Ship type conceptual design method and device based on ship typical performance driving and medium
By using a ship hull design method driven by typical ship performance, and generating target ship hulls through semantic parsing and performance prediction models, the problem of low design efficiency is solved, and efficient and accurate ship hull design is achieved to meet user needs.
Patent Information
- Application Number
- CN202511137185.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-14
- Publication Date
- 2025-11-28
AI Technical Summary
Existing ship design processes are characterized by long design cycles, reliance on expert knowledge, difficulty in achieving multi-objective collaborative optimization, low design efficiency, and a lack of real-time performance feedback during the iterative process.
A ship hull design method based on typical ship performance is adopted. By obtaining the geometric parameters to be designed and fuzzy performance requirements, semantic parsing and index decomposition are performed using a ship hull generation model. Combined with the performance prediction model and the generation model, the target ship hull design is quickly generated.
It achieves efficient and precise ship design, shortens the design cycle, improves design efficiency, provides real-time feedback on performance indicators, and supports the precise fulfillment of fuzzy requirements.
Smart Images
Figure CN121030919A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of ship design technology, and in particular to a ship hull concept design method, equipment and medium based on typical ship performance. Background Technology
[0002] The hull concept design embodies the overall geometry of the main hull and is an important carrier of hydrodynamic performance. Its design process is often a spiral iterative optimization, involving multiple iterative stages such as determining the main dimensions, initial hull design, and overall performance evaluation and verification.
[0003] Current ship design mainly relies on human experience or parametric modeling tools, but it suffers from problems such as long design cycles, dependence on expert knowledge, and difficulty in achieving multi-objective collaborative optimization, resulting in low design efficiency. Furthermore, it lacks real-time feedback on performance indicators for subsequent model iterations, leading to low iteration efficiency. Summary of the Invention
[0004] In response to the aforementioned problems and technical requirements, the applicant proposes a ship hull design method, equipment, and medium based on typical ship performance to solve the problem of low design efficiency in existing ship hull design, and to achieve efficient and accurate completion of ship hull design that meets user needs.
[0005] This application provides a ship hull design method based on typical ship performance, the method comprising:
[0006] Obtain the geometric parameters to be designed and the required performance indicators, wherein the required performance indicators are fuzzy requirements;
[0007] The geometric parameters to be designed and the required performance indicators are input into the ship type generation model. The required performance indicators are semantically parsed by the ship type generation model to obtain the semantic parsing results. The target performance indicators corresponding to the semantic parsing results are determined. The target ship type design corresponding to the geometric parameters to be designed is obtained by using the target performance indicators as constraints. The target performance indicators are explicit requirements.
[0008] According to the ship hull design method based on typical ship performance provided in the embodiments of this application, the semantic parsing results are used to characterize some performance indicators;
[0009] Determine the target performance metrics corresponding to the semantic parsing results, including:
[0010] A preset feature mapping map is used to perform indicator analysis and indicator decomposition on some performance indicators.
[0011] The decomposed performance indicators are input into a preset conditional diffusion model to obtain the target performance indicators output by the conditional diffusion model after supplementing some performance indicators.
[0012] According to the ship hull design method based on typical ship performance provided in this application, the ship hull generation model obtains the target ship hull design corresponding to the geometric parameters to be designed using the required performance indicators as constraints, including:
[0013] The ship type generation model uses the required performance index as a constraint to obtain multiple ship type designs corresponding to the geometric parameters to be designed.
[0014] The target ship design is obtained from multiple ship design options in response to a user-triggered ship type determination command.
[0015] According to the ship type conceptual design method based on typical ship performance provided in the embodiments of this application, the performance prediction model includes: a hydrodynamic performance sub-model, a vibration and noise sub-model, and a structural safety sub-model;
[0016] The hydrodynamic performance sub-model is used to predict the ship resistance, ship speed, self-propulsion factor, and six degrees of freedom corresponding to the geometric parameters based on the random forest algorithm and / or BP neural network algorithm.
[0017] The vibration noise sub-model is used to predict the self-noise level and / or initial cavitation number of ship components based on the geometric parameters;
[0018] The structural safety sub-model is used to predict the torque and / or structural force of the plate frame at different stations based on the geometric parameters.
[0019] According to the ship hull conceptual design method based on typical ship performance provided in the embodiments of this application, before obtaining the geometric parameters to be designed and the required performance indicators, the method further includes:
[0020] Extract the geometric parameters corresponding to the bare ship from the dimensional information and hull feature curves of the bare ship;
[0021] The geometric parameters are input into a preset performance prediction model, and the performance evaluation results corresponding to the preset performance indicators are predicted through the performance prediction model, wherein the performance prediction model and the preset performance indicators correspond.
[0022] A dataset is constructed based on the geometric parameters, the preset performance indicators, the performance evaluation results, and the mapping relationship between the three.
[0023] The ship type generation model was trained using the dataset.
[0024] According to the ship hull design method based on typical ship performance provided in this application, the geometric parameters corresponding to the bare ship are extracted from the dimensional information and hull feature curves of the bare ship, including:
[0025] The bare ship is divided into regions, and piecewise quadratic curves of different regions on the YZ plane are constructed to fit the ship's cross-sectional profile. Continuous cubic curves are constructed along the XY plane to generate multiple grids to obtain the ship's configuration.
[0026] The geometric parameters are extracted based on the dimensional information of the ship configuration and the hull feature curves.
[0027] According to the ship hull design method based on typical ship performance provided in the embodiments of this application, the geometric parameters to be designed include any one or more of the following: principal dimension parameters, mid-section, bow, stern and fore-and-aft spherical geometry.
[0028] According to the ship type conceptual design method based on typical ship performance provided in the embodiments of this application, some performance indicators are decomposed to obtain multiple sets of decomposition results, and each set of decomposition results corresponds to a target performance indicator.
[0029] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the ship type conceptual design method based on typical ship performance as described above.
[0030] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the ship morphology conceptual design method based on typical ship performance as described above.
[0031] The present application provides a ship hull design method, equipment, and medium based on typical ship performance. This method acquires the geometric parameters and performance requirements to be designed, where the performance requirements are fuzzy requirements. The geometric parameters and performance requirements are input into a ship hull generation model, which performs semantic analysis on the performance requirements to obtain the semantic analysis results. The target performance requirements corresponding to the semantic analysis results are then determined. Using the target performance requirements as constraints, the target ship hull design corresponding to the geometric parameters to be designed is obtained. Therefore, this application can quickly obtain the target ship hull design corresponding to the geometric parameters and performance requirements based on the ship hull generation model. Furthermore, this application processes the performance requirements of fuzzy requirements, achieving the goal of accurately obtaining the target ship hull design. This application solves the problem of low design efficiency in ship hull concept design, achieving efficient and accurate completion of ship hull designs that meet user needs. Attached Figure Description
[0032] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0033] Figure 1 This is one of the flowcharts illustrating the ship hull concept design method based on typical ship performance provided in this application embodiment;
[0034] Figure 2 This is a schematic diagram of a three-dimensional model of the ship's hull provided in an embodiment of this application;
[0035] Figure 3 This is the second flowchart illustrating the ship hull concept design method based on typical ship performance provided in this application embodiment;
[0036] Figure 4 This is a schematic diagram of the dataset generation process provided in the embodiments of this application;
[0037] Figure 5 This is the third flowchart of the ship hull concept design method based on typical ship performance provided in the embodiments of this application;
[0038] Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0039] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0040] This application provides a ship hull conceptual design method based on typical ship performance. This method can be applied to smart terminals and servers. This application uses the application of this method in a server as an example for illustration, and some other descriptions in the embodiments are illustrative and not intended to limit the scope of protection of this application, and will not be described in detail thereafter. The specific implementation of the method is as follows... Figure 1 As shown:
[0041] Step 101: Obtain the geometric parameters and required performance indicators to be designed.
[0042] Among them, the demand performance index is a fuzzy demand.
[0043] Step 102: Input the geometric parameters to be designed and the required performance indicators into the ship type generation model, perform semantic parsing on the required performance indicators through the ship type generation model to obtain the semantic parsing results; determine the target performance indicators corresponding to the semantic parsing results; and use the target performance indicators as constraints to obtain the target ship type design corresponding to the geometric parameters to be designed.
[0044] The target performance indicators are explicit expressions of requirements.
[0045] Among them, through Figure 2 A schematic diagram of the generated target ship design (3D hull model) is provided.
[0046] The ship hull design method based on typical ship performance provided in this application obtains the geometric parameters and performance requirements to be designed, wherein the performance requirements are fuzzy requirements. The geometric parameters and performance requirements are input into a ship hull generation model, which performs semantic parsing on the performance requirements to obtain the semantic parsing results. The target performance requirements corresponding to the semantic parsing results are determined. The target performance requirements are used as constraints to obtain the target ship hull design corresponding to the geometric parameters to be designed. Therefore, this application can quickly obtain the target ship hull design corresponding to the geometric parameters and performance requirements based on the ship hull generation model. Furthermore, this application processes the performance requirements of fuzzy requirements, achieving the goal of accurately obtaining the target ship hull design. This application solves the problem of low design efficiency in ship hull concept design, achieving efficient and accurate completion of ship hull designs that meet user needs.
[0047] In one specific embodiment, before obtaining the geometric parameters and required performance indicators to be designed, a dataset is set up, a ship form generation model is trained using the dataset, and the trained ship form generation model is used to predict the target ship form design. See details below. Figure 3 :
[0048] Step 301: Extract the geometric parameters corresponding to the bare ship from the dimensional information and hull feature curves of the bare ship.
[0049] Alternatively, ship type data can be generated and filtered in multiple rounds by combining random sampling and normal distribution sampling within the original geometric constraints of the performance forecast model.
[0050] Step 302: Input the geometric parameters into the preset performance prediction model, and predict the performance evaluation results corresponding to the preset performance indicators through the performance prediction model.
[0051] Among them, the performance forecast model corresponds to the preset performance indicators.
[0052] Step 303: Construct a dataset based on geometric parameters, preset performance indicators, performance evaluation results, and the mapping relationship between the three.
[0053] Step 304: Train and obtain the ship shape generation model using the dataset.
[0054] Step 305: Input the geometric parameters to be designed and the required performance indicators into the ship type generation model. The ship type generation model uses the required performance indicators as constraints to obtain the target ship type design corresponding to the geometric parameters to be designed.
[0055] pass Figure 4 The process of generating the dataset is illustrated in detail below:
[0056] For example, taking 45 geometric parameters as an example, random sampling is performed, followed by a first round of filtering, then random selection of seed data to construct a second round of filtering data, followed by a second round of filtering, and finally the output dataset is obtained.
[0057] Among them, Figure 4 In this context, A represents the initial parameter set (composed of geometric parameters), (min A ,min B () represents the parameter range, B represents the parameter set after sequentially filtering A based on the filtering conditions, and τ(*) represents the filtering conditions, for example, representing the constraint relationship between waterline length / width, draft, and drainage volume. This represents a normal distribution with the seed parameter as the expected value. This represents the data from the second round of screening, where D represents the parameter set after a second screening of C based on the screening criteria. P This represents the dataset, where N, M, O, and P represent preset values.
[0058] In one specific embodiment, the geometric parameters include: principal dimension parameters, mid-section, bow, stern, and fore and aft sphere geometry.
[0059] The main scale parameters include: ship length, beam and depth, etc. The shape of the mid-section and the geometry of the bow sphere are key parameters that control the shape of the hull and are used to ensure that the generated hull mesh does not self-intersect and is watertight.
[0060] The geometric parameters also include the coefficients of the hull characteristic curves for each region.
[0061] In one specific embodiment, the extraction of the geometric parameters corresponding to the bare ship from the dimensional information and hull feature curves of the bare ship includes:
[0062] The bare ship is divided into regions, and piecewise quadratic curves of different regions on the YZ plane are constructed to fit the ship's cross-sectional profile. Continuous cubic curves are constructed along the XY plane to generate multiple grids to obtain the ship's configuration. Geometric parameters are extracted based on the ship's configuration scale information and hull feature curves.
[0063] For example, the bare hull can be divided into a bow region, a midship region, and a stern region.
[0064] In this process, a series of cubic curves are constructed along the XY plane to generate a dense and uniform grid.
[0065] The geometric parameters include scale information for different regions and overall principal scale parameters, as well as coefficients of the hull characteristic curves for different regions.
[0066] While extracting geometric parameters, the principal dimensions, displacement volume, and hull parameters (such as forward displacement volume, waterline coefficient, block coefficient, rhombus coefficient, waterline coefficient, mid-section coefficient, and vertical rhombus coefficient) can be simultaneously calculated using the generated mesh file.
[0067] In one specific embodiment, the performance prediction model includes: a hydrodynamic performance sub-model, a vibration and noise sub-model, and a structural safety sub-model.
[0068] The hydrodynamic performance sub-model is used to predict ship resistance, ship speed, self-propulsion factor and six degrees of freedom corresponding to geometric parameters based on random forest algorithm or neural network; the vibration and noise sub-model is used to predict the self-noise level and / or initial cavitation number of ship components based on geometric parameters; the structural safety sub-model is used to predict the torque and / or structural force of plate frame at different positions based on geometric parameters.
[0069] Specifically, the performance prediction model is constructed based on intelligent data-driven approaches (such as deep learning models) and empirical formulas (such as resistance calculation formulas), and includes performance indicators such as hydrodynamic performance, vibration and noise, and structural safety. Furthermore, a rapid solution workflow for geometric parameters and performance indicators, along with performance evaluation results, is set up within the performance prediction model to achieve collaborative evaluation of geometric parameters and performance predictions, providing a real-time evaluation tool for multi-objective optimization.
[0070] The performance prediction model is trained based on geometric parameter samples, preset performance index samples, and performance evaluation result samples.
[0071] The hydrodynamic performance sub-model is trained using a random forest algorithm and / or a backpropagation neural network algorithm, based on geometric parameter samples, ship resistance samples, ship speed samples, self-propulsion factor samples, and six-degree-of-freedom samples.
[0072] The vibration noise sub-model is trained based on geometric parameter samples, self-noise level samples, and initial cavitation number samples.
[0073] The structural safety sub-model was trained based on geometric parameter samples, torque samples at different locations, and structural force samples of the plate frame.
[0074] Specifically, different performance forecasting models are selected based on the different performance indicator requirements of users.
[0075] In one specific embodiment, the ship hull generation model, using demand performance indicators as constraints, obtains the target ship hull design corresponding to the geometric parameters to be designed, including:
[0076] The ship type generation model uses demand performance indicators as constraints to obtain multiple ship type designs corresponding to the geometric parameters to be designed; in response to the ship type determination command triggered by the user, the target ship type design is obtained from the multiple ship type designs.
[0077] Specifically, the ship type generation model includes a fully connected network. The weight matrix output by the fully connected network is used as the attention weights in the attention mechanism, and the geometric parameters are constrained by the demand performance indicators to achieve multiple ship type designs that meet the demand performance indicators. The resulting multiple ship type designs are displayed to the user on a screen, and the target ship type design is obtained from the multiple ship type designs in response to the user's triggered ship type determination command.
[0078] Specifically, ship shape generation models include generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs).
[0079] Using the constructed dataset, the denoising process is optimized through an attention mechanism to generate various ship designs that meet performance expectations.
[0080] In one specific embodiment, the semantic parsing results represent some performance metrics.
[0081] The specific implementation of determining the target performance metrics corresponding to the semantic parsing results includes:
[0082] The system uses a preset feature mapping map to perform index analysis and index decomposition on some performance indicators; the decomposed performance indicators are then input into a preset conditional diffusion model to obtain the target performance indicators output by the conditional diffusion model after completing the partial performance indicators.
[0083] Specifically, the decomposed performance indicators are multiple, so multiple target performance indicators are output through the conditional diffusion model, thereby obtaining multiple ship type designs.
[0084] One set of target performance indicators can yield one or more ship type designs. If there is only one ship type design, it is the target ship type design. If there are multiple ship type designs, the ship type design selected by the user is the target ship type design.
[0085] By decomposing some performance indicators, multiple sets of decomposition results can be obtained, thus yielding multiple sets of completed target performance indicators.
[0086] The conditional expansion model is trained based on the decomposed performance index samples and the completed target performance index samples.
[0087] Specifically, the ship type generation model uses the target performance index as a constraint to obtain multiple ship type designs corresponding to the geometric parameters to be designed, and then determines the target ship type design from the multiple ship type designs.
[0088] This application can also output a 3D hull model (e.g., IGS format, STL format, etc.) that meets the user's target ship type design even for fuzzy performance indicators.
[0089] This application supports generating a 3D hull model that meets fuzzy performance requirements (e.g., low drag and good seaworthiness) through semantic parsing and index decomposition. The entire process is time-efficient and provides real-time feedback on performance indicators, enabling multi-objective collaborative optimization and rapid conceptual design of a mother ship without a parent model.
[0090] Below, through Figure 5 This application will be described in detail as follows:
[0091] Step 501: By quantifying the ambiguity in user needs, semantic parsing and performance indicator mapping reasoning are performed to obtain some performance indicators.
[0092] Step 502: Based on partial performance metrics, obtain complete performance metrics according to performance correlation.
[0093] Step 503: Input the complete performance indicators into the performance prediction model to obtain the geometric parameters of multiple candidate ship types.
[0094] The performance forecast model takes geometric parameters as input and outputs performance evaluation results, and takes performance indicators as input and outputs geometric parameters.
[0095] Step 504: Input the above geometric parameters into the ship shape generation model to generate multiple ship shape designs, and simultaneously calculate the principal dimensions and dimensionless coefficients, and output the mesh file in STL / LGS format.
[0096] The following is a specific example to illustrate this further:
[0097] Suppose the user requirement is "a large monohull vessel, approximately 130m in length, capable of navigating in high sea states for cargo transport." Partial performance inputs, including seakeeping grade factors, stability, and principal dimensions, are obtained through semantic reasoning. Then, based on associative reasoning using a knowledge graph, the performance inputs of the conditional diffusion model are completed. These completed performance indicators are input into the performance-driven hull type generation system, resulting in five different hull type parameters and their corresponding three-dimensional geometric models (STLs), as well as the necessary calculation results for ship parameters such as principal dimensions and dimensionless coefficients.
[0098] This application first extracts modeling parameters from the characteristic curves of the main dimensions and contours of the hull of the light-body ship, forming a parametric modeling foundation. Then, through an automated batch processing interface, it connects modeling tools with a performance prediction platform to rapidly evaluate the typical performance of the geometric configuration under the current modeling parameters, thereby constructing a dataset relating modeling parameters and performance indicators. Finally, during the reverse encoding of the modeling parameters in the ship generation model, high-dimensional features of the performance indicators are embedded to constrain the distribution of modeling parameters corresponding to each geometric region of the hull, thus generating a ship form that meets performance expectations.
[0099] This application utilizes quantified fuzzy performance indicators to generate multiple conceptual ship design schemes that meet user needs through association and reasoning, allowing users to quickly select the appropriate option. Therefore, this application explores new capabilities for ship conceptual design, starting directly from the design requirements and achieving the goal of transforming fuzzy requirements into multiple conceptual ship designs. This significantly shortens the design cycle, reduces trial-and-error costs in ship design, improves design efficiency, and enables highly efficient and precise completion of ship design.
[0100] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 601, a communications interface 602, a memory 603, and a communication bus 604. The processor 601, communications interface 602, and memory 603 communicate with each other via the communication bus 604. The processor 601 can call logical instructions from the memory 603 to execute a ship hull design method based on typical ship performance.
[0101] Furthermore, the logical instructions in the aforementioned memory 603 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0102] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer is able to execute the ship type concept design method based on typical ship performance provided by the above methods.
[0103] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the ship hull design method based on typical ship performance provided in the above embodiments.
[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0105] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0106] Finally, it should be noted that the above descriptions are merely preferred embodiments of this application, and this application is not limited to the above embodiments. It is understood that other improvements and variations directly derived or conceived by those skilled in the art without departing from the spirit and concept of this application should be considered to be included within the protection scope of this application.
Claims
1. A ship hull design method based on typical ship performance, characterized in that, The method includes: Obtain the geometric parameters to be designed and the required performance indicators, wherein the required performance indicators are fuzzy requirements; The geometric parameters to be designed and the required performance indicators are input into the ship type generation model. The required performance indicators are semantically parsed by the ship type generation model to obtain the semantic parsing results. The target performance indicators corresponding to the semantic parsing results are determined. The target ship type design corresponding to the geometric parameters to be designed is obtained by using the target performance indicators as constraints. The target performance indicators are explicit requirements.
2. The ship hull design method based on typical ship performance as described in claim 1, characterized in that, The semantic parsing results are used to characterize some performance metrics; Determine the target performance metrics corresponding to the semantic parsing results, including: A preset feature mapping map is used to perform indicator analysis and indicator decomposition on some performance indicators. The decomposed performance indicators are input into a preset conditional diffusion model to obtain the target performance indicators output by the conditional diffusion model after supplementing some performance indicators.
3. The ship hull design method based on typical ship performance as described in claim 1 or 2, characterized in that, The ship hull generation model uses the aforementioned performance requirements as constraints to obtain the target ship hull design corresponding to the geometric parameters to be designed, including: The ship type generation model uses the required performance index as a constraint to obtain multiple ship type designs corresponding to the geometric parameters to be designed. The target ship design is obtained from multiple ship design options in response to a user-triggered ship type determination command.
4. The ship hull design method based on typical ship performance as described in claim 1 or 2, characterized in that, The performance prediction model includes: a hydrodynamic performance sub-model, a vibration and noise sub-model, and a structural safety sub-model; The hydrodynamic performance sub-model is used to predict the ship resistance, ship speed, self-propulsion factor, and six degrees of freedom corresponding to the geometric parameters based on the random forest algorithm and / or BP neural network algorithm. The vibration noise sub-model is used to predict the self-noise level and / or initial cavitation number of ship components based on the geometric parameters; The structural safety sub-model is used to predict the torque and / or structural force of the plate frame at different stations based on the geometric parameters.
5. The ship hull design method based on typical ship performance as described in claim 1 or 2, characterized in that, Before obtaining the geometric parameters to be designed and the required performance indicators, the following steps are also included: Extract the geometric parameters corresponding to the bare ship from the dimensional information and hull feature curves of the bare ship; The geometric parameters are input into a preset performance prediction model, and the performance evaluation results corresponding to the preset performance indicators are predicted through the performance prediction model, wherein the performance prediction model and the preset performance indicators correspond. A dataset is constructed based on the geometric parameters, the preset performance indicators, the performance evaluation results, and the mapping relationship between the three. The ship type generation model was trained using the dataset.
6. The ship hull design method based on typical ship performance as described in claim 5, characterized in that, Extracting the geometric parameters corresponding to the bare ship from the dimensional information and hull feature curves of the bare ship, including: The bare ship is divided into regions, and piecewise quadratic curves of different regions on the YZ plane are constructed to fit the ship's cross-sectional profile. Continuous cubic curves are constructed along the XY plane to generate multiple grids to obtain the ship's configuration. The geometric parameters are extracted based on the dimensional information of the ship configuration and the hull feature curves.
7. The ship hull design method based on typical ship performance as described in claim 1 or 2, characterized in that, The geometric parameters to be designed include any one or more of the following: principal dimension parameters, mid-section, bow, stern, and fore and aft spherical geometry.
8. The ship hull design method based on typical ship performance as described in claim 2, characterized in that, By decomposing some performance indicators, multiple sets of decomposition results are obtained, and each set of decomposition results corresponds to a target performance indicator.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the ship hull design method based on typical ship performance as described in any one of claims 1 to 8.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the ship hull design method based on typical ship performance as described in any one of claims 1 to 8.