/2012.This paper presents Six-degrees-of-freedom ship simulation system which allows simulated ship handling under complicated environmental conditions and threat scenarios. This system simulates real-time six degrees of freedom ship motions (pitch, heave, roll, surge, sway, and yaw) under user interactions, and environmental conditions. The simulation system consists of a ship motion prediction system and a perception enhanced immersive virtual environment with greater ecological validity. This ship motion prediction system uses a few model parameters which can be evaluated by using standard ship maneuvering test or determined easily from databases such as Lloyd’s register. This virtual environment supports multiple-display viewing that can greatly enhance user perception. Ecological environment for strong sensation of immersion is also developed. The virtual environment facilitates the incorporation of real world ships, geographical sceneries, different environmental conditions and wide range of visibility and illumination effects. This simulation system can be used to demonstrate ship motions, maneuvering tactics and assign focused missions to trainees and evaluate their performance. Trainees can use the simulation system to study at their own pace. Implementation and operational cost of this ship simulation system is only a fraction of the conventional training involving real ships. DOI: http://dx.doi.org/10.4038/icter.v3i2.2847 The International Journal on Advances in ICT for Emerging Regions 2010 03 (02) :34 - 47

Verification and validation of ShipMo3D ship motion predictions in the time and frequency domains

This paper compares frequency domain and time domain predictions from the ShipMo3D ship motion library with observed motions from model tests and sea trials. ShipMo3D evaluates hull radiation and diffraction forces using the frequency domain Green function for zero forward speed, which is a suitable approach for ships travelling at moderate speed (e.g., Froude numbers up to 0.4). Numerical predictions give generally good agreement with experiments. Frequency domain and linear time domain predictions are almost identical. Evaluation of nonlinear buoyancy and incident wave forces using the instantaneous wetted hull surface gives no improvement in numerical predictions. Consistent prediction of roll motions remains a challenge for seakeeping codes due to the associated viscous effects.

Wave loads and flexible fluid-structure interactions: current developments and future directions

The function of a Classification Society includes the setting of standards for the design, construction and maintenance of ship hulls to ensure adequate safety throughout their service life. Fundamental to this is the determination of the design loads to support the prescriptive Rule requirements and for application in direct calculations. The current design philosophy for the prediction of motions and wave-induced loads is driven by first-principles calculation procedures based on well-proven applications such as ship motion prediction programs. In recent years, the software and computer technology available to predict design loads has improved dramatically. With the stepwise increase in ship size and complexity it is necessary to utilise the latest technologies to assess the design loads on new ship designs. This paper discusses some of the recent experiences of Lloyd's Register with regard to the current state of the art in the assessment of design loads and structural responses by reviewing recent work on the effects of flexible fluid-structure interaction for hull girder and also for sloshing applications. The paper also discusses the Lloyd's Register strategic research programme on hydrodynamics, involving the use of state-of-the-art technologies for the solution of ship dynamic response problems.

State-of-the-Art of Wave Measurement for Ship Motion Prediction

Abstract Ship motion prediction is useful for several purposes, related to navigation or to special operations. For instance the short-term predictions, perhaps a few seconds ahead, is important to help helicopter pilots when landing on ships. This paper reviews technologies for wave height measurement in order to predict ship motion. Two main philosophies are distinguished: one looks to distant incoming waves to get more prediction time, the other points downwards near the bow. Radar is a key technology, and in particular X-band radar: new relevant developments are taking place in this direction.