..., the fuzzy method and the PID algorithm are combined to develop the fuzzy PID controller, and the genetic algorithm is applied to solve the thrust distribution problem. The dedicated experiments of the DP lifting operation are carried out at Tianjin University. Comparisons between the experimental results...

... conditions, multiple machine learning models were used to train and predict the data samples, and the better model was compared to the random forest. Bayesian optimization algorithm was used to optimize the hyperparameters of the random forest, and the accuracy of the prediction model was evaluated through...

... Optimization Algorithm, introduces Logistic chaos mapping and adaptive weights (LIWOA) to optimize the weights and thresholds of the neural network, and forms a ship lift duration prediction model based on the LIWOA optimized neural network. The model achieved better prediction results. INTRODUCTION...

... that send multiple rays and calculate the depth at each point from the time-of-flight of each light ray (Nouguier 2013) to wave Radars that rely on models of how the light is backscattered (Plant et al., 2012) and hence require more complex algorithms. Stereoscopy is an affordable solution that uses two...

... navigation aids has become urgent. We introduce an innovative communication resource optimization algorithm based on deep reinforcement learning, combined with the MQTT protocol, to construct a comprehensive communication network model. This algorithm incorporates constraints such as battery capacity...

... ABSTRACT For the problem of unmanned ships trajectory tracking with unknown parameters. Firstly, this article establishes a three degree of freedom ship kinematics and dynamics model. Secondly, an offline parameter identification algorithm is proposed based on the least squares method...

... applications, the obstacle avoidance path planned by classical algorithms often deviates significantly from the global planned path, thereby affecting both the safety and cost-effectiveness of navigation. To address this issue, this paper proposes a real-time obstacle avoidance control algorithm based...

... by coupling a genitic algorithms (GA). A series of numerical experiments are conducted to analyze the accuracy and effectiveness of the neural network surrogate model. Additionally, CFD simulations are performed on both the optimized hull form scheme and the parent ship scheme. The calculation results show...

... system for an underactuated Unmanned Surface Vessel (USV). Based on the line-of-sight algorithm and control requirements of ships, the ship trajectory tracking control problem is modeled as a Markov decision process, designing its state space, action space, and reward function, which rewards the agent...

... intelligence ctra sensor uit bridge simulator machine learning mechanism precision adaptive kalman filter-based estimator innovation noise algorithm simulated maneuver maneuver estimation threshold ship sea-trial experiment dataset Proceedings of the Thirty-fourth (2024) International Ocean...

.... machine learning exploration maneuver reinforcement learning ship marine science maneuvering simulation model-based reinforcement trajectory artificial intelligence dataset simulation ann journal identification algorithm technology denote ocean engineering threshold disturbance...

... as the DP system is usually over actuated. The input data to the TA have a crucial impact on the vessel response and efficiency. Typically, fuel consumption and wear and tear of the thrusts are used to construct the objective functions of the optimizing TA algorithm. The thruster models and thrust losses...

.... The multi-objective genetic algorithm (NSGA-II) is used to optimize the power allocation problem between the main engine and the generator, and a trade-off is made among all the objectives to achieve the Pareto optimum as much as possible. Ju Wang et al (2023) built a parallel diesel-electric hybrid...

... obtained by the proposed method achieved a reduction of 5.94% in mid-ship section area compared with the initial design scheme. The result obtained by the proposed method with less burden is better than that of the state-of-the-art method and classical metaheuristic algorithms. The domain knowledge-based...

... disturbance sliding mode control equation algorithm development combine sliding mode control neural network usv simulation mode stern thruster yaw mode system Proceedings of the Thirty-fourth (2024) International Ocean and Polar Engineering Conference Rhodes, Greece, June 16 21, 2024 Copyright...

.... This article develops a DIC algorithm based on MATLAB using digital image correlation methods, and conducts experiments to obtain deformation images of specimens. By using the DIC algorithm and VIC-2D software to analyze simulated speckle patterns and experimental images, the accuracy and practicality...

... genetic algorithm is employed. The calculation results show that the optimal ship main dimension is mainly affected by the flood season duration. In addition, this study gives the optimal ship main dimension corresponding to different flood season duration. INTRODUCTION With the global reduction...

... deformation (FFD) algorithm, avoids mesh re-generation of the new computer-aided-design (CAD) model while making the optimization process more efficient. This code incorporates a robust wave resistance numerical solver based on the Neumann-Michell theory and an improved genetic algorithm (IGA) to implement...

... is constructed to generate virtual data for the offline identification. An online model is established with reference to the offline model. The online model is trained by two state-of-the-art online algorithms, kernel adaptive projection and projection support vector machine. It has been verified...

... ABSTRACT Abstract: Currently, most mobile robot path planning algorithms only consider a single factor, which is the length of the path. Therefore, research on global path planning based on improved A* algorithm and cubic B-spline interpolation curve has been conducted. The improved...