Injection mold deformation quantity model construction and analysis method and device and terminal equipment

The image data of the injection mold is analyzed through the fuzzy clustering model and the JACAD distance measurement method, a real-time three-dimensional model is constructed, and the evaluation index of forming deformation is set, which solves the problem of difficult detection of injection mold deformation and improves the accuracy and abnormality of deformation judgment. Identification ability avoids economic losses.

CN118941546AActive Publication Date: 2024-11-12SHENZHEN JINGSHENG MOULD CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411095526.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-12
Estimated Expiration
2044-08-28

AI Technical Summary

Technical Problem

Injection molds will deform during use, resulting in defective products, and minor deformations are difficult to observe through the naked eye, resulting in economic losses.

Method used

By obtaining image data of the injection mold, using the fuzzy clustering model and the Jaccard distance measurement method for analysis, a real-time three-dimensional model is constructed, the molding deformation evaluation index is set, the mold deformation situation is analyzed, and the corresponding suggestions are generated.

Benefits of technology

It improves the accuracy of the deformation judgment of injection molds, enhances the abnormal recognition ability, and avoids economic losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941546A_ABST
    Figure CN118941546A_ABST
Patent Text Reader

Abstract

The invention relates to an injection mold deformation quantity model construction and analysis method, an injection mold deformation quantity model construction and analysis device and terminal equipment, and belongs to the technical field of injection mold model analysis. And the real-time three-dimensional model diagram of the injection mold is analyzed based on the injection molding deformation quantity evaluation indexes, an analysis result is obtained, finally, a related report is generated according to the analysis result, and related injection molding suggestions are displayed according to a preset mode. According to the method, the image data of the injection mold is analyzed, the pixel points are clustered and segmented through the fuzzy clustering algorithm, and the segmentation of the image data is optimized by integrating the Jaccard distance measurement algorithm, so that the image data with a better segmentation effect can be extracted; therefore, a more accurate real-time three-dimensional model of the injection mold is established, the deformation quantity of the injection mold is judged more accurately, the recognition precision of the abnormal injection mold is higher, and economic losses are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of injection molding model analysis, and in particular to a method, device and terminal equipment for constructing and analyzing a deformation variable model of an injection mold. Background Art

[0002] Injection mold is a tool for producing plastic products; it is also a tool that gives plastic products a complete structure and precise dimensions. Injection molding is a processing method used in the mass production of certain parts with complex shapes. Specifically, it refers to the high-pressure injection of heated and melted plastic into the mold cavity by the injection molding machine, and the molded product is obtained after cooling and solidification. The structure of the mold may vary depending on the type and performance of the plastic, the shape and structure of the plastic product, and the type of injection molding machine. The injection mold is mainly composed of a movable mold and a fixed mold. The movable mold is installed on the movable template of the injection molding machine, and the fixed mold is installed on the fixed template of the injection molding machine. However, after a certain number of years or times of use, the injection mold will produce a certain amount of deformation. For some high-demand injection molded parts, the subtle deformation amount cannot be observed by the naked eye. If the corresponding defects cannot be discovered in time, a large number of defective products will be produced, which will eventually cause certain economic losses. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a method, device and terminal device for constructing and analyzing a deformation variable model of an injection mold. To achieve the above purpose, the technical solution adopted by the present invention is: The first aspect of the present invention provides a method for constructing and analyzing a deformation variable model of an injection mold, comprising the following steps: Acquire image data information of the injection mold in various directions, and analyze the image data information of the injection mold in various directions by using a fuzzy clustering model and a Jaccard distance measurement method to acquire clustered image feature data; Acquire injection mold target features based on the clustered image feature data, and construct a real-time three-dimensional model diagram of the injection mold based on the injection mold target features; Acquire drawing data of the part to be injected, and set an injection molding deformation variable evaluation index based on the drawing data of the injection mold, analyze the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation variable evaluation index, and obtain an analysis result; A relevant report is generated according to the analysis result, and the relevant injection molding suggestions are displayed in a preset manner.

[0004] Furthermore, in this method, image data information of the injection mold in various directions is obtained, and the image data information of the injection mold in various directions is analyzed by a fuzzy clustering model and a Jaccard distance measurement method to obtain clustered image feature data, specifically: Acquire image data information of the injection mold in various directions, and obtain pre-processed image data by filtering and denoising the image data information of the injection mold in various directions, and introduce a fuzzy clustering algorithm; Initializing cluster centers based on the fuzzy clustering algorithm, and initializing clustering for each pixel in the preprocessed image data according to the cluster centers, obtaining pixel point sets after a number of clustering, and introducing the Jaccard distance measurement method; The Jaccard coefficient between each clustered pixel point set is calculated by the Jaccard distance measurement method, and the Jaccard distance between the clustered pixel point sets is calculated based on the Jaccard coefficient, and a Jaccard distance threshold is preset; When the Jaccard distance between the pixel point sets after clustering is not greater than the Carder distance threshold, the cluster center is adjusted, and the pixel point sets after clustering are re-clustered until the Jaccard distance between the pixel point sets after clustering is no longer less than the Carder distance threshold, the pixel point sets after clustering are output, and segmentation is performed according to the pixel point sets after clustering to obtain the image feature data after clustering.

[0005] Furthermore, in the present method, the target features of the injection mold are obtained based on the clustered image feature data, and a real-time three-dimensional model diagram of the injection mold is constructed based on the target features of the injection mold, which specifically includes: Acquire image feature data of the injection mold after clustering in various directions, and acquire contour features of the injection mold in various directions by performing feature extraction on the image feature data of the injection mold after clustering in various directions; Using the contour features of the injection mold in various directions as injection mold target features, acquiring the positions of the injection mold target features, and splicing the injection mold target features based on the positions of the injection mold target features; By splicing, several model images are obtained, and by performing secondary splicing on the model images in each three-dimensional direction, a real-time three-dimensional model image of the injection mold is constructed, and the real-time three-dimensional model image of the injection mold is output.

[0006] Furthermore, in this method, the drawing data of the part to be injected is obtained, and the injection molding deformation evaluation index is set based on the drawing data of the injection mold, specifically: Acquire drawing data of the part to be injected, and acquire upper limits of data deviations of each region of the part to be injected and lower limits of data deviations of each region of the part to be injected according to the drawing data of the part to be injected, and construct a first evaluation index based on the upper limits of data deviations of each region of the part to be injected; A second evaluation index is constructed based on the lower limit of the data deviation of each region of the injection molded part, an injection molding deformation variable evaluation index is set based on the first evaluation index and the second evaluation index, and the injection molding deformation variable evaluation index is output.

[0007] Furthermore, in the present method, the real-time three-dimensional model diagram of the injection mold is analyzed based on the injection molding deformation evaluation index to obtain the analysis result, which specifically includes: Obtaining model parameters of each position of the real-time three-dimensional model diagram of the injection mold, and determining whether the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation evaluation index; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation variable evaluation index, an analysis result of a normal injection mold deformation variable is generated and used as a first analysis result, and the first analysis result is output; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are not within the corresponding injection molding deformation variable evaluation index, an analysis result of the injection mold deformation variable abnormality is generated and output as a second analysis result.

[0008] Furthermore, in this method, a relevant report is generated according to the analysis results, and the relevant injection molding suggestions are displayed in a preset manner, specifically: When the analysis result is the second analysis result, a relevant scrapping report is generated, and the relevant scrapping report is displayed in a preset manner; When the analysis result is the second analysis result, a related normal report is generated, and the related normal report is displayed in a preset manner.

[0009] A second aspect of the present invention provides an injection mold deformation variable model construction and analysis device, the device includes a memory and a processor, the memory includes an injection mold deformation variable model construction and analysis method program, when the injection mold deformation variable model construction and analysis method program is executed by the processor, the steps of any one of the injection mold deformation variable model construction and analysis methods are implemented.

[0010] A third aspect of the present invention provides a terminal device, including: An image processing module, which obtains image data information of the injection mold in various directions, and analyzes the image data information of the injection mold in various directions by using a fuzzy clustering model and a Jaccard distance measurement method to obtain clustered image feature data; A model building module, which acquires target features of the injection mold based on the clustered image feature data, and constructs a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold; A deformation variable analysis module, which obtains drawing data of the part to be injected, sets an injection molding deformation variable evaluation index based on the drawing data of the injection mold, and analyzes the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation variable evaluation index to obtain an analysis result; The report generation module generates a relevant report according to the analysis result and displays the relevant injection molding suggestions in a preset manner.

[0011] The present invention solves the defects existing in the background technology and has the following beneficial effects: The present invention obtains image data information of the injection mold in various directions, analyzes the image data information of the injection mold in various directions through a fuzzy clustering model and a Jaccard distance measurement method, obtains clustered image feature data, and then obtains the target feature of the injection mold based on the clustered image feature data, and constructs a real-time three-dimensional model diagram of the injection mold based on the target feature of the injection mold, thereby obtaining the drawing data of the part to be injected, and setting the injection molding deformation evaluation index based on the drawing data of the injection mold, analyzing the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation evaluation index, obtaining the analysis result, and finally generating a relevant report according to the analysis result, and displaying the relevant injection molding suggestions in a preset manner. The present invention analyzes the image data of the injection mold, clusters and segments the pixels through a fuzzy clustering algorithm, and integrates the Jaccard distance measurement algorithm to optimize the segmentation of the image data, so as to extract image data with better segmentation effect, thereby establishing a more accurate real-time three-dimensional model of the injection mold, making the deformation judgment of the injection mold more accurate, and thus having a higher recognition accuracy for abnormal injection molds, thereby avoiding economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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 some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0013] Figure 1 The overall flow chart of the injection mold deformation variable model construction and analysis method is shown; Figure 2 A schematic flow chart of the injection mold deformation variable model construction and analysis method is shown; Figure 3A device block diagram of a device for constructing and analyzing a deformation model of an injection mold is shown; Figure 4 A schematic diagram of a terminal device is shown. DETAILED DESCRIPTION

[0014] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0015] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0016] like Figure 1 As shown, the first aspect of the present invention provides a method for constructing and analyzing a deformation variable model of an injection mold, comprising the following steps: S102: Obtain image data information of the injection mold in various directions, and analyze the image data information of the injection mold in various directions by using a fuzzy clustering model and a Jaccard distance measurement method to obtain clustered image feature data; S104: acquiring target features of the injection mold based on the clustered image feature data, and constructing a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold; S106: obtaining drawing data of the part to be injected, and setting an injection molding deformation variable evaluation index based on the drawing data of the injection mold, analyzing the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation variable evaluation index, and obtaining an analysis result; S108: Generate a relevant report based on the analysis results, and display the relevant injection molding suggestions in a preset manner.

[0017] It is worth mentioning that the present invention analyzes the image data of the injection mold, clusters and segments the pixels through the fuzzy clustering algorithm, and integrates the Jaccard distance metric algorithm to optimize the segmentation of the image data, so as to extract image data with better segmentation effect, thereby establishing a more accurate real-time three-dimensional model of the injection mold, making the deformation judgment of the injection mold more accurate, and thus having higher recognition accuracy for abnormal injection molds, thus avoiding economic losses. For example, the image data of the injection mold can be obtained through instruments such as infrared cameras, cameras, and infrared thermal imagers.

[0018] like Figure 2 As shown, further, in step 102 of the method, specifically: S202: Obtain image data information of the injection mold in various directions, and obtain pre-processed image data by filtering and denoising the image data information of the injection mold in various directions, and introduce a fuzzy clustering algorithm; S204: Initializing cluster centers based on the fuzzy clustering algorithm, and initializing clustering for each pixel in the preprocessed image data according to the cluster centers, obtaining a pixel point set after a number of clustering, and introducing the Jaccard distance measurement method; S206: Calculate the Jaccard coefficient between each clustered pixel point set by using the Jaccard distance measurement method, calculate the Jaccard distance between the clustered pixel point sets based on the Jaccard coefficient, and preset the Jaccard distance threshold; S208: When the Jaccard distance between the pixel point sets after clustering is not greater than the Carder distance threshold, the cluster centers (the number and position of the cluster centers, etc.) are adjusted, and the pixel point sets after clustering are re-clustered until the Jaccard distance between the pixel point sets after clustering is no longer less than the Carder distance threshold, the pixel point sets after clustering are output, and segmented according to the pixel point sets after clustering to obtain the image feature data after clustering.

[0019] It is worth mentioning that in this method, the collected image data is segmented by a fuzzy clustering algorithm. During the segmentation process, when the number of cluster centers is not suitable, a local optimal solution phenomenon is likely to occur, which will result in the presence of data that is not a cluster of this type in the classified data set. At this time, the Jaccard distance between the pixel point sets after clustering is calculated by the Jaccard distance measurement method. When the Jaccard distance is smaller, it means that there is no similar data. When the Jaccard distance is larger, it means that there is similar data in the data set, and a local optimal solution phenomenon occurs. This method can optimize the segmentation of the collected images and improve the segmentation accuracy of the images, which is conducive to making the subsequent model more accurate.

[0020] Furthermore, in step S104 of the method, it specifically includes: Acquire image feature data of the injection mold after clustering in various directions, and obtain contour features of the injection mold in various directions by performing feature extraction on the image feature data of the injection mold after clustering in various directions; The contour features of the injection mold in various directions are used as target features of the injection mold, and the positions of the target features of the injection mold are obtained, and the target features of the injection mold are spliced ​​based on the positions of the target features of the injection mold; By splicing, several model images are obtained, and by performing secondary splicing on the model images in each three-dimensional direction, a real-time three-dimensional model image of the injection mold is constructed, and the real-time three-dimensional model image of the injection mold is output.

[0021] It is worth mentioning that the feature contour is extracted from the image feature data after clustering in various directions of the injection mold, and then the target features of the injection mold are spliced ​​through 3D modeling software (such as SolidWorks, UG third-dimensional modeling software) to form a real-time 3D model diagram of the injection mold.

[0022] Furthermore, in this method, the drawing data of the part to be injected is obtained, and the injection molding deformation evaluation index is set based on the drawing data of the injection mold, specifically: Obtain drawing data of the part to be injected, and obtain upper limits of data deviations of each region of the part to be injected and lower limits of data deviations of each region of the part to be injected according to the drawing data of the part to be injected, and construct a first evaluation index based on the upper limits of data deviations of each region of the part to be injected; A second evaluation index is constructed based on the lower limit of the data deviation of each region of the injection molded part, an injection molding deformation variable evaluation index is set based on the first evaluation index and the second evaluation index, and the injection molding deformation variable evaluation index is output.

[0023] It is worth mentioning that the deformation of the injection mold will cause the injection molded parts to change. Since the injection molded parts have certain standards, such as contour accuracy, surface finish, etc., there will be an upper limit and a lower limit of the data deviation to form a range that meets specific requirements, thereby forming an injection molding deformation variable evaluation index.

[0024] Furthermore, in this method, the real-time three-dimensional model diagram of the injection mold is analyzed based on the injection molding deformation evaluation index to obtain the analysis results, which specifically include: Obtaining model parameters of each position of the real-time three-dimensional model diagram of the injection mold, and determining whether the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation variable evaluation index; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation variable evaluation index, a normal analysis result of the injection mold deformation variable is generated and used as a first analysis result, and the first analysis result is output; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are not within the corresponding injection molding deformation variable evaluation index, an analysis result of the injection mold deformation variable abnormality is generated and output as a second analysis result.

[0025] Furthermore, in this method, a relevant report is generated according to the analysis results, and the relevant injection molding suggestions are displayed in a preset manner, specifically: When the analysis result is the second analysis result, a relevant scrap report is generated, and the relevant scrap report is displayed in a preset manner; When the analysis result is the second analysis result, a related normal report is generated, and the related normal report is displayed in a preset manner.

[0026] In addition, the method may further include: The historical deformation variable change characteristic data of the injection mold under each working environment is obtained through big data, and a Markov chain is introduced to input the historical deformation variable change characteristic data of the injection mold under each working environment into the Markov chain; Taking the deformation variable features as state values, constructing a state matrix, and calculating the state value transition probability value of each state value in the state matrix transferring to the next level, constructing a transition probability value matrix, and constructing a deformation variable prediction model based on a deep neural network; Inputting the transfer probability value matrix into the deformation variable prediction model for training, obtaining the trained deformation variable prediction model, and obtaining the working environment characteristics of the injection mold and the deformation variable characteristics of the current timestamp, and inputting the working environment characteristics of the injection mold and the deformation variable characteristics of the current timestamp into the trained deformation variable prediction model for prediction; Through prediction, the transfer probability value of the shape variable feature of the current timestamp to the shape variable feature of the next level is obtained. When the transfer probability value is greater than the preset transfer probability value, the shape variable feature of the next level is used as the shape variable feature of the current timestamp, and an early warning is issued based on the shape variable feature of the current timestamp.

[0027] It should be noted that different working environments will cause different deformation variables of the injection mold during operation. For example, the higher the temperature, the greater the deformation due to thermal expansion and contraction of the material. The Markov chain can use the deformation variable feature as the state value to predict the transfer probability value of the deformation variable feature of the current timestamp to the deformation variable feature of the next level. For example, the deformation variable of a certain position of the injection mold at a certain moment is 0.1mm, and the transfer probability value of the next level 0.2mm is 95%, which means that the deformation variable is already 0.2mm. This method can predict the deformation variable feature of the current timestamp, issue a warning in time, and recover losses in time.

[0028] In addition, issuing an early warning according to the deformation characteristics of the current timestamp includes the following steps: Acquire processing order information of each injection molding machine during the processing process, and acquire characteristic data of the maximum deformation amount that the injection molding part can accept according to the processing order information of the injection molding machine during the processing process; Determine whether the deformation variable characteristic of the current timestamp is greater than the maximum deformation variable characteristic data that the injection molded part can accept, and when the deformation variable characteristic of the current timestamp is not greater than the maximum deformation variable characteristic data that the injection molded part can accept, generate a continue processing instruction; When the deformation variable characteristic of the current timestamp is greater than the maximum deformation variable characteristic data that the injection molded part can accept, the position of the corresponding injection molding machine is obtained, and an early warning is issued according to the position of the corresponding injection molding machine, and at the same time, a stop processing instruction is generated; Based on the stop processing instruction, the corresponding injection molding machine is controlled through the Internet of Things control network.

[0029] It should be noted that when the deformation variable characteristic of the current timestamp is greater than the maximum deformation variable characteristic data that the injection molded part can accept, it means that the processed part is a defective product. This method can dynamically control the operation of the injection molding machine according to the predicted deformation variable data, making the injection molding machine more reasonable during operation.

[0030] like Figure 3 As shown, the second aspect of the present invention provides an injection mold deformation variable model construction and analysis device 4, the device 4 includes a memory 41 and a processor 42, the memory 41 includes an injection mold deformation variable model construction and analysis method program, when the injection mold deformation variable model construction and analysis method program is executed by the processor, any step of the injection mold deformation variable model construction and analysis method is implemented.

[0031] like Figure 4 As shown, the third aspect of the present invention provides a terminal device, including: The image processing module 10 obtains image data information of the injection mold in various directions, and analyzes the image data information of the injection mold in various directions through a fuzzy clustering model and a Jaccard distance measurement method to obtain clustered image feature data; A model building module 20 acquires target features of the injection mold based on the clustered image feature data, and constructs a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold; The deformation analysis module 30 obtains the drawing data of the part to be injected, sets the injection molding deformation evaluation index based on the drawing data of the injection mold, analyzes the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation evaluation index, and obtains the analysis result; The report generation module 40 generates relevant reports according to the analysis results and displays relevant injection molding suggestions in a preset manner.

[0032] Furthermore, in this device, image data information of the injection mold in various directions is obtained, and the image data information of the injection mold in various directions is analyzed by the fuzzy clustering model and the Jaccard distance measurement method to obtain clustered image feature data, specifically: Obtain image data information of the injection mold in various directions, and obtain pre-processed image data by filtering and denoising the image data information of the injection mold in various directions, and introduce a fuzzy clustering algorithm; Initialize the cluster center based on the fuzzy clustering algorithm, and initialize the clustering of each pixel in the preprocessed image data according to the cluster center, obtain the pixel point set after several clustering, and introduce the Jaccard distance measurement method; The Jaccard coefficient between each clustered pixel point set is calculated by the Jaccard distance measurement method, and the Jaccard distance between the clustered pixel point sets is calculated based on the Jaccard coefficient, and a Jaccard distance threshold is preset; When the Jaccard distance between the pixel point sets after clustering is not greater than the Carder distance threshold, the cluster center is adjusted, and the pixel point sets after clustering are re-clustered until the Jaccard distance between the pixel point sets after clustering is no longer less than the Carder distance threshold, the pixel point sets after clustering are output, and segmentation is performed according to the pixel point sets after clustering to obtain the clustered image feature data.

[0033] Furthermore, in the present device, the target features of the injection mold are obtained based on the clustered image feature data, and a real-time three-dimensional model diagram of the injection mold is constructed based on the target features of the injection mold, specifically including: Acquire image feature data of the injection mold after clustering in various directions, and obtain contour features of the injection mold in various directions by performing feature extraction on the image feature data of the injection mold after clustering in various directions; The contour features of the injection mold in various directions are used as target features of the injection mold, and the positions of the target features of the injection mold are obtained, and the target features of the injection mold are spliced ​​based on the positions of the target features of the injection mold; By splicing, several model images are obtained, and by performing secondary splicing on the model images in each three-dimensional direction, a real-time three-dimensional model image of the injection mold is constructed, and the real-time three-dimensional model image of the injection mold is output.

[0034] Furthermore, in this device, the drawing data of the part to be injected is obtained, and the injection molding deformation evaluation index is set based on the drawing data of the injection mold, specifically: Obtain drawing data of the part to be injected, and obtain upper limits of data deviations of each region of the part to be injected and lower limits of data deviations of each region of the part to be injected according to the drawing data of the part to be injected, and construct a first evaluation index based on the upper limits of data deviations of each region of the part to be injected; A second evaluation index is constructed based on the lower limit of the data deviation of each region of the injection molded part, an injection molding deformation variable evaluation index is set based on the first evaluation index and the second evaluation index, and the injection molding deformation variable evaluation index is output.

[0035] Furthermore, in the present device, the real-time three-dimensional model diagram of the injection mold is analyzed based on the injection molding deformation evaluation index to obtain the analysis results, which specifically include: Obtaining model parameters of each position of the real-time three-dimensional model diagram of the injection mold, and determining whether the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation variable evaluation index; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation variable evaluation index, a normal analysis result of the injection mold deformation variable is generated and used as a first analysis result, and the first analysis result is output; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are not within the corresponding injection molding deformation variable evaluation index, an analysis result of the injection mold deformation variable abnormality is generated and output as a second analysis result.

[0036] Furthermore, in the present device, a relevant report is generated according to the analysis results, and the relevant injection molding suggestions are displayed in a preset manner, specifically: When the analysis result is the second analysis result, a relevant scrap report is generated, and the relevant scrap report is displayed in a preset manner; When the analysis result is the second analysis result, a related normal report is generated, and the related normal report is displayed in a preset manner.

[0037] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0038] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0039] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0040] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0041] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0042] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. The method for constructing and analyzing the deformation model of injection mold is characterized by: The following steps are involved: Acquire image data information of the injection mold in various directions, and analyze the image data information of the injection mold in various directions by using a fuzzy clustering model and a Jaccard distance measurement method to acquire clustered image feature data; Acquire injection mold target features based on the clustered image feature data, and construct a real-time three-dimensional model diagram of the injection mold based on the injection mold target features; Acquire drawing data of the part to be injected, and set an injection molding deformation variable evaluation index based on the drawing data of the injection mold, analyze the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation variable evaluation index, and obtain an analysis result; A relevant report is generated according to the analysis result, and the relevant injection molding suggestions are displayed in a preset manner.

2. The method for constructing and analyzing the injection mold deformation variable model according to claim 1, characterized in that: The image data information of the injection mold in various directions is obtained, and the image data information of the injection mold in various directions is analyzed by using a fuzzy clustering model and a Jaccard distance measurement method to obtain clustered image feature data, specifically: Acquire image data information of the injection mold in various directions, and obtain pre-processed image data by filtering and denoising the image data information of the injection mold in various directions, and introduce a fuzzy clustering algorithm; Initializing cluster centers based on the fuzzy clustering algorithm, and initializing clustering for each pixel in the preprocessed image data according to the cluster centers, obtaining pixel point sets after a number of clustering, and introducing the Jaccard distance measurement method; The Jaccard coefficient between each clustered pixel point set is calculated by the Jaccard distance measurement method, and the Jaccard distance between the clustered pixel point sets is calculated based on the Jaccard coefficient, and a Jaccard distance threshold is preset; When the Jaccard distance between the pixel point sets after clustering is not greater than the Carder distance threshold, the cluster center is adjusted, and the pixel point sets after clustering are re-clustered until the Jaccard distance between the pixel point sets after clustering is no longer less than the Carder distance threshold, the pixel point sets after clustering are output, and segmentation is performed according to the pixel point sets after clustering to obtain the image feature data after clustering.

3. The method for constructing and analyzing the injection mold deformation variable model according to claim 1, characterized in that: Acquiring the target features of the injection mold based on the clustered image feature data, and constructing a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold, specifically including: Acquire image feature data of the injection mold after clustering in various directions, and acquire contour features of the injection mold in various directions by performing feature extraction on the image feature data of the injection mold after clustering in various directions; Using the contour features of the injection mold in various directions as injection mold target features, acquiring the positions of the injection mold target features, and splicing the injection mold target features based on the positions of the injection mold target features; By splicing, several model images are obtained, and by performing secondary splicing on the model images in each three-dimensional direction, a real-time three-dimensional model image of the injection mold is constructed, and the real-time three-dimensional model image of the injection mold is output.

4. The method for constructing and analyzing the injection mold deformation variable model according to claim 1, characterized in that: Obtain drawing data of the part to be injected, and set the injection molding deformation evaluation index based on the drawing data of the injection mold, specifically: Acquire drawing data of the part to be injected, and acquire upper limits of data deviations of each region of the part to be injected and lower limits of data deviations of each region of the part to be injected according to the drawing data of the part to be injected, and construct a first evaluation index based on the upper limits of data deviations of each region of the part to be injected; A second evaluation index is constructed based on the lower limit of the data deviation of each region of the injection molded part, an injection molding deformation variable evaluation index is set based on the first evaluation index and the second evaluation index, and the injection molding deformation variable evaluation index is output.

5. The method for constructing and analyzing the injection mold deformation variable model according to claim 1, characterized in that: The real-time three-dimensional model diagram of the injection mold is analyzed based on the injection molding deformation evaluation index to obtain analysis results, specifically including: Obtaining model parameters of each position of the real-time three-dimensional model diagram of the injection mold, and determining whether the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation evaluation index; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding injection molding deformation variable evaluation index, an analysis result of a normal injection mold deformation variable is generated and used as a first analysis result, and the first analysis result is output; When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are not within the corresponding injection molding deformation variable evaluation index, an analysis result of the injection mold deformation variable abnormality is generated and output as a second analysis result.

6. The method for constructing and analyzing the injection mold deformation variable model according to claim 1, characterized in that: Generate relevant reports based on the analysis results, and display the relevant injection molding suggestions in a preset manner, specifically: When the analysis result is the second analysis result, a relevant scrapping report is generated, and the relevant scrapping report is displayed in a preset manner; When the analysis result is the second analysis result, a related normal report is generated, and the related normal report is displayed in a preset manner.

7. An injection mold deformation model construction and analysis device, characterized in that: The device includes a memory and a processor, wherein the memory includes a program for constructing and analyzing a method for a deformation variable model of an injection mold. When the program for constructing and analyzing a method for a deformation variable model of an injection mold is executed by the processor, the steps of the method for constructing and analyzing a deformation variable model of an injection mold as described in any one of claims 1 to 6 are implemented.

8. A terminal device, characterized in that: include: An image processing module, which obtains image data information of the injection mold in various directions, and analyzes the image data information of the injection mold in various directions by using a fuzzy clustering model and a Jaccard distance measurement method to obtain clustered image feature data; A model building module, which acquires target features of the injection mold based on the clustered image feature data, and constructs a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold; A deformation variable analysis module, which obtains drawing data of the part to be injected, sets an injection molding deformation variable evaluation index based on the drawing data of the injection mold, and analyzes the real-time three-dimensional model diagram of the injection mold based on the injection molding deformation variable evaluation index to obtain an analysis result; The report generation module generates a relevant report according to the analysis result and displays the relevant injection molding suggestions in a preset manner.

Citation Information

Patent Citations

  • Hybrid stitching

    CN103392191A

  • Semantic segmentation method for large complex curved surface part point cloud

    CN115063787A

  • Stamping die wear assessment method based on quantum multivariate universe optimization point cloud reference plane

    CN116823801A

  • Hole identification method and device of three-dimensional network model, storage medium and electronic equipment

    CN117975438A

  • Imprint method, imprint apparatus, manufacturing method of mold, and article manufacturing method

    US20200363716A1