Hull molded line design method and equipment based on specified wake field and medium

Abstract

The invention discloses a ship body molded line design method and device based on a specified wake field and a medium, and relates to the technical field of ship design, and the method comprises the steps: carrying out the regional feature transformation processing of an initial ship body curved surface, and obtaining a plurality of to-be-predicted ship body curved surfaces; inputting the plurality of ship body curved surfaces to be predicted into the wake field prediction model to obtain a plurality of predicted wake fields; comparing the predicted wake flow field with a preset specified wake flow field to obtain a comparison result; and optimizing the previous ship body curved surface based on the comparison result, the design requirement and the optimization target to obtain an optimized previous ship body curved surface, inputting the optimized previous ship body curved surface into the wake field prediction model, and determining that the ship body molded line design is completed under the condition that the comparison result reaches a preset requirement. The method is used for solving the problems of long consumed time, low efficiency and poor effect during hull molded line design in the prior art, and the hull molded line meeting the design requirement is rapidly and accurately obtained.

Description

Technical Field

[0001] The present application relates to the technical field of ship design, and in particular to a method, device and medium for designing a hull line based on a specified wake field. Background Art

[0002] The ship's wake field is closely related to the propulsion performance of the ship and the energy-saving effect of various energy-saving devices during navigation. It also greatly affects the ship's operating environment, and thus has a significant impact on the ship's cavitation and noise performance.

[0003] Existing ship designs are generally completed in stages. First, the bare ship light body line type is optimized to obtain a ship type with low bare ship hull resistance and a more uniform flow field, and then the propeller matching design and hydrodynamic energy-saving device design are carried out based on this. The entire design process is based on design experience and continuous design attempts, and is verified by tank tests. The overall time-consuming and inefficient.

[0004] However, for ships with excellent bare ship performance, the energy-saving effect of matching hydrodynamic energy-saving devices may not be the best, or the ship with the lowest bare ship resistance and a more uniform flow field may not be conducive to the design of energy-saving devices, nor may it have the best comprehensive navigation performance, and the final effect is not ideal. Summary of the invention

[0005] In response to the above-mentioned problems and technical needs, the applicant has proposed a hull line design method, equipment and medium based on a specified wake field, so as to solve the problems of long time consumption, low efficiency and poor effect in hull line design in the prior art, and to quickly and accurately obtain hull lines that meet the design requirements.

[0006] The embodiment of the application provides a hull line design method based on a specified wake field, the method comprising:

[0007] Acquire an initial hull surface corresponding to the mother ship, and perform regional feature transformation processing on the initial hull surface to obtain multiple hull surfaces to be predicted;

[0008] Inputting the plurality of hull surfaces to be predicted into a pre-trained wake field prediction model to obtain a plurality of predicted wake fields output by the wake field prediction model, wherein the wake field prediction model is trained based on hull surface samples and wake field samples;

[0009] Comparing the predicted wake field with the preset designated wake field to obtain a comparison result;

[0010] Based on the comparison results and design requirements, an optimization target for the previous hull surface is determined, and based on the design requirements and the optimization target, the previous hull surface is optimized to obtain an optimized hull surface, and the optimized hull surface is input into the wake field prediction model until the comparison result meets the preset requirements, and the hull line design is determined to be completed, wherein the previous hull surface includes: the initial hull surface.

[0011] According to the hull line design method based on the specified wake field provided in the embodiment of the present application, the optimization objectives include: optimization area, optimization direction and optimization magnitude;

[0012] Optimizing the previous hull surface based on the design requirements and the optimization target to obtain an optimized hull surface includes:

[0013] Reconstruct the previous hull surface to obtain the hull surface to be designed;

[0014] For the hull surface to be designed, the optimization region is designed using the optimization direction and the optimization magnitude based on the design requirements and the optimization target to obtain an optimized hull surface.

[0015] According to the hull line design method based on the specified wake field provided in the embodiment of the present application, before determining the optimization target for the previous hull surface based on the comparison result and the design requirements, the method further includes:

[0016] Determine at least one optimization region conforming to Gaussian distribution from the hull surface to be designed by using the center point coordinates of the Gaussian function and the first covariance matrix;

[0017] Based on the center point coordinates, the first covariance matrix and the design requirements, determining the control points to be processed from the optimization region, and determining the design parameters of the control points to be processed using a Gaussian kernel function;

[0018] Based on the design parameters, the optimization direction and optimization magnitude are determined, wherein the positive or negative sign of the design parameters is used to determine the optimization direction, and the magnitude of the design parameters is used to determine the optimization magnitude.

[0019] According to the hull line design method based on the specified wake field provided in an embodiment of the present application, based on the center point coordinates, the first covariance matrix and the design requirements, determining the control points to be processed from the optimization area includes:

[0020] Determine the control point to be processed from the optimization area based on a preset control point selection index formula, center point coordinates and a first covariance matrix;

[0021] The control point selection index formula includes:

[0022]

[0023] Among them, ρ P (x) represents the control point selection index, which is obtained based on the design requirements, μ n represents the coordinates of the center point of the nth Gaussian function, σ n represents the first covariance matrix of the nth Gaussian function, x represents the coordinates of the control point to be processed, N represents the number of Gaussian functions, and the center point coordinates are determined based on the design requirements.

[0024] According to the hull line design method based on the specified wake field provided in the embodiment of the present application, the design parameters of the control points to be processed are determined by using a Gaussian kernel function, including:

[0025] Selecting an index based on the control point to obtain the Gaussian kernel function;

[0026] Wherein, the Gaussian kernel function includes:

[0027]

[0028] Among them, x' represents the transpose of x, l represents the Euclidean distance from the coordinates of the control point to be processed to the coordinates of the center point;

[0029] Based on the eigenvalue decomposition formula, calculate the eigenvalue basis function corresponding to the Gaussian kernel of the Gaussian kernel function and the eigenvalue corresponding to the eigenvalue basis function;

[0030] Wherein, the eigenvalue decomposition formula includes:

[0031]

[0032] in, represents the characteristic basis function, represents the eigenvalue;

[0033] Based on the modal decomposition formula, the characteristic basis function and the eigenvalue, the control points of the hull surface to be designed are projected into an n-dimensional characteristic space to obtain the design parameters;

[0034] Wherein, the modal decomposition formula includes:

[0035]

[0036] in, represents the control point of the hull surface to be designed, A i represents the design parameters, represents the eigenvalue corresponding to the i-th dimension feature space, Represents the characteristic basis function corresponding to the i-th dimension feature space.

[0037] According to the hull line design method based on the specified wake field provided in the embodiment of the present application, the design requirements include: design objectives and design constraints;

[0038] Before optimizing the previous hull surface based on the design requirements and the optimization target, the method further includes:

[0039] When it is determined that the first data dimension corresponding to the predicted wake field is smaller than the second data dimension corresponding to the mother ship type, a preset optimization function must be satisfied;

[0040] Wherein, the optimization function includes:

[0041]

[0042] x opt represents the optimization result, J(x) represents the loss function;

[0043] Wherein, the loss function includes:

[0044]

[0045] Among them, x represents the coordinates of the control points on the hull surface during the optimization process, u represents the predicted wake field, H() represents the observation operator, represents the transpose of the variable matrix inside the double vertical line multiplied by the subscript matrix and then multiplied by the variable matrix inside the double vertical line, where t = P, R, O and W, P, R, O and W represent the covariance matrix of the variable matrix inside the double vertical line, respectively. represents the prior distribution of the input ship type information, characterizing the influence of prior physical knowledge, x f represents the coordinates of the control points of the initial hull surface, H o (u) is the part of the observation operator that is set as the optimization target, H r (x) is the part of the observation operator that is set as a constraint, To specify the performance parameter quantity as a constraint, J r (x) is the regularization term of the loss function, which is the part that directly constrains the input parameters, λ 1 and λ 2 is the weight of the two constraints, indicating the strength of the constraints, are constraints on the hull geometry input, Refers to higher-order derived quantities that constrain the hull geometry.

[0046] According to the hull line design method based on the specified wake field provided in the embodiment of the present application, after the optimized hull curved surface is input into the wake field prediction model, the method further includes:

[0047] Obtaining the predicted wake field output by the wake field prediction model during the d+1th iteration;

[0048] Calculate the average wake field and the second covariance matrix corresponding to d+1 times;

[0049] Calculate a Kalman gain matrix based on the second covariance matrix;

[0050] The next hull surface is optimized based on the Kalman gain matrix, the design requirements and the optimization objective.

[0051] According to the hull line design method based on the specified wake field provided in an embodiment of the present application, after calculating the Kalman gain matrix based on the second covariance matrix, the method further includes:

[0052] Determining a correction term corresponding to the d-th iteration process; optimizing the next hull surface based on the correction term; The amendments include:

[0053]

[0054] Among them, λ 2 represents the weight, represents the constraint on the hull geometry input corresponding to the dth iteration, Refers to higher-order derived quantities that constrain the hull geometry.

[0055] An embodiment of the present 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, the steps of the hull line design method based on a specified wake field as described in any one of the above items are implemented.

[0056] An embodiment of the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above methods for designing hull lines based on a specified wake field.

[0057] The hull line design method, device and medium based on the specified wake field provided in the embodiment of the present application obtain an initial hull surface corresponding to the mother ship, and perform regional feature transformation processing on the initial hull surface to obtain multiple hull surfaces to be predicted; input the multiple hull surfaces to be predicted into the wake field prediction model to obtain multiple predicted wake fields output by the wake field prediction model; compare the predicted wake field with the preset specified wake field to obtain a comparison result; based on the comparison result and design requirements, determine the optimization target for the previous hull surface, and optimize the previous hull surface based on the design requirements and the optimization target to obtain the optimized hull surface. The optimized previous hull surface is input into the wake field prediction model, and the hull line design is determined to be completed when the comparison result reaches the preset requirements. The present application adopts the wake field prediction model to perform forward prediction of the wake field, and reversely iterates the design of the ship type based on the comparison result of the prediction result and the specified wake field to predict the hull line that meets the design requirement information. It can be seen that the present application can quickly and accurately meet the design requirements (for example, any one or more of the bare ship performance, the energy-saving effect of the hydrodynamic energy-saving device, the bare ship resistance, and the navigation performance) and the hull line of the specified wake field. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 It is a flow chart of a hull line design method based on a specified wake field provided in an embodiment of the present application;

[0060] Figure 2 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] The embodiment of the present application provides a method for designing a hull line based on a specified wake field. The method can be applied to a smart terminal or a server. The present application uses the method applied to a server as an example for illustration, which is not intended to limit the scope of protection of the present application. Some other descriptions in the embodiment are also for illustration, and will not be described one by one. The specific implementation of the method is as follows: Figure 1 As shown:

[0063] Step 101, obtaining an initial hull surface corresponding to a mother ship, and performing regional feature transformation processing on the initial hull surface to obtain a plurality of hull surfaces to be predicted.

[0064] Specifically, the ensemble Kalman filter algorithm is used to perform parameter sampling on the initial hull surface to obtain multiple hull surfaces to be predicted. Specifically, a new set of data is obtained by forward integration of the initial hull surface and integration with the new data, and the set is updated by the Kalman filter equation. The data here is the point cloud data corresponding to the initial hull surface.

[0065] Specifically, which areas are to be processed can be set in advance by the user according to their actual needs, or can be processed randomly.

[0066] Step 102: input a plurality of hull surfaces to be predicted into a pre-trained wake field prediction model to obtain a plurality of predicted wake fields output by the wake field prediction model.

[0067] Among them, the wake field prediction model is trained based on hull surface samples and wake field samples.

[0068] Step 103, comparing the predicted wake field with the preset designated wake field to obtain a comparison result.

[0069] Step 104, based on the comparison results and design requirements, determine the optimization target for the previous hull surface, and optimize the previous hull surface based on the design requirements and the optimization target to obtain the optimized hull surface, and input the optimized hull surface into the wake field prediction model until the comparison results meet the preset requirements and the hull line design is determined to be completed.

[0070] The previous hull surface includes: an initial hull surface.

[0071] The design requirements include: design objectives (any one or more of the bare ship performance corresponding to the specified wake field, the energy-saving effect of the hydrodynamic energy-saving device, the bare ship resistance, and the navigation performance) and constraints (design constraints).

[0072] The optimization objectives include: optimization area, optimization direction and optimization magnitude, etc. The optimization direction is used to characterize the direction of regional change, and the optimization magnitude is used to characterize the limit threshold of regional change.

[0073] The hull line design method based on the specified wake field provided in the embodiment of the present application obtains an initial hull surface corresponding to the parent ship, and performs regional feature transformation processing on the initial hull surface to obtain multiple hull surfaces to be predicted; the multiple hull surfaces to be predicted are input into the wake field prediction model to obtain multiple predicted wake fields output by the wake field prediction model; the predicted wake field is compared with the preset specified wake field to obtain a comparison result; based on the comparison result and design requirements, an optimization target for the previous hull surface is determined, and the previous hull surface is optimized based on the design requirements and the optimization target to obtain an optimized hull surface. The previous hull surface is input into the optimized previous hull surface prediction model until the comparison result reaches the preset requirements and the hull line design is determined to be completed. The present application adopts the wake field prediction model to perform forward prediction of the wake field, and reversely iterates the design of the ship type based on the comparison result of the prediction result and the specified wake field to predict the hull line that meets the design requirement information. It can be seen that the present application can quickly and accurately meet the design requirements (for example, any one or more of the bare ship performance, the energy-saving effect of the hydrodynamic energy-saving device, the bare ship resistance, and the navigation performance) and the hull line of the specified wake field.

[0074] In a specific embodiment, the wake field prediction model is trained based on hull surface samples and wake field samples.

[0075] Specifically, a variety of hull lines are obtained to obtain the corresponding hull surfaces, and the nominal wake field corresponding to the hull surface is obtained by means of computational fluid dynamics (CFO) and model tests. The hull surface is used as a hull surface sample, and the nominal wake field is used as a wake field sample to train the wake field prediction model.

[0076] For example, the mapping relationship between the hull surface sample and the wake field sample is represented by formula (1):

[0077] u'=f(s')…………(1)

[0078] Where u' represents the wake field characteristics corresponding to the wake field sample, for example, the fluid velocity field within 1.2 times the propeller diameter at the propeller disk surface, and s' represents the coordinates corresponding to the hull surface sample, expressed in the form of a three-dimensional point cloud, which is a set of spatial coordinate vectors, that is, u' = {u' t ,t=1,...,T}, T is the number of point clouds.

[0079] Specifically, the mapping relationship between the hull surface samples and the wake field samples is used to train the forward model (wake field prediction model).

[0080] Among them, s' is the FV expression of low-latitude ship parameters obtained by combining the NURBS expression of the hull surface with the 3DmFV method of point cloud recognition. u' is a wake field feature extraction method based on POD analysis, which realizes the complete expression of the wake field through low-dimensional decomposition coefficients combined with characteristic functions.

[0081] Among them, the wake field prediction model is based on a 3D convolutional neural network. The low-dimensional FV three-dimensional matrix and POD coefficient are input, and a large amount of historical calculation data is used to build a training data set to train the deep neural network. The mapping relationship model obtained after training can use the specified ship type point cloud as input and the wake field as output.

[0082] In a specific embodiment, the initial hull surface is optimized based on the design requirements and the optimization target, and the specific implementation of obtaining the optimized initial hull surface includes:

[0083] The previous hull surface is reconstructed to obtain the hull surface to be designed; for the hull surface to be designed, the optimization area is designed using the optimization direction and optimization magnitude based on the design requirements and optimization objectives to obtain the optimized hull surface.

[0084] Specifically, the mother ship was analyzed for the first time, and the surface was reconstructed based on NURBS. In the subsequent iteration process, the hull surface was used as the basis for redesign.

[0085] The regional modification design based on feature analysis in this application (performing regional feature transformation processing) is based on the mother ship, and the optimized area is modified according to the design requirements, thereby achieving the purpose of generating batch ship modifications based on low-dimensional design parameters.

[0086] In a specific embodiment, based on the comparison results and design requirements, before determining the optimization target for the previous hull surface, at least one optimization region that conforms to the Gaussian distribution is determined from the hull surface to be designed using the center point coordinates and the first covariance matrix of the Gaussian function; based on the center point coordinates, the first covariance matrix and the design requirements, the control points to be processed are determined from the optimization region, and the design parameters of the control points to be processed are determined using the Gaussian kernel function; based on the design parameters, the optimization direction and optimization magnitude are determined.

[0087] The positive and negative values ​​of the design parameters are used to determine the optimization direction, and the size of the design parameters is used to determine the optimization magnitude.

[0088] In a specific embodiment, based on the center point coordinates, the first covariance matrix and the design requirements, the specific implementation of determining the control points to be processed from the optimization region includes:

[0089] Based on the preset control point selection index formula, the center point coordinates and the first covariance matrix, the control points to be processed are determined from the optimization area.

[0090] The control point selection index formula is shown in formula (2):

[0091]

[0092] Among them, ρ P (x) represents the control point selection index, which is obtained based on the design requirements, μ n represents the coordinates of the center point of the nth Gaussian function, σ n represents the first covariance matrix of the nth Gaussian function, x represents the coordinates of the control point to be processed, N represents the number of Gaussian functions, and the coordinates of the center point are determined based on design requirements.

[0093] Specifically, the entire design process includes: ship type NURBS surface reconstruction, optimization area setting, Gaussian kernel function calculation, design parameter setting (based on optimization direction and optimization magnitude) and new ship type point cloud generation.

[0094] In order to facilitate the selection of the optimization area and facilitate automatic integrated optimization, the Gaussian mixture function is used to calculate the selection index function of the control points in the optimization area, and the control point selection index in the natural coordinate system (see Formula 2). It only needs to specify the center point coordinates and variance to select a deformation area that obeys the Gaussian distribution.

[0095] In a specific embodiment, the specific implementation of determining the design parameters of the control point to be processed by using the Gaussian kernel function includes:

[0096] The Gaussian kernel function is obtained based on the index of the control points. The characteristic basis function corresponding to the Gaussian kernel of the Gaussian kernel function and the eigenvalue corresponding to the characteristic basis function are calculated based on the eigenvalue decomposition formula. Based on the modal decomposition formula, the characteristic basis function and the eigenvalue, the control points of the hull surface to be designed are projected into the n-dimensional characteristic space to obtain the design parameters.

[0097] The Gaussian kernel function is shown in formula (3):

[0098]

[0099] Among them, x' represents the transpose of x, and l represents the Euclidean distance from the coordinates of the control point to be processed to the coordinates of the center point.

[0100] The eigenvalue decomposition formula is shown in formula (4):

[0101]

[0102] in, represents the characteristic basis function, Represents the eigenvalue.

[0103] The modal decomposition formula is shown in formula (5):

[0104]

[0105] in, represents the control points of the hull surface to be designed, A i represents the design parameters, represents the eigenvalue corresponding to the i-th dimension feature space, Represents the characteristic basis function corresponding to the i-th dimension feature space.

[0106] According to the NURBS surface theory, the NURBS control state parameter (coordinates of the control points) of a certain ship-shaped surface is known to be x = [x p ,y p ,z p ,ω p ], the ship's surface value point cloud can be reconstructed and calculated. The two are equivalent, so x can be used to represent the ship's surface, where x is based on the pre-created three-dimensional rectangular coordinate system and the angle of the corresponding point cloud point. n ,σ n ,A i ), the regional design parameter is (μ n ,σ n ) and design parameter A i Automatic sampling can be performed to obtain batch ship types. n and σ n These two parameters control the design area.

[0107] This application simplifies the high-dimensional complex set design problem into a finite order, and realizes the acquisition of new control point coordinates based on low-dimensional design parameters, thereby driving the deformation of the hull surface and realizing ship type modification.

[0108] In a specific embodiment, based on the forward evaluation model, the ship type optimization process can be expressed as solving the following optimization problem, that is, given a mother ship, represented by its NURBS control point coordinates, denoted by x f , we hope to find such a new ship type x * , so that it meets the input geometric constraints (such as drainage volume unchanged), satisfying the specified target wake field (specified wake field) u * Under the premise of minimum total resistance / received power performance.

[0109] Before optimizing the previous hull surface based on design requirements and optimization objectives, when it is determined that the first data dimension corresponding to the predicted wake field is smaller than the second data dimension corresponding to the mother ship type, the preset optimization function must be satisfied.

[0110] The optimization function is shown in formula (6):

[0111]

[0112] x opt represents the optimization result, and J(x) represents the loss function.

[0113] The loss function is shown in formula (7):

[0114]

[0115] Among them, x represents the coordinates of the control point of the previous hull surface, u represents the predicted wake field, H() represents the observation operator, represents the transpose of the variable matrix inside the double vertical line multiplied by the subscript matrix and then multiplied by the variable matrix inside the double vertical line, where t = P, R, O and W, P, R, O and W represent the covariance matrix of the variable matrix inside the double vertical line, respectively. represents the prior distribution of the input ship type information, characterizing the influence of prior physical knowledge, H o (u) is the part of the observation operator that is set as the optimization target, H r (x) is the part of the observation operator that is set as a constraint, To specify the performance parameter quantity as a constraint, J r (x) is the regularization term of the loss function, which is the part that directly constrains the input parameters, λ 1 and λ 2 is the weight of the two constraints, indicating the strength of the constraints, are constraints on the hull geometry input, Refers to higher-order derived quantities that constrain the hull geometry.

[0116] Specifically, for the specified wake field inverse design problem, the loss function is configured specifically to meet the design requirements:

[0117] (1) Optimize the target part || H o (u)||: It is expressed as the minimum mean square error between the predicted wake field and the target wake field, that is, the L2 norm of the designed wake field and the target wake field, see formula (8):

[0118]

[0119] Where u = f(x) is the wake field of any ship type, u * is the target wake field, and S is the number of data sampling points in the wake field area.

[0120] (2) Design constraints Indicates the deviation of the ship performance constraint The mapping relationship between ship geometry and ship performance parameters is expressed by the continuity equation is the constrained performance parameter, such as the total resistance of the ship or the received power.

[0121] (3) Regularization term J r (x): Geometric constraints on the design results, such as displacement volume, center of buoyancy position, etc., expressed as:

[0122] in, are constraints on the hull geometry input, Refers to higher-order derived quantities that constrain the hull geometry, such as displacement volume, center of buoyancy position, etc.

[0123] Specifically, when the first data dimension is smaller than the second data dimension, the inverse problem is a statically indeterminate problem, which is equivalent to solving an optimization problem, namely, formula (6).

[0124] In a specific embodiment, after the optimized hull surface is input into the wake field prediction model, the predicted wake field output by the wake field prediction model during the d+1th iteration is obtained; the average wake field and the second covariance matrix corresponding to the d+1th iteration are calculated; the Kalman gain matrix is ​​calculated based on the second covariance matrix; and the next hull surface is optimized based on the Kalman gain matrix, design requirements and optimization objectives.

[0125] Specifically, the solution to the uncertain Bayesian inference problem is achieved based on the iterative ensemble Kalman filtering method. The optimization process replaces the original deterministic variables with the probability distribution of the variables, and the optimization problem is transformed into finding the input variable x that maximizes the probability of p(x|u), and its output variable u = predicted result + ε, where ε represents the prediction error of the accompanying flow field prediction model.

[0126] The specific implementation is as follows:

[0127] sampling:

[0128] Based on the mother ship, the Gaussian distribution Latin hypercube sampling method is used to generate a set of multiple hull surfaces to be predicted. For example, the set consists of M sequences. Among them, the set is obtained according to the prior distribution of the data.

[0129] forecast:

[0130] Perform wake field prediction for each sequence and obtain the prediction result at the d+1th iteration

[0131] analyze:

[0132] Based on the first calculation formula, the average wake field corresponding to the d+1th time is calculated, and based on the second calculation formula, the second covariance matrix is ​​calculated.

[0133] The first calculation formula is shown in formula (9):

[0134]

[0135] The second calculation formula is shown in formula (10):

[0136]

[0137] The Kalman gain matrix is ​​calculated based on the third calculation formula.

[0138] The third calculation formula is shown in formula (11):

[0139] K (n+1) =P (n+1) H T (HP (n+1) H T +R) -1 ………(11)

[0140] Among them, H represents the observation matrix, which is the matrix corresponding to the mapping of control points from the state space to the observation space, and R represents the covariance matrix of the prediction error, which is used to represent the uncertainty of the observation matrix.

[0141] The set corresponding to the d+1th time is updated based on the fourth calculation formula and the Kalman gain matrix to obtain a new set.

[0142] Among them, the fourth calculation formula (12) is:

[0143]

[0144] Specifically, adding constraints to the calculation process of the Kalman filter method is a design requirement and an important means to avoid the optimization problem from being too pathological. Since the feedback of the Kalman filter searches in the Gaussian space, such constraints are generally necessary, otherwise the stability of the inference process will be reduced.

[0145] Specifically, the constraints can be divided into strong constraints and weak constraints. Strong constraints are required to be strictly satisfied and are imposed through the data preprocessing step. They must be accurately satisfied, otherwise it will affect the subsequent calculation, model processing or shipbuilding process. Weak constraints mean that the final inference result may be as close to the constraint requirement as possible, but strict constraints cannot be guaranteed, and can be imposed in the form of a posteriori estimation.

[0146] In a specific embodiment, after calculating the Kalman gain matrix based on the second covariance matrix, a corresponding correction term in the d-th iteration process is determined; and the set is updated based on the correction term.

[0147] The correction term is shown in formula (13):

[0148]

[0149] The optimized fourth calculation formula is shown in formula (14):

[0150]

[0151] The present application includes a forward prediction part based on the wake field prediction model and a reverse design part based on Bayesian inference. The wake field corresponding to the hull curve input by the user is obtained, and then the hull line design based on Bayesian estimation is realized by applying the iterative collective Malman filter algorithm, and the hull line corresponding to the specified wake field is obtained, thereby realizing the rapid design of the hull line.

[0152] Figure 2 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 2 As shown, the electronic device may include: a processor 201, a communications interface 202, a memory 203 and a communication bus 204, wherein the processor 201, the communications interface 202 and the memory 203 communicate with each other through the communication bus 204. The processor 201 may call the logic instructions in the memory 203 to execute the hull line design method based on the specified wake field.

[0153] In addition, the logic instructions in the above-mentioned memory 203 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0154] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the hull line design method based on the specified wake field provided by the above-mentioned methods.

[0155] On the other hand, 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 execute the hull line design method based on a specified wake field provided in the above-mentioned embodiments.

[0156] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0157] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0158] Finally, it should be noted that the above is only the preferred implementation of the present application, and the present application is not limited to the above embodiments. It is understood that other improvements and changes directly derived or associated by those skilled in the art without departing from the spirit and concept of the present application should be considered to be included in the scope of protection of the present application.

Claims

1. A hull line design method based on a specified wake field, characterized in that: The method comprises: Acquire an initial hull surface corresponding to the mother ship, and perform regional feature transformation processing on the initial hull surface to obtain multiple hull surfaces to be predicted; Inputting the plurality of hull surfaces to be predicted into a pre-trained wake field prediction model to obtain a plurality of predicted wake fields output by the wake field prediction model, wherein the wake field prediction model is trained based on hull surface samples and wake field samples; Comparing the predicted wake field with the preset designated wake field to obtain a comparison result; Based on the comparison results and design requirements, an optimization target for the previous hull surface is determined, and based on the design requirements and the optimization target, the previous hull surface is optimized to obtain an optimized hull surface, and the optimized hull surface is input into the wake field prediction model until the comparison result meets the preset requirements, and the hull line design is determined to be completed, wherein the previous hull surface includes: the initial hull surface.

2. The hull line design method based on the specified wake field according to claim 1 is characterized in that: The optimization objectives include: optimization area, optimization direction and optimization magnitude; Optimizing the previous hull surface based on the design requirements and the optimization target to obtain an optimized hull surface includes: Reconstruct the previous hull surface to obtain the hull surface to be designed; For the hull surface to be designed, the optimization region is designed using the optimization direction and the optimization magnitude based on the design requirements and the optimization target to obtain an optimized hull surface.

3. The hull line design method based on the specified wake field according to claim 2 is characterized in that: Based on the comparison results and design requirements, before determining the optimization target for the previous hull surface, it also includes: Determine at least one optimization region conforming to Gaussian distribution from the hull surface to be designed by using the center point coordinates of the Gaussian function and the first covariance matrix; Based on the center point coordinates, the first covariance matrix and the design requirements, determining the control points to be processed from the optimization region, and determining the design parameters of the control points to be processed using a Gaussian kernel function; Based on the design parameters, the optimization direction and optimization magnitude are determined, wherein the positive or negative sign of the design parameters is used to determine the optimization direction, and the magnitude of the design parameters is used to determine the optimization magnitude.

4. The hull line design method based on the specified wake field according to claim 3 is characterized in that: Based on the center point coordinates, the first covariance matrix and the design requirements, determining the control points to be processed from the optimization region includes: Determine the control point to be processed from the optimization area based on a preset control point selection index formula, center point coordinates and a first covariance matrix; The control point selection index formula includes: Among them, ρ P (x) represents the control point selection index, which is obtained based on the design requirements, μ n represents the coordinates of the center point of the nth Gaussian function, σ n represents the first covariance matrix of the nth Gaussian function, x represents the coordinates of the control point to be processed, N represents the number of Gaussian functions, and the center point coordinates are determined based on the design requirements.

5. The hull line design method based on the specified wake field according to claim 4 is characterized in that: The Gaussian kernel function is used to determine the design parameters of the control point to be processed, including: Selecting an index based on the control point to obtain the Gaussian kernel function; Wherein, the Gaussian kernel function includes: Among them, x' represents the transpose of x, l represents the Euclidean distance from the coordinates of the control point to be processed to the coordinates of the center point; Based on the eigenvalue decomposition formula, calculate the eigenvalue basis function corresponding to the Gaussian kernel of the Gaussian kernel function and the eigenvalue corresponding to the eigenvalue basis function; Wherein, the eigenvalue decomposition formula includes: in, represents the characteristic basis function, represents the eigenvalue; Based on the modal decomposition formula, the characteristic basis function and the eigenvalue, the control points of the hull surface to be designed are projected into an n-dimensional characteristic space to obtain the design parameters; Wherein, the modal decomposition formula includes: in, represents the control point of the hull surface to be designed, A i represents the design parameters, represents the eigenvalue corresponding to the i-th dimension feature space, Represents the characteristic basis function corresponding to the i-th dimension feature space.

6. The hull line design method based on a specified wake field according to any one of claims 1 to 5, characterized in that: The design requirements include: design goals and design constraints; Before optimizing the previous hull surface based on the design requirements and the optimization target, the method further includes: When it is determined that the first data dimension corresponding to the predicted wake field is smaller than the second data dimension corresponding to the mother ship type, a preset optimization function must be satisfied; Wherein, the optimization function includes: x opt represents the optimization result, J(x) represents the loss function; Wherein, the loss function includes: Among them, x represents the coordinates of the control point of the previous hull surface, u represents the predicted wake field, H() represents the observation operator, represents the transpose of the variable matrix inside the double vertical line multiplied by the subscript matrix and then multiplied by the variable matrix inside the double vertical line, where t = P, R, O and W, P, R, O and W represent the covariance matrix of the variable matrix inside the double vertical line, respectively. represents the prior distribution of the input ship type information, characterizing the influence of prior physical knowledge, x f represents the coordinates of the control points of the initial hull surface, H o (u) is the part of the observation operator that is set as the optimization target, H r (x) is the part of the observation operator that is set as a constraint, To specify the performance parameter quantity as a constraint, J r (x) is the regularization term of the loss function, which is the part that directly constrains the input parameters. λ1 and λ2 are the weights of the two constraint terms, indicating the strength of the constraint. are constraints on the hull geometry input, Refers to higher-order derived quantities that constrain the hull geometry.

7. The method for designing hull lines based on a specified wake field according to any one of claims 1 to 5, characterized in that: After the optimized hull surface is input into the wake field prediction model, the method further includes: Obtaining the predicted wake field output by the wake field prediction model during the d+1th iteration; Calculate the average wake field and the second covariance matrix corresponding to d+1 times; Calculate a Kalman gain matrix based on the second covariance matrix; The next hull surface is optimized based on the Kalman gain matrix, the design requirements and the optimization objective.

8. The method for designing hull lines based on a specified wake field according to claim 7, characterized in that: After calculating the Kalman gain matrix based on the second covariance matrix, the method further includes: Determining a correction term corresponding to the d-th iteration process; optimizing the next hull surface based on the correction term; The amendments include: Among them, λ2 represents the weight, represents the constraint on the hull geometry input corresponding to the dth iteration, Refers to higher-order derived quantities that constrain the hull geometry.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the hull line design method based on the specified wake field as described in any one of claims 1 to 8 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the hull line design method based on a specified wake field as described in any one of claims 1 to 8 are implemented.

Images