Hull Optimization Research Articles

Reinforcement Learning-Based Optimal Hull Form Design with Variations in Fore and Aft Parts

Abstract With recent advancements in artificial intelligence technology, various studies are being conducted in the shipbuilding industry. Traditionally, hull form variation methods have relied on the intuition and expertise of designers, leading to inconsistent results and unintended changes in the ship's main dimensions depending on the designer's competence. Moreover, the iterative process of design variation and analysis to derive the optimal hull form is both costly and time-consuming. To address these issues, this study proposes an optimal hull design technique utilizing reinforcement learning, a type of unsupervised learning in machine learning. Reinforcement learning allows the model to learn from past policies by recording and accumulating the rewards associated with various actions taken by an agent in a specific environment. In this study, after calculating the main parameters of the ship, the agent defines a state representing hull information and performs local transformations of the bow and stern. The reward of reinforcement learning is defined as the change in total resistance due to the hull deformation, constrained by limiting the tolerance of the ship's prismatic coefficient (CP) and longitudinal center of buoyancy (LCB). In this study, the problem is solved by comparing the proximal policy optimization (PPO) algorithm and the deep deterministic policy gradient (DDPG) algorithm to find the best deep reinforcement learning (DRL) model for the hull optimization problem. The results were compared with the genetic algorithm and speed-constrained multi-objective particle swarm optimization (SMPSO), and the optimal hull resistance values were less different, but the time of the reinforcement learning model was five times shorter.

Automatic Optimal Design Method for Minimum Total Resistance Hull Based on Enhanced FFD Method

Hull optimization plays a crucial role in enhancing ship performance and efficiency. This study aimed to improve ship performance, particularly by reducing total resistance, through automated optimization methods. To this end, an integrated, fully automated optimization program was developed based on Python, incorporating Enhanced Free-Form Deformation (FFD) technology, scripted CFD numerical evaluation, and the Particle Swarm Optimization (PSO) algorithm. This program allowed precise control of hull form, improving efficiency while reducing costs. The KCS hull, known for its excellent resistance performance, was chosen as the optimization target, with the goal of minimizing total resistance by adjusting the bulbous bow line plan. The research results indicated that the optimized scheme exhibited lower resistance characteristics compared to the original design while satisfying design constraints. This study not only provides a new optimization strategy for ship design but also lays a foundation for future hull optimization research.

A pointwise weighting prediction variance–high-dimensional model representation model-based global optimization approach for ship hull parametric design

Ship hull optimization techniques based on computer-aided design/computational fluid dynamics can effectively enhance the efficiency and stability of ship designs, with significant application prospects. To enhance the potential of ship hull optimization, increasing design variable dimensionality is essential, but can cause a significant increase in hydrodynamic simulations. To reduce simulations required for high-dimensional ship hull optimization, a new surrogate method, pointwise weighting prediction variance–high-dimensional model representation (PWPV-HDMR), which uses pointwise weighting prediction variance (PWPV) to aggregate different a priori assumptions, is developed. Moreover, a differential evolution algorithm is used to identify promising hull design parameters, using the PWPV-HDMR model instead of costly simulation as the fitness function. The proposed approach is tested on the hydrostatic resistance optimization of KRISO Container Ship. The results show that PWPV-HDMR outperforms kriging-HDMR, with a better resistance optimization effect, illustrating the effectiveness of the PWPV-HDMR-based global optimization approach in discovering promising ship hull parameters.

CFD-based hull optimization in calm water using adaptive grid deformation method

CFD-based hull optimization in calm water using adaptive grid deformation method

Geometric space construction method combined of a spline-skinning based geometric variation method and PCA dimensionality reduction for ship hull form optimization

In the construction stage of ship hull geometric space, the representation and variation of hull forms pose challenges due to the complex nature of the geometry and the necessity for enhanced flexibility in space. In this study, we utilize T-spline technology for the representation of ship hulls, enabling a unified parameter domain with a reduced number of control points to effectively depict the entire hull surface. Furthermore, we introduce a method for geometric variation based on the T-spline parameter domain, which permits both local and global alterations, thus offering greater flexibility in modifying the geometry. By leveraging the T-spline representation and the geometric variation method, we developed a hybrid geometric approach for constructing the geometric space, which significantly increased the geometric flexibility in ship hull optimization. A geometric space characterized by a high degree of geometric freedom typically requires the use of numerous optimization variables and incurs considerable computational resource consumption. In this research, we apply a linear dimensionality reduction method, principal component analysis, to decrease the dimensionality of the geometric space. This method effectively preserves the original geometric design space, thereby eliminating the need for performance analyses. The numerical optimization results clearly indicate that the proposed method significantly enhances optimization efficiency.

Convex Hull Optimization for Robust Localization in ISAC Systems

Convex Hull Optimization for Robust Localization in ISAC Systems

Ship hull optimization – past, present, prospects

ABSTRACT The paper surveys the development of practical ship hull optimization over more than five decades and trends to extrapolate to (likely) future applications. The paper looks at individual elements of hull optimization, such as geometric model, hydrodynamic model, optimization algorithms, and objective functions (and constraints). For all elements, the discussion includes further room for improvement or further R&D efforts.

Design-space dimensionality reduction in global optimization of functional surfaces: recent developments and way forward

ABSTRACT In shape optimization of complex industrial products (such as, but not limited to, hull forms, rudder and appendages, propellers), there exists an inherent similarity between global optimization (GO) and uncertainty quantification (UQ): they rely on an extensive exploration of the design and operational spaces, respectively; often, they need local refinements to ensure accurate identification of optimal solutions or probability density regions (such as distribution tails), respectively; they both are dramatically affected by the curse of dimensionality as GO and UQ algorithms' complexity and especially computational cost rapidly increase with the problem dimension. Therefore, there exists a natural ground for transferring dimensionality reduction methods from UQ to GO. These enable the efficient exploration of large design spaces in shape optimization, which, in turn, enable global optimization (possibly in a multidisciplinary and stochastic setting). The paper reviews and discusses recent techniques for design-space dimensionality reduction in shape optimization, based on the Karhunen-Loève expansion (equivalent to proper orthogonal decomposition and, at the discrete level, principal component analysis). An example is shown and discussed for the hydrodynamic optimization of a ship hull.

A reduced-order model for fast predicting ionized flows of hypersonic vehicles along flight trajectory

An improved Reduced-Order Model (ROM) is proposed based on a flow-solution preprocessing operation and a fast sampling strategy to efficiently and accurately predict ionized hypersonic flows. This ROM is generated in low-dimensional space by performing the Proper Orthogonal Decomposition (POD) on snapshots and is coupled with the Radial Basis Function (RBF) to achieve fast prediction speed. However, due to the disparate scales in the ionized flow field, the conventional ROM usually generates spurious negative errors. Here, this issue is addressed by performing flow-solution preprocessing in logarithmic space to improve the conventional ROM. Then, extra orthogonal polynomials are introduced in the RBF interpolation to achieve additional improvement of the prediction accuracy. In addition, to construct high-efficiency snapshots, a trajectory-constrained adaptive sampling strategy based on convex hull optimization is developed. To evaluate the performance of the proposed fast prediction method, two hypersonic vehicles with classic configurations, i.e. a wave-rider and a reentry capsule, are used to validate the proposed method. Both two cases show that the proposed fast prediction method has high accuracy near the vehicle surface and the free-stream region where the flow field is smooth. Compared with the conventional ROM prediction, the prediction results are significantly improved by the proposed method around the discontinuities, e.g. the shock wave and the ionized layer. As a result, the proposed fast prediction method reduces the error of the conventional ROM by at least 45%, with a speedup of approximately 2.0 × 105 compared to the Computational Fluid Dynamic (CFD) simulations. These test cases demonstrate that the method developed here is efficient and accurate for predicting ionized hypersonic flows.

Fast 3D Object Measurement Based on Point Cloud Modeling

Automated object measurement is becoming increasingly important due to its ability to reduce manual costs, increase production efficiency, and minimize errors in various fields. In this paper, we present a novel approach to three-dimensional (3D) object measurement based on point cloud modeling. Our method introduces a fast point cloud modeling computation framework consisting of five stages: coordinate centralization, rotation and translation, noise filtering, plane projection, and geometric computation. Furthermore, we propose a fast convex hull optimization algorithm to reduce the high complexity problem of traditional convex hull calculation. Our extensive experiments demonstrate that our approach outperforms existing methods in terms of measurement error rate and time savings, with a maximum time saving of 31.03% under certain error conditions.

Model Experimental Study on a T-Foil Control Method with Anti-Vertical Motion Optimization of the Mono Hull

T-foils with active control systems can adjust their attack angle according to the movement of the ship in real time, providing higher lift force and improving the seakeeping performance of a ship. The optimization of the control signal and that of the control method have an important influence on the effect of active T-foils. In this paper, the control method of the T-foil’s swinging angle is established and optimized on the basis of model testing in order to increase the effect of the T-foil. First, the governing equation is introduced by establishing the proportional relationship between the angular motion of the hull and the lift moment of the T-foil. On the basis of the model of the T-foil’s lift force, the governing equation of the T-foil’s swinging angle is deduced and simplified using the test results of the ship model with a passive T-foil and without a T-foil. Then, the active T-foil control system is established by comparing the effects of T-foils with different control signals. Finally, the efficacies of the passive and active T-foil are reported and discussed. It is found that the pitch angular velocity is a more appropriate signal than the pitch angle and pitch angular acceleration. T-foils with pitch angular velocity control can decrease the vertical motion response in the resonance region of a ship’s encounter frequency by more than about 20% compared to the case of the bare ship model, while also increasing the anti-bow acceleration effect by more than 15% compared to the case of passive control. The results obtained by model testing have a certain guiding significance for specific engineering practices.

An experimental and numerical hydrodynamic study on the Argentinian fishing vessels

The purpose of this work is the validation of the hydrodynamic resistance for a small fishing vessel providing more details about the ship’s hydrodynamics. The selected ship is a traditional vessel that has been sailing in Argentina for more than 20 years without a previous numerical resistance evaluation. Because of the absence of previous numerical optimization, the ship might be a non-efficient vessel from a consumption, operating and polluting point of view. For this reason, in order to bring a more detailed evaluation of the flow around this hull, numerical studies are carried out with the open source OpenFOAM code and validated with experimental results obtained at the University of Buenos Aires towing tank. Reynolds Averaged Navier Stokes (RANS) method together with volume of fluid (VOF) are used for the numerical procedure. Once the resistance results are validated, the total resistance coefficient is split into viscous and wave coefficients in order to provide insight into ship hydrodynamics. Pressure distributions on the hull and wave patterns will be also presented for different ship loading conditions, focusing on the flow around the hull that might give information for a future hull optimization.

Decarbonizing the Bay of Kotor: Preliminary Electrification Concept of a Ferry

International Maritime Organization (IMO) and regional authorities have been gradually introducing decarbonization policies and regulations. Shipping sector’s primary response remains the reduction of the cruising speed. Other solutions can include hull optimization, application of energy saving devices, alternative fuels. Alternative fuels are still under the development and could significantly reduce emissions, through the application of batteries, hydrogen, ammonia, etc. However, domestic voyages by ferries have not been exposed to the regulations’ scrutiny. Nevertheless, in the regions such as the Bay of Kotor (Montenegro), protected by UNESCO, maritime transport is expected to follow environmental policies. In order to encourage the decarbonization of such regions, this paper offers a preliminary concept solution of an electric ferry for the Bay of Kotor with reduced onboard emissions. The concept is based on available data on the most energy demanding ferry in Bay of Kotor that has operated for the past decade. The ferry follows the short route suitable for the application of electric drive. Analysis of an operational profile and the ferry concept design parameters are presented, as well as the advantages and disadvantages of electric ferry proposal.

Numerical validation and optimization of hybrid composite beam hull using multiple failure criteria

The number of structurally deficient bridges continues to increase due to corrosion of steel sections and concrete rebar, therefore the replacement of decaying structures and the development of innovative systems have become of high priority to extend the life span of newly built bridges. Hybrid Composite Beam (HCB) produced by Hillman is one of those systems that use a combination of materials i.e., concrete, steel, and Glass Fiber-Reinforced Polymer (GFRP) to integrate each main advantage in a single bridge beam structure. Despite its several apparent advantages; it is not widely spread as expected within the last decade. The HCB is manufactured of self-consolidating concrete (SCC), which is poured in the shape of a traditional arch and tied at its ends by high-strength tendons. A durable FRP composite hull encapsulates the SCC arch and the high-strength tying tendons in order to create a structural beam element for bridge applications. The HCB's design aims to provide pure compressive stresses to the concrete and pure tensile stresses to the steel. The current study performs a deep numerical investigation of the FRP hull instead of other components comprehensively studied. Numerical validation is performed for the deflection results on the experimentally tested Knickerbocker HCB Bridge, the deformations are validated at four stages of HCB manufacturing and testing. Further, the FRP hull strength ratios are quantified for the worst value of four failure criteria. The results showed an excess use of FRP material, where more than 90% of FRP areas have strength ratios of 5 to 50. The FRP hull thickness is minimized using Genetic Algorithm optimization under the worst case of loading. The results achieved more than 60% decrease in FRP weight, that led to only 20% cost difference between traditional precast concrete and HCB girders. It is finally concluded that the overdesign of FRP hull contributed to the high cost of HCB usage consequently inefficient market spread.

Optimization Design of Pressure Hull for Long-Range Underwater Glider Based on Energy Consumption Constraints

Underwater gliders are a class of ocean observation equipment driven by buoyancy, and their energy consumption source is mainly generated by the active regulation of buoyancy. The periodic elastic deformation of the pressure hull during the upward and downward movement of the underwater glider can have a large impact on its driving buoyancy. This paper relates the optimization problem of the pressure hull with the energy consumption of underwater glider, and the energy improvement factor is taken as the optimization objective. Based on the mechanical theory, the theoretical optimization model and constraint model are derived. A hybrid genetic simulated annealing algorithm (HGSAA) is adopted to optimize the pressure hull of the underwater glider developed by Huazhong University of Science and Technology (HUST). Additionally, the effectiveness of the optimized mathematical model and optimization results were verified by the tests. The sea trial results show that after the pressure hull optimization, the energy consumption of the buoyancy regulation unit decreased by 21.9%, and the total energy carried increased by 12.4%.

Hydrodynamic Decomposition-Based Optimization of Ship’s Hull–Propeller System Under Multiple Operating Conditions

_ In this research, a framework for the analysis and design optimization of ship hull–propeller systems (HPSs) in waves is developed. This framework can be utilized as an efficient synthesis tool to determine the main geometric characteristics of the HPSs during the early stage of ship design. The optimization is carried out in two levels and under multipoint operating conditions (OC). Multiobjective evolutionary algorithm based on decomposition (MOEA/D) as an efficient multiobjective evolutionary algorithm, Michell integral and OpenProp tool as low-fidelity hydrodynamic solvers and boundary element method (BEM) as medium-fidelity solver are applied on two case studies to minimize the effective power and maximize the propulsive efficiency of HPSs. To estimate the added wave resistance, an efficient semiempirical formula is also employed. The Series 60 hull form with DTMB P4118 single propeller and S175 hull form with KP505 twin-propeller are considered as the original models. The numerical results show that the framework can find optimized designs with better hydrodynamic performance. Introduction Optimizing the hydrodynamic performance of ships’ hull and propeller(s) based on multiple design condition has gained considerable importance over the last few years. High fuel oil costs are the reason that shipyards and ship owners are now focusing more than ever on the reduction of effective power and propulsive efficiency. Hydrodynamic performance parameters, such as effective power and propulsive efficiency, are determined by the hull form and propeller shape, so it is very important to choose a hull–propeller system (HPS) with good performance in early stage ship design. There exist two main factors in the hydrodynamic design optimization of marine systems. The first factor is simultaneously considering all components of the system influencing objective function(s) and the second one is selecting a less time-consuming solver with satisfactory accuracy. In the ship design process, these two factors must be taken for conducting a reasonable optimization into consideration.

An improved radial basis function for marine vehicle hull form representation and optimization

The marine vehicle is one of the most important platforms in oceanic research and development. During the evolution of marine vehicle design, hull optimization is a key topic consisting of various steps such as hull deformation analysis, optimization algorithm selection and hydrodynamic performance evaluation. For hull deformation analysis, radial based function interpolation technique is usually applied with Wendland’s ψ3,1 function, which requires a great number of fixed points. To improve the optimization effect, this paper proposes a novel radial basis function for better support radius condition. According to the support radius condition, the effect of different deformation functions acting on hull form is studied. To verify the effectiveness of the improved radial basis function in marine vehicle hull optimization, a Series 60 hull is taken as the initial hull, and the Rankine source method is utilized as the solver to calculate the wave resistance coefficient. The Non-dominated Sorting Genetic Algorithm (NSGA) is applied to determine the optimal hull form at given speeds. By comparing the optimization results, the benefits and drawbacks of the improved radial basis function are analyzed. The results show that the number of fixed control points can be reduced by applying the improved radial basis function. When different deformation functions are acting on the marine vehicle hull, the improved radial basis function makes the gradient transition smoother. In the process of hull optimization, the wave resistance coefficient obtained by utilizing the improved function to deform the hull is smaller than that of using Wendland’s ψ3,1 function under different support radii.

Design and optimization of cylindrical hull with non-uniform arch ribs for underwater gliders based on approximate model and experiments

The underwater glider is one of the most promising autonomous underwater vehicles for long-term ocean observations, whose battery capacity and energy consumption are directly affected by compressibility and buoyancy factor of its pressure hull. Thus, to further increase compressibility and decrease buoyancy factor of underwater vehicles, this study proposes a cylindrical hull with non-uniform arch ribs by analyzing design and test results of the existing hulls used in the Petrel-L glider, China. Considering complexity of the proposed cylindrical hull, the approximate model of mass and other output responses of hull is established based on a parametric model by response surface method, which is used to optimize design variables and thus obtain an optimal cylindrical hull. Additionally, the performance of the optimal hull is verified by finite element method and pressure tests. Compared with a conventional cylindrical hull, the deformation of optimal hull is increased by 38.79%, which can indirectly reduce the energy consumption of the buoyancy drive unit and improve endurance of the Petrel-L glider. Meanwhile, the mass of the optimal hull is decreased by 21.57%, which allows more battery or sensor load under the same pressure. Furthermore, the proposed hull can apply to other underwater vehicles.

Three-Dimensional Ship Hull Encoding and Optimization via Deep Neural Networks

Abstract Design and optimization of hull shapes for optimal hydrodynamic performance have been a major challenge for naval architectures. Deep learning bears the promise of comprehensive geometric representation and new design synthesis. In this work, we develop a deep neural network (DNN)-based approach to encode the hull designs to condensed representations, synthesize novel designs, and optimize the synthetic design based on the hydrodynamic performance. A variational autoencoder (VAE) with the hydro-predictor is developed to learn the representation through reconstructing the Laplacian parameterized hulls and encode the geometry-drag function simulated through computational fluid dynamics (CFD). Two data augmentation techniques, Perlin noise mapping and free-form deformation (FFD), are implemented to create the training set from a parent hull. The trained VAE is leveraged to efficiently optimize from massive synthetic hull vessels toward the optimal predicted drag performance. The selected geometries are further investigated and virtually screened under CFD simulations. Experiments show that our convolutional neural network (CNN) model accurately reconstructs the input vessels and predicts the corresponding drag coefficients. The proposed framework is demonstrated to synthesize realistic hull designs and optimize toward new hull designs with the drag coefficient decreased by 35% comparing to the parent design.

A Method for Optimizing the Hull Form of Fishing Vessels

Hull optimization is an important aspect of ship design to improve safety and economic-technical efficiency for ships. This problem has been studied for a long time and has achieved many significant results, but in practical applications, there are still some contents that need to be improved such as the presentation and transformation of the existing hulls, an optimal mathematical model suitable for a specific type of ship, or method for solving the objective function, etc. On that basis, in this paper, a method for optimizing the hull form of fishing vessels is presented, including algorithms using interpolating cubic spline to generate the existing hulls that pass exactly through the given offsets and are constructed in a format to use both Computational Fluid Dynamics (CFD) analysis in resistance prediction and Lackenby method in hull form transformation, a suitable mathematical model for hull optimization problem of fishing vessels, an effective solver based on a combination of CFD, Kriging surrogate models, and traditional optimization techniques. In addition, solutions for improving the accuracy of CFD-based resistance predictions are also presented based on ensuring the accuracy of the 3D hull models and determining the suitable input parameters used for CFD simulations. This study was applied to optimize the hull form of a Vietnamese traditional wooden fishing vessel, symbol MH076, and obtained results that are consistent with the theoretical and practical trends, with the deviations of CFD-based resistance values and corresponding model test data are within the range of 63% and the reduction in total resistance or required power at design operating is around 8.81%.