Unmanned surface vessels (USVs) are required to follow a path during a task. This is essential for the USV, especially when following a curvilinear path or considering the interference of waves, and this work has been proven to be complicated. In this paper, a PID parameter tuning and optimizing method based on deep reinforcement learning were proposed to control the USV heading. Firstly, the Abkowite dynamics model with three degrees of freedom (DOF) is established. Secondly, the guidance law on the line-of-sight (LOS) method and the USV heading control system of the PID controller are designed. To satisfy the time-varying demand of PID parameters for guiding control, especially when the USV moves in waves, the soft actor–critic auto (SAC-auto) method is presented to adjust the PID parameters automatically. Thirdly, the state, action, and reward functions of the agent are designed for training and learning. Finally, numerical simulations are performed, and the results validated the feasibility and validity of the feasibility and effectiveness of the proposed method.

Maneuverability, which is closely related to operational performance and safety, is one of the important hydrodynamic properties of an underwater vehicle (UV), and its accurate prediction is essential for preliminary design. The purpose of this study is to analyze the turning ability of a UV while rising or submerging; the computational fluid dynamics (CFD) method was used to numerically predict the six-DOF self-propelled maneuvers of submarine model BB2, including steady turning maneuvers and space spiral maneuvers. In this study, the overset mesh method was used to deal with multi-body motion, the body force method was used to describe the thrust distribution of the propeller at the model scale, and the numerical prediction also included the dynamic deflection of the control planes, where the command was issued by the autopilot. Then, this study used the published model test results of the tank to verify the effectiveness of the CFD prediction of steady turning maneuvers, and the prediction of space spiral maneuvers was carried out on this basis. The numerical results show that the turning motion has a great influence on the depth and pitch attitude of the submarine, and a “stern heavier” phenomenon occurs to a submarine after steering. The underwater turning of a submarine can not only reduce the speed to brake but also limit the dangerous depth. The conclusion is of certain reference significance for submarine emergency maneuvers.

Nowadays, system-based simulation is one of the main methods for ship manoeuvring prediction. Great efforts are usually devoted to the determination of hydrodynamic derivatives as required for the mathematical models used for such methods. System identification methods can be applied to determine hydrodynamic derivatives. The purpose of this work is to present a parameter identification study based on least-squares support-vector machines (LS-SVMs) to obtain hydrodynamic derivatives for an Abkowitz-type model. An approach for constructing training data is used to reduce parameter drift. In addition, wavelet threshold denoising is applied to filter out the noise from the sample data during data pre-processing. Most of the resulting derivatives are very close to the original ones—especially for linear derivatives. Although the errors of high-order derivatives seem large, the final predicted results of the turning circle and zigzag manoeuvres agree pretty well with the reference ones. This indicates that the used methods are effective in obtaining manoeuvring hydrodynamic derivatives.

The wave-induced motions, and steady wave forces and moments for the oil tanker KVLCC2 in regular head and oblique waves are numerically predicted by using the expanded RANS solver based on OpenFOAM. New modules of wave boundary condition are programed into OpenFOAM for this purpose. In the present consideration, the steady wave forces and moments include not only the contribution of hydrodynamic effects but also the contribution of the inertial effects due to wave-induced ship motions. The computed results show that the contribution of the inertial effects due to heave and pitch in head waves is non-negligible when wave-induced motions are of large amplitude, for example, in long waves. The influence of wave amplitude on added resistance in head waves is also analyzed. The dimensionless added resistance becomes smaller with the increasing wave amplitude, indicating that added resistance is not proportional to the square of wave amplitude. However, wave amplitude seems not to affect the heave and pitch RAOs significantly. The steady wave surge force, sway force and yaw moment for the KVLCC2 with zero speed in oblique waves are computed as well. The present RANS results are compared with available experimental data, and very good agreements are found between them.

Unmanned surface vessels (USVs) are required to perform motion prediction during a task. This is essential for USVs, especially when conducting motion control, and this work has been proven to be complicated. In this paper, an off-line black box modeling method for USV maneuvering, the Sparrow search algorithm-based weighted-least-squares support vector machine (SSA-WLS-SVM) was proposed to recognize the motion model of a USV. Firstly, the construction of the USV test platform and the processing process of the experimental data were introduced, the correctness of the MMG model was verified using a comparison of the test data and the simulation results, and then the MMG model was used to produce sample data later. To improve the stability and robustness of LS-SVM, weighted least squares and SSA were introduced to perform the optimization of the parameters of the algorithm and its kernel function. Then, the random maneuvering dataset was obtained using simulation on the MMG model, which was then preprocessed and used for training the black-box model. To verify the generalization ability of the identified model, the black-box model was used for comparison analysis between motion prediction with the proposed model and maneuvering test on the USV platform in a scenario different from the training data.

Ship maneuvering performance in waves has attracted much attention in recent years. One of main research efforts for this problem has been devoted to the high-accuracy computation of hydrodynamic forces and moments, as well as wave-induced motions, for ships performing maneuvering motions in waves. The objective of this article is to present a numerical study on the computation of the mean forces and moments, and wave-induced six degrees of freedom motions for a ship moving obliquely in regular head and beam waves. The RANS (Reynolds-Averaged Navier-Stokes) solver based on OpenFOAM is used for this purpose. The RANS computations herein are carried out in a horizontal coordinate system. The numerical wave maker with prescribing values of flow variables on the domain boundaries is applied for the wave generation in the computational domain. However, in order to prevent wave reflection, relaxed zones adjacent to the wave maker boundaries are set up. A new program module is inserted into OpenFOAM to update the flow velocity and wave evaluation on the wave-maker boundaries and in the relaxed zones during the RANS computation. The mesh deformation method is employed to allow the ship to perform motions in space. However, a virtual spring system is attached to the ship so as to restrain the surge, sway and yaw, while heave, pitch and roll are completely free, so that the ship is able to oscillate periodically around a certain position in space. The computed mean forces and moments with the inertia effects agree fairly well with the experimental data, and the computed wave-induced motions are also in quite reasonable agreement with the experimental data. This study shows a very successful computation, as well as the procedure of the RANS results processing.