Injection Mold Deformation Quantity Model Construction and Analysis Method, Device and Terminal Equipment

Abstract

The present invention relates to a method, device and terminal equipment for constructing and analyzing the deformation amount model of an injection mold, belonging to the technical field of injection mold analysis. The present invention sets the evaluation index of the injection molding deformation amount based on the drawing data of the injection mold, analyzes the real-time three-dimensional model diagram of the injection mold based on the evaluation index of the injection molding deformation amount to obtain the analysis result, and finally generates a relevant report according to the analysis result and displays the relevant injection molding suggestions in a preset manner. By analyzing the image data of the injection mold, clustering and segmenting the pixel points through the fuzzy clustering algorithm, and integrating the Jaccard distance metric algorithm to optimize the segmentation of the image data, the present invention can extract the image data with better segmentation effect, thereby establishing a more accurate three-dimensional model of the real-time injection mold, making the judgment of the deformation amount of the injection mold more accurate, and further having a higher recognition accuracy for abnormal injection molds, avoiding economic losses.

Description

Technical Field

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

[0002] An injection mold is a tool for producing plastic products; it is also a tool for giving plastic products a complete structure and precise dimensions. Injection molding is a processing method used when mass-producing some complex-shaped parts. Specifically, it means injecting the heat-melted plastic into the mold cavity under high pressure by an injection molding machine, and after cooling and solidifying, a formed product is obtained. The structure of the mold may vary greatly due to different plastic varieties and properties, the shape and structure of plastic products, and the type of injection molding machine. The injection mold mainly consists of a moving mold and a fixed mold. The moving mold is installed on the moving template of the injection molding machine, and the fixed mold is installed on the fixed template of the injection molding machine. However, after the injection mold is used for a certain number of years or times, certain deformations will occur. For some high-precision injection parts, the minute 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, resulting in certain economic losses in the end. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method, device and terminal device for constructing and analyzing an injection mold deformation amount model. To achieve the above object, the technical solution adopted by the present invention is as follows:

[0004] The first aspect of the present invention provides a method for constructing and analyzing an injection mold deformation amount model, including the following steps:

[0005] Obtain the image data information of the injection mold in each direction, and analyze the image data information of the injection mold in each direction through a fuzzy clustering model and the Jaccard distance metric method to obtain the clustered image feature data;

[0006] Based on the clustered image feature data, obtain the target features of the injection mold, and construct a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold;

[0007] Obtain the drawing data of the to-be-injected part, and set an injection molding deformation amount 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 amount evaluation index to obtain an analysis result;

[0008] Generate a relevant report according to the analysis result, and display the relevant injection molding suggestions in a preset manner.

[0009] Further, in this method, image data information of the injection mold in each direction is obtained, and the image data information of the injection mold in each direction is analyzed by a fuzzy clustering model and the Jaccard distance metric method to obtain the clustered image feature data. Specifically:

[0010] Obtain the image data information of the injection mold in each direction, and through filtering and denoising processing of the image data information of the injection mold in each direction, obtain the preprocessed image data, and introduce a fuzzy clustering algorithm;

[0011] Based on the fuzzy clustering algorithm, initialize the clustering centers, and initialize the clustering of each pixel point in the preprocessed image data according to the clustering centers to obtain several sets of clustered pixel points, and introduce the Jaccard distance metric method;

[0012] Calculate the Jaccard coefficients between each set of clustered pixel points through the Jaccard distance metric method, calculate the Jaccard distance between the sets of clustered pixel points based on the Jaccard coefficients, and preset the Jaccard distance threshold;

[0013] When the Jaccard distance between the sets of clustered pixel points is not greater than the Jaccard distance threshold, adjust the clustering centers and re-cluster the sets of clustered pixel points until the situation where the Jaccard distance between the sets of clustered pixel points is not greater than the Jaccard distance threshold no longer appears, output the sets of clustered pixel points, and segment according to the sets of clustered pixel points to obtain the clustered image feature data.

[0014] Further, in this method, based on the clustered image feature data, obtain the target features of the injection mold, and construct a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold. Specifically include:

[0015] Obtain the clustered image feature data of the injection mold in each direction, and through feature extraction of the clustered image feature data of the injection mold in each direction, obtain the contour features of the injection mold in each direction;

[0016] Use the contour features of the injection mold in each direction as the target features of the injection mold, and obtain the positions where the target features of the injection mold are located, and splice the target features of the injection mold based on the positions where the target features of the injection mold are located;

[0017] Through splicing, obtain several model diagrams, and through secondary splicing in each three-dimensional direction of the model diagrams, construct a real-time three-dimensional model diagram of the injection mold, and output the real-time three-dimensional model diagram of the injection mold.

[0018] Further, in this method, drawing data of the to-be-injection-molded part is obtained, and an evaluation index for the injection molding deformation amount is set based on the drawing data of the injection mold, specifically:

[0019] Obtain the drawing data of the to-be-injection-molded part, and based on the drawing data of the to-be-injection-molded part, obtain the upper limit of the data deviation of each area of the to-be-injection-molded part and the lower limit of the data deviation of the to-be-injection-molded part in each area. Construct a first evaluation index based on the upper limit of the data deviation of each area of the to-be-injection-molded part;

[0020] Construct a second evaluation index based on the lower limit of the data deviation of the to-be-injection-molded part in each area. Set the evaluation index for the injection molding deformation amount based on the first evaluation index and the second evaluation index, and output the evaluation index for the injection molding deformation amount.

[0021] Further, in this method, analyze the real-time three-dimensional model diagram of the injection mold based on the evaluation index for the injection molding deformation amount to obtain an analysis result, specifically including:

[0022] Obtain the model parameters of each position of the real-time three-dimensional model diagram of the injection mold, and determine whether the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding evaluation index for the injection molding deformation amount;

[0023] When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding evaluation index for the injection molding deformation amount, generate an analysis result that the deformation amount of the injection mold is normal as the first analysis result, and output the first analysis result;

[0024] When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are not within the corresponding evaluation index for the injection molding deformation amount, generate an analysis result that the deformation amount of the injection mold is abnormal as the second analysis result, and output the second analysis result.

[0025] Further, in this method, generate a relevant report according to the analysis result, and display the relevant injection molding suggestions in a preset manner, specifically:

[0026] When the analysis result is the second analysis result, generate a relevant scrapping report and display the relevant scrapping report in a preset manner;

[0027] When the analysis result is the second analysis result, generate a relevant normal report and display the relevant normal report in a preset manner.

[0028] In a second aspect of the present invention, there is provided an apparatus for constructing and analyzing the deformation amount model of an injection mold. The apparatus includes a memory and a processor. The memory includes a program for the method of constructing and analyzing the deformation amount model of the injection mold. When the program for the method of constructing and analyzing the deformation amount model of the injection mold is executed by the processor, the steps of any of the methods for constructing and analyzing the deformation amount model of the injection mold are implemented.

[0029] In a third aspect of the present invention, there is provided a terminal device, comprising:

[0030] An image processing module, which acquires the 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 metric method to obtain the clustered image feature data;

[0031] A model establishment module, which obtains the 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;

[0032] A deformation amount analysis module, which acquires the drawing data of the part to be injected, sets an evaluation index for the injection molding deformation amount 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 evaluation index for the injection molding deformation amount to obtain an analysis result;

[0033] A report generation module, which generates a relevant report according to the analysis result, and displays the relevant injection molding suggestions in a preset manner.

[0034] The present invention solves the defects existing in the background technology, and the present invention has the following beneficial effects:

[0035] The present invention obtains the image data information of an injection mold in various directions, analyzes the image data information of the injection mold in various directions through a fuzzy clustering model and the Jaccard distance metric method, obtains the image feature data after clustering, and then obtains the target features of the injection mold based on the image feature data after clustering. Based on the target features of the injection mold, a real-time three-dimensional model diagram of the injection mold is constructed, thereby obtaining the drawing data of the part to be injected. Based on the drawing data of the injection mold, an evaluation index for the injection molding deformation amount is set. The real-time three-dimensional model diagram of the injection mold is analyzed based on the evaluation index for the injection molding deformation amount to obtain an analysis result. Finally, a relevant report is generated according to the analysis result, and the relevant injection molding suggestions are displayed in a preset manner. By analyzing the image data of the injection mold, clustering and segmenting pixel points through a fuzzy clustering algorithm, and integrating the Jaccard distance metric algorithm to optimize the segmentation of the image data, the present invention can extract image data with a better segmentation effect, thereby establishing a more accurate three-dimensional model of the real-time injection mold, making a more accurate judgment on the deformation amount of the injection mold, and having a higher recognition accuracy for abnormal injection molds, thus avoiding economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0037] Figure 1 Shows the overall flowchart of the method for constructing and analyzing the injection mold deformation amount model;

[0038] Figure 2 Shows the schematic flowchart of the method for constructing and analyzing the injection mold deformation amount model;

[0039] Figure 3 Shows the block diagram of the device for constructing and analyzing the injection mold deformation amount model;

[0040] Figure 4 Shows the schematic diagram of the terminal device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to be able to more clearly understand the above-mentioned objects, features, and advantages of the present invention, the present invention will be further described in detail below in conjunction with the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0042] In the following description, many specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited by the specific embodiments disclosed below.

[0043] As Figure 1 shown, the first aspect of the present invention provides a method for constructing and analyzing the deformation amount model of an injection mold, including the following steps:

[0044] S102: Obtain the image data information of the injection mold in each direction, and analyze the image data information of the injection mold in each direction through a fuzzy clustering model and the Jaccard distance metric method to obtain the clustered image feature data;

[0045] S104: Obtain the target features of the injection mold based on the clustered image feature data, and construct a real-time three-dimensional model diagram of the injection mold based on the target features of the injection mold;

[0046] S106: Obtain the drawing data of the part to be injected, set the evaluation index of the injection molding deformation amount based on the drawing data of the injection mold, and analyze the real-time three-dimensional model diagram of the injection mold based on the evaluation index of the injection molding deformation amount to obtain the analysis result;

[0047] S108: Generate a relevant report according to the analysis result, and display the relevant injection molding suggestions in a preset manner.

[0048] It is worth mentioning that the present invention analyzes the image data of the injection mold, clusters and segments the pixel points through the fuzzy clustering algorithm, and incorporates the Jaccard distance metric algorithm to optimize the segmentation of the image data, can extract image data with better segmentation effect, thus establishing a more accurate real-time three-dimensional model of the injection mold, making the judgment of the deformation amount of the injection mold more accurate, and further having a higher recognition accuracy for abnormal injection molds, 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.

[0049] As Figure 2 shown, further, in step 102 of this method, specifically:

[0050] S202: Obtain the image data information of the injection mold in each direction, and perform filtering and denoising processing on the image data information of the injection mold in each direction to obtain the preprocessed image data, and introduce the fuzzy clustering algorithm;

[0051] S204: Initialize the clustering centers based on the fuzzy clustering algorithm, and perform initial clustering on each pixel point in the preprocessed image data according to the clustering centers to obtain several sets of pixel points after clustering, and introduce the Jaccard distance metric;

[0052] S206: Calculate the Jaccard coefficients between each set of pixel points after clustering through the Jaccard distance metric, calculate the Jaccard distance between the sets of pixel points after clustering based on the Jaccard coefficients, and preset the Jaccard distance threshold;

[0053] S208: When the Jaccard distance between the sets of pixel points after clustering is not greater than the Jaccard distance threshold, adjust the clustering centers (the number, position, etc. of the clustering centers), and re-cluster the sets of pixel points after clustering until the Jaccard distance between the sets of pixel points after clustering is no longer not greater than the Jaccard distance threshold, output the sets of pixel points after clustering, and segment according to the sets of pixel points after clustering to obtain the image feature data after clustering.

[0054] It is worth mentioning that in this method, the collected image data is segmented by the fuzzy clustering algorithm. During the segmentation process, when the number of clustering centers is not appropriate, the phenomenon of local optimal solutions is likely to occur, which will lead to the existence of data that does not belong to this cluster in the classified dataset. At this time, the Jaccard distance between the sets of pixel points after clustering is calculated through the Jaccard distance metric. 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 dataset and the phenomenon of local optimal solutions occurs. Through this method, the segmentation of the collected image can be optimized, the segmentation accuracy of the image can be improved, and it is beneficial to make the accuracy of the subsequent model higher.

[0055] Further, in step S104 of this method, it specifically includes:

[0056] Obtain the image feature data after clustering of the injection mold in each direction, and extract features from the image feature data after clustering of the injection mold in each direction to obtain the contour features of the injection mold in each direction;

[0057] Take the contour features of the injection mold in each direction as the target features of the injection mold, and obtain the positions where the target features of the injection mold are located, and splice the target features of the injection mold based on the positions where the target features of the injection mold are located;

[0058] Through splicing, obtain several model diagrams, perform secondary splicing in each three-dimensional direction on the model diagrams to construct a real-time three-dimensional model diagram of the injection mold, and output the real-time three-dimensional model diagram of the injection mold.

[0059] It is worth mentioning that feature contours are extracted from the image feature data of the injection mold clustered in all directions, and then the target features of the injection mold are spliced through 3D modeling software (such as SolidWorks and ug 3D modeling software) to form a real-time 3D model diagram of the injection mold.

[0060] Furthermore, in this method, the drawing data of the part to be injection-molded is obtained, and an evaluation index for the injection molding deformation amount is set based on the drawing data of the injection mold, specifically:

[0061] The drawing data of the part to be injection-molded is obtained, and the upper limit of the data deviation in each area of the part to be injection-molded and the lower limit of the data deviation in each area of the part to be injection-molded are obtained according to the drawing data of the part to be injection-molded. A first evaluation index is constructed based on the upper limit of the data deviation in each area of the part to be injection-molded;

[0062] A second evaluation index is constructed based on the lower limit of the data deviation in each area of the part to be injection-molded. An evaluation index for the injection molding deformation amount is set based on the first evaluation index and the second evaluation index, and the evaluation index for the injection molding deformation amount is output.

[0063] It is worth mentioning that since the deformation of the injection mold will cause the injection-molded part to change abnormally, and since the injection-molded parts have certain standards, such as contour accuracy and surface finish, there will be an upper limit and a lower limit of data deviation at this time to form a range that meets specific requirements, thereby forming an evaluation index for the injection molding deformation amount.

[0064] Furthermore, in this method, the real-time 3D model diagram of the injection mold is analyzed based on the evaluation index for the injection molding deformation amount to obtain an analysis result, specifically including:

[0065] The model parameters at each position of the real-time 3D model diagram of the injection mold are obtained, and it is judged whether the model parameters at each position of the real-time 3D model diagram of the injection mold are within the corresponding evaluation index for the injection molding deformation amount;

[0066] When the model parameters at each position of the real-time 3D model diagram of the injection mold are within the corresponding evaluation index for the injection molding deformation amount, an analysis result indicating that the deformation amount of the injection mold is normal is generated and used as the first analysis result, and the first analysis result is output;

[0067] When the model parameters at each position of the real-time 3D model diagram of the injection mold are not within the corresponding evaluation index for the injection molding deformation amount, an analysis result indicating that the deformation amount of the injection mold is abnormal is generated and used as the second analysis result, and the second analysis result is output.

[0068] Furthermore, in this method, a relevant report is generated according to the analysis result, and the relevant injection molding suggestions are displayed in a preset manner, specifically:

[0069] 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;

[0070] When the analysis result is the second analysis result, a relevant normal report is generated and the relevant normal report is displayed in a preset manner.

[0071] In addition, the method may further include:

[0072] Obtain historical deformation amount change characteristic data of the injection mold under each working environment through big data, introduce a Markov chain, and input the historical deformation amount change characteristic data of the injection mold under each working environment into the Markov chain;

[0073] Take the deformation amount characteristic as a state value, construct a state matrix, calculate the state value transition probability value of each state value in the state matrix transferring to the next level, construct a transition probability value matrix, and construct a deformation amount prediction model based on a deep neural network;

[0074] Input the transition probability value matrix into the deformation amount prediction model for training, obtain the trained deformation amount prediction model, obtain the working environment characteristic of the injection mold and the deformation amount characteristic of the current timestamp, and input the working environment characteristic of the injection mold and the deformation amount characteristic of the current timestamp into the trained deformation amount prediction model for prediction;

[0075] Through prediction, obtain the transition probability value of the deformation amount characteristic of the current timestamp transferring to the deformation amount characteristic of the next level. When the transition probability value is greater than the preset transition probability value, take the deformation amount characteristic of the next level as the deformation amount characteristic of the current timestamp, and give an early warning according to the deformation amount characteristic of the current timestamp.

[0076] It should be noted that different working environments will cause different deformation amounts of the injection mold during work. For example, the higher the temperature, the greater the deformation due to the thermal expansion and contraction of the material. The Markov chain can take the deformation amount characteristic as a state value, so as to predict the transition probability value of the deformation amount characteristic of the current timestamp transferring to the deformation amount characteristic of the next level. For example, the deformation amount of a certain position of the injection mold at a certain moment is 0.1 mm, and the transition probability value when transferring to the next level of 0.2 mm is 95%, which means that the deformation amount has reached 0.2 mm. Through this method, the deformation amount characteristic of the current timestamp can be predicted, an early warning can be given in time, and losses can be recovered in time.

[0077] In addition, giving an early warning according to the deformation amount characteristic of the current timestamp includes the following steps:

[0078] Obtain the processing order information of each injection molding machine during the processing, and obtain the maximum deformation feature data that the injection molded part can accept according to the processing order information of the injection molding machine during the processing;

[0079] Judge whether the deformation feature at the current timestamp is greater than the maximum deformation feature data that the injection molded part can accept. When the deformation feature at the current timestamp is not greater than the maximum deformation feature data that the injection molded part can accept, a continue processing instruction is generated;

[0080] When the deformation feature at the current timestamp is greater than the maximum deformation feature data that the injection molded part can accept, obtain the location of the corresponding injection molding machine, and give an alarm according to the location of the corresponding injection molding machine. At the same time, a stop processing instruction is generated;

[0081] Control the corresponding injection molding machine through the Internet of Things control network based on the stop processing instruction.

[0082] It should be noted that when the deformation feature at the current timestamp is greater than the maximum deformation feature data that the injection molded part can accept, it means that the processed product is defective. Through this method, the operation of the injection molding machine can be dynamically regulated according to the predicted deformation data, making the injection molding machine more reasonable during operation.

[0083] As Figure 3 shown, the second aspect of the present invention provides an injection mold deformation 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 model construction and analysis method program. When the injection mold deformation model construction and analysis method program is executed by the processor, the steps of any injection mold deformation model construction and analysis method are implemented.

[0084] As Figure 4 shown, the third aspect of the present invention provides a terminal device, including:

[0085] An image processing module 10, which obtains the image data information of the injection mold in each direction, and analyzes the image data information of the injection mold in each direction through a fuzzy clustering model and a Jaccard distance metric method to obtain the clustered image feature data;

[0086] A model establishment module 20, which obtains the 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;

[0087] The deformation variable analysis module 30 obtains the drawing data of the to-be-injected part, sets the evaluation index of the injection molding deformation variable based on the drawing data of the injection mold, analyzes the real-time three-dimensional model diagram of the injection mold based on the evaluation index of the injection molding deformation variable, and obtains the analysis result;

[0088] The report generation module 40 generates a relevant report according to the analysis result and displays the relevant injection molding suggestions in a preset manner.

[0089] Furthermore, in this device, the image data information of the injection mold in each direction is obtained, and the image data information of the injection mold in each direction is analyzed by means of a fuzzy clustering model and the Jaccard distance metric method to obtain the clustered image feature data. Specifically:

[0090] Obtain the image data information of the injection mold in each direction, perform filtering and denoising processing on the image data information of the injection mold in each direction to obtain the preprocessed image data, and introduce a fuzzy clustering algorithm;

[0091] Initialize the clustering center based on the fuzzy clustering algorithm, and perform initial clustering on each pixel point in the preprocessed image data according to the clustering center to obtain several clustered pixel point sets, and introduce the Jaccard distance metric method;

[0092] Calculate the Jaccard coefficient between each clustered pixel point set by means of the Jaccard distance metric method, calculate the Jaccard distance between the clustered pixel point sets based on the Jaccard coefficient, and preset the Jaccard distance threshold;

[0093] When the Jaccard distance between the clustered pixel point sets is not greater than the Jaccard distance threshold, adjust the clustering center and re-cluster the clustered pixel point sets until the situation where the Jaccard distance between the clustered pixel point sets is not greater than the Jaccard distance threshold no longer appears, output the clustered pixel point sets, and perform segmentation according to the clustered pixel point sets to obtain the clustered image feature data.

[0094] Furthermore, in this device, the target features of the injection mold are obtained based on the clustered image feature data, and the real-time three-dimensional model diagram of the injection mold is constructed based on the target features of the injection mold. Specifically include:

[0095] Obtain the clustered image feature data of the injection mold in each direction, and perform feature extraction on the clustered image feature data of the injection mold in each direction to obtain the contour features of the injection mold in each direction;

[0096] Take the contour features of the injection mold in all directions as the target features of the injection mold, obtain the positions where the target features of the injection mold are located, and splice the target features of the injection mold based on the positions where the target features of the injection mold are located;

[0097] Through splicing, obtain several model diagrams, and through secondary splicing in each three-dimensional direction of the model diagrams, construct a real-time three-dimensional model diagram of the injection mold, and output the real-time three-dimensional model diagram of the injection mold.

[0098] Further, in this equipment, obtain the drawing data of the part to be injected, and set the evaluation index of the injection molding deformation amount based on the drawing data of the injection mold, specifically:

[0099] Obtain the drawing data of the part to be injected, and based on the drawing data of the part to be injected, obtain the upper limit of the data deviation of each area of the part to be injected and the lower limit of the data deviation of the part to be injected in each area, and construct the first evaluation index based on the upper limit of the data deviation of each area of the part to be injected;

[0100] Construct the second evaluation index based on the lower limit of the data deviation of the part to be injected in each area, set the evaluation index of the injection molding deformation amount based on the first evaluation index and the second evaluation index, and output the evaluation index of the injection molding deformation amount.

[0101] Further, in this equipment, analyze the real-time three-dimensional model diagram of the injection mold based on the evaluation index of the injection molding deformation amount, and obtain the analysis result, specifically including:

[0102] Obtain the model parameters of each position of the real-time three-dimensional model diagram of the injection mold, and judge whether the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding evaluation index of the injection molding deformation amount;

[0103] When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are within the corresponding evaluation index of the injection molding deformation amount, generate an analysis result that the deformation amount of the injection mold is normal, and use it as the first analysis result, and output the first analysis result;

[0104] When the model parameters of each position of the real-time three-dimensional model diagram of the injection mold are not within the corresponding evaluation index of the injection molding deformation amount, generate an analysis result that the deformation amount of the injection mold is abnormal, and use it as the second analysis result, and output the second analysis result.

[0105] Further, in this equipment, generate a relevant report according to the analysis result, and display the relevant injection molding suggestions in a preset manner, specifically:

[0106] When the analysis result is the second analysis result, generate a relevant scrap report, and display the relevant scrap report in a preset manner;

[0107] When the analysis result is the second analysis result, a relevant normal report is generated and the relevant normal report is displayed in a preset manner.

[0108] In 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 merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed components can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0109] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] In addition, in each embodiment of the present invention, each functional unit can be fully integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit; the above integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0111] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media that can store program codes such as removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs.

[0112] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0113] 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 within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to 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; Generate relevant reports according to the analysis results, and display the relevant reports in a preset manner; 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, a plurality of model images are obtained, and a real-time three-dimensional model image of the injection mold is constructed by performing secondary splicing on the model images in each three-dimensional direction, and the real-time three-dimensional model image of the injection mold is output; 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.

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 Jaccard 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 Jaccard 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: 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.

4. 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 reports 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.

5. 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 4 are implemented.

6. 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; A report generation module generates a relevant report according to the analysis result and displays the relevant injection molding suggestions in a preset manner; 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, a plurality of model images are obtained, and a real-time three-dimensional model image of the injection mold is constructed by performing secondary splicing on the model images in each three-dimensional direction, and the real-time three-dimensional model image of the injection mold is output; 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.

Images