ObjectiveThis study seeks to predict the hydrodynamic properties of composite propellers and analyze their fluid-structure interaction characteristics. MethodsCombined with the boundary element method (BEM) and finite element method (FEM), a composite propeller fluid-structure interaction calculation method is established. The surface pressure and hydrodynamic force of the composite propeller blade are calculated by BEM, and the calculated surface pressure of the propeller is transferred to a finite element structure model. The displacement and stress distribution of the composite propeller under load are then predicted by FEM, and the deformation is transferred to the hydraulic force calculation of the propeller BEM so as to realize two-way fluid-structure interaction calculation. The feasibility of this method is verified by calculating a 5471 propeller and comparing it with the experimental values in the literature, then comparing and analyzing the hydrodynamic performance of the 5471 composite propeller and a rigid propeller. Results The results show that the proposed method can realize the hydrodynamic performance analysis of composite propellers, which has the advantages of simple implementation, high calculation efficiency and high accuracy.ConclusionThe findings of this study can provide reliable data support for the adaptive design of composite propellers and improve their design efficiency.

ObjectiveThis study aims to investigate the influence and mechanism of a cup structure on the hydrodynamic performance of a surface-piercing propeller. MethodsBased on the RANS method and combined with the volume of fluid (VOF) and sliding mesh methods, a numerical simulation is carried out on an 841-B surface-piercing propeller with a cup structure modification under natural ventilation conditions. On the basis of verifying the effectiveness of the numerical simulation method, the trailing edge angle is adjusted according to the dichotomy method to change the cup structure of the benchmark surface-piercing propeller, and a series of propellers is obtained for simulation calculation and research. ResultsChanging the cup structure has a significant impact on the thrust and torque of the surface-piercing propeller, but relatively little impact on its efficiency. Enlarging the cup structure allows more water to be attached to the blades when it emerges from the free surface, resulting in increased waves and droplet splashing behind the propeller. ConclusionThe method and results of this paper can provide useful references for the design of surface-piercing propellers.

ObjectiveTo overcome the dynamic constraints faced by an unmanned surface vehicle (USV) in sea area coverage tasks, a coverage path planning scheme is constructed that considers the motion characteristics of USVs. MethodsFor obstacle-free environments, polygon region coverage path planning is used to generate coverage paths. For obstructed or restricted environments, trapezoidal decomposition is adopted to decompose the target area into several sub-regions, and a genetic algorithm (GA) is used to optimize the link path between each sub-region. Based on the predicted trajectory set of the USV maneuvering motion model, the turning path and its corresponding reference propeller speed are optimized, and the full coverage of the target sea area is achieved. ResultsThe simulation results show that the proposed method can achieve 100% path coverage in sea areas containing obstacles, with each turning path satisfying the maneuvering motion characteristics of the USV. ConclusionThe full-coverage path planning scheme proposed herein can generate a path that satisfies the maneuvering constraints of the USV, giving it obvious practical value in the fields of intelligent fishery, marine exploration, and marine communication relay.

ObjectiveA longitudinal motion control algorithm based on deep reinforcement learning is proposed, focusing on the dependency of traditional control algorithms on precise mathematical models and system parameters in longitudinal motion control of catamarans. MethodsBy designing reward functions and neural network structures and adjusting relevant hyper-parameters, in combination with the catamaran model, through experiments, the control effect of the deep reinforcement learning DDPG algorithm and the GA-LQR algorithm under three different control modes and the robustness under different operating conditions and initial states were compared. Results Under the same operating conditions, the DDPG algorithm has a slight advantage over the GA-LQR algorithm in control effect, but its fin angle output during the control process is more aggressive. In the simulation experiments under different operating conditions and initial states, when the system and the environmental models undergo significant changes, the control effect of the DDPG algorithm is significantly affected. However, when the system and the environment undergo small changes, the DDPG algorithm exhibits better adaptability and superiority over the GA-LQR algorithm. The comprehensive analysis shows that the DDPG algorithm demonstrates similarity to the GA-LQR algorithm in terms of performance. ConclusionsThe DDPG algorithm based on deep reinforcement learning has the potential of applications in the longitudinal motion control of catamarans, providing new research directions and methodological support for ship motion control under complex sea conditions in the future.

ObjectiveTo address the limitations of traditional surrogate models in handling time-dependent dynamic processes and heterogeneous data, this paper proposes a dynamic load surrogate model method based on a long short-term memory (LSTM) network. MethodsThe surrogate model is comprised of two modules: the load feature encoder and load response decoder. First, the LSTM in the load feature encoder performs feature extraction on the time series of dynamic external loads. Next, the extracted load features are combined with the structural parameter features. The LSTM in the load decoder conducts further feature extraction and finally generates output while comprehensively considering the heterogeneous data input of the dynamic external load time series and one-dimensional structural parameter features in order to predict the time history of internal force responses. Finally, the model's accuracy is evaluated using a finite element simulation dataset and compared with other surrogate model methods. ResultsThe results show that the average accuracy of the dynamic load surrogate model can reach 98%, which is higher than that of other methods, and its calculation speed is faster than that of the finite element method. ConclusionsThe proposed method addresses the issue of heterogeneous data involving both time-series and non-time-series features, and offers advantages such as high accuracy and efficiency, making it effective for fast iterative computation tasks.

ObjectiveThis paper aims to investigates the impacts of acoustic emission (AE) signals on the propagation characteristics of composite hetero-structures. MethodsFirst, the calculation procedure of the dispersion curves is developed on the basis of the semi-analytical finite element method in order to calculate the group velocity dispersion curves of AE waves in composite panels. Next, ABAQUS is used to establish a finite element model and analyze the dispersion and attenuation characteristics of AE signals in the composite structure. Finally, the time-frequency characteristics and mode conversion of AE signals in a T-section composite hetero-structure are analyzed in combination with wavelet transform and modal acoustic emission theory. ResultsThe attenuation of AE signals is related to the propagation distance and direction of signals, in which a signal is significantly attenuated when passing through the hetero-structure interface. The interaction between AE signals and the hetero-structure will produce complex propagation phenomena including T-shaped transformation and modal conversion. The signal strength of the reflected signal is strongest in the T-shaped transformation of the AE signal, and the signal strengths of the transmitted signals across the structure and the transmitted signals through the 90° corner of the structure are comparable.ConclusionThis paper quantifies the scattering characteristics of AE signals using reflection and transmission coefficients, thereby providing theoretical references for the application of AE technology in the health monitoring of marine structures.

ObjectivesThe aim of this paper is to evaluate the longitudinal ultimate strength of a hull girder more accurately and determine its collapse process. MethodsA bulk carrier is finely modeled in nonlinear finite element software ABAQUS, and the effects of slight, average, and severe welding initial deformations and average welding residual stress on the ultimate strength of the hull girder under hogging and sagging bending moments are fully considered. ResultsThe calculation results show that the hull girder's ultimate strength and bending stiffness decrease gradually with the increase of the initial deformation amplitude. Severe welding initial deformation makes the ultimate strength of the bulk carrier decrease by 14.25%, and the bulk carrier's ultimate strength decreases by up to 8.22% under the effect of welding residual stress individually. The combined effect of welding initial deformation and residual stress on the hull girder's ultimate strength is not a linear combination of the effects of the two initial deformations individually. ConclusionsThe combined effect of welding initial deformation and residual stress on a hull girder's ultimate strength should be considered more carefully in research on the ultimate strength of hull girders.

ObjectiveAs composite material design and structural design are separated in the "dual track" state, this paper proposes an integrated design method for composite materials in order to improve the ultimate strength of marine composite structures. Methods Based on the multi-scale method, the correlation between the meso-scale material and macro-scale structure is established, and the influence of the meso-scale parameters on the ultimate strength of macro-scale stiffened panels is explored, as well as the differences in mechanical properties between intra-layer and inter-layer hybrid carbon/glass fiber composite material. Through comparison, the superior structural form is obtained. ResultsThe proposed micro-meso-macro mechanical analysis method can improve the ultimate strength of macro-scale stiffened panels by enhancing the meso-scale parameters of composite materials. By adjusting the spacing and cross-sectional area of TC33 yarn, cross-sectional area of WR yarn, and mixing mode, the designed composite top-hat stiffened structure has better ultimate strength. ConclusionsThe results of this study show that the integrated design of material and structure can be realized through multi-scheme comparison and optimization while satisfying the requirements of the rules, providing theoretical guidance and technical support for the novel design of naval ships.

Objectives The aim of this paper is to study the influence of wind load on the safety of the bridge wing structure of a large container ship. MethodsThe variation patterns of dynamic wind load at different vertical positions are investigated and a method is proposed that applies dynamic nonlinear wind load. ABAQUS software is used to solve the nonlinear finite element model of the bridge wing structure and obtain the stress and deformation results of the structure under dynamic wind load. The synergistic effects of multiple loads on the structural response are then obtained and compared with the results of static wind load structural strength calculations in order to explore the impact of dynamic wind load effects on the response of upper building structures. ResultsThe results indicate that the dynamic effects of wind load significantly affect the bridge wing structure, causing periodic oscillations of the bridge wing and leading to significant structural periodic responses under the combined action of multiple loads. ConclusionsThe findings of this study can provide important references for further understanding and considering the role of wind load in structural design.

With the vigorous development of artificial intelligence, knowledge-based engineering (KBE), as an engineering technology discipline that studies the intelligent processing of knowledge, has gradually become a research hotspot, and KBE-based ship design method have also received increasing attention. This article systematically summarizes and analyzes the application and development of KBE in the field of ship design in three aspects: overall conceptual ship design, hull structure design, and ship layout design. It also introduces two typical cases of the KBE application in ship hull form design and shipyard-institute collaborative design. Meanwhile, it summarizes and refines the main problems and constraints in the KBE application, and looks forward to the promotion of KBE development by large language model (LLM) technology. Through KBE technology, ship design can be intelligentized, relevant specifications and requirements can be quickly invoked, and the existing ship design knowledge that has been fully proven through practice can be stored and derived, thereby improving design efficiency and shortening the design cycle. However, the full application of KBE techniques still faces numerous challenges and requires further exploration and improvement.

ObjectiveAiming at the complexity of the navigation environment for shipping on the Yangtze River, as well as the high energy consumption and serious pollution of some ship types, there is an urgent need to carry out research on green and intelligent ship types. In this study, a knowledge graph is applied to the hull form design method so as to adapt to the green and intelligent technological development requirements in the optimization of ship types.MethodsThe knowledge graph and inference model of a Yangtze River bulk cargo ship hull form are introduced, and a knowledge graph-based hull form design process is proposed for the first time to complete the rapid design of an excellent hull form for a 6 000-ton Yangtze River bulk cargo ship. The hull form is then compared with that of a ship designed by conventional methods.ResultsDrag reduction effect of 2.39% is obtained compared with the conventionally designed hull form. ConclusionThe results of this study verify the effectiveness of the proposed knowledge graph-based hull form design method.

ObjectiveThis paper seeks to solve the problem in which directly invoking an optimization algorithm for the worst-case analysis of a three-span beam structure under multiple wheel patch loads raises the possibility of falling into the local optimal solution rather than the global solution. MethodAn analysis method comprising embedded domain knowledge with the general black-box optimization algorithm is proposed for the worst-case analysis of the beam. On the one hand, the position of each wheel patch load is defined as a design variable, so there is no need to specify the relative position of the group of wheel patch loads inadvance,which is more universal; on the other, by integrating knowledge of ship structural mechanics, such as “large stress resulting from the close aggregation of loads in order of magnitude, large bending moment and shear force usually generated by the load in the mid span of the beam and near the support”, into the optimization algorithm, a strategy for generating dangerous initial populations based on the genetic algorithm （GA） and the overall translational strategy of the wheel patch load are proposed respectively, thereby reducing the possibility of falling into the local optimal solution. The theoretical bending moment and shear force distribution of a three-span beam under a single wheel patch load are derived respectively. The theoretical most dangerous positions of multiple wheel patch loads are then determined by enumerating all possible combinations to verify the correctness of the proposed algorithm. ResultsCompared with the classical method using GAs without domain knowledge and under the same computational resources, the most dangerous bending normal stress and shear stress increase by 5.98% and 8.59% respectively under six wheel patch loads, and the error between the calculation results and the theoretical solution is less than 0.5%. ConclusionThe numerical results show that the proposed method can accurately, stably, and quickly obtain the most dangerous load positions.

ObjectiveAs creating finite element models for the finite element analysis of ship structures is time-consuming and highly dependent on engineers' experience, this paper proposes a knowledge-based fast finite element modeling method to solve this problem. MethodsThe proposed method makes full use of the existing model data of the CAD system and shares model data between the CAD and CAE systems through model features. First, based on expert knowledge, the CAD geometric features are marked with engineering semantics to generate CAD information models. Second, the feature reduction of the CAD information model is carried out based on the constructed knowledge rules. Finally, the neutral file XML is used to construct a knowledge-based data transfer and matching method which allows the geometric features and attribute information to be matched with the pre-constructed CAE parameterized template, thereby speeding up the finite element modeling of the ship structure. ResultsTaking the structural strength analysis of a 66000 DWT bulk carrier under typical loading conditions as an example, this approach can realize the automatic extraction, labeling and model reduction of the geometric model, boundary conditions and other information, and quickly complete the finite element modeling and analysis of the structure through the knowledge-based feature matching rules, effectively reducing data loss in the transmission process and realizing the reuse of knowledge.ConclusionsThe proposed fast finite element modeling method with embedded knowledge reuse rules improves the conversion efficiency of data, information and knowledge between the CAD and CAE systems, and has good universality and expansibility in practical engineering.

ObjectiveAiming at the problem that it is difficult to model user requirements with fuzzy characteristics in existing ship conceptual scheme design (SCSD), this study focuses on a rapid SCSD system based on a fuzzy inference system (FIS) that can quickly obtain ship performance values that meet the user requirements and generate the corresponding ship hull design parameter values.MethodsFirst, the existing ship hull parameter data is collected and sorted as prior knowledge for hyper-parameter initialization in the process of user requirement modeling. Second, based on the fuzzy set theory, the user requirements are quantitatively mapped to the fuzzy space, and the sorted prior knowledge is used to infer the ship performance values that meet the user requirements in an interpretable way. Finally, the best ship hull design parameters are matched for each ship performance value that meets the user requirements, and through the "AND" principle in fuzzy set theory, the ship design parameters that meet all the user requirements for ship performance are further inferred and taken as the SCSD. ResultsThe experimental results show that the intelligent FIS can quickly infer multiple SCSDs with deviations within 3.5% according to the fuzzy user requirements within 30 seconds. ConclusionsThe intelligent FIS quantifies the fuzziness in user requirements, and after two stages of inference, the SCSD that meets the various user requirements is efficiently generated. The results of this study can provide useful references for rapid intelligent SCSD generation.

ObjectiveThis study proposes a strategy algorithm based on the fuzzy inference method for the rapid optimization of unmanned underwater vehicle (UUV) hull design parameters. MethodThe initial solutions generated by the genetic algorithm are first fuzzified during the fuzzification stage, then used as training samples, and the antecedent parameters of the fuzzy rules are obtained using an equal interval fuzzy partition strategy with the membership values of all calculated UUV solutions. Next, a least learning machine (LLM) is employed to solve the consequent parameters of the fuzzy rules. Based on the generated antecedent and consequent parameters, new UUV solutions are created and the evaluation membership values for speed and range are calculated. Finally, these new UUV solutions are tested against the constraint conditions to obtain optimized and compliant UUV design parameters. ResultsThe experimental results show that within 20 seconds, the intelligent fuzzy inference method can infer multiple UUV hull parameter schemes with a combined evaluation membership degree score for speed and range of over 170 points based on the initial UUV hull parameters generated by genetic algorithms. ConclusionThe proposed method effectively enhances design efficiency and balances speed and range. The findings of this study can provide valuable references for the intelligent and rapid generation of UUV hull parameters.

ObjectiveDue to its high-dimensional, computationally expensive, and 'black-box' characteristics, hull form optimization based on CFD usually leads to low efficiency and poor quality. To solve the above problems, this paper proposes a hierarchical space reduction method (HSRM) based on the self-organizing maps (SOM) method and K-means clustering. MethodThe visualization results of SOM are clustered and the regions of interest are extracted. In this way, data mining is used to extract the knowledge implicit in the sample simulation data which can then be used to guide hull form optimization and improve its efficiency and quality. The proposed method is applied to the hull form optimization of a 7500-ton bulk carrier.ResultsThe results show that the total drag of the optimal hull form obtained using traditional particle swarm optimization (PSO) and HSRM is reduced by 1.854% and 2.266% respectively, with HSRM leading to a higher-quality optimized solution. ConclusionThe proposed method can guide the optimization algorithm to search in the direction of the optimal solution, effectively improving the efficiency and quality of optimization.

Objective To improve hull optimization design efficiency and obtain better optimization results, different fidelity data is organically integrated and a multi-fidelity deep neural network is applied.Methods A multi-fidelity deep neural network is constructed based on the idea of multi-source data fusion and transfer learning. By fusing a large amount of low-fidelity data with a small amount of high-fidelity data, the linear and nonlinear terms between the high-fidelity data are constructed to obtain a high-fidelity surrogate model. Based on this method, the optimization design of the resistance of a DTMB 5415 ship is carried out. The potential flow and viscous flow are used to evaluate the resistance of the sample points respectively. The potential flow calculation results are used as low-fidelity data, while the viscous flow calculation results are used as high-fidelity data. A multi-fidelity deep neural network surrogate model is then constructed. The optimal solution is obtained by genetic algorithm and compared with the optimal solution of the Kriging model constructed by high-fidelity data. Results Based on the multi-fidelity deep neural network method, the resistance of DTMB 5415 is reduced by 6.73%. Based on the Kriging model, the resistance of DTMB 5415 is reduced by 5.59%. Conclusions The multi-fidelity deep neural network surrogate model can take into account both efficiency and accuracy, which can be used for optimization. The optimized hull form obtained by it has a more significant resistance optimization effect.

ObjectiveMulti-fidelity surrogate (MFS) modeling technology can reduce simulation costs in the design process of engineering products. In order to relax the hierarchical relationship between low-fidelity (LF) analysis models and broaden the engineering application of MFS, this paper proposes an MFS modelling method based on variance-weighted sum (VWS-MFS) for the fusion of multiple non-hierarchical LF data. MethodThe proposed method builds LF surrogate models using Kriging technology. By quantifying the uncertainty of the LF surrogate models with variance, the non-hierarchical LF data is weighted to construct a trend function. In addition, the improved hierarchical Kriging (IHK) model is introduced to fuse the high-fidelity (HF) and LF data, enabling the correction coefficient of the trend function to change throughout the design space. The proposed method is then tested on nine typical examples and applied to the performance prediction of a vibration isolator. ResultsAccording to the experimental results, the proposed method shows higher prediction accuracy than similar methods by more than 85%, and its vibration isolator performance prediction is significantly improved by more than 60% compared with the static prediction method. ConclusionThe proposed method integrates the HF analysis model and multiple non-hierarchical LF analysis models. While the hierarchical relationship between LF analysis models is relaxed, the information of LF data is mined to the maximum extent.

ObjectiveTo address the impact of ice-covered environments on ship performance and the limitations of traditional optimization methods based on empirical formulas for ice resistance, a precise ship design optimization method based on CFD & DEM is proposed to optimize both ice resistance and calm water resistance. MethodsFirst, calm water resistance and ice resistance are calculated based on the CFD and CFD & DEM methods, and an innovative hybrid multi-island genetic algorithm (HMIGA) is introduced to simulate realistic ice fields. Next, an efficient surrogate model is established using XGBoost, followed by the execution of the NSGA-III algorithm for optimization. Finally, the method is validated using the KCS standard model. ResultsThe results show that the optimized ship design achieves a 10.58% reduction in ice resistance and a 2.32% reduction in calm water resistance. The optimized ship experiences lower peak loads and further reduces ice resistance by generating waves to push away floating ice.ConclusionsThe proposed method comprehensively considers the effects of flow field and ice field randomness on the optimization results, leading to more accurate and effective improvements in ship ice resistance and calm water resistance. The introduction of HMIGA and XGBoost enhances the practical application of the method, providing valuable guidance for the future optimization design of ships operating in ice-covered environments.

ObjectiveThis paper proposes a hull transverse web topology optimization method based on UNet for application in the optimization design of complex ship structures. MethodsTaking the transverse web of a very large crude carrier (VLCC) as the research object, a UNet topology optimization surrogate model is first created according to optimization mathematical principles. The finite element grid physical quantity is then mapped to the tensor to obtain the dataset for model training. Finally, the intersection over union (IoU) method is used to evaluate the training results, and the method is compared with the solid isotropic material with penalization (SIMP) method in terms of topology configuration. ResultsThe results show that this method can quickly output the material layout of the design domain, and compared with SIMP topology optimization, it can obtain the topology configuration more efficiently. ConclusionThe proposed topology optimization method can provide a new design method for ship transverse web structures.

ObjectivesTo address the difficulty in accurately describing the states of alignment under nonlinear and time-varying conditions in existing monitoring models, a neural network-based method for evaluating the states of alignment is proposed. MethodA BP neural network-based prediction model is developed. The typical working conditions for acquiring training and testing data are defined, and the data is denoised using a moving average filter. The rules for adjusting the model's hyperparameters are summarized. Experimental studies are then carried out on both small and large air spring isolation devices.ResultsThe results demonstrate that the neural network model can accurately predict the states of isolation devices alignment using only the air spring pressure data. The model exhibits strong generalizability across different device types, with a prediction error of less than 0.5 and an alignment prediction accuracy of 96.29%.ConclusionThe proposed model does not rely on system parameters and performs well in predicting the states of alignment for both small and large devices. The results of this study can provide theoretical support for the state prediction of alignment in a dynamic way and shaft alignment control of power equipment after startup.

ObjectiveThe Blended-Wing-Body (BWB) underwater glider is prone to structural damage during the lifting process. This study seeks to ensure its structural safety and achieve the goal of lightweight design by optimizing the internal pressure-resistant cabin fixing bracket. MethodsA multi-fidelity data-driven optimization method is adopted and combined with the structural parametric modeling method and finite element method to carry out the structural design of the fixing bracket. High and low fidelity numerical models of the bracket structure are established, and a multi-fidelity data-driven optimization method based on the hierarchical Kriging model is proposed, on which basis a fully automatic optimization design framework for the cabin fixing frame is constructed and used to complete the optimization design. ResultsWhile ensuring structural safety, the mass of the optimized cabin fixing bracket is reduced by 16.4%. Compared with the particle swarm optimization algorithm, the proposed optimization design method can reduce computational costs by 75% while obtaining the same level of optimization design results, greatly improving the efficiency of optimization design. ConclusionThe results of this study can provide an efficient optimization design approach for the structural design of pressure-resistant cabin fixing brackets for BWB underwater gliders.

ObjectiveThis paper aims to study the influence of the approximation model, consistency constraints, and boundary update strategy of the BLISS-2000 multidisciplinary design optimization method on its convergence performance and optimization efficiency based on OpenMDAO. MethodFirst, the optimization process and boundary update strategy of BLISS-2000 are given. A BLISS-2000 model is then established based on OpenMDAO, and its accuracy is verified by mathematical and engineering examples. Finally, the effects of the approximation model's accuracy, consistency equality constraints, constraint relaxation, and boundary update strategy on the convergence performance and optimization efficiency of the model are studied. ResultsThe results show that improving the accuracy of the approximation model and selecting the appropriate constraint relaxation factors and boundary update factors can greatly improve the convergence performance and optimization efficiency of the BLISS-2000 model. At the same time, the recommended values of the relevant parameters based on constraint relaxation are obtained. ConclusionThe results of this study can provide useful references for the improvement of the BLISS-2000 method and its application in the conceptual design stage of ships and marine equipment.

ObjectiveAiming at the low proportion of feasible solutions and convergence difficulties in existing optimization algorithms for ship engine room layout optimization problems, this study conducts research on multi-objective intelligent design methods to achieve the intelligent layout design of the engine room. MethodsA two-stage multi-objective optimization method is proposed. In the first stage, the order of the equipment layout is used as the variable and the initial layout scheme is screened by solving the integer programming problem based on the non-dominated sorting genetic algorithm-II (NSGA-II) algorithm and mixed packing algorithm. The mixed packing algorithm integrates the ideas of shelf and skyline algorithms, with optimization objectives including space utilization rate, aisle and maintenance space, and maintenance efficiency, and constraints covering equipment interference, maintenance accessibility, exclusivity, and center of gravity, among others. In the second stage, based on the initial scheme, the best layout is optimized with equipment spacing and aisle width as variables.ResultsApplying this method to the optimization of equipment layout in a local area of a ship's engine room, maintenance efficiency is increased by 17.18%, the maximum width of aisles and maintenance space is optimized by 0.47%, and the overall space utilization rate is significantly increased by 33.36%, with all optimization objectives not lower than the manual layout schemes. At the same time, parameter experiments verify the rationality of the NSGA-II algorithm parameters, elite strategies, grid parameters, and generality of the method. ConclusionsThe two-stage optimization method is feasible and applicable, effectively improving the efficiency and effectiveness of engine room layout optimization, and providing a solution for intelligent layout design.

ObjectivesAiming to overcome the efficiency and engineering practicality issues of existing pipeline layout design methods, this study explores a high-efficiency EPA-star (escape pruning A-star algorithm) for pipeline layout optimization.MethodThe layout space is discretized based on the escape graph method, the resulting connection points are stored as the adjacency table, the estimated traversal cost and penalty function are introduced to reduce the bending and folding phenomenon in the path, and the path is pruned to improve the quality of paths in the case of large spans. A method of branching point selection for branch pipelines considering the forbidden region is proposed which improves the quality and efficiency of the path design. By improving the layout efficiency at the pipeline level within the collaborative strategy, a more effective collaborative layout algorithm can be achieved. ResultsThe feasibility and effectiveness of the EPA-star algorithm in the piping layout of conventional ships and its practicality in the complex layout of special ships are verified through the simulation examples of the nacelle fuel piping of real ships and the nacelle piping of nuclear-powered ships respectively, wherein the length of the piping is shortened by 0.52% and 35.41%, and the number of elbows is reduced by 32.3% and 6.5%, leaving more space for maintenance. The effect of the collaborative piping is more compact than that of the original engineering case, and the quality of the piping is significantly improved. ConclusionThe results of this study can provide useful guidance for the design of piping layout schemes for common ships and special ships.

ObjectivesThe point cloud data of hull segment closure obtained by a 3D scanner has such advantages as high precision and large data volume, and can accurately reflect the construction status of segment closure. Since the existing PointNet++ network is unable to process large-capacity point cloud data, an algorithm based on improved PointNet++ is proposed to realize the intelligent recognition of components for large-capacity hull segment convergence surface point cloud data. MethodsBased on the hypervoxel growth theory, the hull segment closure point cloud data is segmented and simplified, and a hull segment closure point cloud data set is constructed and used to train a PointNet++ network improved by deep learning theory. ResultsThe convergence results of the network model on the training and testing sets of hull segment closure surface point cloud data tend to be stable, achieving an accuracy rate of 90.012% on the testing set. ConclusionsThe proposed method has good recognition ability and can achieve the intelligent recognition of hull segment closure surface components.

ObjectiveThe bow lines of a planing craft have a significant influence on its seakeeping performance, making their intelligent optimization design necessary.MethodsThis study focuses on a certain type of wave-piercing bow planing craft and uses the stem angle, second-order curve shape factors, and coordinates of the knuckle line bow control points as parameters for driving the deformation of the bow lines and carrying out the parametric modeling of the bow. It validates numerical calculation methods based on model test results and establishes a surrogate model according to the numerical results. It optimizes the still water resistance and motion response amplitude in regular waves at a speed corresponding to a volume Froude number of $Fr~~{\nabla} $ = 2.7, and explores bow designs that balance resistance and seakeeping at the designed speed.ResultsThe results under the constraint show that the still water resistance and the average wave-making resistance increase does not exceed 12% and the optimized hull form sees a reduction of about 20% in acceleration amplitude, heave amplitude, pitch amplitude, and heaving compared to the initial craft. ConclusionsBy optimizing the bow lines, the planing craft's low resistance is ensured while improving its motion response in regular waves, providing an intelligent optimization design method for planing craft lines.

ObjectiveAiming at the significant features of high-resolution synthetic aperture radar (SAR) ship targets with multiple scenes, multi-scale and dense arrangements, and the problem of the blurring of target edge details due to coherent noise in the imaging process, a high-resolution SAR ship detection method is proposed with joint wavelet thresholding and fast non-local mean (F-NLM) de-noising. MethodsFirst, wavelet thresholding and F-NLM de-noising modules are utilized to preprocess the SAR image and reduce the sea clutter noise, enhance the detailed features and edge information of the detection target, and make the extracted features more discriminative. Next, a YOLOv7 detection algorithm combined with a bi-directional feature pyramid network (Bi-FPN) is selected to effectively aggregate the multi-scale features and further improve the model's accuracy. ResultsThe experimental results show that the average precision of ship detection using the de-noised dataset D-SSDD can reach 98.69% and the false alarm rate is reduced to 2.37%.ConclusionsIt is clear that the proposed high-resolution SAR ship detection method not only homogenizes the background clutter to improve the image quality, but also improves the interactivity of multi-scale feature information to ensure precise and accurate target detection.

ObjectiveThis paper addresses a problem affecting small target ship detection in which network models have a low recognition rate caused by the insignificance of features in small target ships. MethodsA fusion method based on the integration of image and motion features is proposed to enrich the feature representation of small ships in scenarios where the features of small target ship images are not prominent. Additionally, a hybrid attention model incorporates the prior information of ship targets under data-driven conditions to enhance the model's perception and utilization of key features. ResultsThe proposed method achieves the recognition of small target ships with a resolution of 720P at a distance of up to 4 kilometers, enabling wide-area ship recognition and localization functionality. ConclusionThe improved target recognition network exhibits pixel-level small target detection capability while also demonstrating robustness against environmental noise interference, thereby overcoming the bottleneck of the low recognition rate of network models in small target ship detection.

ObjectiveIn high-density traffic areas, ship collision automatic identification system (AIS) signals often occur, so high requirements are put forward for the separation performance and real-time performance of the receiver.MethodsFor mixed signals with different signal-to-noise ratios (SNR), a separation algorithm S-RICA based on singular spectrum analysis (SSA) and robust independent component analysis (RobustICA) is proposed. The Hankel matrix of the single-channel AIS signal is processed by singular value decomposition and reconstructed by time series respectively, SSA is used to replace whitening pre-processing in traditional independent component analysis (ICA), and the optimal step size of each iteration of the separation matrix is calculated using the kurtosis contrast function to quickly obtain the optimal separation matrix.ResultsThe simulation results show that the signal mean squared error (SMSE) value of S-RICA is stable at about 1.5 when the signal length changes, while the SMSE of fast independent component analysis (FastICA) is very unstable. S-RICA has a bit error rate of 0.97×10-2 to 1.97×10-2 at a SNR of 0 dB to 9 dB, an order of magnitude improvement over RobustICA and FastICA, and an improvement of 4 dB to 6 dB over S-FICA at an SNR of 0 dB to 7 dB. The average calculation time and number of iterations of S-RICA are about 18.5 ms and 13.6 times respectively, showing obvious advantages.ConclusionsWhen the sample size and SNR change, S-RICA shows better separation performance. The results of this study have certain reference value for the application of S-RICA in future satellite-based AIS systems.

ObjectiveAs the traditional ship trajectory prediction method is prone to gradient explosion and long calculation time, this paper seeks to improve its accuracy and calculation efficiency by proposing a ship trajectory prediction model based on an improved Bayesian optimization algorithm (IBOA) and temporal convolution network (TCN). MethodA temporal pattern attention (TPA) mechanism is introduced to extract the weights of each input feature and ensure the timing of the historical flight track data. At the same time, a reversible residual network （RevNet） is introduced to reduce the memory occupied by TCN model training. The IBOA is then used to find the optimality of the hyperparameters in the TCN (size of kernel K, expansion coefficient d). The model is finally validated using a five-fold cross-validation method, and trajectory prediction is carried out after obtaining the optimal model. ResultThe trajectory data is collected by automatic identification system (AIS) and verified. The root mean square error (RMSE) is found to be increased by 5.5×10-5, 3.5×10-4 and 6×10-4 in weak coupling, medium coupling and strong coupling track prediction respectively.ConclusionThe proposed network has good adaptability to complex trajectories and higher accuracy than the traditional model and long short-term memory (LSTM) model, while maintaining high prediction accuracy for trajectories with strong coupling.