Ship RBF neural network sliding mode PID heading control

In view of the inherent non-linearity, complexity, susceptibility to external wind, wave, and current interference of under-driven ships, and the difficulty of adjusting and adjusting control parameters, to improve the performance of ship’s autopilot, a kind of RBF neural network sliding mode variable structure PID controller is designed. Traditional PID control is sensitive to parameter changes, online tuning is difficult, and easy to overshoot. In order to solve this problem, combining the variable structure characteristics of PID, a differential compensation term is added to the integral term to convert the PID control parameters into three parameters with more obvious physical meanings, and then combined with the RBF neural network learning and identification function to realize online tuning and adaptive control of ship control parameters. Using MATLAB software to simulate the container ship “MV KOTA SEGAR” MMG model shows that the designed RBF neural network sliding mode PID controller can effectively eliminate the ship’s lateral deviation caused by external interference such as wind, waves, currents, etc., with high control accuracy,robustness and strong adaptability.

FEATURES ANALYSIS AND SYSTEM IDENTIFICATION OF MECHANOMYOGRAPHY AND ELECTROMYOGRAPHY UNDER TRANSCRANIAL MAGNETIC STIMULATION

Transcranial magnetic stimulation (TMS) is an electrophysiological technique that uses alternating magnetic fields to deliver electric current and stimulate the cerebral cortex. When TMS is used for the evaluation of brain diseases, it is necessary to detect the contraction of the corresponding muscles in the cerebral cortex stimulated by TMS, and the muscle activity referred to as motor evoked potential (MEP). This study simultaneously recorded the mechanomyography (MMG) and electromyography (EMG) from the right abductor pollicis brevis muscle during TMS with different intensities in order to observe whether the MEP parameters from MMG signals showed similar trait of EMG recordings. Moreover, the subspace method (N4SID) and transfer function were used to identify the TMS–MMG system. In this system, the input was a pulse signal of TMS, and the output was the MMG signal detected from the target muscle. The TMS–MMG system was identified as a fourth-order model. This study also analyzed the internal features of the system and demonstrated that the poles of healthy subjects were distributed in a range, and the gain increased with the increase of the TMS intensity. It was found that MMG signals can be used as diagnostic indicators of TMS, and the TMS–MMG model can be used to further explore the details of how TMS generates responses measured with MMG.

Modeling and Simulation of Automatic Berthing based on Bow and Stern Thruster Assist for Unmanned Surface Vehicle

The purpose of this study is to meet the maneuverability requirements of the Unmanned Surface Vehicle (USV) in different conditions by the effective use of the bow and stern thruster, thus completing the automatic berthing task. Based on the MMG model, the maneuverability mathematical model of the USV with bow and stern thruster was established. And the motion simulation of USV maneuvering was carried out through the numerical simulation calculation. Then the berthing plan was designed basedon the maneuverability analysis of the USV low-speed motion, and the simulation of automatic berthing for USV was carried out. The research results of this paper can be of certain practical significance for the USV based on the support of the bow and stern thruster in the berthing. At the same time, it also provides a certain theoretical reference for the handling of the USV automatic berthing.

EXPERIMENTAL AND NUMERICAL INVESTIGATION ON MANEUVERING PERFORMANCE OF SMALL WATERPLANE AREA TWIN HULL

Free running model tests and a system-based method are employed to evaluate maneuvering performance for a Small Waterplane Area Twin Hull (SWATH) ship in this paper. A 3 degrees of freedom Maneuvering Modeling Group (MMG) model is implemented to numerically simulate the maneuvering motions in calm water. Virtual captive model tests are performed by using a Reynolds-averaged Navier-Stokes (RANS) method to acquire hydrodynamic derivatives, after a convergence study to check the numerical accuracy. The turning and zigzag maneuvers are simulated by solving the maneuvering motion model and the predicted results agree well with the experimental data. Moreover, free running model tests are carried out for three lateral separations and the influence of the lateral separations on maneuvering performance is investigated. The research results of this paper will be helpful for the maneuvering prediction of the small waterplane area twin hull ship.

NUMERICAL SIMULATION OF SHIP NAVIGATION IN ROUGH SEAS BASED ON ECMWF DATA

Recently, several changes have been observed in the Earth’s environment. This is also applicable to the ocean environment. The concept of weather routing has been applied for ship navigation for a long time. Many service providers offer weather routing service with the availability of high-quality satellite data. Unfortunately, not much information is available in the public domain as to how much the recent change in the weather pattern has affected ship navigation. The purpose of this paper is to fill this information gap. We investigate the influence of recent changes in the ocean environment on ship navigation. Weather data from ECMWF, namely ERA-Interim, is used for this purpose. The ECMWF data for the last 27 years is analysed. We compute the statistical characteristics of this data for the first 10 years, last 10 years, and 27 years. The statistical characteristics of the data are determined based on “summer” and “winter” zones as defined by international maritime regulations. Six different worldwide commercial ship routes are selected covering all the ocean regions. Navigation on great ellipse with waypoint is considered. MMG type ship manoeuvring model for 3 different ship types (DTMB 5415, PCC, VLCC) is used. The added resistance due to wave, wind and the effort of keeping the ship on the desired course using autopilot in the rough ocean environment is included in the MMG model. The fuel consumption and the duration of each one of the voyage are computed. Based on the analysis and simulation results it is shown that: (i) The mean wave height, wave period, and wind speed has increased in some ocean zones and decreased in other ocean zones. If any change has occurred, it is uniform for both seasons (summer and winter). (ii) In which ocean regions there is a perceptible change in fuel consumption, average ship speed and voyage time due to the changes in the weather pattern. (iii) The changing weather pattern in different ocean zones affects each ship type differently.

System-Based Modelling of KCS Manoeuvring in Calm Water, Current and Waves

Maritime autonomous surface ships (MASS) require accurate future state projection to initiate collision-avoidance manoeuvres. Forecasts of the vessels’ trajectories and motions are fundamentally based on the mathematical manoeuvring model, which is an essential component of their hydrodynamic digital twin nowadays. Using the benchmark container ship KCS as an object of study, this paper adopts a 4-DOF modular-type manoeuvring (MMG) model to predict the vessel trajectories in calm water and under the presence of steady current and regular waves. The current effects are treated as additional ship over water speed, while the wave effects are considered by superimposing the second-order mean wave drift loads to the calm water hull hydrodynamics. The wave drift loads are solved using the potential flow solver WASIM, which is based on Rankine panel method. The computed vessel trajectories and motions are compared with available literature results and show good correlation.

Numerical Simulation on Oblique Towing Tests and Pure Yaw Tests of a Containership in Surf-Riding Condition

Maneuvering in waves is a complex and critical issue that confuses researchers for the last several decades. Among the existing methods for predicting the maneuverability in waves, the widely-used mathematical model approach (MMG model) is considered to be efficient and accurate in large wavelength and small wave steepness conditions. However, based on the assumption that the maneuvering forces in waves are the same as those in calm water, the wave effect on the hydrodynamic derivatives is neglected in most mathematical model approaches. According to the previous theoretical analysis and experimental data, this assumption is flawed. Therefore, several experiments and some numerical simulations have conducted to research the wave effect on hydrodynamic derivatives. In the present study, oblique towing tests and pure yaw tests will be simulated using the state-of-the-art CFD techniques to obtain the linear hydrodynamic derivatives in waves. The simulation cases in the present study are set according to previous PMM tests of S175 containership in surf-riding conditions. And the simulation results are in good agreement with experimental ones. Based on that, the wave effect on hydrodynamic derivatives is obtained and some discussions are made. Finally, the course stability of the containership on the different relative position of the wave are calculated to analyze the preliminary reason for the broaching-to phenomenon.

Path following of underactuated surface ships based on model predictive control with neural network

A model predictive control approach is proposed for path following of underactuated surface ships with input saturation, parameters uncertainties, and environmental disturbances. An Euler iterative algorithm is used to reduce the calculation amount of model predictive control. The matter of input saturation is addressed naturally and flexibly by taking advantage of model predictive control. The mathematical model group (MMG) model as the internal model improves the control accuracy. A radial basis function neural network is also applied to compensate the total unknowns including parameters uncertainties and environmental disturbances. The numerical simulation results show that the designed controller can force an underactuated ship to follow the desired path accurately in the case of input saturation and time-varying environmental disturbances including wind, current, and wave.

Manoeuvring Prediction of KVLCC2 with Hydrodynamic Derivatives Generated by a Virtual Captive Model Test

This paper describes the application of computational fluid dynamics rather than a towing tank test for the prediction of hydrodynamic derivatives using a RANS-based solver. Virtual captive model tests are conducted, including an oblique towing test and circular motion test for a bare model scale KVLCC2 hull, to obtain linear and nonlinear hydrodynamic derivatives in the 3rd-order MMG model. A static drift test is used in a convergence study to verify the numerical accuracy. The computed hydrodynamic forces and derivatives are compared with the available captive model test data, showing good agreement overall. Simulations of standard turning and zigzag manoeuvres are carried out with the computed hydrodynamic derivatives and are compared with available experimental data. The results show an acceptable level of prediction accuracy, indicating that the proposed method is capable of predicting manoeuvring motions.