Method and device for manufacturing injection molds for automobile plastic parts

Abstract

The present invention discloses a method and device for manufacturing an injection mold for automobile plastic parts, and relates to the technical field of mold assembly control. The method comprises: obtaining a conceptual model of a first mold part of an injection mold; performing three-dimensional modeling to obtain a production model; verifying the size of the production model according to the conceptual model to obtain a verification result; when the verification passes, obtaining material information, thickness analysis information, and heat treatment record temperature timing information; configuring the deformation temperature according to this information to obtain deformation temperature threshold distribution information; traversing the second to Nth mold parts to obtain their deformation temperature threshold distribution information; performing splicing temperature optimization to obtain splicing control temperature distribution information; and controlling the assembly of mold parts according to the information. The method solves the technical problems that the docking accuracy error is large during the splicing of multiple parts of the injection mold for plastic parts, and the instability of the splicing effect due to the failure to fully consider the influencing factors such as the environment.

Description

Technical Field

[0001] The present application relates to the technical field of mold assembly control, and in particular to a method and device for manufacturing an injection mold for automobile plastic parts. Background Art

[0002] With the rapid development of the automobile industry, automobile plastic parts have been widely used in automobile manufacturing due to their advantages such as lightweight, corrosion resistance, good processing performance and high design freedom. However, due to the increasingly complex shapes of automobile plastic parts, traditional injection mold manufacturing technology faces huge challenges. In order to meet the high-precision requirements of these complex-shaped parts, the manufacturing process of injection molds has to be innovated and optimized. In the current manufacturing environment, in order to overcome the problem that a single mold is difficult to mold complex-shaped plastic parts at one time, the industry generally adopts the strategy of splitting the injection mold into multiple mold parts and manufacturing them separately. This strategy allows each mold part to be precisely designed and manufactured according to specific shape characteristics, thereby improving manufacturing efficiency and flexibility. However, the problem that follows is that the docking accuracy of multiple mold parts during the splicing process is difficult to guarantee. The existing splicing method mainly relies on visual components to achieve accurate positioning and splicing of mold parts. Although this method improves the splicing accuracy to a certain extent, its limitations are also obvious. Because in the actual production process, the factors that affect the docking accuracy are far more than just visual errors, but also include ambient temperature, humidity, differences in the thermal expansion coefficient of mold materials, the processing accuracy of mold parts, and operational errors during splicing. The interaction of these factors makes it difficult to achieve ideal docking accuracy, which in turn affects the dimensional accuracy and quality stability of the final injection molded product. Summary of the invention

[0003] The present application provides a method and device for manufacturing an injection mold for automobile plastic parts, thereby solving the technical problems of large docking accuracy errors during the splicing of multiple parts of an injection mold for plastic parts, and unstable splicing effects caused by failure to fully consider factors such as the environment. The application achieves the effect of optimizing the splicing control temperature distribution, improving the docking accuracy of the splicing of mold parts, and ensuring the overall quality and dimensional accuracy of the injection mold by comprehensively considering factors such as the material, thickness, and heat treatment temperature sequence of mold parts.

[0004] The present application provides a method for manufacturing an injection mold for an automobile plastic component, the method comprising: obtaining a conceptual model of a first mold component of the injection mold; performing three-dimensional modeling on the first mold component of the injection mold to obtain a production model of the first mold component; performing dimension verification on the first mold component production model according to the conceptual model of the first mold component to obtain a dimension verification result of the first mold component; when the dimension verification result of the first mold component is a verification pass, obtaining material information of the first mold component, thickness analysis information of the first mold component and time series information of a heat treatment record temperature of the first mold component; and ... A mold component is heat treated by recording temperature timing information to configure deformation temperature, and deformation temperature threshold distribution information of the first mold component is obtained; the second mold component is traversed until the Nth mold component, and deformation temperature threshold distribution information of the second mold component is obtained until the Nth mold component is obtained; splicing temperature optimization is performed according to the deformation temperature threshold distribution information of the first mold component, the deformation temperature threshold distribution information of the second mold component until the Nth mold component, and splicing control temperature distribution information is obtained; assembly control of the first mold component, the second mold component until the Nth mold component is performed according to the splicing control temperature distribution information.

[0005] The present application also provides an injection mold manufacturing device for automobile plastic parts, including: a conceptual model acquisition module, the conceptual model acquisition module is used to obtain a conceptual model of a first mold component of the injection mold; a three-dimensional modeling module, the three-dimensional modeling module is used to perform three-dimensional modeling on the first mold component of the injection mold to obtain a first mold component production model; a dimension verification module, the dimension verification module is used to perform dimension verification on the first mold component production model according to the first mold component conceptual model to obtain a dimension verification result of the first mold component; a component information acquisition module, the component information acquisition module is used to obtain the first mold component material information, the first mold component thickness analysis information and the first mold component heat treatment record temperature timing information when the first mold component dimension verification result is verification passed; a first deformation temperature configuration module, the first deformation temperature configuration module is used to perform dimension verification on the first mold component production model according to the first mold component material information, the first mold component thickness analysis information and the first mold component heat treatment record temperature timing information The thickness distribution information of the first mold component and the temperature timing information of the heat treatment record of the first mold component are used to configure the deformation temperature to obtain the deformation temperature threshold distribution information of the first mold component; a second deformation temperature configuration module, the second deformation temperature configuration module is used to traverse the second mold component until the Nth mold component, and obtain the deformation temperature threshold distribution information of the second mold component until the Nth mold component; a splicing temperature optimization module, the splicing temperature optimization module is used to perform splicing temperature optimization according to the deformation temperature threshold distribution information of the first mold component, the deformation temperature threshold distribution information of the second mold component until the Nth mold component deformation temperature threshold distribution information, and obtain splicing control temperature distribution information; an assembly control module, the assembly control module is used to perform assembly control of the first mold component, the second mold component until the Nth mold component according to the splicing control temperature distribution information.

[0006] It is intended to obtain a conceptual model of a first mold component of an injection mold through the method and device for manufacturing an injection mold for an automobile plastic part proposed in this application; perform three-dimensional modeling on the first mold component of the injection mold to obtain a first mold component production model; perform dimension verification on the first mold component production model according to the first mold component conceptual model to obtain a dimension verification result of the first mold component; when the dimension verification result of the first mold component is verified, obtain the material information of the first mold component, the thickness analysis information of the first mold component and the temperature timing information of the heat treatment record of the first mold component; according to the material information of the first mold component, the thickness distribution information of the first mold component and the first mold component, ... The deformation temperature is configured by recording the temperature timing information of the heat treatment of a mold component, and the deformation temperature threshold distribution information of the first mold component is obtained; the second mold component is traversed until the Nth mold component, and the deformation temperature threshold distribution information of the second mold component is obtained until the deformation temperature threshold distribution information of the Nth mold component is obtained; the splicing temperature is optimized according to the deformation temperature threshold distribution information of the first mold component, the deformation temperature threshold distribution information of the second mold component until the deformation temperature threshold distribution information of the Nth mold component, and the splicing control temperature distribution information is obtained; the assembly control of the first mold component, the second mold component until the Nth mold component is performed according to the splicing control temperature distribution information. The technical problem that the docking accuracy error is large during the splicing of multiple parts of the injection mold of plastic parts and the instability of the splicing effect due to the lack of comprehensive consideration of environmental and other influencing factors is solved, and the splicing control temperature distribution is optimized by comprehensively considering the material, thickness, heat treatment temperature timing and other factors of the mold components, improving the docking accuracy of the mold component splicing, and ensuring the overall quality and dimensional accuracy of the injection mold. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0008] Figure 1 A schematic diagram of a process for manufacturing an injection mold for an automobile plastic component provided in an embodiment of the present application;

[0009] Figure 2 This is a schematic diagram of the structure of an injection mold manufacturing device for automobile plastic parts provided in an embodiment of the present application.

[0010] Explanation of the accompanying drawings: conceptual model acquisition module 1, three-dimensional modeling module 2, dimension verification module 3, component information acquisition module 4, first deformation temperature configuration module 5, second deformation temperature configuration module 6, splicing temperature optimization module 7, assembly control module 8. DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The present application provides a method for manufacturing an injection mold for automobile plastic parts, such as Figure 1 As shown, the method includes:

[0015] Obtain the first mold component concept model of the injection mold.

[0016] In an embodiment of the present application, the system terminal selects a standard model applicable to the component as a conceptual model based on industry standards and design specifications. This standard model is usually defined by relevant industry associations or internal company standards and represents the optimal design of the component. Subsequently, detailed data of the standard model is collected, including dimensions, material properties, geometry, and mechanical properties. Ensure that the selected standard model can be used as a benchmark to accurately reflect the design requirements and performance indicators of the component. Afterwards, use computer-aided design (CAD) software to digitize the standard model based on the collected data and create a first mold component conceptual model. This step ensures that the first mold component conceptual model can be used as a standard model in subsequent verification and comparison processes.

[0017] A three-dimensional modeling is performed on the first mold component of the injection mold to obtain a production model of the first mold component.

[0018] In one embodiment, the system terminal collects and organizes all design data related to the first mold component, including two-dimensional drawings, technical specifications, material requirements, tolerance ranges, etc. These data are the basis for three-dimensional modeling. Subsequently, CAD software is used to start modeling according to the design data to build a three-dimensional model. In the modeling process, the geometric shape, size, assembly relationship, etc. of the component are constructed according to the collected design data, and the components are processed in detail, such as chamfers, fillets, hole positions, threads, etc. These details have an important impact on the assembly, use and life of the mold. Afterwards, according to the design requirements, the material properties of the first mold component are set in the three-dimensional model, including the density, elastic modulus, thermal expansion coefficient, etc. of the material. These properties will affect the subsequent simulation analysis and processing parameters in the production process. Then, the three-dimensional model is used to perform simulation analysis, such as stress analysis, thermal analysis, flow analysis, etc., to verify the rationality and feasibility of the model. Through the simulation results, the model is adjusted and optimized as necessary. After repeated verification and optimization, the system terminal obtains the production model of the first mold component. This model contains all the design information and manufacturing requirements of the component, and is the direct basis for subsequent processing and manufacturing.

[0019] According to the first mold component conceptual model, the first mold component production model is dimensionally verified to obtain a first mold component dimension verification result.

[0020] In one embodiment, in the injection mold manufacturing process, based on the established first mold component conceptual model, the first mold component production model established by the system terminal is dimensionally verified. This process is a key step to ensure that the production model is highly consistent with the original design and meets the requirements of precise manufacturing. First, the system terminal imports the first mold component production model and the first mold component conceptual model into a pre-built dimension verification network. The dimension verification network uses the internal feature processing nodes to extract the corresponding dimension features from the first mold component production model and the first mold component conceptual model, respectively, and then uses the internal dimension feature descriptor comparison node to compare the dimension features of the first mold component production model with the dimension features of the first mold component conceptual model. After comprehensive dimension verification, the system terminal obtains the dimension verification result of the first mold component. This result directly reflects the degree of consistency between the first mold component production model and the first mold component conceptual model in terms of size, so as to ensure the accuracy and reliability of the first mold component production model, and provide a strong guarantee for subsequent processing and manufacturing and product quality.

[0021] Further, the present application provides performing dimension verification on the first mold component production model according to the first mold component conceptual model to obtain a first mold component dimension verification result, including:

[0022] The first feature processing node of the dimension verification network is used to perform feature processing on the conceptual model of the first mold component to obtain a conceptual model dimension feature descriptor set; the second feature processing node of the dimension verification network is used to perform feature processing on the production model of the first mold component to obtain a production model dimension feature descriptor set; the dimension feature descriptor comparison node of the dimension verification network is used to compare the conceptual model dimension feature descriptor set with the production model dimension feature descriptor set to obtain the first mold component dimension verification result.

[0023] Preferably, in the manufacturing process of the mold parts, in order to ensure the consistency of the dimensions between the first mold parts production model and the first mold parts conceptual model, the system terminal uses a dimension verification network constructed based on a twin neural network for accurate comparison and verification. Twin neural networks, as a special neural network structure, are suitable for processing the similarity or difference evaluation problem of paired data. First, the system terminal performs feature processing on the first mold parts conceptual model through the first feature processing node of the dimension verification network, that is, the first branch of the twin network. This step uses the powerful learning ability of the neural network to extract key dimension features from the first mold parts conceptual model and form a conceptual model dimension feature descriptor set. These conceptual model dimension feature descriptor sets are abstract representations of the first mold parts conceptual model in the dimension space. Subsequently, the same feature processing process is performed on the first mold parts production model through the second feature processing node of the dimension verification network, that is, the second branch of the twin network. This step also extracts the key dimension features of the production model and forms a production model dimension feature descriptor set. In this way, the system terminal obtains two sets of comparable descriptor sets in the same dimension. After extracting the two sets of descriptor sets, the two sets of descriptor sets are compared and analyzed through the size feature descriptor comparison node of the size verification network, that is, the comparison layer or decision layer of the twin network. The comparison process involves evaluating the degree of dimensional consistency between the first mold component production model and the first mold component concept model by analyzing the number of overlapping coordinates under different positioning postures of the feature description. After that, the size verification network outputs the size verification result of the first mold component according to the comparison result. If the similarity between the two sets of descriptors is greater than or equal to the similarity threshold, it is considered that the first mold component production model and the first mold component concept model are consistent in size, and the verification result is passed. Otherwise, it is considered that there is a size deviation, and the verification result is failed. By accurately evaluating the degree of dimensional consistency between the first mold component production model and the first mold component concept model, it provides strong support for subsequent processing and manufacturing and product quality control.

[0024] Among them, the first feature processing node and the second feature processing node are twin networks, and the output ends of the first feature processing node and the second feature processing node are connected to the input end of the size feature descriptor comparison node, and the first feature processing node and the second feature processing node work in parallel.

[0025] Preferably, in the dimension verification process of the mold parts, the system terminal uses a twin network to construct a dimension verification network. This network consists of two parallel feature processing nodes, namely, a first feature processing node and a second feature processing node. The two nodes have the same structure and function, but they process different input data, namely, the first mold part concept model and the first mold part production model. The two feature processing nodes work independently to extract and process the features of their respective input data. They extract key dimension information from the original data through a complex neural network layer and convert this information into a format that is easier to compare and understand, namely, a dimension feature descriptor. When both feature processing nodes have completed their corresponding work, they will input their generated dimension feature descriptors into a dimension feature descriptor comparison node. This comparison node is a comparison layer or decision layer, which is responsible for comparing the similarity or difference of two descriptor sets, wherein the input end of the comparison layer or decision layer is connected to the output end of the two feature processing nodes. By calculating the similarity between them, the comparison node can evaluate the degree of consistency in size between the first mold part production model and the first mold part concept model.

[0026] When constructing the dimension verification network, the system terminal first collects a large amount of mold component data, including multiple sample concept models and multiple sample production models corresponding to each sample concept model, as well as multiple sample dimension feature descriptor sets of these sample concept models and sample production models, where each sample concept model corresponds to multiple sample production models. These data will be divided into the training set, validation set and test set of the network. Subsequently, based on the idea of ​​the twin network, two parallel feature processing nodes are designed, i.e., two parts of the twin network, each node is responsible for processing a type of model. In each feature processing node, a multi-layer convolutional neural network (CNN) or other types of feature extraction layers are designed to extract key dimension features from the input data. These features can characterize the abstract representation of the model dimension information. A comparison layer or decision layer is then designed to receive the outputs of the two feature processing nodes and calculate the similarity or distance between them. This layer has a built-in comparison algorithm, which is pre-set and can analyze the number of overlapping coordinates of the feature descriptor under different positioning postures and calculate the dimension similarity. After that, the system terminal randomly initializes the weights and biases of the size verification network, and the two feature processing nodes have the same weights and biases, and then sets appropriate hyperparameters such as learning rate, batch size, and training rounds. After the size verification network is initialized, each pair of sample concept models and sample production models in the training set are input into the two feature processing nodes respectively. The feature vectors are calculated layer by layer in the two feature processing nodes to obtain the corresponding size feature description subsets. Then, the system terminal uses the mean square error loss to calculate the loss value of the concept model size feature description subset and the production model size feature description subset with the corresponding sample size feature description subset, and then uses the back propagation algorithm to calculate the gradient of the loss value to the network parameters, and updates the weights and biases of the network according to the gradient to minimize the loss value. After each training round, the performance of the two feature processing nodes is evaluated using the validation set, and the performance of the two feature processing nodes on the validation set is checked. If overfitting occurs, the hyperparameters are adjusted, such as reducing the learning rate, increasing the regularization term, or using the early stopping strategy. Repeat the process of forward propagation, loss calculation, back propagation, and verification adjustment until the preset training round is reached or the validation set performance no longer improves. After the training is completed, the two trained feature processing nodes are tested using the test set to evaluate the performance on unknown data and calculate indicators such as accuracy and recall. The deficiencies of the two feature processing nodes are analyzed based on the test results, and further optimization and improvement are performed, for example, changing the feature extraction method to improve the performance of the model. Finally, the system terminal connects the output ends of the two feature processing nodes whose accuracy is greater than or equal to the preset accuracy to the input ends of the comparison layer or decision layer constructed based on the comparison algorithm to construct a size verification network.

[0027] Furthermore, the present application provides a method of comparing the conceptual model dimension feature description subset with the production model dimension feature description subset through a dimension feature description subset comparison node of a dimension verification network to obtain the first mold component dimension verification result, including:

[0028] The first mold component conceptual model and the first mold component production model are rotationally edge aligned in a virtual positioning space to obtain a conceptual model alignment posture and a production model alignment posture; a first coordinate label set of the conceptual model size feature description subset in the conceptual model alignment posture is obtained; and a second coordinate label set of the production model size feature description subset in the production model alignment posture is obtained.

[0029] Optionally, during the dimension verification process of the mold parts, the system terminal processes the obtained first mold part conceptual model and the first mold part production model in the virtual positioning space in the comparison layer or decision layer to ensure that they can be compared from the same perspective or direction. This process includes rotating the two models so that their edges or key features are aligned, thereby obtaining the alignment posture of the two models, namely the conceptual model alignment posture and the production model alignment posture. Subsequently, for the aligned models, the system terminal will associate the conceptual model dimension feature description subset and the production model dimension feature description subset transmitted to the comparison layer or decision layer at the same time with the aligned first mold part conceptual model and the first mold part production model, respectively, and then extract the coordinates corresponding to these features to obtain the first coordinate label set and the second coordinate label set, which facilitates the subsequent dimension verification.

[0030] The proportion of the number of overlapping coordinates of the first coordinate label set and the second coordinate label set is counted, and is set as the first alignment posture size similarity; the alignment postures are enumerated in the virtual positioning space to obtain the second alignment posture size similarities until the Mth alignment posture size similarity; when the maximum value of the first alignment posture size similarity, the second alignment posture size similarity, and the Mth alignment posture size similarity is greater than or equal to the similarity threshold, the first mold component size verification result is verification passed; when the maximum value of the first alignment posture size similarity, the second alignment posture size similarity, and the Mth alignment posture size similarity is less than the similarity threshold, the first mold component size verification result is verification failed.

[0031] Optionally, after obtaining the first coordinate label set and the second coordinate label set, the system terminal counts the number of coordinates that overlap in the first coordinate label set and the second coordinate label set, and then calculates the proportion of these coordinates to the total coordinates, and uses the calculated proportion as the first alignment posture size similarity. Subsequently, in the virtual positioning space, the conceptual model and the production model of the first mold component are enumerated for multiple alignment postures. For each alignment posture, the coordinate label sets of the conceptual model and the production model size feature descriptor set are obtained respectively, and the proportion of the number of overlapping coordinates in the two sets is counted to obtain the size similarity under the alignment posture. Through this process, the system terminal obtains M alignment posture size similarities. This similarity calculation method avoids the redundant calculations that may exist in the traditional size comparison method, and evaluates the size similarity by directly analyzing the number of overlapping coordinates of the feature descriptor, thereby greatly reducing the computing power requirements. Afterwards, the maximum value of the size similarity is found in all the enumerated alignment postures. If this maximum value is greater than or equal to the preset similarity threshold, the system terminal determines that the size verification result of the first mold component is passed, that is, the conceptual model and the production model are consistent or close enough in size. On the contrary, if the maximum value is less than the similarity threshold, the verification result is a failure, indicating that there is a significant difference in size between the two. This method does not rely solely on a single alignment posture for size verification, but improves the accuracy and robustness of the verification by enumerating multiple alignment postures and finding the optimal solution. At the same time, by directly analyzing the number of overlapping coordinates of feature descriptors to evaluate size similarity, the computational complexity is effectively reduced, making the entire verification process more efficient.

[0032] When the first mold component dimension verification result is verification passed, the first mold component material information, the first mold component thickness analysis information and the first mold component heat treatment record temperature timing information are obtained.

[0033] In one embodiment, when the dimension verification result of the first mold component is displayed as passed, it means that the mold component meets or is close to the expected standard in terms of key dimensions and meets the preliminary design and production requirements. Subsequently, in order to evaluate the comprehensive performance and quality of the mold component, the system terminal will obtain and organize other important information related to the component, including the material information of the first mold component, the thickness analysis information of the first mold component, and the time series information of the heat treatment record temperature of the first mold component. Among them, the material information of the first mold component refers to the key data such as the specific material type, component ratio, material performance, etc. used to manufacture the mold component. These material information are crucial for understanding the durability, wear resistance, corrosion resistance, etc. of the component. The thickness analysis information of the first mold component involves the thickness information of different parts of the component. Through the thickness distribution of the component, its structural strength, stress distribution and possible weak points can be understood, so as to ensure that the component can withstand the expected load and deformation during use. The time series information of the heat treatment record temperature of the first mold component records the detailed data of the temperature change of the component over time during the heat treatment process. Through these temperature timing information, we can understand the execution of the heat treatment process, including key parameters such as heating rate, holding time, cooling method, and then evaluate the impact of heat treatment on component performance.

[0034] Furthermore, the present application also includes:

[0035] When the first mold component dimension verification result is verification failure, a dimension deviation area is obtained; the first mold component is dimensionally abnormally marked according to the dimension deviation area, and the first mold component dimension abnormality marking result is obtained and sent to the user end.

[0036] Preferably, when the dimension verification result of the first mold component fails, it means that the component does not meet the expected standard in terms of size. In order to clarify the problem and take corresponding solutions, the system terminal calculates the distance between the corresponding coordinates, and adds a pair of coordinates whose distance is greater than or equal to the preset difference distance to the dimension deviation area. Repeating this process, the system terminal obtains a complete dimension deviation area, and then the system terminal marks the dimension anomaly of the first mold component according to the coordinates in the dimension deviation area. This identification is presented in a visual way, for example, highlighting the deviation area on the production model of the first mold component. After completing the dimension anomaly identification, the system terminal will send this result to the user terminal in a timely manner, and clearly present the problem to the user, so that timely measures can be taken to solve the problem, ensuring the smooth progress of the production process and the stability and reliability of product quality.

[0037] The deformation temperature is configured according to the material information of the first mold component, the thickness distribution information of the first mold component and the temperature timing information recorded during the heat treatment of the first mold component to obtain the deformation temperature threshold distribution information of the first mold component.

[0038] In one embodiment, when processing the first mold component, the system terminal collects deformation transactions based on the material information of the first mold component, the thickness distribution information of the first mold component, and the time sequence information of the heat treatment recorded temperature of the first mold component, and obtains multiple deformation temperature monitoring record values ​​and multiple deformation temperature duration record values ​​with similar thickness, the same material, and similar heat treatment process parameters. Subsequently, according to the obtained multiple deformation temperature monitoring record values ​​and multiple deformation temperature duration record values, a logical AND relationship is configured to generate multiple partition deformation temperature thresholds, and then according to the obtained partition deformation temperature thresholds, a logical OR relationship is configured to construct the first mold component deformation temperature threshold distribution information, so that the temperature conditions can be controlled more accurately to avoid deformation or damage of the components due to excessive temperature, so as to ensure that they can maintain excellent performance and stability under various conditions.

[0039] Further, the present application provides a method for configuring deformation temperature according to the material information of the first mold component, the thickness distribution information of the first mold component, and the temperature timing information of the heat treatment record of the first mold component to obtain the deformation temperature threshold distribution information of the first mold component, including:

[0040] According to the thickness distribution information of the first mold component, the first mold component is partitioned based on the thickness deviation threshold to obtain the first mold component thickness partition result; according to the first mold component thickness partition result, the first partition thickness is extracted; based on the first partition thickness, the first mold component material information and the first mold component heat treatment record temperature timing information, deformation transactions are collected to obtain deformation temperature monitoring record values ​​and deformation temperature duration record values, wherein the deformation size of any deformation transaction is greater than or equal to the deformation size threshold, and the deformation size threshold is the maximum size deviation allowed by the mold.

[0041] Preferably, when processing the first mold component, the system terminal compares the first mold component thickness distribution information of the first mold component with the set thickness deviation threshold, and partitions the first mold component, so as to better understand the performance changes caused by thickness differences in different regions, especially deformation behavior. Among them, the thickness deviation threshold is determined according to the component characteristics, usage requirements and industry standards. Through partitioning, the system terminal obtains the thickness partition result of the first mold component, which provides a basis for subsequent analysis. Subsequently, the system terminal randomly extracts a partition from the first mold component thickness partition result as the first partition thickness. This step is to analyze the deformation characteristics of the region under specific conditions in a targeted manner. The system terminal collects deformation transactions based on the thickness of the first partition, the material information of the first mold component and the temperature timing information of the heat treatment record of the first mold component. Deformation transactions refer to dimensional change events that occur in components under specific conditions (such as temperature, pressure, etc.). In all deformation transactions, the deformation size of the collected deformation transactions is greater than or equal to the deformation size threshold, because only when the deformation size in the deformation transaction is greater than or equal to this threshold, it will be regarded as a valid deformation record, wherein the deformation size threshold is the maximum size deviation allowed by the mold. Afterwards, in order to ensure that the collected deformation events are representative, the system terminal selects materials with similar thickness, the same material and similar heat treatment process parameters from the deformation events that meet the deformation size threshold for data monitoring and collection, and obtains the deformation temperature monitoring record value and the deformation temperature duration record value. These two indicators reflect the degree and duration of deformation of parts under specific temperature conditions.

[0042] The one-to-one corresponding deformation temperature monitoring record values ​​and the deformation temperature duration record values ​​are configured as a logical AND relationship to construct a first partition deformation temperature threshold; a logical OR relationship is configured for the first partition deformation temperature threshold, the second partition deformation temperature threshold, and the Hth partition deformation temperature threshold to generate the first mold component deformation temperature threshold distribution information.

[0043] Preferably, after obtaining the deformation temperature monitoring record value and deformation temperature duration record value of the first partition thickness, the system terminal performs cluster analysis on the deformation temperature monitoring record value based on the deformation temperature deviation threshold, and then divides the deformation temperature duration record value according to the clustering result to obtain the duration record value corresponding to each cluster cluster. Subsequently, outlier analysis is performed on all cluster clusters and all divided duration record values, and multiple deformation temperature distribution intervals and multiple deformation duration thresholds are constructed, and then these deformation temperature distribution intervals and deformation duration thresholds are configured as logical and relationships to obtain multiple deformation temperature thresholds. Afterwards, a logical or relationship is configured for these deformation temperature thresholds to obtain the first partition deformation temperature threshold. Only when the monitored temperature reaches a certain deformation temperature distribution interval and the duration of this temperature also meets the corresponding deformation duration threshold, the deformation state of the partition is determined to meet the set first mold component deformation temperature threshold. For other partitions in the first mold component thickness partition result, such as the second partition, the third partition, and up to the Hth partition, the system terminal uses the same method as above to construct their respective deformation temperature thresholds. Then, the deformation temperature thresholds of all partitions are integrated by configuring logic or relationships to generate the first mold component deformation temperature threshold distribution information. In summary, the accuracy and effectiveness of the mold component deformation temperature threshold determination are ensured through the above-mentioned partition management and logic condition setting.

[0044] Furthermore, the present application provides configuring the one-to-one corresponding deformation temperature monitoring record values ​​and the deformation temperature duration record values ​​into a logical AND relationship to construct a first partition deformation temperature threshold, including:

[0045] Based on the deformation temperature deviation threshold, the deformation temperature monitoring record values ​​are clustered and analyzed to obtain multiple clusters of deformation temperature monitoring record values; the deformation temperature duration record values ​​are grouped according to the multiple clusters of deformation temperature monitoring record values ​​to obtain multiple clusters of deformation temperature duration record values.

[0046] Optionally, the system terminal defines a neighborhood distance threshold ε based on a preset deformation temperature deviation threshold, and then determines the minimum number of points MinPts required to form a dense area according to actual needs. A point is considered a core point if its ε-neighborhood contains at least MinPts points. Among them, the deformation temperature deviation threshold is determined based on material properties, plastic processing requirements and historical experience. Subsequently, the system terminal marks all points in the deformation temperature monitoring record value as unvisited, and randomly selects an unvisited point as the starting point, and then calculates the number of points in the ε-neighborhood of the point by Euclidean distance. If the number of points in the ε-neighborhood is less than MinPts, the point is marked as a noise point. If the number of points in the ε-neighborhood is greater than or equal to MinPts, the point is marked as a core point and a new cluster is created. After that, all unvisited points in its ε-neighborhood are recursively added to the cluster, and the ε-neighborhood of these points is continued to be searched until no more points can be added to the cluster. Repeat the above process until all points are visited and marked as part of the cluster or noise points. After clustering, the system terminal obtains a series of clusters and noise points. Each cluster contains a set of points that are mutually reachable within the ε distance and have similar deformation temperature characteristics. These clusters will together constitute multiple clusters of deformation temperature monitoring record values. Then, according to the obtained multiple clusters of deformation temperature monitoring record values, the deformation temperature duration record values ​​are grouped, that is, the duration record values ​​corresponding to the deformation temperature monitoring record values ​​belonging to the same cluster are grouped together to form multiple clusters of deformation temperature duration record values. Such processing and analysis helps to gain a deeper understanding of the deformation behavior of mold parts under different conditions and provide an important basis for subsequent optimization design.

[0047] The multiple clusters of deformation temperature monitoring record values ​​are traversed to perform outlier analysis and construct multiple deformation temperature distribution intervals; the multiple clusters of deformation temperature duration record values ​​are traversed to perform outlier analysis, and the minimum value of the deformation temperature duration record values ​​in the multiple clusters is extracted to obtain multiple deformation duration thresholds; the multiple deformation temperature distribution intervals and the multiple deformation duration thresholds corresponding to each other are configured as a logical AND relationship to generate multiple deformation temperature thresholds; the multiple deformation temperature thresholds are configured with a logical OR relationship to generate the first partition deformation temperature threshold.

[0048] Optionally, for the multi-cluster deformation temperature monitoring record values ​​obtained by cluster analysis, outlier analysis is performed. This step is to exclude those abnormal or extreme data points to ensure that the subsequent analysis is based on representative and stable temperature data. Specifically, the system terminal uses methods such as Z-score and IQR (interquartile range) to identify outliers. The Z-score method identifies outliers by calculating the distance (in standard deviation) between each data point and the mean; the IQR method calculates the range (IQR) between the first quartile (Q1) and the third quartile (Q3), and defines points that exceed this range by a certain multiple (such as 1.5 times or 3 times IQR) as outliers. After the outlier analysis, for each cluster of data, its deformation temperature distribution interval is constructed, which reflects the temperature fluctuation of the cluster data within the normal deformation range. Similarly, the multi-cluster deformation temperature duration record values ​​are also subjected to outlier analysis, with the aim of removing those data points with abnormally long or short durations, which may not represent normal deformation behavior. Subsequently, for each cluster, the minimum value of the duration record after removing outliers is extracted as the deformation duration threshold of the cluster. This threshold represents the shortest duration required for the mold parts to deform under this cluster. After that, the deformation temperature distribution interval of each cluster and the corresponding deformation duration threshold are configured as a logical AND relationship. This means that only when the deformation temperature falls within the specified distribution interval and the duration is greater than or equal to the corresponding duration threshold, it is judged to be a valid deformation event. In this way, a specific deformation temperature threshold is generated for each cluster of data, which takes into account both temperature and time. Then, the system terminal configures the deformation temperature thresholds of all clusters as a logical OR relationship to generate the first partition deformation temperature threshold. This first partition deformation temperature threshold is a comprehensive indicator. As long as the deformation temperature and duration of the mold parts meet the threshold conditions of any cluster, it is judged that a deformation event may have occurred. Such a design enables more flexible and comprehensive response to deformation under different conditions.

[0049] Traverse the second mold component until the Nth mold component, and obtain the deformation temperature threshold distribution information of the second mold component until the Nth mold component.

[0050] In one embodiment, the system terminal traverses the remaining parts from the injection mold, including the second mold part to the Nth mold part, and uses the same operation as the first mold part to determine the deformation temperature threshold distribution information of the second mold part to the Nth mold part for subsequent splicing temperature optimization.

[0051] The splicing temperature is optimized according to the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and the Nth mold component deformation temperature threshold distribution information to obtain the splicing control temperature distribution information.

[0052] In one embodiment, in order to splice together a plurality of such mold parts and ensure the stability of the overall structural performance after splicing, the system terminal needs to find a suitable splicing control temperature range. This range will not trigger the deformation of any single component, and can ensure that the thermal stress in the splicing process is reasonably controlled, thereby avoiding cracks, dislocations or other quality problems. In order to achieve this goal, the system terminal performs a logical or relationship on the deformation temperature threshold distribution information of all mold parts to obtain the splicing deformation temperature threshold. Subsequently, the system terminal optimizes the splicing control temperature distribution information based on the genetic algorithm and the splicing deformation temperature threshold until the splicing control temperature distribution information no longer triggers the splicing deformation temperature threshold.

[0053] Further, the present application provides a method for optimizing the splicing temperature according to the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and the Nth mold component deformation temperature threshold distribution information to obtain the splicing control temperature distribution information, including:

[0054] A logic or relationship is configured for the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and up to the Nth mold component deformation temperature threshold distribution information to generate a splicing deformation temperature threshold; when the splicing deformation temperature threshold is not triggered, the splicing control temperature distribution information is output.

[0055] Preferably, in order to ensure that all mold parts involved in the splicing will not be deformed due to excessively high or low temperatures, the system terminal uses a logical or relationship to configure the first mold part deformation temperature threshold distribution information, the second mold part deformation temperature threshold distribution information, and the Nth mold part deformation temperature threshold distribution information to generate a splicing deformation temperature threshold. The purpose of this is to ensure that during the splicing process, no matter which part is in what state, as long as the operating temperature does not exceed the splicing deformation temperature threshold, the deformation of any part will not be triggered. Subsequently, the system terminal randomly generates a certain number of individuals, each of which represents a set of splicing control temperature values. A fitness function is then designed to evaluate the quality of each individual. This function can reflect whether the splicing control temperature value meets the requirements of the splicing deformation temperature threshold. For example, the fitness function can be a weighted sum, and the weight is used to punish the temperature value that exceeds the splicing deformation temperature threshold. Afterwards, according to the result of the fitness function, a part of excellent individuals is selected as the parent generation of the next generation. The selected parent individuals are crossover and mutation operations are performed to generate new child individuals. Selection, crossover, mutation and fitness evaluation are repeated until the splicing deformation temperature threshold is not triggered. When the splicing deformation temperature threshold is not triggered, it means that in actual operation, the temperature value represented by the splicing control temperature distribution information always remains within the safe range of the splicing deformation temperature threshold, and will not cause any parts to deform. At this time, the system terminal determines that the optimization is successful and outputs the splicing control temperature distribution information as the final optimization result. This optimization result will guide the subsequent mold splicing process to ensure the high efficiency of production and the high quality of products.

[0056] The assembly control of the first mold component, the second mold component, and up to the Nth mold component is performed according to the splicing control temperature distribution information.

[0057] In one embodiment, the system terminal performs assembly control on N parts in the mold splicing process according to the splicing control temperature distribution information obtained after optimization. This splicing control temperature distribution information provides the system terminal with a set of temperature values, which are the optimal temperature settings calculated by the optimization algorithm under the premise of ensuring that the deformation temperature threshold of any parts is not triggered. In actual operation, the system terminal will adjust and control the heating or cooling system according to these temperature values ​​to ensure that each mold part can be stably controlled and maintained within its specific temperature range during the splicing process. In this way, not only can the deformation of parts caused by excessively high or low temperatures be prevented, but other aspects of the splicing process can also be optimized, such as improving splicing efficiency, reducing energy consumption, and enhancing splicing quality. In summary, by applying the splicing control temperature distribution information, accurate, efficient and safe assembly control between mold parts can be achieved.

[0058] In the above, refer to Figure 1 The present invention is described in detail in detail. Figure 2 An apparatus for manufacturing an injection mold for an automobile plastic component according to an embodiment of the present invention is described.

[0059] The manufacturing device for injection molds of automobile plastic parts according to the embodiment of the present invention solves the technical problems that the docking accuracy error is large during the splicing process of multiple parts of the injection mold of plastic parts, and the splicing effect is unstable due to the failure to fully consider the influencing factors such as the environment, and achieves the effect of optimizing the splicing control temperature distribution by comprehensively considering the materials, thickness, heat treatment temperature sequence and other factors of the mold parts, improving the docking accuracy of the splicing of the mold parts, and ensuring the overall quality and dimensional accuracy of the injection mold. The manufacturing device for injection molds of automobile plastic parts includes: a concept model acquisition module 1, a three-dimensional modeling module 2, a dimension verification module 3, a component information acquisition module 4, a first deformation temperature configuration module 5, a second deformation temperature configuration module 6, a splicing temperature optimization module 7, and an assembly control module 8.

[0060] Concept model acquisition module 1: the concept model acquisition module 1 is used to obtain a first mold component concept model of the injection mold;

[0061] Three-dimensional modeling module 2: the three-dimensional modeling module 2 is used to perform three-dimensional modeling on the first mold component of the injection mold to obtain a production model of the first mold component;

[0062] Dimension verification module 3: the dimension verification module 3 is used to perform dimension verification on the first mold component production model according to the first mold component conceptual model to obtain the first mold component dimension verification result;

[0063] Component information acquisition module 4: the component information acquisition module 4 is used to obtain the first mold component material information, the first mold component thickness analysis information and the first mold component heat treatment record temperature timing information when the first mold component dimension verification result is verification passed;

[0064] First deformation temperature configuration module 5: The first deformation temperature configuration module 5 is used to configure the deformation temperature according to the material information of the first mold component, the thickness distribution information of the first mold component and the temperature timing information recorded during the heat treatment of the first mold component, and obtain the deformation temperature threshold distribution information of the first mold component;

[0065] Second deformation temperature configuration module 6: The second deformation temperature configuration module 6 is used to traverse the second mold component until the Nth mold component, and obtain the deformation temperature threshold distribution information of the second mold component until the Nth mold component;

[0066] Splicing temperature optimization module 7: the splicing temperature optimization module 7 is used to optimize the splicing temperature according to the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and the Nth mold component deformation temperature threshold distribution information to obtain splicing control temperature distribution information;

[0067] Assembly control module 8: The assembly control module 8 is used to perform assembly control of the first mold component, the second mold component, and up to the Nth mold component according to the splicing control temperature distribution information.

[0068] Furthermore, the size verification module 3 also includes:

[0069] The first mold component conceptual model is feature processed by the first feature processing node of the dimension verification network to obtain the conceptual model dimension feature descriptor set; the first mold component production model is feature processed by the second feature processing node of the dimension verification network to obtain the production model dimension feature descriptor set; the conceptual model dimension feature descriptor set is compared with the production model dimension feature descriptor set by the dimension feature descriptor comparison node of the dimension verification network to obtain the first mold component dimension verification result; wherein the first feature processing node and the second feature processing node are twin networks, and the output ends of the first feature processing node and the second feature processing node are connected to the input end of the dimension feature descriptor comparison node, and the first feature processing node and the second feature processing node work in parallel.

[0070] Furthermore, the size verification module 3 also includes:

[0071] The first mold component conceptual model and the first mold component production model are rotationally aligned in the virtual positioning space to obtain the conceptual model alignment posture and the production model alignment posture; the first coordinate label set of the conceptual model dimension feature description subset in the conceptual model alignment posture is obtained; the second coordinate label set of the production model dimension feature description subset in the production model alignment posture is obtained; the proportion of the number of overlapping coordinates between the first coordinate label set and the second coordinate label set is counted, and set as the first alignment posture dimension similarity; the alignment postures are enumerated in the virtual positioning space to obtain the second alignment posture dimension similarity until the Mth alignment posture dimension similarity; when the maximum value of the first alignment posture dimension similarity, the second alignment posture dimension similarity until the Mth alignment posture dimension similarity is greater than or equal to the similarity threshold, the first mold component dimension verification result is verification passed; when the maximum value of the first alignment posture dimension similarity, the second alignment posture dimension similarity until the Mth alignment posture dimension similarity is less than the similarity threshold, the first mold component dimension verification result is verification failed.

[0072] Furthermore, the component information acquisition module 4 also includes:

[0073] When the first mold component dimension verification result is verification failure, a dimension deviation area is obtained; the first mold component is dimensionally abnormally marked according to the dimension deviation area, and the first mold component dimension abnormality marking result is obtained and sent to the user end.

[0074] Furthermore, the first deformation temperature configuration module 5 also includes:

[0075] According to the thickness distribution information of the first mold component, the first mold component is partitioned based on the thickness deviation threshold to obtain the first mold component thickness partition result; according to the first mold component thickness partition result, the first partition thickness is extracted; based on the first partition thickness, the first mold component material information and the first mold component heat treatment record temperature timing information, deformation transaction collection is performed to obtain deformation temperature monitoring record value and deformation temperature duration record value, wherein the deformation size of any deformation transaction is greater than or equal to the deformation size threshold, and the deformation size threshold is the maximum size deviation allowed by the mold; the one-to-one corresponding deformation temperature monitoring record value and the deformation temperature duration record value are configured as a logical AND relationship to construct a first partition deformation temperature threshold; 6 configure a logical OR relationship for the first partition deformation temperature threshold, the second partition deformation temperature threshold until the Hth partition deformation temperature threshold, and generate the first mold component deformation temperature threshold distribution information.

[0076] Furthermore, the first deformation temperature configuration module 5 also includes:

[0077] Based on the deformation temperature deviation threshold, the deformation temperature monitoring record values ​​are clustered and analyzed to obtain multiple clusters of deformation temperature monitoring record values; the deformation temperature duration record values ​​are grouped according to the multiple clusters of deformation temperature monitoring record values ​​to obtain multiple clusters of deformation temperature duration record values; the multiple clusters of deformation temperature monitoring record values ​​are traversed to perform outlier analysis to construct multiple deformation temperature distribution intervals; the multiple clusters of deformation temperature duration record values ​​are traversed to perform outlier analysis, and the minimum value of the deformation temperature duration record values ​​in the multiple clusters is extracted to obtain multiple deformation duration thresholds; the multiple deformation temperature distribution intervals and the multiple deformation duration thresholds corresponding to each other are configured as a logical AND relationship to generate multiple deformation temperature thresholds; a logical OR relationship is configured for the multiple deformation temperature thresholds to generate the first partition deformation temperature threshold.

[0078] Furthermore, the splicing temperature optimization module 7 also includes:

[0079] A logic or relationship is configured for the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and up to the Nth mold component deformation temperature threshold distribution information to generate a splicing deformation temperature threshold; when the splicing deformation temperature threshold is not triggered, the splicing control temperature distribution information is output.

[0080] The automobile plastic parts injection mold manufacturing device provided in the embodiment of the present invention can execute the automobile plastic parts injection mold manufacturing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0081] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0082] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for manufacturing an injection mold for automobile plastic parts, characterized in that: include: Obtaining a first mold component conceptual model of the injection mold, wherein the first mold component conceptual model is a standard model suitable for the first mold component selected according to industry standards and design specifications; Performing three-dimensional modeling on the first mold component of the injection mold to obtain a production model of the first mold component; According to the first mold component conceptual model, the first mold component production model is dimensionally verified to obtain a first mold component dimension verification result; When the first mold component dimension verification result is verification passed, obtaining the first mold component material information, the first mold component thickness analysis information and the first mold component heat treatment record temperature time sequence information; Perform deformation temperature configuration according to the material information of the first mold component, the thickness distribution information of the first mold component, and the temperature timing information recorded during heat treatment of the first mold component to obtain the deformation temperature threshold distribution information of the first mold component; Traversing the second mold component until the Nth mold component, obtaining the deformation temperature threshold distribution information of the second mold component until the Nth mold component; Optimize the splicing temperature according to the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and up to the Nth mold component deformation temperature threshold distribution information to obtain splicing control temperature distribution information; The assembly control of the first mold component, the second mold component, and up to the Nth mold component is performed according to the splicing control temperature distribution information.

2. The method for manufacturing an injection mold for an automobile plastic component according to claim 1, characterized in that: Also includes: When the dimension verification result of the first mold component is failure to pass the verification, a dimension deviation area is obtained; The first mold component is marked for dimensional anomaly according to the dimensional deviation area, and a result of the dimensional anomaly marking of the first mold component is obtained and sent to a user end.

3. The method for manufacturing an injection mold for an automobile plastic part according to claim 1, characterized in that: According to the first mold component conceptual model, the first mold component production model is dimensionally verified to obtain the first mold component dimension verification result, including: Performing feature processing on the first mold component conceptual model through a first feature processing node of a dimension verification network to obtain a conceptual model dimension feature descriptor set; Performing feature processing on the first mold component production model through a second feature processing node of the dimension verification network to obtain a production model dimension feature descriptor set; Comparing the conceptual model dimensional feature descriptor set with the production model dimensional feature descriptor set through a dimensional feature descriptor comparison node of a dimensional verification network to obtain a dimensional verification result of the first mold component; Among them, the first feature processing node and the second feature processing node are twin networks, and the output ends of the first feature processing node and the second feature processing node are connected to the input end of the size feature descriptor comparison node, and the first feature processing node and the second feature processing node work in parallel.

4. The method for manufacturing an injection mold for an automobile plastic component according to claim 3, characterized in that: The dimension feature descriptor comparison node of the dimension verification network compares the dimension feature descriptor set of the conceptual model with the dimension feature descriptor set of the production model to obtain the dimension verification result of the first mold component, including: Performing rotational edge alignment on the first mold component conceptual model and the first mold component production model in a virtual positioning space to obtain a conceptual model alignment posture and a production model alignment posture; Obtain a first coordinate label set of the conceptual model size feature descriptor set in the conceptual model alignment posture; Obtain a second coordinate label set of the production model size feature descriptor set in the production model alignment posture; Counting the proportion of the number of overlapping coordinates between the first coordinate label set and the second coordinate label set, and setting it as the first alignment posture size similarity; Enumerate the alignment postures in the virtual positioning space, and obtain the second alignment posture size similarity until the Mth alignment posture size similarity; When the maximum value of the first alignment posture dimension similarity, the second alignment posture dimension similarity, and the Mth alignment posture dimension similarity is greater than or equal to the similarity threshold, the first mold component dimension verification result is verification passed; When the maximum value of the first alignment posture dimension similarity, the second alignment posture dimension similarity, and even the Mth alignment posture dimension similarity is less than the similarity threshold, the first mold component dimension verification result is verification failure.

5. The method for manufacturing an injection mold for an automobile plastic component according to claim 1, wherein: Deformation temperature configuration is performed according to the material information of the first mold component, the thickness distribution information of the first mold component, and the temperature timing information of the heat treatment record of the first mold component to obtain the deformation temperature threshold distribution information of the first mold component, including: Partitioning the first mold component based on the thickness distribution information of the first mold component and the thickness deviation threshold to obtain a first mold component thickness partitioning result; Extracting the thickness of the first partition according to the thickness partition result of the first mold component; Deformation events are collected based on the thickness of the first partition, the material information of the first mold component, and the time series information of the heat treatment recorded temperature of the first mold component, to obtain deformation temperature monitoring record values ​​and deformation temperature duration record values, wherein the deformation size of any deformation event is greater than or equal to a deformation size threshold, and the deformation size threshold is the maximum size deviation allowed by the mold; The deformation temperature monitoring record values ​​and the deformation temperature duration record values ​​corresponding to each other are configured as a logical AND relationship to construct a first partition deformation temperature threshold; A logical or relationship is configured for the first partition deformation temperature threshold, the second partition deformation temperature threshold, and up to the Hth partition deformation temperature threshold to generate the first mold component deformation temperature threshold distribution information.

6. The method for manufacturing an injection mold for an automobile plastic component according to claim 5, characterized in that: The one-to-one corresponding deformation temperature monitoring record values ​​and the deformation temperature duration record values ​​are configured as a logical AND relationship to construct a first partition deformation temperature threshold, including: Based on the deformation temperature deviation threshold, cluster analysis is performed on the deformation temperature monitoring record values ​​to obtain multiple clusters of deformation temperature monitoring record values; The deformation temperature duration record values ​​are grouped according to the multiple clusters of deformation temperature monitoring record values ​​to obtain multiple clusters of deformation temperature duration record values; Traversing the multiple clusters of deformation temperature monitoring record values ​​to perform outlier analysis and construct multiple deformation temperature distribution intervals; Traversing the multiple clusters of deformation temperature duration record values ​​to perform outlier analysis, and respectively extracting the minimum value of the deformation temperature duration record values ​​in the multiple clusters to obtain multiple deformation duration thresholds; The multiple deformation temperature distribution intervals and the multiple deformation time thresholds corresponding to each other are configured as a logical AND relationship to generate multiple deformation temperature thresholds; A logical OR relationship is configured for the plurality of deformation temperature thresholds to generate the first partition deformation temperature threshold.

7. The method for manufacturing an injection mold for an automobile plastic component according to claim 1, wherein: The splicing temperature optimization is performed according to the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and the Nth mold component deformation temperature threshold distribution information to obtain the splicing control temperature distribution information, including: Configuring a logic or relationship for the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and up to the Nth mold component deformation temperature threshold distribution information to generate a splicing deformation temperature threshold; When the splicing deformation temperature threshold is not triggered, the splicing control temperature distribution information is output.

8. An injection mold manufacturing device for automobile plastic parts, characterized in that: The device is used to implement the method for manufacturing an injection mold for an automobile plastic component according to any one of claims 1 to 7, comprising: Concept model acquisition module: obtains the first mold component concept model of the injection mold; Three-dimensional modeling module: performing three-dimensional modeling on the first mold component of the injection mold to obtain a production model of the first mold component; Dimension verification module: performing dimension verification on the production model of the first mold component according to the conceptual model of the first mold component to obtain the dimension verification result of the first mold component; Component information acquisition module: when the dimension verification result of the first mold component is verified to be passed, the material information of the first mold component, the thickness analysis information of the first mold component and the time sequence information of the heat treatment record temperature of the first mold component are obtained; A first deformation temperature configuration module: configures the deformation temperature according to the material information of the first mold component, the thickness distribution information of the first mold component and the temperature timing information recorded during the heat treatment of the first mold component, and obtains the deformation temperature threshold distribution information of the first mold component; The second deformation temperature configuration module: traverses the second mold component until the Nth mold component, and obtains the deformation temperature threshold distribution information of the second mold component until the deformation temperature threshold distribution information of the Nth mold component; A splicing temperature optimization module: performs splicing temperature optimization according to the first mold component deformation temperature threshold distribution information, the second mold component deformation temperature threshold distribution information, and the Nth mold component deformation temperature threshold distribution information to obtain splicing control temperature distribution information; Assembly control module: performs assembly control of the first mold component, the second mold component, and up to the Nth mold component according to the splicing control temperature distribution information.

Images