CN116522781B

CN116522781B - Sample data generation method, model training method and device

Info

Publication number: CN116522781B
Application number: CN202310491301.8A
Authority: CN
Inventors: 陈其朋; 张艳博; 周原野; 赵乔
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-05-04
Filing date: 2023-05-04
Publication date: 2024-04-05
Anticipated expiration: 2043-05-04
Also published as: CN116522781A

Abstract

The disclosure provides a sample data generation method, a model training method and a model training device, relates to the field of artificial intelligence, and particularly relates to the technical fields of computer aided engineering and deep learning. The specific implementation scheme is as follows: acquiring a configuration file for an application object and measurement data corresponding to each of a plurality of sampling points associated with the application object; the configuration file is used for representing a triangular mesh model aiming at the application object; analyzing the configuration file to obtain a plurality of triangular patch data; determining a target region based on the plurality of triangular patch data; the target area is used for representing the spatial distribution range of sample data to be generated; and generating a plurality of sample data matched with the target area according to the measurement data and the distance screening conditions corresponding to the sampling points.

Description

Sample data generation method, model training method and device

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to the technical fields of artificial intelligence, deep learning, computer aided engineering, and the like. And more particularly to a method and apparatus for generating sample data, a method and apparatus for training a state data determination model, a method and apparatus for generating a state data distribution map, an electronic device, a storage medium, and a computer program product.

Background

Currently, artificial intelligence technology has been gradually applied to related fields such as computer-aided engineering, etc., to perform performance analysis, prediction, optimization, etc., for specific types of engineering and products. In the process of analyzing and optimizing an application object by applying artificial intelligence technology, sample data corresponding to a plurality of sampling points are generally required to be extracted from a computer numerical simulation experiment result, so that the state and structural aspects of the application object are analyzed by using the sample data. However, in the related art, the sample data is usually extracted manually, which not only results in low extraction efficiency of the sample data, but also results in poor quality of the obtained sample data, and it is difficult to obtain a satisfactory effect.

Disclosure of Invention

The present disclosure provides a sample data generating method and apparatus, a training method and apparatus of a state data determination model, a state data distribution map generating method and apparatus, an electronic device, a storage medium, and a computer program product.

According to one aspect of the present disclosure, there is provided a sample data generating method including: acquiring a configuration file for an application object and measurement data corresponding to each of a plurality of sampling points associated with the application object; the configuration file is used for representing a triangular mesh model aiming at the application object; analyzing the configuration file to obtain a plurality of triangular patch data; determining a target region based on the plurality of triangular patch data; the target area is used for representing the spatial distribution range of sample data to be generated; and generating a plurality of sample data matched with the target area according to the measurement data and the distance screening conditions corresponding to the sampling points.

According to another aspect of the present disclosure, there is provided a training method of a state data determination model, including: acquiring sample data; training the deep learning model by using the sample data to obtain a state data determining model; wherein the sample data is obtained according to the sample data generation method described above.

According to another aspect of the present disclosure, there is provided a status data distribution map generating method, including: acquiring second coordinate information of each of the plurality of sampling points at a second moment; inputting the plurality of second coordinate information into a state data determining model to obtain second state data of each of the plurality of sampling points at a second moment; generating a state data distribution map associated with the application object according to the second state data of each of the plurality of sampling points at the second moment; wherein the state data determining model is trained according to the training method of the state data determining model described above.

According to another aspect of the present disclosure, there is provided a sample data generating apparatus including: the first acquisition module is used for acquiring a configuration file aiming at the application object and measurement data corresponding to each of a plurality of sampling points associated with the application object; the configuration file is used for representing a triangular mesh model aiming at the application object; the analysis module is used for analyzing the configuration file to obtain a plurality of triangular patch data; a determining module for determining a target area based on the plurality of triangular patch data; the target area is used for representing the spatial distribution range of sample data to be generated; and the first generation module is used for generating a plurality of sample data matched with the target area according to the measurement data and the distance screening conditions corresponding to the sampling points.

According to another aspect of the present disclosure, there is provided a training apparatus of a state data determination model, including: the second acquisition module is used for acquiring sample data; the training module is used for training the deep learning model by using the sample data to obtain a state data determining model; wherein the sample data is generated according to the sample data generating means described above.

According to another aspect of the present disclosure, there is provided a status data profile generating apparatus including: the third acquisition module is used for acquiring second coordinate information of each of the plurality of sampling points at a second moment; the input module is used for inputting a plurality of second coordinate information into the state data determining model to obtain second state data of each of the plurality of sampling points at a second moment; and a second generating module, configured to generate a status data distribution map associated with the application object according to second status data of each of the plurality of sampling points at a second time; wherein the state data determination model is trained based on the training means of the state data determination model described above.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method provided in accordance with the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method provided according to the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method provided according to the present disclosure.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of an exemplary system architecture to which sample data generation methods and apparatus, state data determination model training methods and apparatus, state data profile generation methods and apparatus may be applied, in accordance with embodiments of the present disclosure;

FIG. 2 is a flow chart of a sample data generation method according to an embodiment of the present disclosure;

FIGS. 3A and 3B are schematic diagrams of a method of determining a target area according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a sample data generation method according to an embodiment of the present disclosure;

fig. 5A to 5C are effect diagrams of a sample data generating process according to an embodiment of the present disclosure;

FIG. 6 is a flow chart of a training method of a state data determination model according to an embodiment of the present disclosure;

FIG. 7 is a flow chart of a status data profile generation method according to an embodiment of the present disclosure;

FIG. 8 is a block diagram of a sample data generating device according to an embodiment of the present disclosure;

FIG. 9 is a block diagram of a training apparatus of a state data determination model according to an embodiment of the present disclosure;

FIG. 10 is a block diagram of a state data profile generation apparatus according to an embodiment of the present disclosure; and

fig. 11 is a block diagram of an electronic device used to implement the sample data generation method, the training method of the state data determination model, and the state data profile generation method of an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

FIG. 1 is a schematic diagram of an exemplary system architecture to which sample data generation methods and apparatus, state data determination model training methods and apparatus, state data profile generation methods and apparatus may be applied, according to embodiments of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which embodiments of the present disclosure may be applied to assist those skilled in the art in understanding the technical content of the present disclosure, but does not mean that embodiments of the present disclosure may not be used in other devices, systems, environments, or scenarios.

As shown in fig. 1, a system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 1 05. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and/or wireless communication links, and the like.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications can be installed on the terminal devices 101, 102, 103. For example, computer aided engineering class applications, web browser applications, search class applications, instant messaging tools, mailbox clients or social platform software, and the like (just examples).

The terminal devices 101, 102, 103 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that, the sample data generating method provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the sample data generating device provided by the embodiments of the present disclosure may be generally provided in the server 105. The sample data generation method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the sample data generating apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.

It should be noted that, the training method of the state data determination model provided by the embodiments of the present disclosure may be generally performed by the server 105. Accordingly, the training means of the state data determination model provided by the embodiments of the present disclosure may be generally provided in the server 105. The training method of the state data determination model provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the training apparatus of the state data determination model provided by the embodiments of the present disclosure may also be provided in a server or a server cluster different from the server 105 and capable of communicating with the terminal device 1, 102, 103 and/or the server 105.

It should be noted that, the method for generating a status data distribution map provided by the embodiment of the present disclosure may be generally performed by the server 105. Accordingly, the status data profile generation apparatus provided by embodiments of the present disclosure may be generally provided in the server 105. The status data profile generation method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the status data profile generating apparatus provided by the embodiments of the present disclosure may also be provided in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.

Alternatively, the status data profile generation method provided by the embodiments of the present disclosure may also be generally performed by the terminal device 101, 102, or 103. Accordingly, the status data profile generating apparatus provided by the embodiments of the present disclosure may also be provided in the terminal device 101, 102, or 103.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

It should be noted that the sequence numbers of the respective operations in the following methods are merely representative of the operations for the purpose of description, and should not be construed as representing the order of execution of the respective operations. The method need not be performed in the exact order shown unless explicitly stated.

Fig. 2 is a flowchart of a sample data generation method according to an embodiment of the present disclosure.

As shown in fig. 2, the sample data generating method 200 may include operations S210 to S240.

In operation S210, a configuration file for an application object and measurement data corresponding to each of a plurality of sampling points associated with the application object are acquired.

In operation S220, the configuration file is parsed to obtain a plurality of triangular patch data.

In operation S230, a target area is determined based on the plurality of triangular patch data.

In operation S240, a plurality of sample data matching the target area is generated according to the measurement data and the distance screening condition corresponding to each of the plurality of sampling points.

According to an embodiment of the present disclosure, an application object refers to a study object involved in computer aided engineering (Computer Aided Engineering, CAE). For example, in the wing bypass problem, the application object may be a wing, for example. Of course, besides fluid mechanics, the application object may be a research object involved in related engineering problems such as electromagnetic and thermal conduction, and the application object is not limited herein.

The measurement data corresponding to each of the plurality of sampling points may be, for example, experimental test data obtained when performing numerical simulation on the application object and related data obtained by solving based on a numerical simulation method. For example, in an example in which the application object is subjected to flow field numerical simulation, the measurement data may include, for example, coordinates of each sampling point at different times and state data (such as flow rate, pressure, etc.) of each sampling point at different times.

The configuration file is a STL (Stereolithography) file indicating the application object. The STL file may be used to characterize a triangle mesh model for an application object. The triangular mesh model is a curved surface formed by connecting a plurality of triangular patches according to a certain topological structure.

By parsing the configuration file, a plurality of triangular patch data can be obtained. Each triangular patch data includes coordinate information of three vertices in the triangular patch and a normal vector of the triangular patch.

It will be appreciated that the normal vector of the triangular patches has directionality and that the direction of the normal vector of each triangular patch in the triangular mesh model has consistency. For example, the normal vector of each triangular patch points to the inside or outside of the triangular mesh model. Thus, in the disclosed embodiments, the target region may be determined based on the direction of the normal vector in the plurality of triangular patch data. The target region may be used to characterize a spatially distributed range of sample data to be generated.

Since the coordinate information of the corresponding sampling point is included in each measurement data, after the target area is acquired, a plurality of sample data matched with the target area can be generated according to the measurement data and the distance screening condition corresponding to each of the plurality of sampling points. The distance screening condition is used for screening measurement data of sampling points at preset positions in the target area.

For example, it is possible to extract target measurement data matching a sampling point at a preset position in a target area from measurement data corresponding to each of a plurality of sampling points according to coordinate information of each sampling point and a distance screening condition, and use the target measurement data as sample data. By the above means, the position accuracy of the sample data can be controlled based on the distance screening condition, whereby more representative sample data can be screened from the plurality of measurement data, and the accuracy and precision of the sample data can be improved.

In some embodiments, if the measurement data corresponding to the plurality of sampling points is missing, the target measurement data corresponding to the sampling points cannot be extracted from the measurement data, and at this time, interpolation processing may be performed on the measurement data corresponding to each of the plurality of sampling points in the target area, so as to obtain the target measurement data corresponding to the sampling points. Then, the target measurement data obtained by the interpolation processing and the extracted target measurement data described above may be determined as sample data.

In the technical scheme of the disclosure, the target area for extracting the sample data can be conveniently defined based on the triangular patch data obtained by analyzing the configuration file. Then, based on the measurement data and the distance screening condition corresponding to each of the plurality of sampling points, a plurality of sample data matching the target region can be extracted from the plurality of measurement data. In addition, interpolation processing can be performed on measurement data corresponding to each of the plurality of sampling points in the target area, so as to obtain sample data corresponding to a missing sampling point in the plurality of measurement data. By the method, the position accuracy of the sample data can be automatically and reliably controlled, so that more representative sample data can be screened from a plurality of measurement data, and the accuracy and precision of the sample data can be improved.

Fig. 3A and 3B are schematic diagrams of a method of determining a target area according to an embodiment of the present disclosure. The determination manner of the target area is exemplified below with reference to fig. 3A and 3B.

Fig. 3A shows a schematic diagram of a triangular mesh model of an application object "airplane" (by way of example only). As shown in fig. 3A, the triangular mesh model 31A to be applied is a curved surface formed by connecting a plurality of triangular patches in a certain topology. Wherein, the triangle mesh model 31A of the application object is obtained according to the STL file of the application object.

By analyzing the STL file of the application object, a plurality of triangular patch data associated with the triangular mesh model 31A of the application object can be obtained. Each triangular patch data includes coordinate information of three vertices in the triangular patch and a normal vector of the triangular patch.

As described above, the normal vector of the triangular patches has directionality, and the direction of the normal vector of each triangular patch in the triangular mesh model has consistency. Therefore, the above-described target area can be determined by configuring the direction of the normal vector in the plurality of triangular patch data.

For example, first configuration information for a normal vector direction of a triangular patch may be received. If it is determined that the normal vector of the triangular patch is directed to the inside of the triangular mesh model (as shown in fig. 3A) according to the first configuration information, the spatial region covered by the triangular mesh model may be determined as the target region.

For example, when the structural mechanics or internal flow problem of the application object is studied, the normal vector of the triangular patch in the triangular network model of the application object can be configured to point to the interior of the triangular mesh model based on the first configuration information, so that the spatial region covered by the triangular network model is determined as a target region for subsequent sample data extraction in the target region.

In another example, the target region may also be determined by means of an auxiliary model.

For example, at least one auxiliary model may be generated upon determining, based on the first configuration information, that the normal vector of the triangular patch points outside the triangular mesh model. Wherein, at least one auxiliary model comprises at least one auxiliary model of a coated triangular mesh model. And then, determining a target area according to the spatial position relation between the at least one auxiliary model and the triangular mesh model and the size of the spatial area respectively covered by the at least one auxiliary model and the triangular mesh model.

In an embodiment of the present disclosure, each of the at least one auxiliary model may be, for example, a triangular mesh model having an arbitrary regular shape. The triangular mesh model corresponding to each auxiliary model can be obtained according to the STL file.

FIG. 3B illustrates a schematic diagram of determining a target region from at least one auxiliary model and a triangular mesh model.

As shown in fig. 3B, after the triangular mesh model 31B of the application object is acquired, the STL file of the application object is parsed to obtain a plurality of triangular patch data associated with the triangular mesh model 31B. Each triangular patch data includes coordinate information of three vertices in the triangular patch and a normal vector of the triangular patch.

After receiving the first configuration information for the normal vector direction of the triangular patches, if it is determined that the normal vector of the triangular patches in the triangular mesh model 31B points outside the triangular mesh model 31B according to the first configuration information, at least one auxiliary model, such as the auxiliary model 32A and the auxiliary model 32B, may be generated. Wherein the triangular mesh model 31B is located inside the auxiliary model 32B.

Likewise, configuration information for the normal vector direction of the triangular patches in the auxiliary model 32A and the auxiliary model 32B may be received. From this configuration information, it can be determined that the normal vector of the triangular patch in the auxiliary model 32A is directed to the outside of the auxiliary model 32A, and the normal vector of the triangular patch in the auxiliary model 32B is directed to the inside of the auxiliary model 32B.

The target region may be determined based on the spatial positional relationship between the auxiliary model 32A and the auxiliary model 32B and the triangular mesh model 31B, and the size of the spatial region covered by each of the auxiliary model 32A and the auxiliary model 32B and the triangular mesh model 31B.

For example, the spatial region covered by the auxiliary model 32B may be subtracted from the spatial region covered by the auxiliary model 32A and the spatial region covered by the triangular mesh model 31B included therein, thereby obtaining the target region.

In some embodiments, the target region may also be determined from only the auxiliary model 32B and the triangular mesh model 31B, or using a plurality of auxiliary models other than the auxiliary model 32A and the auxiliary model 32B. The normal vector directions of the triangular patches in each auxiliary model and the triangular mesh model can be configured according to actual situations, and the present disclosure is not limited thereto.

In addition, it should be further noted that the shape, size, etc. of the triangular mesh model shown in fig. 3A and 3B are merely exemplary to facilitate the understanding of the solution of the present disclosure by those skilled in the art, but the present disclosure is not limited thereto, and may be specifically selected and set according to application scenarios.

Illustratively, where hydrodynamic problems such as three-dimensional bypass flow are involved, the target region may be determined in a manner as shown in FIG. 3B for subsequent sample data extraction within the target region.

According to an embodiment of the present disclosure, a plurality of sample data matching a target area may be generated in the following manner.

For example, a plurality of target measurement data matching the target region may be extracted from the measurement data corresponding to each of the plurality of sampling points based on the distance screening condition. Then, based on the measurement data corresponding to each of the plurality of sampling points, a plurality of additional measurement data matching the target area are generated. The additional measurement data is obtained by interpolation processing of measurement data corresponding to each of the plurality of sampling points. Then, a plurality of sample data are obtained from the plurality of target measurement data and the plurality of additional measurement quantities.

According to an embodiment of the present disclosure, the measurement data may include, for example, first coordinate information of the sampling point at the first time and first state data acquired by the sampling point at the first time. The first coordinate information may be two-dimensional coordinate information or three-dimensional coordinate information. The dimensions of the coordinate information may be determined from the state data.

According to an embodiment of the present disclosure, the distance screening condition may include a first condition, a second condition, and a third condition. An exemplary process of extracting a plurality of target measurement data matching a target region from measurement data corresponding to each of a plurality of sampling points according to three conditions included in the distance screening condition will be described below.

For example, for each measurement data, relative position information between the sampling points and the triangular mesh model is determined from the first coordinate information and the plurality of triangular patch data. And then, projecting the first coordinate information to the triangular mesh model to obtain projection position information. Then, a first distance from the sampling point to the triangular mesh model is determined based on the first coordinate information and the plurality of triangular patch data. Next, it may be determined whether the relative position information meets a first condition, the projection position information meets a second condition, and the first distance meets a third condition.

And if the relative position information is determined to be in accordance with the first condition, the projection position information is determined to be in accordance with the second condition, and the first distance is determined to be in accordance with the third condition, determining the measurement data as target measurement data. Otherwise, it is determined that the measurement data is not the target measurement data. Based on the above, a plurality of target measurement data matching the target region can be extracted from the measurement data corresponding to the plurality of sampling points.

The first condition includes: the sampling point is located at one side of the space region pointed by the normal vector of the triangular patch in the triangular mesh model.

In one example, for any one sampling point P, it may be determined whether the position where the sampling point P is located satisfies the first condition in the following manner. For example, the vector is determined based on the coordinate information of the sampling point P and the coordinate information of any one of the vertices a in the triangular patchAfter that, vector ++>And carrying out cross multiplication on the normal vector corresponding to the triangular patch. If the value of the cross multiplication is positive, the position of the sampling point P is indicated to meet a first condition; otherwise, the position of the sampling point P is not satisfied with the first condition.

The second condition includes: the projection position information is located in any one of the triangular patches in the triangular mesh model. In the embodiment of the present disclosure, whether the projection position information is located within any one of the triangular patches in the triangular mesh model may be determined according to a method in the related art. For example, the determination may be performed by a triangle area method, a vector method, or the like.

The third condition includes: the first distance satisfies a first distance threshold.

In the embodiment of the present disclosure, the first distance threshold may be, for example, a distance preset value, or may be a distance preset range, which may be specifically set according to an actual situation.

In some embodiments, the third condition may also be set such that the first distance satisfies at least one of a plurality of first distance thresholds. Wherein the plurality of first distance thresholds may be a plurality of different distance preset ranges.

In some embodiments, extracting a plurality of target measurement data matching the target region from the measurement data corresponding to each of the plurality of sampling points based on the distance screening condition further includes at least one of the following operations.

For example, a second distance between the sampling point and a preset point within the target area may be determined, and the measurement data is determined to be target measurement data in response to determining that the second distance meets a second distance threshold.

For example, a third distance between the sampling point and a preset line within the target region may be determined, and the measurement data is determined to be target measurement data in response to determining that the third distance satisfies a third distance threshold.

For example, a fourth distance between the sampling point and a preset plane within the target region may be determined, and the measurement data is determined to be target measurement data in response to determining that the fourth distance satisfies a fourth distance threshold.

For example, a fifth distance between the point and a preset geometry within the target area may be sampled, and the measurement data is determined to be target measurement data in response to determining that the fifth distance satisfies a fifth distance threshold.

In this embodiment of the present disclosure, the second to fifth distance thresholds, the preset point, the preset line, the preset plane, the preset geometric body, and the like may be set according to actual situations, and will not be described herein.

After the target measurement data is acquired according to at least one of the above modes, the target measurement data may be further combined with the target measurement data extracted based on the distance screening condition, thereby obtaining a plurality of target measurement data.

In an embodiment of the present disclosure, the measurement data corresponding to the plurality of sampling points may be interpolated using an inverse distance weighting method to generate a plurality of additional measurement data that match the target area.

For example, second configuration information for coordinate information of each of the plurality of additional sampling points may be received. Wherein the coordinate information of each additional sampling point is the coordinate information corresponding to the additional sampling point at the first time. A plurality of additional sampling points are located in the target region.

Then, a plurality of additional sampling points are determined in the target area according to the second configuration information.

Then, for each additional sampling point, determining the distance between the additional sampling point and each sampling point according to the coordinate information of the additional sampling point and the first coordinate information corresponding to each sampling point.

For example, it is assumed that the measurement data corresponding to the plurality of sampling points includes measurement data corresponding to n sampling points, where n is a positive integer. Wherein the j (j=1, 2 …, n) th sampling point P _j The corresponding measurement data may be denoted as P _j (t _j ，x _j ，y _j ，z _i ，r _j ). That is, the j (j=1, 2 …, n) th sampling point P _j At a first time (t _j ) The first coordinate information at (x) _j ，y _j ，z _j ) The first state data is r _j 。

For the i-th additional sampling point P _i The ith additional sampling point P _i The coordinate information at the first time is (x _i ，y _i ，z _i ) I is a positive integer.

The ith additional sampling point P may be determined using the following equation (1) _i And each sampling point P _j Distance between them.

In the above formula (1), d _ij Representing the i-th additional sampling point P _i And the j-th sampling point P _j Distance between them.

And then, according to the first state data corresponding to each sampling point and the distance between the additional sampling point and each sampling point, determining the first state data corresponding to the additional sampling point.

The first state data r corresponding to the additional sampling point may be determined using the following equation (2) _i 。

In the above formula (2), r _i Representing first state data corresponding to the additional sampling points, alpha represents a constant for characterizing the extent of influence of the distance. In one example, α may take on a value of 2 or 3.

And finally, generating additional measurement data according to the coordinate information of the additional sampling points and the first state data corresponding to the additional sampling points.

For example, the i-th additional sampling point P can be used _i Coordinate information (x _i ，y _i ，z _i ) And the first state data r _i Generating additional measurement data P _i (t _i ，x _i ，y _i ，z _i ，r _i )。

Fig. 4 is a schematic diagram of a sample data generating method according to an embodiment of the present disclosure, and fig. 5A to 5C are effect diagrams of a sample data generating process according to an embodiment of the present disclosure. The scheme of the present disclosure is exemplified below by taking a three-dimensional bypass flow problem as an example, and referring to fig. 4, 5A to 5C. It will be appreciated that the illustrations of fig. 4, 5A-5C are merely exemplary to facilitate an understanding of aspects of the present disclosure by those skilled in the art, and that aspects of the present disclosure are not limited thereto.

Please refer to fig. 4 and fig. 5A together. First, a configuration file 401 for an application object (e.g., a vessel) and measurement data 402 corresponding to each of a plurality of sampling points associated with the application object are acquired. Wherein configuration file 401 refers to an STL file corresponding to an application object, which may be used to characterize a triangular mesh model for the application object (e.g., vessel 51 shown in fig. 5A).

Then, the configuration file 401 is parsed to obtain a plurality of triangular patch data 404. Each triangular patch data includes coordinate information of three vertices in the triangular patch and a normal vector of the triangular patch.

Then, first configuration information 403 for the normal vector direction of the triangular patch is received.

Referring to fig. 5B, when the three-dimensional streaming problem is involved, it is generally necessary to extract measurement data in an area outside the triangular mesh model 51, and therefore, when determining the target area, it is necessary to consider the area outside the triangular mesh model 51. In the disclosed embodiments, the measurement data may include, for example, first coordinate information of the sampling point at a first time and first state data acquired by the sampling point at the first time. Here, the first coordinate information is three-dimensional coordinate information, and may be expressed as (x, y, z). The first state data may include, for example, pressure, flow velocity components of the fluid in three dimensions (x, y, z), and the like. The measurement data can be obtained based on a computational fluid dynamics numerical solution.

In view of this, the normal vector direction for the triangular patch in the first configuration information 403 may be configured to point to the outside of the triangular mesh model 51. Upon determining, from the first configuration information 403, that the normal vector of the triangular patch points outside the triangular mesh model 51, at least one auxiliary model may be generated, wherein the at least one auxiliary model includes at least one auxiliary model of the coated triangular mesh model. For example, in addition to the triangular mesh model 51 corresponding to the vessel, an auxiliary model 52 having a rectangular parallelepiped shape is generated, and the auxiliary model 52 may cover the triangular mesh model 51.

Then, the target region 406, that is, the spatial region between the triangular mesh model 51 and the auxiliary model 52 is determined based on the spatial positional relationship between the auxiliary model 52 and the triangular mesh model 51, and the size of the spatial region covered by each of the auxiliary model 52 and the triangular mesh model 51.

Next, based on the distance screening condition 405, a plurality of target measurement data 407 matching the target region 406 are extracted from the measurement data 402 corresponding to each of the plurality of sampling points in the manner described above.

In addition, second configuration information 408 for the coordinate information of the plurality of additional sampling points may be received, and the plurality of additional sampling points may be determined within the target area 406 based on the coordinate information 409 of the plurality of additional sampling points in the second configuration information 408.

Then, for each additional sampling point, based on the inverse distance weighting method, first state data corresponding to each additional sampling point is determined from the measurement data 402 corresponding to each of the plurality of sampling points. Then, additional measurement data 410 is generated from the coordinate information 409 of the additional sampling point and the first state data corresponding to the additional sampling point. Thus, interpolation processing is performed on the measurement data 402 corresponding to each of the plurality of sampling points in the target area 406, so as to obtain sample data corresponding to a missing sampling point in the plurality of measurement data.

Finally, a plurality of sample data 411 is obtained from the plurality of target measurement data 407 and the plurality of additional measurement quantities 410.

Referring to fig. 5C, based on the above, a plurality of sample data 511 can be obtained in the spatial region between the triangular mesh model 51 and the auxiliary model 52.

According to the technical scheme, the position accuracy of the sample data can be automatically and reliably controlled, so that more representative sample data can be screened from a plurality of measurement data, and the accuracy and the precision of the sample data can be improved.

FIG. 6 is a flow chart of a training method of a state data determination model according to an embodiment of the present disclosure.

As shown in fig. 6, the training method 600 of the state data determination model includes operations S610 to S620.

In operation S610, sample data is acquired. Wherein the sample data is obtained according to the sample data generating method described above.

In operation S620, the deep learning model is trained using the sample data, resulting in a state data determination model.

For example, first coordinate information of a plurality of sampling points at a first time in the sample data may be used as input information, and state data prediction may be performed based on the input information by using a deep learning model, so as to obtain sample state data corresponding to each of the plurality of sampling points at the first time. And then, carrying out loss calculation by using the sample state data corresponding to each of the plurality of sampling points at the first moment and the first state data corresponding to each of the plurality of sampling points in the sample data at the first moment, and adjusting parameters of the deep learning model based on the calculated loss value so as to obtain a state data determination model. The state data determination model may predict state data of a sampling point at a certain moment according to coordinate information of the sampling point at the certain moment.

In the embodiment of the disclosure, the deep learning model is trained by adopting high-quality sample data, so that the model can obtain better effect, and the accuracy of model output is improved.

Fig. 7 is a flowchart of a status data profile generation method according to an embodiment of the present disclosure.

As shown in fig. 7, the status data profile generation method 700 includes operations S710 to S730.

In operation S710, second coordinate information of each of the plurality of sampling points at a second time is acquired.

In operation S720, a plurality of second coordinate information is input into the state data determination model, resulting in second state data of each of the plurality of sampling points at a second time. Wherein the state data determining model is trained according to the training method of the state data determining model described above.

In operation S730, a state data profile associated with the application object is generated from the second state data of each of the plurality of sampling points at the second time instant.

For example, a three-dimensional streaming problem is taken as an example. The second state data of each of the plurality of sampling points at the second time may be predicted based on the second coordinate information of each of the plurality of sampling points at the second time using the state data determination model, and include, for example, flow rates (flow rate components in respective directions), pressures, and the like of each of the plurality of sampling points at the second time.

Then, a flow velocity profile and a pressure profile at the second time may be generated from the flow velocity and the pressure at the second time at the respective sampling points, respectively. Based on the flow velocity and pressure distribution conditions, the conditions of the structure, the motion state and the like of an application object (such as a ship) can be analyzed and optimized.

In the scheme of the embodiment of the disclosure, the accuracy of the output result of the model can be improved by utilizing the state data obtained through training in the above manner to determine the model to predict the state data.

Fig. 8 is a block diagram of a sample data generating device according to an embodiment of the present disclosure.

As shown in fig. 8, the sample data generating apparatus 800 includes a first acquisition module 810, an analysis module 820, a determination module 830, and a first generation module 840.

The first obtaining module 810 is configured to obtain a configuration file for an application object and measurement data corresponding to each of a plurality of sampling points associated with the application object, where the configuration file is used to characterize a triangle mesh model for the application object.

The parsing module 820 is configured to parse the configuration file to obtain a plurality of triangular patch data.

The determining module 830 is configured to determine a target area based on the plurality of triangular patch data; the target region is used to characterize the spatial distribution range of the sample data to be generated.

The first generation module 840 is configured to generate a plurality of sample data that matches the target area according to the measurement data and the distance screening condition corresponding to each of the plurality of sampling points.

According to an embodiment of the present disclosure, each triangular patch data includes coordinate information of three vertices in the triangular patch and a normal vector of the triangular patch. The determining module 830 includes: a receiving unit and a first determining unit. The receiving unit is used for receiving first configuration information of the normal vector direction of the triangular patch; and the first determining unit is used for determining that the normal vector of the triangular patch points to the inside of the triangular mesh model according to the first configuration information, and determining the space area covered by the triangular mesh model as a target area.

According to an embodiment of the present disclosure, the determining module 830 further includes: a second determination unit and a third determination unit. The second determining unit is used for responding to the first configuration information, determining that the normal vector of the triangular patch points to the outside of the triangular mesh model, and generating at least one auxiliary model; wherein the at least one auxiliary model at least comprises an auxiliary model of a coated triangular mesh model; and the third determining unit is used for determining the target area according to the spatial position relation between the at least one auxiliary model and the triangular mesh model and the size of the spatial area respectively covered by the at least one auxiliary model and the triangular mesh model.

According to an embodiment of the present disclosure, the first generation module 840 includes: an extraction unit, a generation unit and a fourth determination unit. The extraction unit is used for extracting a plurality of target measurement data matched with the target area from the measurement data corresponding to each of the plurality of sampling points based on the distance screening condition; the generating unit is used for generating a plurality of additional measurement data matched with the target area based on the measurement data corresponding to the sampling points; and a fourth determining unit for obtaining a plurality of sample data based on the plurality of target measurement data and the plurality of additional measurement quantities.

According to an embodiment of the present disclosure, the measurement data includes first coordinate information of the sampling point at a first time instant; the distance screening conditions comprise a first condition, a second condition and a third condition; the extraction unit includes: the projection unit comprises a first determining subunit, a projection subunit, a second determining subunit and a third determining subunit. The first determining subunit is used for determining relative position information between the sampling points and the triangular mesh model according to the first coordinate information and the triangular patch data for each measurement data; the projection subunit is used for projecting the first coordinate information to the triangular mesh model to obtain projection position information; the second determining subunit is used for determining a first distance from the sampling point to the triangular mesh model according to the first coordinate information and the triangular patch data; and a third determination subunit configured to determine the measurement data as target measurement data in response to determining that the relative position information meets the first condition, the projection position information meets the second condition, and the first distance meets the third condition.

According to an embodiment of the present disclosure, the first condition includes: the position of the sampling point is positioned at one side of a space area pointed by a normal vector of the triangular patch in the triangular mesh model; the second condition includes: the projection position information is positioned in any triangular patch in the triangular mesh model; the third condition includes: the first distance satisfies a first distance threshold.

According to an embodiment of the present disclosure, the extraction unit further comprises at least one of: a fourth determining subunit, configured to determine a second distance between the sampling point and a preset point in the target area, and determine that the measurement data is target measurement data in response to determining that the second distance meets a second distance threshold; a fifth determining subunit, configured to determine a third distance between the sampling point and a preset straight line in the target area, and determine that the measurement data is target measurement data in response to determining that the third distance meets a third distance threshold; a sixth determining subunit, configured to determine a fourth distance between the sampling point and a preset plane in the target area, and determine that the measurement data is target measurement data in response to determining that the fourth distance meets a fourth distance threshold; and a seventh determining subunit configured to determine a fifth distance between the sampling point and a preset geometry in the target area, and determine that the measurement data is target measurement data in response to determining that the fifth distance satisfies a fifth distance threshold.

According to an embodiment of the present disclosure, the measurement data further includes: the sampling point acquires first state data at a first moment; the generation unit includes: a receiving subunit, an eighth determining subunit, a ninth determining subunit, a tenth determining subunit, and a generating subunit. The receiving subunit is used for receiving second configuration information of coordinate information of a plurality of additional sampling points; the coordinate information of each additional sampling point is the coordinate information corresponding to the additional sampling point at the first moment; the eighth determining subunit is configured to determine a plurality of additional sampling points in the target area according to the second configuration information; the ninth determining subunit is configured to determine, for each additional sampling point, a distance between the additional sampling point and each sampling point according to coordinate information of the additional sampling point and first coordinate information corresponding to each sampling point; the tenth determination subunit is configured to determine, according to the first state data corresponding to each sampling point and the distance between the additional sampling point and each sampling point, the first state data corresponding to the additional sampling point; and the generation subunit is used for generating additional measurement data according to the coordinate information of the additional sampling points and the first state data corresponding to the additional sampling points.

Fig. 9 is a block diagram of a training apparatus of a state data determination model according to an embodiment of the present disclosure.

As shown in fig. 9, the training apparatus 900 of the state data determination model includes: a second acquisition module 910 and a training module 920.

The second acquisition module 910 is configured to acquire sample data. Wherein the sample data is generated according to the sample data generating means described in the above embodiments.

The training module 920 is configured to train the deep learning model by using the sample data to obtain a state data determination model.

Fig. 10 is a block diagram of a state data profile generation apparatus according to an embodiment of the present disclosure.

As shown in fig. 10, the status data distribution map generating apparatus 1000 includes: a third acquisition module 1010, an input module 1020, and a second generation module 1030.

The third obtaining module 1010 is configured to obtain second coordinate information of each of the plurality of sampling points at a second time.

The input module 1020 is configured to input a plurality of second coordinate information into the state data determining model to obtain second state data of each of the plurality of sampling points at a second time. Wherein the state data determination model is trained on the training device of the state data determination model described in the above embodiments.

The second generating module 1030 is configured to generate a status data distribution map associated with the application object according to the second status data of each of the plurality of sampling points at the second time instant.

It should be noted that, in the embodiment of the apparatus portion, the implementation manner, the solved technical problem, the realized function, and the achieved technical effect of each module/unit/subunit and the like are the same as or similar to the implementation manner, the solved technical problem, the realized function, and the achieved technical effect of each corresponding step in the embodiment of the method portion, and are not described herein again.

In the technical scheme of the disclosure, the related data (such as including but not limited to personal information of a user) are collected, stored, used, processed, transmitted, provided, disclosed, applied and the like, and all meet the requirements of related laws and regulations without violating the public welfare.

In the technical scheme of the disclosure, the authorization or consent of the data attribution is acquired before the related data is acquired or collected.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method as in an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a method as in an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a computer program product comprising a computer program which, when executed by a processor, implements a method as an embodiment of the present disclosure.

Fig. 11 illustrates a schematic block diagram of an example electronic device 1100 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 11, the apparatus 1100 includes a computing unit 1101 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, ROM 1102, and RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

Various components in device 1100 are connected to I/O interface 1105, including: an input unit 1106 such as a keyboard, a mouse, etc.; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108, such as a magnetic disk, optical disk, etc.; and a communication unit 1109 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 1109 allows the device 1100 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 1101 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 1101 performs the respective methods and processes described above, such as a sample data generation method, a training method of a state data determination model, and a state data distribution map generation method. For example, in some embodiments, the sample data generation method, the training method of the state data determination model, and the state data profile generation method may be implemented as computer software programs tangibly embodied on a machine-readable medium, such as storage unit 1108. In some embodiments, some or all of the computer programs may be loaded and/or installed onto device 1100 via ROM 1102 and/or communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the sample data generating method, the training method of the state data determination model, and the state data distribution map generating method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the sample data generation method, the training method of the state data determination model, and the state data profile generation method in any other suitable way (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A sample data generation method, comprising:

acquiring a configuration file for an application object and measurement data corresponding to each of a plurality of sampling points associated with the application object; the configuration file is used for representing a triangular mesh model aiming at the application object, and the measurement data comprises coordinates of each of the plurality of sampling points at different moments and state data of each of the plurality of sampling points at different moments when the application object is subjected to flow field numerical simulation;

analyzing the configuration file to obtain a plurality of triangular patch data;

determining a target region based on the plurality of triangular patch data; the target area is used for representing the space distribution range of sample data to be generated; and

generating a plurality of sample data matched with the target area according to the measurement data and the distance screening conditions corresponding to the sampling points;

The distance screening condition is used for screening measurement data of sampling points at preset positions in the target area; the generating a plurality of sample data matched with the target area according to the measurement data and the distance screening condition corresponding to the sampling points respectively includes:

extracting target measurement data matched with sampling points at preset positions in the target area from measurement data corresponding to the sampling points respectively based on the distance screening conditions;

generating a plurality of additional measurement data matched with the target area based on the measurement data corresponding to each of the plurality of sampling points, wherein the additional measurement data is obtained by performing interpolation processing on the measurement data corresponding to each of the plurality of sampling points; and

and obtaining the plurality of sample data according to the plurality of target measurement data and the plurality of additional measurement quantities.

2. The method of claim 1, wherein each of the triangular patch data includes coordinate information of three vertices in a triangular patch and a normal vector of the triangular patch; the determining a target region based on the plurality of triangular patch data includes:

Receiving first configuration information of a normal vector direction of the triangular patch; and

and responding to the first configuration information, determining that the normal vector of the triangular patch points to the inside of the triangular mesh model, and determining the space area covered by the triangular mesh model as the target area.

3. The method of claim 2, wherein the determining a target region based on the plurality of triangular patch data further comprises:

in response to determining that the normal vector of the triangular patch points to the outside of the triangular mesh model according to the first configuration information, generating at least one auxiliary model; wherein the at least one auxiliary model at least comprises an auxiliary model for coating the triangular mesh model; and

and determining the target area according to the spatial position relation between the at least one auxiliary model and the triangular mesh model and the size of the spatial area respectively covered by the at least one auxiliary model and the triangular mesh model.

4. The method of claim 1, wherein the measurement data includes first coordinate information of a sampling point at a first time instant; the distance screening condition includes a first condition, a second condition, and a third condition, the first condition including: the position of the sampling point is positioned at one side of a space area pointed by a normal vector of a triangular patch in the triangular mesh model; the second condition includes: the projection position information is positioned in any triangular patch in the triangular mesh model; the third condition includes: the first distance meets a first distance threshold; the extracting, based on the distance screening condition, a plurality of target measurement data matched with the target area from the measurement data corresponding to each of the plurality of sampling points includes: for each of the measurement data,

Determining relative position information between the sampling point and the triangular mesh model according to the first coordinate information and the triangular patch data, wherein the triangular patch data comprise coordinate information of any vertex of a triangular patch and normal vectors of the triangular patch, and the relative position information is determined based on a cross multiplication result between vectors formed by the sampling point and the vertex and the normal vectors;

projecting the first coordinate information to the triangular mesh model to obtain projection position information;

determining a first distance from the sampling point to the triangular mesh model according to the first coordinate information and the triangular patch data; and

in response to determining that the relative position information meets the first condition, the projected position information meets the second condition, and the first distance meets the third condition, the measurement data is determined to be the target measurement data.

5. The method of claim 4, wherein the extracting, based on the distance screening condition, a plurality of target measurement data matching the target region from the measurement data corresponding to each of the plurality of sampling points further comprises at least one of:

Determining a second distance between the sampling point and a preset point in the target area, and determining the measurement data as target measurement data in response to determining that the second distance meets a second distance threshold;

determining a third distance between the sampling point and a preset straight line in the target area, and determining the measurement data as target measurement data in response to determining that the third distance meets a third distance threshold;

determining a fourth distance between the sampling point and a preset plane in the target area, and determining the measurement data as target measurement data in response to determining that the fourth distance meets a fourth distance threshold; and

and determining a fifth distance between the sampling point and a preset geometric body in the target area, and determining the measurement data as target measurement data in response to determining that the fifth distance meets a fifth distance threshold.

6. The method of claim 4 or 5, wherein the measurement data further comprises: the sampling point acquires first state data at a first moment; the generating, based on the measurement data corresponding to each of the plurality of sampling points, a plurality of additional measurement data that matches the target region includes:

Receiving second configuration information of coordinate information for a plurality of additional sampling points; the coordinate information of each additional sampling point is the coordinate information corresponding to the additional sampling point at the first moment;

determining a plurality of additional sampling points in the target area according to the second configuration information;

for each additional sampling point, determining the distance between the additional sampling point and each sampling point according to the coordinate information of the additional sampling point and the first coordinate information corresponding to each sampling point;

determining first state data corresponding to the additional sampling points according to the first state data corresponding to each sampling point and the distance between the additional sampling points and each sampling point; and

and generating the additional measurement data according to the coordinate information of the additional sampling point and the first state data corresponding to the additional sampling point.

7. A training method of a state data determination model, comprising:

acquiring sample data; and

training the deep learning model by using the sample data to obtain a state data determining model;

wherein the sample data is obtained according to the method of any one of claims 1 to 6.

8. A method of state data profile generation, comprising:

acquiring second coordinate information of each of the plurality of sampling points at a second moment;

inputting a plurality of second coordinate information into a state data determining model to obtain second state data of each of the plurality of sampling points at a second moment; and

generating a state data distribution map associated with the application object according to the second state data of each of the plurality of sampling points at the second moment;

wherein the state data determination model is trained in accordance with the method of claim 7.

9. A sample data generating apparatus comprising:

the device comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is used for acquiring a configuration file for an application object and measurement data corresponding to a plurality of sampling points associated with the application object; the configuration file is used for representing a triangular mesh model aiming at the application object, and the measurement data comprises coordinates of each of the plurality of sampling points at different moments and state data of each of the plurality of sampling points at different moments when the application object is subjected to flow field numerical simulation;

the analysis module is used for analyzing the configuration file to obtain a plurality of triangular patch data;

A determining module configured to determine a target area based on the plurality of triangular patch data; the target area is used for representing the space distribution range of sample data to be generated; and

the first generation module is used for generating a plurality of sample data matched with the target area according to the measurement data and the distance screening conditions corresponding to the sampling points;

10. The apparatus of claim 9, wherein each of the triangular patch data includes coordinate information of three vertices in a triangular patch and a normal vector of the triangular patch; the determining module includes:

a receiving unit configured to receive first configuration information for a normal vector direction of the triangular patch; and

and the first determining unit is used for determining that the normal vector of the triangular patch points to the inside of the triangular mesh model according to the first configuration information, and determining the space area covered by the triangular mesh model as the target area.

11. The apparatus of claim 10, wherein the means for determining further comprises:

a second determining unit, configured to generate at least one auxiliary model in response to determining that a normal vector of the triangular patch points to the outside of the triangular mesh model according to the first configuration information; wherein the at least one auxiliary model at least comprises an auxiliary model for coating the triangular mesh model; and

and a third determining unit, configured to determine the target area according to a spatial position relationship between the at least one auxiliary model and the triangular mesh model, and a size of a spatial area covered by each of the at least one auxiliary model and the triangular mesh model.

12. The apparatus of claim 9, wherein the measurement data includes first coordinate information of a sampling point at a first time instant; the distance screening condition includes a first condition, a second condition, and a third condition, the first condition including: the position of the sampling point is positioned at one side of a space area pointed by a normal vector of a triangular patch in the triangular mesh model; the second condition includes: the projection position information is positioned in any triangular patch in the triangular mesh model; the third condition includes: the first distance meets a first distance threshold; the extraction unit includes:

a first determining subunit, configured to determine, for each measurement data, relative position information between the sampling point and the triangular mesh model according to the first coordinate information and the plurality of triangular patch data, where the plurality of triangular patch data includes coordinate information of any vertex of a triangular patch and a normal vector of the triangular patch, and the relative position information is determined based on a cross result between a vector formed by the sampling point and the vertex and the normal vector;

the projection subunit is used for projecting the first coordinate information to the triangular mesh model to obtain projection position information;

A second determining subunit, configured to determine, according to the first coordinate information and the plurality of triangular patch data, a first distance from the sampling point to the triangular mesh model; and

and a third determination subunit configured to determine the measurement data as the target measurement data in response to determining that the relative position information meets the first condition, the projection position information meets the second condition, and the first distance meets the third condition.

13. The apparatus of claim 12, wherein the extraction unit further comprises at least one of:

a fourth determining subunit, configured to determine a second distance between the sampling point and a preset point in the target area, and determine that the measurement data is target measurement data in response to determining that the second distance meets a second distance threshold;

a fifth determining subunit, configured to determine a third distance between the sampling point and a preset straight line in the target area, and determine that the measurement data is target measurement data in response to determining that the third distance meets a third distance threshold;

a sixth determining subunit, configured to determine a fourth distance between the sampling point and a preset plane in the target area, and determine that the measurement data is target measurement data in response to determining that the fourth distance meets a fourth distance threshold; and

A seventh determining subunit, configured to determine a fifth distance between the sampling point and a preset geometry in the target area, and determine that the measurement data is target measurement data in response to determining that the fifth distance meets a fifth distance threshold.

14. The apparatus of claim 12 or 13, wherein the measurement data further comprises: the sampling point acquires first state data at a first moment; the generation unit includes:

a receiving subunit configured to receive second configuration information of coordinate information for a plurality of additional sampling points; the coordinate information of each additional sampling point is the coordinate information corresponding to the additional sampling point at the first moment;

an eighth determining subunit, configured to determine a plurality of additional sampling points in the target area according to the second configuration information;

a ninth determining subunit, configured to determine, for each additional sampling point, a distance between the additional sampling point and each sampling point according to coordinate information of the additional sampling point and first coordinate information corresponding to each sampling point;

a tenth determining subunit, configured to determine, according to first state data corresponding to each sampling point and a distance between the additional sampling point and each sampling point, first state data corresponding to the additional sampling point; and

And the generation subunit is used for generating the additional measurement data according to the coordinate information of the additional sampling points and the first state data corresponding to the additional sampling points.

15. A training apparatus of a state data determination model, comprising:

the second acquisition module is used for acquiring sample data; and

the training module is used for training the deep learning model by utilizing the sample data to obtain a state data determining model;

wherein the sample data is generated by the sample data generating device according to any one of claims 9 to 14.

16. A state data profile generation apparatus comprising:

the third acquisition module is used for acquiring second coordinate information of each of the plurality of sampling points at a second moment;

the input module is used for inputting a plurality of second coordinate information into the state data determining model to obtain second state data of each of the plurality of sampling points at a second moment; and

a second generating module, configured to generate a status data distribution map associated with the application object according to second status data of each of the plurality of sampling points at a second time;

wherein the state data determination model is trained by the training apparatus of the state data determination model according to claim 15.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 8.

19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 8.