Design method of pouring and rising head, related device and computer storage medium

Abstract

The present application provides a design method for a pouring riser, a related device and a computer storage medium, which are applied to the field of computer-aided manufacturing technology. The method determines the design variables of the pouring riser according to the layout restriction information and the parameter information of the pouring riser, and then samples the design variables of the pouring riser for each design variable of the pouring riser to obtain a sample point set of the design variables; then, a solver is used to perform batch simulation on the sample points to obtain a response data set of the sample points; then, for the response data of each sample point, an estimated value of the response data of the sample point is generated according to the response data set of the sample point; finally, the optimal value of the sample point is determined according to the estimated value of the response data of the sample point and the sample data set; and the optimal result of the design variable is generated according to the optimal value of all sample points. The optimal result of the design variable of the pouring riser is quickly and effectively determined.

Description

Technical Field

[0001] The present application relates to the technical field of computer-aided manufacturing, and in particular to a design method for a pouring riser, a related device and a computer storage medium. Background Art

[0002] The shape, size and position of the pouring head will directly affect the casting filling process, and also determine the solidification, shrinkage compensation, casting shrinkage stress and the formation of casting defects such as shrinkage cavity and shrinkage, thus determining the final quality of the casting.

[0003] In traditional casting process design, pouring and riser design usually adopts semi-empirical formula modulus method, repeated experiments or optimization methods based on experimental or software simulation data to achieve design iteration. First, casting process simulation generally uses fluid mechanics solver, with a large number of grids and nodes, and a large number of solution time steps. Whether through simulation or experiment, the labor and time or cost of obtaining data are relatively high; second, the simulation accuracy and optimization iteration degree of modulus method are not enough. Summary of the invention

[0004] In view of this, the present application provides a design method for a pouring head, a related device and a computer storage medium, so as to achieve the optimal result of quickly and effectively determining the design variables of the pouring head.

[0005] The first aspect of the present application provides a method for designing a pouring riser, comprising:

[0006] Obtain parameter information and layout restriction information of pouring and riser;

[0007] Determine the design variables of the pouring and riser according to the layout restriction information and the parameter information of the pouring and riser;

[0008] For each design variable of the pouring and riser, sampling is performed on the design variable of the pouring and riser to obtain a sample point set of the design variable; wherein the sample point set includes at least one sample point;

[0009] The solver is used to perform batch simulation on the sample points to obtain a response data set of the sample points;

[0010] For each of the response data of the sample point, generating an estimated value of the response data of the sample point according to the response data set of the sample point;

[0011] Determining the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set; wherein the sample data set includes the corresponding relationship between the sample point and the response target value;

[0012] Generate optimal results for design variables based on the optimal values ​​of all sample points.

[0013] Optionally, if the response data is field quantity data, the response data for each sample point generates an estimated value of the response data of the sample point according to the response data set of the sample point, including:

[0014] The response data in the regional grid are synthesized into a snapshot matrix;

[0015] Reduce the snapshot matrix to obtain the modal space;

[0016] The coefficients of the modal space are modified according to the design variables to obtain the modified coefficients of the modal space;

[0017] An estimate of the response data for the sample point is determined based on the modal space, the modified coefficients of the modal space, and the average value of the response data.

[0018] Optionally, before synthesizing the response data in the regional grid into a snapshot matrix, the method further includes:

[0019] The grid is discretized and spatially linearly interpolated according to the required granularity to obtain the interpolated regional grid.

[0020] Optionally, determining the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set includes:

[0021] The optimization improvement expectation is determined based on the estimated value of the response data of the sample point, the minimum response target value in the sample data set, the standard normal density function, the distribution function and the standard deviation of the sample point; wherein the optimal value of the sample point is the optimal solution when the optimization improvement expectation is maximized.

[0022] A second aspect of the present application provides a design device for a pouring riser, comprising:

[0023] An acquisition unit, used for acquiring parameter information and layout restriction information of the pouring and riser;

[0024] A first determining unit is used to determine the design variables of the pouring and riser according to the arrangement restriction information and the parameter information of the pouring and riser;

[0025] A sampling unit, for sampling the design variables of the pouring and riser for each design variable of the pouring and riser, to obtain a sample point set of the design variables; wherein the sample point set includes at least one sample point;

[0026] A simulation unit, used for performing batch simulation on sample points using a solver to obtain a response data set of the sample points;

[0027] A first generating unit, configured to generate, for each sample point, a response data set of the sample point, an estimated value of the response data of the sample point;

[0028] A design unit, configured to determine an optimal value of a sample point according to an estimated value of the response data of the sample point and a sample data set; wherein the sample data set includes a correspondence between the sample point and the response target value;

[0029] The second generating unit is used to generate the optimal result of the design variable according to the optimal value of all sample points.

[0030] Optionally, if the response data is field quantity data, the first generating unit includes:

[0031] A snapshot matrix generating unit, used for synthesizing the response data in the regional grid into a snapshot matrix;

[0032] The order reduction unit is used to reduce the order of the snapshot matrix to obtain the modal space;

[0033] A correction unit, used for correcting the coefficients of the modal space according to the design variables to obtain the corrected coefficients of the modal space;

[0034] The estimated value determination unit is used to determine the estimated value of the response data of the sample point according to the modal space, the modified coefficient of the modal space and the average value of the response data.

[0035] Optionally, the design device of the pouring and riser also includes:

[0036] The preprocessing unit is used to discretize and spatially linearly interpolate the grid according to the required granularity to obtain the interpolated regional grid.

[0037] Optionally, the design unit includes:

[0038] The second determination unit is used to determine the optimization improvement expectation based on the estimated value of the response data of the sample point, the minimum response target value in the sample data set, the standard normal density function, the distribution function and the standard deviation of the sample point; wherein the optimal value of the sample point is the optimal solution when the optimization improvement expectation is maximized.

[0039] A third aspect of the present application provides an electronic device, including:

[0040] one or more processors;

[0041] a storage device having one or more programs stored thereon;

[0042] When the one or more programs are executed by the one or more processors, the one or more processors implement the pouring head design method as described in any one of the first aspects.

[0043] A fourth aspect of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for designing a pouring head as described in any one of the first aspects is implemented.

[0044] As can be seen from the above scheme, the present application provides a design method, related device and computer storage medium for a pouring riser. After determining the design variables of the pouring riser according to the layout restriction information and the parameter information of the pouring riser, the design variables of the pouring riser are sampled for each design variable of the pouring riser to obtain a sample point set of the design variables; then, the sample points are batch simulated using a solver to obtain a response data set of the sample points; then, for the response data of each sample point, an estimated value of the response data of the sample point is generated according to the response data set of the sample point; finally, the optimal value of the sample point is determined according to the estimated value of the response data of the sample point and the sample data set; wherein the sample data set includes the corresponding relationship between the sample point and the target value; and the optimal result of the design variable is generated according to the optimal value of all sample points. The optimal result of the design variables of the pouring riser is quickly and effectively determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0046] Figure 1 A specific flow chart of a method for designing a pouring riser provided in an embodiment of the present application;

[0047] Figure 2 A flowchart of a method for generating estimated values ​​of response data of a sample point provided by another embodiment of the present application;

[0048] Figure 3 A schematic diagram of a single hidden layer neural network provided in another embodiment of the present application;

[0049] Figure 4 A schematic diagram of a design device for a pouring riser provided in another embodiment of the present application;

[0050] Figure 5 A schematic diagram of an electronic device for implementing a method for designing a pouring riser is provided in accordance with another embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0053] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0054] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0055] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0056] The present application embodiment provides a method for designing a pouring riser, such as Figure 1 As shown, the specific steps include:

[0057] S101. Obtain parameter information and layout restriction information of pouring and riser.

[0058] The parameter information of the pouring head includes but is not limited to the size, shape, position, etc. of the pouring head, which is not limited here. The layout restriction information includes but is not limited to the layout restriction of the pouring head position and the space layout restriction of the runner, which is not limited here.

[0059] In the specific implementation process of the present application, the size, shape and position of the pouring head are first discretized to obtain the parameter information of the pouring head.

[0060] The position of the pouring and riser is expressed by the relative position dimension parameters of the casting parting surface; the riser and sprue are expressed by parameters such as length, angle, and diameter; for the curved runner, the Bezier curve is used to parameterize the projection of the curved intersection on the parting surface (two-dimensional model), and it can also be described by B-spline curve or NURBS curve. The Bezier curve is defined by a set of control points, and the curve is expressed by a parameterized polynomial, where the number of control points for each Bezier curve is selected as n, 2≤n≤4.

[0061] Bezier curve of degree n ,in, is the Bernstein basis function, n is the number of control points, P i is the i-th control point, t is a parameter whose value is between [0, 1].

[0062] S102: Determine design variables of the pouring and riser according to the layout restriction information and the parameter information of the pouring and riser.

[0063] Continuing with the above example, according to the location layout restrictions of the pouring and riser and the spatial layout restrictions of the runner, the reasonable value range of the parameter information of the pouring and riser is determined. The r design variables (input parameters) include: the relative spatial position and size of the pouring and riser, and the coordinates of the n control points of the curved runner.

[0064] In the specific implementation process of the present application, on the basis of the above parameters, process parameters such as alloy pouring temperature and mold shell temperature may also be added, which are not limited here.

[0065] S103 . For each design variable of the pouring and riser, sample the design variable of the pouring and riser to obtain a sample point set of the design variable.

[0066] The sample point set includes at least one sample point.

[0067] In the specific implementation process of the present application, the sampling method can be but is not limited to Latin hypercube, orthogonal test, sobol sampling method, etc. to sample the input parameters to obtain N sample points, which is not limited here.

[0068] S104, using a solver to perform batch simulation on the sample points to obtain a response data set of the sample points.

[0069] First of all, it should be noted that the CAD model input before simulation in this application is divided into two parts, the casting body and the pouring and rising system. The casting body remains unchanged, and the pouring and rising system is modeled by geometric parameterization as a whole. The two parts are merged through Boolean operations. After the CAD model is input, the regional grid is drawn, and CAE simulation is performed based on the regional grid.

[0070] In the specific implementation process of the present application, the solver may be, but is not limited to, a lattice Boltzmann solver, etc., which is not limited here.

[0071] Specifically, a solver is used to perform batch simulation of high-precision filling and solidification of the casting process based on the sampling points of the design variables to obtain N sets of response data. The response data may include but are not limited to temperature field, shrinkage and porosity information, solidification time and other types of results, which are not limited here.

[0072] It can be understood that the response data can be field quantity data or scalar quantity data, which is not limited here.

[0073] In the specific implementation process of this application, the simulation data can also be processed and DOE (Design of Experiments) analyzed to analyze the sensitivity of parameters. It is understandable that when a parameter is more sensitive, it is necessary to increase the sampling, which is not limited here.

[0074] S105 . For the response data of each sample point, generate an estimated value of the response data of the sample point according to the response data set of the sample point.

[0075] Optionally, in another embodiment of the present application, if the response data is field quantity data, for multiple response targets, proxy models are established respectively, and the field quantity data can be used to establish a fast simulation model using, but not limited to, intrinsic orthogonal decomposition, such as Figure 2 As shown, an implementation of step S105 includes:

[0076] S201, synthesizing the response data in the regional grid into a snapshot matrix.

[0077] For example: N groups (the number of sampling points is N) of temperature field and other field data of the casting body area grid Combine into one The design matrix (snapshot matrix) of order is p, where p is the number of node degrees of freedom, x is the sampling point vector, For a snapshot.

[0078] Snapshot matrix S: ;

[0079] Optionally, in another embodiment of the present application, before synthesizing the response data in the regional grid into a snapshot matrix, the method further includes:

[0080] The grid is discretized and spatially linearly interpolated according to the required granularity to obtain the interpolated regional grid.

[0081] The granularity of the requirements is set and input in advance by the user and is not limited here.

[0082] S202, reducing the order of the snapshot matrix to obtain a modal space.

[0083] Continuing with the above example, the design matrix is ​​reduced in order using, but not limited to, the intrinsic orthogonal decomposition method to map the high-dimensional field data into a low-dimensional linear modal space. , which is not limited here. The order M of the modal space is selected according to the tolerance of 0.99 and the minimum value of m, and m can be determined according to the efficiency required by the user.

[0084] Then we have: ;

[0085] in, Field quantity results The estimated value of express The mean of N snapshots, The eigenvector representing the i-th mode of the eigendecomposition is called the i-th POD basis. represents the coefficient of the i-th mode.

[0086] S203. Correct the coefficients of the modal space according to the design variables to obtain corrected coefficients of the modal space.

[0087] Continuing with the above example, since the proper orthogonal decomposition (POD) reflects a linear mapping, considering the nonlinearity of the entire casting process, a method based on a neural network or a Gaussian random process (Kriging proxy model) can be used to predict and correct the coefficients of the above modal space for nonlinear correction, which is not limited here.

[0088] Taking the back propagation neural network solution as an example, the back propagation neural network (BPNN) has strong nonlinear mapping ability and high self-learning and adaptive ability, mainly including input layer, hidden layer and output layer. This application can use a single hidden layer neural network, such as Figure 3 As shown, is the weight value. Among them, the input layer is the design variable, and the output layer is the coefficient of the above modal space , the Loss function is the MRE deviation value of the response data:

[0089] ;

[0090] in, Field quantity results The estimated value of .

[0091] In the specific implementation process of this application, the specific training steps of BPNN can be as follows:

[0092] 1) Initialize the weights, which are usually given randomly by setting the weight range.

[0093] 2) Calculate the output values ​​of the hidden layer and the output layer.

[0094] 3) Calculate the reverse error of each layer.

[0095] 4) Determine whether the training requirements are met. If so, the model training is completed and the model is output; if not, update the weights and repeat steps 2) to 3).

[0096] Finally, the corrected coefficients of the modal space are updated according to the results of BPNN .

[0097] S204: Determine an estimated value of the response data of the sample point according to the modal space, the corrected coefficient of the modal space and the average value of the response data.

[0098] Specifically, the estimated value of the response data of the sample point can be calculated according to the following formula:

[0099] ;

[0100] In the specific implementation process of this application, the shrinkage porosity or solidification time results are also fitted using a neural network or a Gaussian random process, which is not limited here, that is, the input is each discrete design variable, and the output is the shrinkage porosity or solidification time results.

[0101] Optionally, in another embodiment of the present application, if the response data is scalar data, the Kriging model can be directly used for prediction, which is not limited here.

[0102] S106 . Determine the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set.

[0103] The sample data set includes the corresponding relationship between sample points and response target values.

[0104] Continuing from the above example, sample point , assuming that the corresponding response target value is The sample data set (X, Y) is constructed based on all sample points and the corresponding response target values.

[0105] S107. Generate optimal results of design variables according to the optimal values ​​of all sample points.

[0106] Optionally, in another embodiment of the present application, an implementation of step S106 specifically includes:

[0107] The optimization improvement expectation is determined based on the estimated value of the response data of the sample point, the minimum target value in the sample data set, the standard normal density function, the distribution function, and the standard deviation of the sample point.

[0108] Among them, the optimal value of the sample point is the optimal solution under the condition of maximizing the optimization improvement expectation.

[0109] Assume that the smallest target value in the current sample data set is known to be , then for the sample point , whose estimated value is ,and , then the expectation of objective function improvement can be expressed as follows:

[0110] ;

[0111] in, and are the standard normal density function and distribution function, respectively. and Respectively represent the Kriging estimate and standard deviation at the sample point, express By maximizing To search for the next approximate optimal solution. The EI function can be optimized by using, but not limited to, optimization algorithms (such as genetic algorithms or local optimization methods), which are not limited here.

[0112] In the specific implementation process of this application, a Kriging model can be constructed based on the initial sample set (X, Y) to obtain the predicted mean and predicted variance; then, the EI criterion is calculated based on the predicted mean and predicted variance to select new sample points. , and calculate the objective function value on the new sample point ; The new sample point ( , ) add the sample set, retrain the Kriging model, update the predicted mean and predicted variance; iterate through the EGO algorithm (Efficient Global Optimization), and the iteration termination condition (any one of the conditions can be met): the maximum number of iterations is reached, EI < prediction threshold, and the objective function value meets the accuracy requirement; if the termination condition is not met, return to execute according to the predicted mean and prediction variance, calculate the EI criterion (expected improvement criterion), and select new sample points , and calculate the objective function value on the new sample point steps until the termination condition is met.

[0113] In the specific implementation process of this application, the model can use cross-validation, which is not limited here.

[0114] Taking the K-fold cross validation method as an example, the specific steps are as follows:

[0115] (1) Randomly divide the data set into K subsets, each subset is called a fold, usually K=5 or K=10;

[0116] (2) Each time, K-1 subsets are used to train the Kriging model, and the remaining subset is used as a validation set;

[0117] (3) Repeat K times, selecting a different subset as the validation set each time;

[0118] (4) Finally, the error indicators of K validations are averaged as the overall evaluation indicator of the model;

[0119] (5) Adjust the structure and parameters of the Kriging model based on the verified evaluation results.

[0120] The accuracy evaluation used in the K-times validation is the determination coefficient: Evaluation can effectively determine the reliability of the Kriging model and provide a basis for subsequent design optimization and practical application.

[0121] in, represents the true value, represents an estimated value, Represents the mean of the true values.

[0122] The optimization model and algorithm may also use other intelligent optimization algorithms such as NAGS-II or discrete optimization algorithms to solve the Pareto frontier, which is not limited here.

[0123] It can be seen from the above scheme that the present application provides a design method for a pouring riser. After determining the design variables of the pouring riser according to the layout restriction information and the parameter information of the pouring riser, the design variables of the pouring riser are sampled for each design variable of the pouring riser to obtain a sample point set of the design variables; then, the sample points are batch simulated using a solver to obtain a response data set of the sample points; then, for the response data of each sample point, an estimated value of the response data of the sample point is generated according to the response data set of the sample point; finally, the optimal value of the sample point is determined according to the estimated value of the response data of the sample point and the sample data set; wherein the sample data set includes the correspondence between the sample point and the response target value; and the optimal result of the design variable is generated according to the optimal value of all sample points. The optimal result of the design variables of the pouring riser is quickly and effectively determined.

[0124] The present application embodiment provides a design device for a pouring riser, such as Figure 4 As shown, specifically including:

[0125] The acquisition unit 401 is used to acquire the parameter information and layout restriction information of the pouring and riser.

[0126] The first determining unit 402 is used to determine the design variables of the pouring head according to the arrangement restriction information and the parameter information of the pouring head.

[0127] The sampling unit 403 is used to sample the design variables of the pouring and riser for each design variable of the pouring and riser to obtain a sample point set of the design variables.

[0128] The sample point set includes at least one sample point.

[0129] The simulation unit 404 is used to perform batch simulation on the sample points using a solver to obtain a response data set of the sample points.

[0130] The first generating unit 405 is configured to generate an estimated value of the response data of each sample point according to the response data set of the sample point.

[0131] Optionally, in another embodiment of the present application, if the response data is field quantity data, an implementation of the first generation unit includes:

[0132] The snapshot matrix generating unit is used to synthesize the response data in the regional grid into a snapshot matrix.

[0133] The order reduction unit is used to reduce the order of the snapshot matrix to obtain the modal space.

[0134] The correction unit is used to correct the coefficients of the modal space according to the design variables to obtain the corrected coefficients of the modal space.

[0135] The estimated value determination unit is used to determine the estimated value of the response data of the sample point according to the modal space, the modified coefficient of the modal space and the average value of the response data.

[0136] For the specific working process of the units disclosed in the above embodiments of the present application, please refer to the corresponding method embodiments, such as Figure 2 As shown, no further description is given here.

[0137] The design unit 406 is used to determine the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set.

[0138] The sample data set includes the corresponding relationship between sample points and response target values.

[0139] The second generating unit 407 is used to generate the optimal result of the design variable according to the optimal values ​​of all sample points.

[0140] For the specific working process of the units disclosed in the above embodiments of the present application, please refer to the corresponding method embodiments, such as Figure 1 As shown, no further description is given here.

[0141] Optionally, in another embodiment of the present application, an implementation of the design device for the pouring and riser further includes:

[0142] The preprocessing unit is used to discretize and spatially linearly interpolate the grid according to the required granularity to obtain the interpolated regional grid.

[0143] The specific working process of the units disclosed in the above embodiments of the present application can be found in the corresponding method embodiments, which will not be repeated here.

[0144] Optionally, in another embodiment of the present application, an implementation of the design unit 406 includes:

[0145] The second determination unit is used to determine the optimization improvement expectation according to the estimated value of the response data of the sample point, the minimum response target value in the sample data set, the standard normal density function, the distribution function and the standard deviation of the sample point.

[0146] Among them, the optimal value of the sample point is the optimal solution under the condition of maximizing the optimization improvement expectation.

[0147] The specific working process of the units disclosed in the above embodiments of the present application can be found in the corresponding method embodiments, which will not be repeated here.

[0148] As can be seen from the above scheme, the present application provides a design device for a pouring head, wherein the acquisition unit 401 acquires parameter information and layout restriction information of the pouring head, and the first determination unit 402 determines the design variables of the pouring head according to the layout restriction information and the parameter information of the pouring head. Then, the sampling unit 403 samples the design variables of the pouring head for each design variable of the pouring head to obtain a sample point set of the design variables; then, the simulation unit 404 uses a solver to perform batch simulation on the sample points to obtain a response data set of the sample points; then, the first generation unit 405 generates an estimated value of the response data of the sample point according to the response data set of the sample point for the response data of each sample point; finally, the design unit 406 determines the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set; wherein the sample data set includes the corresponding relationship between the sample point and the response target value; and the second generation unit 407 generates the optimal result of the design variable according to the optimal value of all sample points. The optimal result of the design variable of the pouring head is achieved by quickly and effectively determining the optimal result of the design variable of the pouring head.

[0149] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0150] Another embodiment of the present application provides an electronic device, such as Figure 5 As shown, including:

[0151] One or more processors 501 .

[0152] The storage device 502 stores one or more programs.

[0153] When the one or more programs are executed by the one or more processors 501, the one or more processors 501 implement the pouring head design method as described in any one of the above embodiments.

[0154] Another embodiment of the present application provides a computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for designing a pouring head as described in any one of the above embodiments is implemented.

[0155] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0156] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0157] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0158] Another embodiment of the present application provides a computer program product. When the computer program product is executed, it is used to execute the above-mentioned pouring head design method.

[0159] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0160] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in this application is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing this application.

[0161] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0162] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A method for designing a pouring riser, characterized in that: include: Obtain parameter information and layout restriction information of pouring and riser; Determine the design variables of the pouring and riser according to the layout restriction information and the parameter information of the pouring and riser; For each design variable of the pouring and riser, sampling is performed on the design variable of the pouring and riser to obtain a sample point set of the design variable; wherein the sample point set includes at least one sample point; The solver is used to perform batch simulation on the sample points to obtain a response data set of the sample points; For each of the response data of the sample point, generating an estimated value of the response data of the sample point according to the response data set of the sample point; Determining the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set; wherein the sample data set includes the corresponding relationship between the sample point and the response target value; Generate optimal results for design variables based on the optimal values ​​of all sample points.

2. The method for designing a pouring and riser according to claim 1, characterized in that: If the response data is field quantity data, the response data for each sample point generates an estimated value of the response data of the sample point according to the response data set of the sample point, including: The response data in the regional grid are synthesized into a snapshot matrix; Reduce the snapshot matrix to obtain the modal space; The coefficients of the modal space are modified according to the design variables to obtain the modified coefficients of the modal space; An estimate of the response data for the sample point is determined based on the modal space, the modified coefficients of the modal space, and the average value of the response data.

3. The method for designing a pouring and riser according to claim 2, characterized in that: Before synthesizing the response data in the regional grid into a snapshot matrix, the method further includes: The grid is discretized and spatially linearly interpolated according to the required granularity to obtain the interpolated regional grid.

4. The method for designing a pouring and riser according to claim 1, characterized in that: The step of determining the optimal value of the sample point according to the estimated value of the response data of the sample point and the sample data set comprises: The optimization improvement expectation is determined based on the estimated value of the response data of the sample point, the minimum response target value in the sample data set, the standard normal density function, the distribution function and the standard deviation of the sample point; wherein the optimal value of the sample point is the optimal solution when the optimization improvement expectation is maximized.

5. A design device for a pouring and riser, characterized in that: include: An acquisition unit, used for acquiring parameter information and layout restriction information of the pouring and riser; A first determining unit is used to determine the design variables of the pouring and riser according to the arrangement restriction information and the parameter information of the pouring and riser; A sampling unit, for sampling the design variables of the pouring and riser for each design variable of the pouring and riser, to obtain a sample point set of the design variables; wherein the sample point set includes at least one sample point; A simulation unit, used for performing batch simulation on sample points using a solver to obtain a response data set of the sample points; A first generating unit, configured to generate, for each sample point, a response data set of the sample point, an estimated value of the response data of the sample point; A design unit, configured to determine an optimal value of a sample point according to an estimated value of the response data of the sample point and a sample data set; wherein the sample data set includes a correspondence between the sample point and the response target value; The second generating unit is used to generate the optimal result of the design variable according to the optimal value of all sample points.

6. The design device for pouring and rising nozzles according to claim 5, characterized in that: If the response data is field quantity data, the first generating unit includes: A snapshot matrix generating unit, used for synthesizing the response data in the regional grid into a snapshot matrix; The order reduction unit is used to reduce the order of the snapshot matrix to obtain the modal space; A correction unit, used for correcting the coefficients of the modal space according to the design variables to obtain the corrected coefficients of the modal space; The estimated value determination unit is used to determine the estimated value of the response data of the sample point according to the modal space, the modified coefficient of the modal space and the average value of the response data.

7. The pouring head design device according to claim 6, characterized in that: Also includes: The preprocessing unit is used to discretize and spatially linearly interpolate the grid according to the required granularity to obtain the interpolated regional grid.

8. The design device for pouring and rising nozzles according to claim 5, characterized in that: The design unit comprises: The second determination unit is used to determine the optimization improvement expectation based on the estimated value of the response data of the sample point, the minimum response target value in the sample data set, the standard normal density function, the distribution function and the standard deviation of the sample point; wherein the optimal value of the sample point is the optimal solution when the optimization improvement expectation is maximized.

9. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the pouring head design method according to any one of claims 1 to 4.

10. A computer storage medium, characterized in that: A computer program is stored thereon, wherein when the computer program is executed by a processor, the method for designing a pouring head as claimed in any one of claims 1 to 4 is implemented.

Images