Hydrodynamic performance forecasting method and device for planing boat based on dynamic data model and medium

Abstract

The invention discloses a hydrodynamic performance forecasting method and device for a planing boat based on a dynamic data model and a medium, and relates to the technical field of hydrodynamic performance forecasting of high-speed boats, and the method comprises the steps: obtaining to-be-forecasted boat type parameters and to-be-forecasted working conditions of a to-be-forecasted boat type corresponding to a planing boat; based on the correlation between a preset boat type parameter sample and a performance index parameter sample, determining the similarity between a sample boat type in a sample library and the to-be-predicted boat type; extracting sample data of which the similarity is greater than a preset value from the sample library, and constructing a forecasting model by utilizing the extracted sample data; and inputting the to-be-forecasted boat type parameters and the to-be-forecasted working conditions into the created forecasting model to obtain a hydrodynamic performance forecasting result output by the forecasting model. The method is used for solving the problem that in the prior art, the prediction accuracy of the hydrodynamic performance of the boat type is low in the initial design stage of the planing boat, and efficient and accurate prediction of the hydrodynamic performance of the boat type is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of high-speed boat hydrodynamic performance prediction, and in particular to a planing boat hydrodynamic performance prediction method, device and medium based on a dynamic data model. BACKGROUND

[0002] Hydrodynamic performance is one of the important performances of a planing boat and is a factor that needs to be considered in design work. In the preliminary design stage, the resistance and other hydrodynamic performances of the preliminary planing boat scheme (set) need to be determined to carry out further design work. The hydrodynamic characteristics of a planing boat are obviously different from those of a conventional displacement ship, and the calculation methods mainly include four types: 1) a semi-empirical and semi-theoretical method obtained by analyzing and summarizing the results of planing plate tests, which determines the hydrodynamic performance of a planing boat by using a series of resistance and lift calculation expressions obtained by summarizing planing plate test data; 2) using a series of model experiment graphs for calculation; 3) high-precision methods such as model tests or numerical calculations; and the like.

[0003] However, in the preliminary design stage, due to the fact that the specific boat structure has not been determined, and considering factors such as time efficiency and cost, model tests or numerical calculations are generally not directly carried out, and instead, a rapid prediction method is used. In the traditional rapid prediction method, the semi-theoretical and semi-empirical method often cannot guarantee accuracy, resulting in low precision of the predicted hydrodynamic performance. SUMMARY

[0004] To solve the problem of low prediction accuracy of the hydrodynamic performance of a planing boat in the preliminary design stage in the prior art, the present application provides a planing boat hydrodynamic performance prediction method, device and medium based on a dynamic data model, which can efficiently and accurately predict the hydrodynamic performance of a planing boat.

[0005] The present application provides a planing boat hydrodynamic performance prediction method based on a dynamic data model, which comprises the following steps:

[0006] Obtaining the to-be-predicted boat type parameters and the to-be-predicted working conditions of a to-be-predicted boat type corresponding to a planing boat;

[0007] Determining the similarity between a sample boat type in a sample library and the to-be-predicted boat type based on the correlation between the preset boat type parameter samples and the performance index parameter samples;

[0008] Extracting sample data with a similarity greater than a preset value from the sample library, and constructing a prediction model using the extracted sample data, wherein the sample data in the sample library includes: performance index parameter samples corresponding to boat type parameter samples under different working conditions, and the correlation between the boat type parameter samples and the performance index parameter samples;

[0009] input the to-be-predicted boat type parameter and the to-be-predicted working condition into the created prediction model, to obtain a water dynamic performance prediction result output by the prediction model.

[0010] According to the method for predicting water dynamic performance of a planing boat based on a dynamic data model provided in the embodiments of the present application, the similarity between a sample boat type in a sample library and the to-be-predicted boat type is determined based on the correlation between the preset boat type parameter sample and the performance index parameter sample, and the method comprises the following steps:

[0011] The weight of the correlation between the boat type parameter sample and each performance index parameter sample is calculated.

[0012] Based on the weight of the correlation, the weighted Euclidean distance between the sample boat type corresponding to the boat type parameter sample and the to-be-predicted boat type at each performance index parameter sample is calculated.

[0013] The sum of the weighted Euclidean distances of each sample boat type at all performance index parameter samples is calculated to obtain a summation result.

[0014] The summation result is used to represent the similarity between the sample boat type and the to-be-predicted boat type.

[0015] According to the method for predicting water dynamic performance of a planing boat based on a dynamic data model provided in the embodiments of the present application, the size of the summation result and the size of the similarity are in an inverse relationship.

[0016] According to the method for predicting water dynamic performance of a planing boat based on a dynamic data model provided in the embodiments of the present application, before the to-be-predicted boat type parameter and the to-be-predicted working condition of the to-be-predicted boat type corresponding to the planing boat are obtained, the method further comprises the following steps:

[0017] A plurality of sample libraries are constructed based on boat type categories.

[0018] Before the sample data with a similarity greater than a preset value is extracted from the sample library and the prediction model is constructed by using the extracted sample data, the method further comprises the following steps:

[0019] The sample library corresponding to the boat type category of the to-be-predicted boat type is determined.

[0020] According to the method for predicting water dynamic performance of a planing boat based on a dynamic data model provided in the embodiments of the present application, before the to-be-predicted boat type parameter and the to-be-predicted working condition of the to-be-predicted boat type corresponding to the planing boat are obtained, the method further comprises the following steps:

[0021] A plurality of sample libraries are constructed based on boat type categories.

[0022] For each sample library, the correlation between the boat type parameter sample and the performance index parameter sample is determined based on a preset correlation calculation formula.

[0023] The correlation calculation formula comprises:

[0024]

[0025] wherein r(x, y) represents the correlation, x i represents the sample of the hull form parameters, y j represents the sample of the performance index parameters, represents the average of the sample of the hull form parameters, represents the average of the sample of the performance index parameters in the sample library, n represents the number of the sample of the hull form parameters, and m represents the number of the sample of the performance index parameters.

[0026] According to the method for predicting the hydrodynamic performance of the planing boat based on the dynamic data model provided in the embodiments of the present application, after the to-be-predicted hull form parameters and the to-be-predicted working conditions are input into the created prediction model, the water dynamic performance prediction result output by the prediction model is obtained, and the method further comprises the following steps:

[0027] monitoring whether the sample data in the sample library changes;

[0028] in the case where it is determined that the sample data in the sample library changes, recalculating the correlation between the sample of the hull form parameters and the sample of the performance index parameters.

[0029] According to the method for predicting the hydrodynamic performance of the planing boat based on the dynamic data model provided in the embodiments of the present application, the hull form parameters are used to represent the geometric characteristics of the overall and local hull, and the performance index parameters are used to represent the performance curve, motion response and maneuverability corresponding to the hull form parameters under different working conditions.

[0030] According to the method for predicting the hydrodynamic performance of the planing boat based on the dynamic data model provided in the embodiments of the present application, the prediction model is constructed based on the regression modeling algorithm.

[0031] The embodiments of the present application further provide an electronic device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method for predicting the hydrodynamic performance of the planing boat based on the dynamic data model according to any one of the above embodiments when executing the program.

[0032] The embodiments of the present application further provide a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method for predicting the hydrodynamic performance of the planing boat based on the dynamic data model according to any one of the above embodiments.

[0033] The method, device and medium for predicting the hydrodynamic performance of a planing boat based on a dynamic data model provided by the embodiments of the present application, by obtaining the to-be-predicted boat type parameters and the to-be-predicted working conditions of the corresponding to-be-predicted boat type of the planing boat; determining the similarity between the sample boat type in the sample library and the to-be-predicted boat type based on the correlation between the preset boat type parameter sample and the performance index parameter sample; extracting sample data with a similarity greater than a preset value from the sample library, and constructing a prediction model using the extracted sample data, the present application selects similar samples to the to-be-predicted boat type parameters from the sample library based on the correlation between the boat type parameter sample and the performance index parameter sample each time the to-be-predicted boat type is predicted, that is, a dynamic approximate sample selection mechanism is adopted to obtain sample data related to the to-be-predicted boat type, and the prediction model is trained to ensure the accuracy of the prediction of the prediction model; the to-be-predicted boat type parameters and the to-be-predicted working conditions are input into the created prediction model to obtain the hydrodynamic performance prediction result output by the prediction model, the present application uses the trained prediction model to quickly predict the hydrodynamic performance, and realizes efficient and accurate prediction of the hydrodynamic performance of the boat type. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0035] Figure 1 is one of the flowcharts of the method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model provided by the embodiments of the present application;

[0036] Figure 2 is the second flowchart of the method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model provided by the embodiments of the present application;

[0037] Figure 3 is a structural schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0039] The embodiment of the present application provides a planing boat hydrodynamic performance prediction method based on a dynamic data model. The method can be applied to an intelligent terminal and can also be applied to a server. The present application takes the method applied to the server as an example for description, and some other descriptions in the embodiment are for example description and do not limit the protection scope of the present application. The specific implementation of the method is as shown in the following Figure 1

[0040] In step 101, the planing boat corresponding to a to-be-predicted boat type is acquired, and to-be-predicted boat type parameters and to-be-predicted working conditions of the to-be-predicted boat type are acquired.

[0041] In step 102, similarity between a sample boat type in a sample library and the to-be-predicted boat type is determined based on a preset correlation between a boat type parameter sample and a performance index parameter sample.

[0042] In step 103, sample data with similarity greater than a preset value is extracted from the sample library, and a prediction model is constructed by using the extracted sample data.

[0043] The sample data in the sample library includes: the performance index parameter sample corresponding to the boat type parameter sample under different working conditions, and the correlation between the boat type parameter sample and the performance index parameter sample.

[0044] In step 104, the to-be-predicted boat type parameters and the to-be-predicted working conditions are input into the created prediction model, and a hydrodynamic performance prediction result output by the prediction model is obtained.

[0045] The planing boat hydrodynamic performance prediction method based on the dynamic data model provided by the embodiment of the present application acquires to-be-predicted boat type parameters and to-be-predicted working conditions of the planing boat corresponding to a to-be-predicted boat type; similarity between a sample boat type in a sample library and the to-be-predicted boat type is determined based on a preset correlation between a boat type parameter sample and a performance index parameter sample; sample data with similarity greater than a preset value is extracted from the sample library, and a prediction model is constructed by using the extracted sample data. In the present application, each time the to-be-predicted boat type is predicted, the sample boat type with similarity to the to-be-predicted boat type is selected from the sample library based on the correlation between the boat type parameter sample and the performance index parameter sample, that is, a dynamic approximate sample selection mechanism is adopted to obtain sample data related to the to-be-predicted boat type, and the prediction model is trained, so that the prediction accuracy of the prediction model is ensured; the to-be-predicted boat type parameters and the to-be-predicted working conditions are input into the created prediction model, and a hydrodynamic performance prediction result output by the prediction model is obtained. In the present application, the trained prediction model is used for rapid prediction of the hydrodynamic performance, so that the prediction of the hydrodynamic performance of the boat type is efficiently and accurately completed.

[0046] In one specific embodiment, the boat type parameters are used to represent the overall and local geometric characteristics of the boat body, and the performance index parameters are used to represent the performance curves, motion responses and maneuverability of the boat type parameters under different working conditions.​

[0047] Specifically, the sample library is constructed based on the ship type parameters and the performance index parameters.

[0048] The sample library is the basis for the hydrodynamic performance prediction of the present application. In order to ensure the integrity of the data in subsequent use, each boat type sample in the database (sample library) should include boat type parameters representing the overall and local size / geometry characteristics of the boat body, including main size parameters of the boat such as overall length, maximum / afterbody width, displacement volume, and local parameters of the boat such as center of gravity position, channel, angle line, and bottom slope angle. The hydrodynamic performance index parameters corresponding to each boat type sample under different working conditions include: speed-resistance / power performance curves corresponding to different loads; main seakeeping motion response indexes such as longitudinal / lateral sway, heave, and acceleration corresponding to different speeds, wave heights, and wave directions (relative to the ship sailing direction); main maneuverability indexes such as turning circle diameter and turning heeling.

[0049] Among them, these performance index data are obtained through real ship test, model test or numerical calculation, and the units are unified.

[0050] In one specific embodiment, when creating the sample library, multiple sample libraries are constructed based on the boat type categories.

[0051] Among them, the boat type categories include: deep V type boat, round bilge type boat, transition type boat, channel type boat, etc.

[0052] Specifically, the sample library is created based on deep V type boat, round bilge type boat, transition type boat, channel type boat, etc.

[0053] In one specific embodiment, the sample library is created, and for each sample library, the correlation between the boat type parameter sample and the performance index parameter sample is determined based on a preset correlation calculation formula.

[0054] Among them, the correlation calculation formula is formula (1):

[0055]

[0056] Among them, r(x, y) represents the correlation, x i represents the boat type parameter sample, y j represents the performance index parameter sample, represents the average value of the boat type parameter sample in the sample, represents the average value of the performance index parameter sample in the sample library, n represents the number of boat type parameter samples, and m represents the number of performance index parameter samples.

[0057] Among them, x i is the independent variable, y i is the dependent variable, and both are dimensionless values.

[0058] wherein the value range of the correlation is [-1, 1], r is less than 0 for negative correlation, and r is greater than 0 for positive correlation. The correlation degree of the variable can be determined according to the absolute value of r, for example, 0.8<|r|≤1, very strong correlation; 0.6<|r|≤0.8, strong correlation; 0.4<|r|≤0.6, moderate correlation; 0.2<|r|≤0.4, weak correlation; 0≤|r|≤0.2, very weak correlation or no correlation.

[0059] Based on the above formula (1), the correlation coefficient between each item of the boat type parameter and each item of the performance index in the database is calculated. When calculating, the sample library of different boat types should be processed respectively according to mode (1), and the calculation result is stored in the database. The subsequent calculation can be directly read to improve the calculation efficiency. When the samples in the database change, the correlation needs to be recalculated and the result saved in the database is updated.

[0060] In one specific embodiment, the present application needs to monitor whether the sample data in the sample library changes in real time; in the case where it is determined that the sample data in the sample library changes, the correlation between the boat type parameter sample and the performance index parameter sample is recalculated.

[0061] Of course, a change standard can be designed here. In the case where the change standard is reached, the correlation is recalculated. The design of the change standard can be designed by the user according to the actual needs, and the present application does not make any limitation.

[0062] In one specific embodiment, before obtaining the to-be-predicted boat type parameter and the to-be-predicted working condition corresponding to the planing boat, the sample library corresponding to the boat type category of the to-be-predicted boat type is determined, the sample data with a similarity greater than a preset value is extracted from the determined sample library, and the prediction model is constructed by using the extracted sample data, thereby providing an effective data basis for the accuracy of model prediction.

[0063] In one specific embodiment, based on the preset correlation between the boat type parameter sample and the performance index parameter sample, the similarity between the sample boat type in the sample library and the to-be-predicted boat type is determined as shown in Figure 2 .

[0064] Step 201, obtaining the correlation between the boat type parameter sample and each performance index parameter sample.

[0065] Specifically, it is assumed that there are n boat type parameter samples, denoted as x i (x i =1, 2, … n), m performance index parameters, denoted as y j (j=1, 2, … m), and the correlation between each boat type parameter sample and each performance index parameter sample is denoted as r ij .

[0066] Step 202, calculate the weight of the correlation between the boat type parameter sample and each performance index parameter sample.

[0067] Specifically, the weight is obtained based on the weight calculation formula, see formula (2):

[0068]

[0069] wherein w ij represents the weight.

[0070] Step 203, based on the weight of the correlation, calculate the weighted Euclidean distance between the sample boat type corresponding to the boat type parameter sample and the to-be-predicted boat type at each performance index parameter sample.

[0071] Specifically, the weighted Euclidean distance is obtained based on the distance calculation formula, see formula (3):

[0072]

[0073] wherein WED jk represents the weighted Euclidean distance, x ik represents the boat type parameter sample corresponding to the kth sample, x i对象 represents the to-be-predicted boat type parameter corresponding to the to-be-predicted boat type, σ i represents the standard deviation of the boat type parameter sample of all sample boat types in the sample library, which is used to standardize the boat type parameter sample to eliminate the influence of the magnitude of the parameter on the calculation result.

[0074] wherein the standardization calculation formula is shown in formula (4):

[0075]

[0076] wherein N represents the number of samples.

[0077] Step 204, calculate the sum of the weighted Euclidean distances of each sample boat type at all performance index parameter samples to obtain a summation result.

[0078] wherein the summation result is used to represent the similarity between the sample boat type and the to-be-predicted boat type.

[0079] Specifically, the summation result is obtained based on the summation formula, see formula (5):

[0080]

[0081] wherein WED k represents the summation result.

[0082] Specifically, the similarity between the sample library and the boat type to be predicted is calculated based on the correlation between the obtained boat type parameter sample and the performance index parameter sample. It should be noted that only the sample library corresponding to the boat type to be predicted should be considered when calculating, for example, if the object to be predicted is a deep-V planing boat, only the data of the deep-V boat sub-library in the database and the corresponding correlation calculation results should be used.

[0083] The implementation mode described in the above embodiment can comprehensively consider the coupling effect of multiple boat type parameters, so that the result of the approximate boat type selection is more reasonable.

[0084] In one specific embodiment, the size of the sum result and the size of the similarity are inversely proportional, that is, the smaller the sum result, the higher the similarity; the larger the sum result, the lower the similarity.

[0085] In one specific embodiment, the prediction model is obtained based on a regression modeling algorithm.

[0086] Specifically, the algorithm for establishing the prediction model includes but is not limited to Random Forest, Support Vector Machine (SVM), Kriging, neural network, and other algorithms that can be used for regression modeling.

[0087] When modeling, the boat type parameter sample and the working condition parameter sample of the boat type sample are used as input values, and the corresponding performance index sample is used as output value (all parameters should be dimensionless values); when predicting, the model outputs the dimensionless performance prediction result according to the boat type parameters and working conditions of the object to be predicted, which can be converted into actual values (such as resistance, power, etc.) as needed.

[0088] Next, the calculation process of the similarity between the library boat type sample and the object boat type to be predicted is demonstrated by taking the resistance prediction process of a deep-V planing boat as an example, considering the influence of the boat type parameters on the resistance performance at multiple speed points, and not considering other performances. When predicting other performances or multiple performances, the relevant steps are consistent with this example.

[0089] The parameters of the object to be predicted and two samples in the database are shown in Table 1:

[0090]

[0091] Table 1: Parameters of the object to be predicted and two samples in the database

[0092] wherein β M represents the angle of inclination of the bottom at the waist, β T represents the angle of inclination of the bottom at the stern, L C / B C represents the aspect ratio of the corner line, X G / B C represents the relative position of the center of gravity, B represents relative volume Cmax B C B represents relative width of the knuckle line at the midship section CT B C B represents relative width of the knuckle line at the stern section. All the parameters are dimensionless.

[0093] The correlation between the boat type parameters and the resistance at F nb = 1.5 / 2.0 / 2.5 / 3.0 / 3.5 is calculated, and the absolute value is taken, such as

[0094] Table 2:

[0095]

[0096] Table 2 shows the results of the correlation calculation

[0097] where F nB represents the width Fourier number.

[0098] The correlation weight of each parameter at F nB = 1.5 / 2.0 / 2.5 / 3.0 / 3.5 is calculated, and since the correlation of β M and β T is relatively weak, it is not involved in the calculation. Then the weight of L C / B C at F nB = 1.5 is seen in formula (6):

[0099]

[0100] According to |r| in Table 2, formula (7) can be obtained:

[0101]

[0102] Similarly, the calculation results of the remaining weights are shown in Table 3. It should be noted that due to the influence of rounding off decimal places, the sum of the weights of each parameter at each speed may not be strictly equal to 1, which does not affect the final result.

[0103]

[0104] Table 3 shows the calculation results of the parameter weights

[0105] The standard deviations of the five parameters of all samples in the data set are calculated, and the results are: σ(L C / B C ) = 0.495; σ(X G / B C ) = 0.258; σ(B Cmax / L C ) = 0.018; σ(BCT / L C ) = 0.013. Substituting the hull type parameters from Table 1 and the weight calculation results from Table 3 into the equation, we can obtain the result in F. nB =1.5, the WED of sample 1 and the predicted object is shown in formula (8):

[0106]

[0107] Similarly, we can obtain Fn B At point 1.5, the WED of sample 2 and the forecast target is approximately 2.824.

[0108] The WED of samples 1 and 2 at other speeds was calculated using the method described above, and the results are shown in Table 4:

[0109]

[0110] Table 4 shows the weighted distance calculation results for example samples.

[0111] The global distances (WEDs) of samples 1 and 2 at all speeds were summed, and the global distances of sample 1 and 2 were 15.194 and 14.302, respectively. This shows that sample 2 has a higher similarity to the forecast target. Therefore, when making forecasts, the program will give priority to using the data of sample 2 to build the forecast model.

[0112] This application addresses the need for evaluating the hydrodynamic performance of design schemes during the preliminary design phase of high-speed boats. It establishes a database to conduct correlation analysis between boat hull parameters and hydrodynamic performance. Based on this, it establishes a dynamic approximate sample selection mechanism that selects samples similar to the predicted boat hull from the database. Based on the approximate samples, it establishes a surrogate model to quickly predict the hydrodynamic performance of the boat hull design scheme, thereby improving the efficiency of boat hull development and design.

[0113] Furthermore, based on the main parameters of the predicted vessel type, its hydrodynamic performance indicators can be quickly provided, and its prediction accuracy can meet the needs of the preliminary design stage. Moreover, its database can be expanded or modified at any time without altering the program, offering higher usability and scalability than traditional methods. This invention can provide effective assistance to designers in the preliminary design stage of high-speed vessels, improving design efficiency and quality.

[0114] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3As shown, the electronic device can include a processor 301, a communications interface 302, a memory 303, and a communications bus 304, wherein the processor 301, the communications interface 302, and the memory 303 complete mutual communication through the communications bus 304. The processor 301 can invoke a logic instruction in the memory 303 to execute the planing boat hydrodynamic performance prediction method based on a dynamic data model.

[0115] In addition, the logic instruction in the memory 303 described above can be realized in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0116] On the other hand, the present application 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 planing boat hydrodynamic performance prediction method based on a dynamic data model provided by the above-mentioned methods.

[0117] In yet another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the planing boat hydrodynamic performance prediction method based on a dynamic data model provided by the above-mentioned embodiments.

[0118] The device embodiments described above are only schematic, wherein the units shown as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0119] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and necessary general hardware platforms through the description of the above embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions 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 a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the various embodiments or some parts of the embodiments.

[0120] Finally, it should be noted that: the above only describes the preferred embodiments of the present application, and the present application is not limited to the above embodiments. It can be understood that other improvements and changes directly derived or thought of 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 protection scope of the present application.

Claims

1. A method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model, characterized in that, The method includes: Obtain the parameters of the boat type to be predicted and the operating conditions to be predicted for the corresponding planing boat; Based on the correlation between preset hull type parameter samples and performance index parameter samples, the similarity between the sample hull types in the sample library and the hull type to be predicted is determined. Sample data with similarity greater than a preset value are extracted from the sample library, and a prediction model is constructed using the extracted sample data. The sample data in the sample library includes: performance index parameter samples corresponding to the hull type parameter samples under different working conditions, and the correlation between the hull type parameter samples and the performance index parameter samples. The prediction model is created by inputting the parameters of the vessel type to be predicted and the operating conditions to be predicted, and the hydrodynamic performance prediction results output by the prediction model are obtained.

2. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to claim 1, characterized in that, Based on the correlation between preset hull type parameter samples and performance index parameter samples, the similarity between sample hull types in the sample library and the hull type to be predicted is determined, including: Calculate the weight of the correlation between the sample of hull type parameters and each sample of performance index parameters; Based on the weights of the correlation, the weighted Euclidean distance between the sample ship type and the ship type to be predicted corresponding to the ship type parameter sample at each of the performance index parameter samples is calculated. Calculate the sum of weighted Euclidean distances for each sample ship type across all performance index parameter samples to obtain the summation result; The summation result is used to characterize the similarity between the sample vessel type and the vessel type to be predicted.

3. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to claim 2, characterized in that, The magnitude of the summation result is inversely proportional to the magnitude of the similarity.

4. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to any one of claims 1-3, characterized in that, Before obtaining the parameters of the target boat type and the target operating conditions for the planing boat, the process also includes: Multiple sample libraries were constructed based on boat type categories; Before extracting sample data with a similarity greater than a preset value from the sample library and constructing a prediction model using the extracted sample data, the process also includes: Determine the sample library corresponding to the boat type category to be predicted.

5. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to any one of claims 1-3, characterized in that, Before obtaining the parameters of the target boat type and the target operating conditions for the planing boat, the process also includes: Multiple sample libraries were constructed based on boat type categories; For each sample library, the correlation between the hull type parameter sample and the performance index parameter sample is determined based on a preset correlation calculation formula; The correlation calculation formula includes: Where r(x,y) represents the correlation, x i This represents a sample of boat hull parameters, y j This represents a sample of performance indicator parameters. This represents the average value of the boat type parameters in the sample. This represents the average value of the performance index parameter samples in the sample library, where n represents the number of boat type parameter samples and m represents the number of performance index parameter samples.

6. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to any one of claims 1-3, characterized in that, After inputting the parameters of the submarine type to be predicted and the operating conditions to be predicted into the prediction model created, and obtaining the hydrodynamic performance prediction results output by the prediction model, the method further includes: Monitor whether the sample data in the sample library has changed; If it is determined that the sample data in the sample library has changed, the correlation between the hull type parameter sample and the performance index parameter sample is recalculated.

7. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to any one of claims 1-3, characterized in that, The hull shape parameters are used to characterize the overall and local geometric features of the hull, while the performance index parameters are used to characterize the performance curves, motion response, and maneuverability of the hull shape parameters under different operating conditions.

8. The method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model according to any one of claims 1-3, characterized in that, The forecast model is constructed using a regression modeling algorithm.

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 planing boat hydrodynamic performance prediction method based on a dynamic data model 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 method for predicting the hydrodynamic performance of a planing boat based on a dynamic data model as described in any one of claims 1 to 8.

Images