Injection mold precision improvement method and system based on product simulation data analysis

Abstract

The invention discloses a method for improving the precision of an injection mold based on product simulation data analysis, and relates to the technical field of injection molding technology, specifically comprising: obtaining three-dimensional point cloud data of an injection mold by laser scanning; performing noise filtering on the three-dimensional point cloud data by bilateral filtering with improved filter weight parameters, obtaining updated point cloud data by identifying abnormal points, and obtaining improved molded parts; performing three-dimensional modeling and injection molding product simulation based on the updated point cloud data, establishing a gate viscoelastic fluid uniform model and a runner velocity discreteness model based on an injection molding parameter set, and calculating an improved gate cross-sectional area to obtain an improved casting part; expanding the injection molding parameter set by an orthogonal design method, establishing an expanded orthogonal table with injection molding temperature, injection molding pressure and injection molding time as variable parameters to perform injection molding product simulation, and calculating an optimal injection molding parameter combination with the accumulated amount of displacement error of a punch as an experimental indicator, thereby improving the precision of the injection mold.

Description

Technical Field

[0001] The present invention relates to the technical field of injection molding technology, and in particular to a method and system for improving the precision of injection molds based on product simulation data analysis. Background Art

[0002] In recent years, China's electronic product manufacturing industry has continued to develop and upgrade, and the requirements for the manufacturing of plastic parts in electronic components have also been continuously improved. Among them, the injection mold is the core component for manufacturing plastic parts, and its conventional components include: molding parts, pouring system, guide mechanism, ejection device, lateral parting and core pulling mechanism, cooling and heating system and exhaust system. During operation, the injection mold heats the plastic particles to a flowable molten state, and then injects the molten plastic into the molding cavity of the mold through the runner and gate. After the mold filling and cooling steps, the product shape is fixed, and finally the final injection molded product is obtained after the demolding step. The biggest feature of the injection mold is that it can quickly and continuously inject the molten plastic into the mold cavity, and cool and solidify it in a short time to form the desired shape, which plays a key role in industrial production. At the same time, the injection mold directly determines the quality of the plastic parts produced. Therefore, in order to produce plastic parts with accurate dimensions and no defects, high-precision injection molds must be used.

[0003] At present, the Chinese invention patent with application number CN202210192543.2 discloses a method and system for improving the punching accuracy of injection molds. The application scheme includes obtaining first injection mold information; obtaining first processing control parameters; fitting punching parameters according to the first processing control parameters to obtain first fitting contour parameters; obtaining a first image acquisition set; performing image feature recognition on the first image acquisition set to obtain first actual contour parameters; inputting the first actual contour parameters and the first fitting contour parameters into the contour parameter correction model to obtain first correction adjustment parameters; adjusting the first processing control parameters according to the first correction adjustment parameters to obtain second processing control parameters, and processing the injection mold based on the second processing control parameters. Although the invention solves the technical problem of low control accuracy in the process of punching injection molds in the prior art, it lacks optimization for the molding parts and casting parts that most affect product quality, and multiple injection molding trial and error tests are required to adjust the parameters. Summary of the invention

[0004] The technical problem solved by the present invention is that when the traditional method is used to improve the precision of the injection mold, there is a lack of optimization of the molded parts and the cast parts, and multiple injection molding production trials and errors are required, and the parameters of the injection molding process are adjusted reciprocally. Not only is it easy to ignore minor defects in the injection mold, but it also relies on manual operation experience, resulting in increased costs and slow parameter adjustment.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A method for improving the precision of an injection mold based on product simulation data analysis comprises the following steps:

[0007] Step S1, performing laser scanning on the injection mold to obtain three-dimensional point cloud data of the injection mold;

[0008] Step S2, filtering the noise of the three-dimensional point cloud data by bilateral filtering with improved filter weight parameters, identifying abnormal points by standard deviation method, removing abnormal point clouds to obtain updated point cloud data, and obtaining improved molded parts;

[0009] Step S3, performing three-dimensional modeling based on the updated point cloud data, simulating the injection molding product through the three-dimensional modeling data to obtain an injection molding parameter set, establishing a gate viscoelastic fluid uniform model and a runner velocity dispersion model based on the injection molding parameter set, and calculating an improved gate cross-sectional area through Lagrange number multiplication to obtain an improved casting component;

[0010] Step S4, expanding the injection molding parameter set through the orthogonal design method, taking the improved molding parts and the improved casting parts as fixed parameters, and establishing an expanded orthogonal table with the injection temperature, injection pressure and injection time as variable parameters, performing product simulation based on the expanded orthogonal table, and calculating the optimal injection molding parameter combination with the accumulated amount of the punch displacement error as the experimental indicator, thereby improving the accuracy of the injection mold.

[0011] As a preferred solution of the method for improving the precision of injection molds based on product simulation data analysis described in the present invention, the light source environment is arranged, the injection mold to be improved in precision is irradiated by a ring-shaped high-uniform LED lamp, the three-dimensional laser scanner is pre-calibrated, and the three-dimensional point cloud data collection is completed by the calibrated three-dimensional laser scanner.

[0012] As a preferred solution of the method for improving the precision of injection molds based on product simulation data analysis described in the present invention, the collected point cloud data is preprocessed, a reference plane of the sampling data points is established based on the curvature of the sampling data points, a threshold judgment is performed on the neighborhood points of the sampling data points based on the reference plane, the value of the curvature weight factor is calculated based on the threshold judgment result, and the improved filtering weight parameter is calculated by the curvature weight factor, the distance weight factor and the normal vector weight factor. The three-dimensional point cloud data is denoised based on the bilateral filtering of the improved filtering weight parameter, and the noise points and outliers are removed while retaining the corner points. The calculation expression is:

[0013]

[0014] q=(k i +k max -2kmin ) / (k max -k min )

[0015] Among them, W k (p i , q) represents the curvature weight factor, q represents the curvature coefficient, p i represents the sampling data points, represents the Gaussian filter coefficient, Indicates the distance between the sampling point and the reference plane, D μ represents the average distance between the neighborhood points of the sampled data points and the curvature plane, θ T represents the threshold, k i represents the curvature of the sampled data points, k max Indicates the maximum curvature of the neighborhood point of the sampled data point, k min Indicates the minimum curvature of the neighborhood point of the sampled data point.

[0016] As a preferred solution of the method for improving the precision of injection molds based on product simulation data analysis described in the present invention, the filtered point cloud data is voxel-gridded, the filtered point cloud data is divided into continuous cubic voxels, the distance value from the point cloud in each voxel to the center position of the voxel is calculated, and abnormal point clouds are identified based on the calculated distance value, and point clouds that do not conform to Gaussian distribution are screened by the standard deviation method. The calculation expression is:

[0017]

[0018] Among them, L i is the distance from the point cloud in the voxel to the center of the voxel, n is the total number of point cloud data in the voxel, and α is the distribution correlation coefficient.

[0019] As a preferred solution of the method for improving the precision of injection molds based on product simulation data analysis described in the present invention, surface fitting is performed based on updated point cloud data and corresponding voxel grid data, and a three-dimensional model of the injection mold of the improved molded part is obtained through surface smoothing and internal missing filling.

[0020] As a preferred solution of the method for improving the precision of injection molds based on product simulation data analysis described in the present invention, the casting parts are optimized through simulation, injection simulation is performed based on the three-dimensional model of the injection mold of the improved molded parts and preset parameters to obtain an injection molding parameter set, a gate viscoelastic fluid uniform model and a runner velocity dispersion model are established based on the injection molding parameter set, and the improved gate cross-sectional radius is calculated by the Lagrange multiplier method, and the calculation expression is:

[0021]

[0022] The casting parts are optimized through simulation. The injection molding simulation is performed based on the three-dimensional model of the injection mold of the improved molding parts and the preset parameters to obtain the injection molding parameter set. The gate viscoelastic fluid uniform model and the runner velocity dispersion model are established based on the injection molding parameter set. The improved gate cross-sectional radius is calculated by the Lagrange multiplier method. The calculation expression is:

[0023]

[0024]

[0025] f(s,λ)=B r +λB e

[0026] Among them, B r represents the uniform gate viscoelastic fluid model, v t Indicates the gate speed, represents the normal vector of the gate direction, δ represents the expansion coefficient of the viscoelastic fluid, R represents the volume of the fluid passing through the gate section per unit time, s represents the gate cross-sectional area, d represents the differential, represents partial differential, Ω represents gate cross-section boundary, B e represents the flow channel velocity dispersion model, m represents the total number of selected nodes, ρ represents the flow channel velocity coefficient, v i represents the flow velocity at the selected node position, v μ represents the average flow velocity of all selected node positions, f(s, λ) represents the Lagrangian function, and λ represents the Lagrangian operator.

[0027] As a preferred solution of the method for improving the precision of injection molds based on product simulation data analysis described in the present invention, the injection molding parameter set is expanded by the orthogonal design method, an expanded orthogonal table is established with injection temperature, injection pressure and injection time as variable parameters, product simulation is performed based on each parameter combination in the expanded orthogonal table, the accumulated amount of the displacement error of the punch is used as the test indicator, and the optimal injection molding parameter combination based on the improved molding parts and the improved casting parts is calculated by the range analysis method.

[0028] The injection mold precision improvement system based on product simulation data analysis specifically includes: point cloud acquisition module, simulation module and data processing module;

[0029] The point cloud acquisition module is used to arrange the injection mold point cloud data acquisition environment, perform three-dimensional scanning of the injection mold components through a laser scanner to collect point clouds, and transmit the three-dimensional point cloud data to the data processing module;

[0030] The simulation module is used to perform product simulation, receive the three-dimensional modeling data of the injection mold transmitted by the data processing module and the preset parameters to perform simulation to obtain injection parameters, transmit the injection parameter data to the data processing module, receive the extended orthogonal table data transmitted by the data processing module to perform simulation, and transmit the product simulation data and the accumulated displacement error of the punch to the data processing module;

[0031] The data processing module is used to analyze and calculate the received data, perform bilateral filtering with improved filter weight parameters on the received three-dimensional point cloud data, perform voxel gridding and abnormal point cloud identification on the filtered point cloud data, perform three-dimensional modeling by updating the point cloud data and transmit it to the simulation module, establish a gate viscoelastic fluid uniform model and a runner velocity discreteness model to optimize the casting parts, and calculate the optimal injection molding parameter combination through the orthogonal design method.

[0032] The present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the injection mold precision improvement system based on product simulation data analysis as described above is run.

[0033] The present invention provides a storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the injection mold precision improvement system based on product simulation data analysis as described above is run.

[0034] The beneficial effects of the present invention are as follows: laser scanning is helpful for obtaining detailed geometric structure information of the injection mold, and converting the injection mold into point cloud data is helpful for subsequent analysis and processing. Before calculating the filter weight parameter, the curvature weight factor is first calculated by threshold screening, and the point cloud with a large deviation from the reference curvature plane is filtered out by taking the average distance between the neighborhood points of the sampling data points and the reference curvature plane as the reference value, which is helpful for improving the accuracy of the improved filter weight parameter and reducing the calculation complexity. Point cloud data is processed by bilateral filtering with improved filter weight parameters, which is helpful for removing noise points and outliers while retaining corner point data. Abnormal point cloud recognition based on statistical Gaussian distribution is helpful for discovering tiny structural defects in the injection mold. A uniform model of gate viscoelastic fluid and a runner velocity discreteness model are established, which fully considers the flow characteristics of the plastic melt in the injection runner and gate. Among them, the state of the plastic melt entering the molded part from the gate has the greatest impact on the quality of the injection molded product, and the calculated improved gate cross-sectional radius is helpful for improving the injection molding accuracy. The establishment of an extended orthogonal table can purposefully perform injection molding simulation based on the table, avoiding multiple injection molding experiments based on manual experience, which is conducive to obtaining accurate injection molding parameter combinations and saving costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A basic flow chart of a method for improving the precision of an injection mold based on product simulation data analysis provided by one embodiment of the present invention;

[0036] Figure 2 A schematic diagram of the framework of an injection mold precision improvement system based on product simulation data analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0038] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for improving the precision of an injection mold based on product simulation data analysis, comprising:

[0039] Step S1, performing laser scanning on the injection mold to obtain three-dimensional point cloud data of the injection mold;

[0040] Step S2, filtering the noise of the three-dimensional point cloud data by bilateral filtering with improved filter weight parameters, identifying abnormal points by standard deviation method, removing abnormal point clouds to obtain updated point cloud data, and obtaining improved molded parts;

[0041] Step S3, performing three-dimensional modeling based on the updated point cloud data, simulating the injection molding product through the three-dimensional modeling data to obtain an injection molding parameter set, establishing a gate viscoelastic fluid uniform model and a runner velocity dispersion model based on the injection molding parameter set, and calculating an improved gate cross-sectional area through Lagrange number multiplication to obtain an improved casting component;

[0042] Step S4, expanding the injection molding parameter set through the orthogonal design method, taking the improved molding parts and the improved casting parts as fixed parameters, and establishing an expanded orthogonal table with the injection temperature, injection pressure and injection time as variable parameters, performing product simulation based on the expanded orthogonal table, and calculating the optimal injection molding parameter combination with the accumulated amount of the punch displacement error as the experimental indicator, thereby improving the accuracy of the injection mold.

[0043] In this embodiment, the light source environment is arranged, the injection mold whose precision is to be improved is illuminated by a ring-shaped high-uniform LED light, the 3D laser scanner is pre-calibrated, and the calibrated 3D laser scanner is used to collect point cloud data. Laser scanning is conducive to obtaining the geometric structure details of the injection mold, and converting the injection mold into point cloud data is conducive to subsequent analysis and processing.

[0044] In this embodiment, the collected point cloud data is preprocessed, a reference plane of the sampling data points is established based on the curvature of the sampling data points, a threshold judgment is performed on the neighborhood points of the sampling data points based on the reference plane, and the value of the curvature weight factor is calculated based on the threshold judgment result. The improved filtering weight parameter is calculated by the curvature weight factor, the distance weight factor and the normal vector weight factor. The three-dimensional point cloud data is denoised based on the bilateral filtering of the improved filtering weight parameter, and the noise points and outliers are removed while retaining the corner points. The calculation expression is:

[0045]

[0046] q=(k i +k max -2k min ) / (k max -k min )

[0047] ξ=W k (p i ,q)W d (p i )W s (n i ) / S(p i )

[0048] p i ′=p i +ξn i

[0049] Among them, W k (p i , q) represents the curvature weight factor, q represents the curvature coefficient, p i represents the position vector of the sampling data point, represents the Gaussian filter coefficient, Indicates the distance between the sampling point and the reference plane, D μ represents the average distance between the neighborhood points of the sampled data points and the curvature plane, θ T represents the threshold, k i represents the curvature of the sampled data points, k max Indicates the maximum curvature of the neighborhood point of the sampled data point, k min Indicates the minimum curvature of the neighborhood point of the sampled data point, p i ′ represents the updated position vector of the sampling data point, n i represents the normal vector of the sampled data point, ξ represents the improved filter weight parameter, W d (p i ) represents the distance weight factor, W s (n i ) represents the normal vector weight factor, S(p i) represents the normalization function. Before calculating the filter weight parameters, the curvature weight factor is first calculated through threshold screening, and the average distance between the neighborhood points of the sampled data points and the reference curvature plane is used as the reference value to filter out the point cloud with a large deviation from the reference curvature plane, which is beneficial to improve the accuracy of the improved filter weight parameters and reduce the calculation complexity. By processing point cloud data with bilateral filtering with improved filter weight parameters, it is beneficial to remove noise points and outliers while retaining corner point data.

[0050] In this embodiment, the filtered point cloud data is voxel-gridized, the filtered point cloud data is divided into continuous cubic voxels, the distance value from the point cloud in each voxel to the center position of the voxel is calculated, and abnormal point clouds are identified based on the calculated distance values. The point clouds that do not conform to the Gaussian distribution are screened by the standard deviation method. The calculation expression is:

[0051]

[0052] Among them, L i is the distance from the point cloud in the voxel to the center of the voxel, n is the total number of point cloud data in the voxel, and α is the distribution correlation coefficient. Voxel gridding of point cloud data is helpful to improve the calculation speed and accuracy. Abnormal point cloud identification based on statistical Gaussian distribution is helpful to find tiny structural defects in injection molds.

[0053] In this embodiment, surface fitting is performed based on the updated point cloud data and the corresponding voxel grid data, and the three-dimensional model of the injection mold of the improved molded part is obtained through surface smoothing and internal missing filling.

[0054] In this embodiment, the casting component is optimized by simulation, and the injection molding simulation is performed based on the three-dimensional model of the injection mold of the improved molded component and the preset parameters to obtain an injection molding parameter set. A gate viscoelastic fluid uniform model and a runner velocity dispersion model are established based on the injection molding parameter set, and the improved gate cross-sectional radius is calculated by the Lagrange multiplier method, and its calculation expression is:

[0055]

[0056] The casting parts are optimized through simulation. The injection molding simulation is performed based on the three-dimensional model of the injection mold of the improved molding parts and the preset parameters to obtain the injection molding parameter set. The gate viscoelastic fluid uniform model and the runner velocity dispersion model are established based on the injection molding parameter set. The improved gate cross-sectional radius is calculated by the Lagrange multiplier method. The calculation expression is:

[0057]

[0058]

[0059] f(s,λ)=B r +λB e

[0060] Among them, B r represents the uniform gate viscoelastic fluid model, v t Indicates the gate speed, represents the normal vector of the gate direction, δ represents the expansion coefficient of the viscoelastic fluid, R represents the volume of the fluid passing through the gate section per unit time, s represents the gate cross-sectional area, d represents the differential, represents partial differential, Ω represents gate cross-section boundary, B e represents the flow channel velocity dispersion model, m represents the total number of selected nodes, ρ represents the flow channel velocity coefficient, v i represents the flow velocity at the selected node position, v μ represents the average velocity of all selected node positions, f(s,λ) represents the Lagrangian function, and λ represents the Lagrangian operator. The gate viscoelastic fluid uniform model and the runner velocity dispersion model are established, and the flow characteristics of the plastic melt in the injection runner and gate are fully considered. Among them, the state of the plastic melt entering the molded part from the gate has the greatest impact on the quality of the injection molded product. The calculated improved gate cross-section radius is conducive to improving the injection molding accuracy.

[0061] In this embodiment, the injection molding parameter set is expanded by the orthogonal design method, and an expanded orthogonal table is established with injection molding temperature, injection molding pressure and injection molding time as variable parameters. Product simulation is performed based on each parameter combination in the expanded orthogonal table, and the accumulated amount of displacement error of the punch is used as the test index. The optimal injection molding parameter combination based on the improved molding part and the improved casting part is calculated by the extreme difference analysis method. The establishment of an expanded orthogonal table can purposefully perform injection molding simulation according to the table, avoiding multiple injection molding experiments based on manual experience, which is conducive to obtaining accurate injection molding parameter combinations and saving costs.

[0062] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides an injection mold precision improvement system based on product simulation data analysis, specifically including: a point cloud acquisition module, a simulation module and a data processing module;

[0063] The point cloud acquisition module is used to arrange the injection mold point cloud data acquisition environment, perform three-dimensional scanning of the injection mold components through a laser scanner to collect point clouds, and transmit the three-dimensional point cloud data to the data processing module;

[0064] The simulation module is used to perform product simulation, receive the three-dimensional modeling data of the injection mold transmitted by the data processing module and the preset parameters to perform simulation to obtain injection parameters, transmit the injection parameter data to the data processing module, receive the extended orthogonal table data transmitted by the data processing module to perform simulation, and transmit the product simulation data and the accumulated displacement error of the punch to the data processing module;

[0065] The data processing module is used to analyze and calculate the received data, perform bilateral filtering with improved filter weight parameters on the received three-dimensional point cloud data, perform voxel gridding and abnormal point cloud identification on the filtered point cloud data, perform three-dimensional modeling by updating the point cloud data and transmit it to the simulation module, establish a gate viscoelastic fluid uniform model and a runner velocity discreteness model to optimize the casting parts, and calculate the optimal injection molding parameter combination through the orthogonal design method.

[0066] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for improving the precision of injection molds based on product simulation data analysis, characterized in that: include: Step S1, performing laser scanning on the injection mold to obtain three-dimensional point cloud data of the injection mold; Step S2, filtering the noise of the three-dimensional point cloud data by bilateral filtering with improved filter weight parameters, identifying abnormal points by standard deviation method, removing abnormal point clouds to obtain updated point cloud data, and obtaining improved molded parts; Step S3, performing three-dimensional modeling based on the updated point cloud data, simulating the injection molding product through the three-dimensional modeling data to obtain an injection molding parameter set, establishing a gate viscoelastic fluid uniform model and a runner velocity dispersion model based on the injection molding parameter set, and calculating an improved gate cross-sectional area through Lagrange number multiplication to obtain an improved casting component; Step S4, expanding the injection molding parameter set through the orthogonal design method, taking the improved molding parts and the improved casting parts as fixed parameters, and establishing an expanded orthogonal table with the injection temperature, injection pressure and injection time as variable parameters, performing product simulation based on the expanded orthogonal table, and calculating the optimal injection molding parameter combination with the accumulated amount of the punch displacement error as the experimental indicator, thereby improving the accuracy of the injection mold.

2. The method for improving the precision of injection molds based on product simulation data analysis according to claim 1, characterized in that: Arrange the light source environment, illuminate the injection mold whose precision needs to be improved through the ring-shaped high-uniform LED light, pre-calibrate the 3D laser scanner, and complete the 3D point cloud data collection through the calibrated 3D laser scanner.

3. The method for improving the precision of injection molds based on product simulation data analysis according to claim 1, characterized in that: The collected point cloud data is preprocessed, a reference plane of the sampling data points is established based on the curvature of the sampling data points, a threshold judgment is performed on the neighborhood points of the sampling data points based on the reference plane, and the value of the curvature weight factor is calculated based on the threshold judgment result. The improved filtering weight parameter is calculated by the curvature weight factor, the distance weight factor and the normal vector weight factor. The three-dimensional point cloud data is denoised by bilateral filtering based on the improved filtering weight parameter. The calculation expression is: q=(k i +k max -2k min ) / (k max -k min ) Among them, W k (p i , q) represents the curvature weight factor, q represents the curvature coefficient, p i represents the sampling data points, represents the Gaussian filter coefficient, D pi Indicates the distance between the sampling point and the reference plane, D μ represents the average distance between the neighborhood points of the sampled data points and the curvature plane, θ T represents the threshold, k i represents the curvature of the sampled data points, k max Indicates the maximum curvature of the neighborhood point of the sampled data point, k min Indicates the minimum curvature of the neighborhood point of the sampled data point.

4. The method for improving the precision of injection molds based on product simulation data analysis according to claim 3, characterized in that: The filtered point cloud data is meshed into voxels, and the filtered point cloud data is divided into continuous cubic voxels. The distance value from the point cloud in each voxel to the center of the voxel is calculated. The abnormal point cloud is identified based on the calculated distance value, and the point cloud that does not conform to the Gaussian distribution is screened by the standard deviation method. The calculation expression is: Among them, L i is the distance from the point cloud in the voxel to the center of the voxel, n is the total number of point cloud data in the voxel, and α is the distribution correlation coefficient.

5. The method for improving the precision of injection molds based on product simulation data analysis according to claim 1, characterized in that: Based on the updated point cloud data and the corresponding voxel grid data, surface fitting is performed, and the three-dimensional model of the injection mold for the improved molded part is obtained through surface smoothing and internal missing filling.

6. The method for improving the precision of injection molds based on product simulation data analysis according to claim 1, characterized in that: The casting parts are optimized through simulation. The injection molding simulation is performed based on the three-dimensional model of the injection mold of the improved molding parts and the preset parameters to obtain the injection molding parameter set. The gate viscoelastic fluid uniform model and the runner velocity dispersion model are established based on the injection molding parameter set. The improved gate cross-sectional radius is calculated by the Lagrange multiplier method. The calculation expression is: f(s,λ)=B r +λB e Among them, B r represents the uniform model of gate viscoelastic fluid, v t Indicates the gate speed, represents the normal vector of the gate direction, δ represents the expansion coefficient of the viscoelastic fluid, R represents the volume of the fluid passing through the gate section per unit time, s represents the gate cross-sectional area, d represents the differential, represents partial differential, Ω represents gate cross-section boundary, B e represents the flow channel velocity dispersion model, m represents the total number of selected nodes, ρ represents the flow channel velocity coefficient, v i represents the flow velocity at the selected node position, v μ represents the average flow velocity of all selected node positions, f(s,λ) represents the Lagrangian function, and λ represents the Lagrangian operator.

7. The method for improving the precision of injection molds based on product simulation data analysis according to claim 1, characterized in that: The injection molding parameter set was expanded through the orthogonal design method, and an expanded orthogonal table was established with injection temperature, injection pressure and injection time as variable parameters. Product simulation was carried out based on each parameter combination in the expanded orthogonal table. The accumulated amount of the punch displacement error was used as the experimental indicator, and the optimal injection molding parameter combination based on the improved molding parts and the improved casting parts was calculated through the range analysis method.

8. The injection mold precision improvement system based on product simulation data analysis is characterized by: include: Point cloud acquisition module, simulation module and data processing module; The point cloud acquisition module is used to arrange the injection mold point cloud data acquisition environment, perform three-dimensional scanning of the injection mold components through a laser scanner to collect point clouds, and transmit the three-dimensional point cloud data to the data processing module; The simulation module is used to perform product simulation, receive the three-dimensional modeling data of the injection mold transmitted by the data processing module and the preset parameters to perform simulation to obtain injection parameters, transmit the injection parameter data to the data processing module, receive the extended orthogonal table data transmitted by the data processing module to perform simulation, and transmit the product simulation data and the accumulated displacement error of the punch to the data processing module; The data processing module is used to analyze and calculate the received data, perform bilateral filtering with improved filter weight parameters on the received three-dimensional point cloud data, perform voxel gridding and abnormal point cloud identification on the filtered point cloud data, perform three-dimensional modeling by updating the point cloud data and transmit it to the simulation module, establish a gate viscoelastic fluid uniform model and a runner velocity discreteness model to optimize the casting parts, and calculate the optimal injection molding parameter combination through the orthogonal design method.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for improving the precision of injection molds based on product simulation data analysis as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for improving the precision of injection molds based on product simulation data analysis as described in any one of claims 1 to 7 are implemented.

Images