CN118832821A - Material forming control system for injection mold - Google Patents

Abstract

The application provides a material molding control system for an injection mold, which relates to the technical field of molding control, and comprises the following steps: the requirement information acquisition module is used for acquiring production requirement information of a target injection product, the attribute classification module is used for classifying attributes of the target injection mold, acquiring application attribute information of the injection mold, and the matching optimizing module is used for constructing a molding space of the injection mold and carrying out matching optimizing to acquire an injection molding control parameter memory bank; and the molding control module is used for performing a preforming test, performing parameter error compensation analysis and determining target injection molding control parameters to perform injection molding control. The application can solve the technical problems of inaccurate molding parameter selection and further influence on the quality and production efficiency of injection molding products because the information processing and parameter selection depend on manual experience and test in the prior art, and improves the efficiency and quality of injection molding through automatic information extraction, accurate attribute classification, matching optimization and error compensation analysis.

Description

Material Forming Control System for Injection Molds

Technical Field

The present application relates to the field of molding control technology, and in particular to a material molding control system for injection molds.

Background Art

With the continuous progress of materials science, more and more high-performance plastic materials have been developed. These materials have excellent physical and chemical properties and can meet various complex and harsh application environments. However, the molding of these high-performance materials often has higher requirements for molds and molding processes, so precise molding control methods are needed to ensure product quality. The mold is the core component of injection molding, and its manufacturing accuracy and quality directly affect the quality of injection molded products.

At present, in the traditional injection molding process, engineers usually need to determine the appropriate molding parameters based on their own experience and repeated trials. This method is not only inefficient, but it is often difficult to ensure the optimality of the selected parameters. If the parameters are not selected properly, it may lead to unstable product quality, high scrap rate, and even damage to molds and equipment. In addition, methods that rely on manual experience and experiments are also easily affected by human factors, such as the engineer's technical level, working status, etc., which will further affect product quality and production efficiency.

In summary, in the prior art, since information processing and parameter selection rely on manual experience and experiments, the molding parameter selection is inaccurate, which further affects the quality of injection molded products and the technical problem of production efficiency.

Summary of the invention

The purpose of this application is to provide a material molding control system for injection molds, so as to solve the technical problem in the prior art that information processing and parameter selection rely on manual experience and experiments, resulting in inaccurate molding parameter selection, further affecting the quality and production efficiency of injection molded products.

In view of the above problems, the present application provides a material molding control system for an injection mold.

The present application provides a material molding control system for an injection mold, wherein the system includes: a requirement information acquisition module, used to execute step S1: acquire production requirement information of a target injection molded product, extract injection molding elements from the production requirement information, and obtain injection molding production element information, wherein the injection molding production element information includes structural dimensions, product appearance, and material properties; an attribute classification module, used to execute step S2: classify the attributes of the target injection mold, acquire injection mold application attribute information, define molding parameters for the injection mold application attribute information based on the injection molding production element information, and determine the optional injection molding control parameter species; A matching and optimization module is used to execute step S3: based on the optional injection molding control parameter species, a traversal search is performed in the injection molding parameter library to construct an injection mold molding space, and the injection molding production factor information is used as a constraint parameter to perform matching and optimization in the injection mold molding space to obtain an injection molding control parameter memory library; a molding control module is used to execute step S4: based on the injection molding control parameter memory library, a pre-molding test is performed on the target injection molding product to obtain injection molding product test performance information, parameter error compensation analysis is performed based on the injection molding product test performance information, and target injection molding control parameters are determined for injection molding control.

One or more technical solutions provided in this application have at least the following technical effects or advantages:

The requirement information acquisition module is used to execute step S1: obtain the production requirement information of the target injection molding product, extract the injection molding elements from the production requirement information, and obtain the injection molding production element information, wherein the injection molding production element information includes the structural size, product appearance and material performance; the attribute classification module is used to execute step S2: classify the attributes of the target injection mold, obtain the injection mold application attribute information, define the molding parameters of the injection mold application attribute information based on the injection molding production element information, and determine the optional injection molding control parameter species; the matching optimization module is used to execute step S3: traverse and search in the injection molding parameter library based on the optional injection molding control parameter species, construct the injection mold molding space, and classify the injection molding production element information as The invention relates to a method for obtaining a memory library of injection molding control parameters for matching and optimizing constraint parameters in the molding space of the injection mold; a molding control module for executing step S4: performing a pre-molding test on the target injection molding product based on the injection molding control parameter memory library to obtain injection molding product test performance information, performing parameter error compensation analysis through the injection molding product test performance information, and determining target injection molding control parameters for injection molding control, which effectively solves the technical problem in the prior art that the molding parameter selection is inaccurate due to the reliance on manual experience and experiments for information processing and parameter selection, further affecting the quality and production efficiency of the injection molding products, and improves the efficiency and quality of injection molding through automated information extraction, precise attribute classification, matching optimization and error compensation analysis.

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 according to the contents of the specification, and 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 specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

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

FIG1 is a schematic diagram of the structure of a material forming control system for an injection mold in the present application;

FIG. 2 is a schematic diagram of a structure for determining optional injection molding control parameter types in a material molding control system for an injection mold of the present application.

Description of reference numerals:

The requirements include an information acquisition module 11 , an attribute classification module 12 , a matching optimization module 13 , a molding control module 14 , a control attribute acquisition module 21 , a parameter set acquisition module 22 , a control analysis module 23 , and a parameter configuration module 24 .

DETAILED DESCRIPTION

The present application provides a material molding control system for injection molds, which solves the technical problem in the prior art that information processing and parameter selection rely on manual experience and experiments, resulting in inaccurate molding parameter selection, further affecting the quality and production efficiency of injection molded products. The efficiency and quality of injection molding are improved through automated information extraction, precise attribute classification, matching optimization and error compensation analysis.

Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

Embodiment 1

Please refer to FIG. 1 , the present application provides a material molding control system for an injection mold, wherein the system includes:

The requirement information acquisition module 11 is used to execute step S1: obtain production requirement information of a target injection molding product, extract injection molding elements from the production requirement information, and obtain injection molding production element information, wherein the injection molding production element information includes structural dimensions, product appearance, and material properties;

Specifically, in this embodiment, the information acquisition module is required to be used for factor extraction. Specifically, the structural dimensions include the overall dimensions of the product, the dimensions of each part, and the dimensions of key matching parts. The product appearance includes the product's color, glossiness, surface texture, degree of flawlessness, and other aspects. The material properties of injection molded products include physical properties, such as strength, hardness, wear resistance, impact resistance, etc., chemical properties, such as corrosion resistance, aging resistance, etc., and thermal properties, such as heat resistance and thermal stability.

The attribute classification module 12 is used to execute step S2: classify the attributes of the target injection mold, obtain the application attribute information of the injection mold, define the molding parameters of the injection mold application attribute information based on the injection molding production factor information, and determine the optional injection molding control parameter species;

Specifically, the attribute classification module in this embodiment is used for parameter definition. Specifically, the mold type includes the structure and function of the mold, such as whether it is a single cavity or multiple cavities, whether there is a side core pulling mechanism, etc. Material properties include the hardness, wear resistance, corrosion resistance and thermal conductivity of the mold material. Dimensional accuracy includes the dimensional accuracy and surface roughness of the mold cavity and core. Obtaining the application attribute information of the injection mold includes usage history, etc. Usage conditions, such as the injection molding machine model, injection pressure range, temperature control range, etc. applicable to the mold. Maintenance records, records of mold maintenance, repair and replacement of parts. Based on the injection molding production factor information, structural dimensions, product appearance, material properties, combined with the application properties of the mold, define the molding parameters. Including temperature parameters, including barrel temperature, nozzle temperature, mold temperature, etc., these parameters affect the melting state, fluidity and cooling rate of the plastic. Pressure parameters, injection pressure, holding pressure, etc., these parameters affect the ability of the plastic to fill the mold and the stress distribution inside the product. Time parameters, injection time, holding time, cooling time, etc., these parameters are related to production efficiency and product quality. Select the appropriate control parameter range according to the model and capacity of the injection molding machine. Determine the type of injection molding parameters that can be selected for control according to the production factors of the injection molding product and the properties of the mold.

The matching and optimization module 13 is used to execute step S3: based on the optional injection molding control parameter species, perform traversal search in the injection molding parameter library to construct an injection mold molding space, use the injection molding production factor information as a constraint parameter to perform matching and optimization in the injection mold molding space, and obtain an injection molding control parameter memory library;

Specifically, the matching optimization module in this embodiment is used to obtain a parameter memory library. Specifically, based on the determined optional injection molding control parameter species, a traversal search is performed in the existing injection molding parameter library. This parameter library contains successful injection molding parameter cases of similar products or materials in history. Through search and analysis, a multi-dimensional molding space is constructed, and each dimension represents a molding control parameter, such as temperature, pressure, time, etc. This space reflects all possible molding parameter combinations under the constraints of given injection molding production factor information. The injection molding production factor information, structural dimensions, product appearance, material properties, etc. are used as constraint parameters and matched in the injection mold molding space. In this space, the optimal parameter combination that meets all constraints is found. The best parameter combination found in the optimization process is stored to form a memory library.

The molding control module 14 is used to execute step S4: based on the injection molding control parameter memory library, the target injection molding product is pre-molded to obtain injection molding product test performance information, and parameter error compensation analysis is performed based on the injection molding product test performance information to determine the target injection molding control parameters for injection molding control.

Specifically, the molding control module in this embodiment is used for error compensation analysis. Specifically, preliminary molding control parameters that match the target injection molding product are selected from the injection molding control parameter memory library. Use these parameters to perform pre-molding tests and produce a small number of samples. Perform detailed performance tests on the samples produced by the pre-molding test, including appearance inspection, dimensional measurement, and physical performance tests, such as strength and hardness. Collect and record all relevant test performance information. Compare the test performance information with the product design requirements and analyze the differences and errors. According to the performance differences, identify the molding control parameters that need to be adjusted, such as temperature, pressure or time. Use error compensation techniques, such as PID, proportional-integral-differential controllers or other advanced control algorithms to adjust and optimize the identified parameters. After multiple iterations and optimizations, determine a set of molding control parameters that can meet the product design requirements. These parameters should be able to ensure that the performance, appearance and size of the injection molding product meet the design requirements. Apply the final target injection molding control parameters to actual production.

Further, as shown in FIG2 , the system further includes:

The control property acquisition module 21 is used to execute step S21: acquiring injection molding control properties, wherein the injection molding control properties include temperature control properties, pressure control properties, speed control properties and time control properties;

The parameter set acquisition module 22 is used to execute step S22: matching and mapping the injection molding production factor information with the injection molding control attribute to obtain a production factor-control attribute mapping relationship;

The control analysis module 23 is used to execute step S22: perform molding parameter control analysis based on the injection mold application attribute information and the injection molding control attributes to obtain a mold molding controllable attribute parameter set;

The parameter configuration module 24 is used to execute step S24: based on the production factor-control attribute mapping relationship, the associated control parameter configuration is performed on the mold molding controllable attribute parameter set to determine the optional injection molding control parameter type.

Specifically, the attribute classification module in this embodiment is used to obtain control attributes, perform matching mapping, and perform parameter control analysis, including a control attribute acquisition module, a parameter set acquisition module, a control analysis module, and a parameter configuration module. Specifically, the temperature control attributes include barrel temperature, nozzle temperature, and mold temperature, etc. These temperature control attributes affect the melting, fluidity, and cooling process of the plastic. Pressure control attributes include injection pressure, holding pressure, etc., which determine how the plastic fills the mold and the stress distribution inside the product. Speed control attributes include injection speed, which affects the speed of filling the mold and the surface quality of the product. Time control attributes include injection time, holding time, cooling time, etc. The injection molding production factor information, structural dimensions, product appearance, and material properties are matched and mapped with the injection molding control attributes. For example, the structural dimensions of the product may be closely related to the injection pressure and speed control attributes, while the appearance of the product may be related to the temperature and time control attributes. Based on the application attribute information of the injection mold, such as mold type, material attributes, dimensional accuracy, etc., molding parameter control analysis is performed with the injection molding control attributes respectively. The corresponding controllable attribute parameter types of molds with different application attributes are also different. According to the application attributes of the injection mold, the specific attribute parameter types of each injection molding control attribute associated with it are determined. For example, the specific parameter types of the speed control attribute associated with the injection mold include injection speed, ejection speed, etc. The mapping relationship between production factors and control attributes is used to configure the associated control parameters of the mold molding controllable attribute parameter set. In order to ensure that the selected molding control parameters can simultaneously meet the production factor requirements of the product and the application attributes of the mold.

Furthermore, the system further comprises:

A discriminator construction module is used to execute step S31: construct an injection molding production feature discriminator, classify and integrate the injection mold molding space based on the injection molding production feature discriminator, and obtain a mold molding feature parameter space;

A similarity screening module is used to execute step S32: using the injection molding production factor information as a constraint parameter to perform similarity screening with the mold molding feature parameter space to obtain an injection molding feature parameter solution space;

An evaluation function construction module is used to execute step S33: perform multivariate evaluation fitting on the injection molding effect data in the injection molding characteristic parameter solution space to construct an injection molding effect excitation degree evaluation function;

A memory library acquisition module is used to execute step S34: based on the injection molding effect excitation degree evaluation function, an optimization analysis is performed in the injection molding characteristic parameter solution space to obtain an injection molding control parameter memory library, wherein the injection molding control parameter memory library includes an optimal injection molding control parameter and multiple suboptimal injection molding control parameters.

Specifically, the matching optimization module in this embodiment is used to obtain the molding parameter space and construct an evaluation function, including a discriminator construction module, a similarity screening module, an evaluation function construction module, and a memory library acquisition module. Specifically, an injection molding production feature discriminator is constructed, which can identify and classify different injection molding production features. The production requirement information of the injection molding product is classified into specific features, such as thermoplastic and high-precision cup appearance products. This discriminator is used to classify and integrate the injection mold molding space, and the mold molding space is divided according to different features, such as the structural complexity, material type, size range, etc. of the product. Through classification and integration, a more refined and orderly mold molding feature parameter space is obtained. The injection molding production factor information, such as structural size, product appearance, material performance, etc., is used as a constraint parameter. These constraint parameters are similarly screened with the mold molding feature parameter space to find the molding feature parameters that best match the production factor information. Through similarity screening, an injection molding feature parameter solution space can be obtained, which contains a molding parameter combination that meets the production factor constraints. In the injection molding characteristic parameter solution space, the injection molding effect data corresponding to each parameter combination is subjected to multivariate evaluation fitting. This includes evaluating the product's appearance quality, dimensional accuracy, physical properties and other aspects. Based on the results of the multivariate evaluation, an injection molding effect excitation evaluation function is constructed. This function can quantitatively evaluate the contribution or excitation degree of each molding parameter combination to the injection molding effect. The injection molding effect excitation evaluation function is used to perform optimization analysis in the injection molding characteristic parameter solution space. By calculating the excitation value of each parameter combination, find the parameter combination with the highest excitation degree, that is, the best molding effect. The optimal injection molding control parameters and multiple suboptimal parameters obtained from the optimization analysis are stored in the injection molding control parameter memory library.

Furthermore, the system further comprises:

An index extraction module is used to extract indexes from injection molding effect data and determine an injection molding effect evaluation index set, wherein the injection molding effect evaluation index set includes injection molding quality, injection molding efficiency, and injection molding cost;

A function construction module is used to construct an injection molding effect incentive evaluation function based on the injection molding effect evaluation index set, wherein the injection molding effect incentive evaluation function is specifically:

in, Characterize the weight of injection molding quality indicators, is the injection molding quality empirical evaluation function, is the i-th group of injection molding control parameters, Characterize the weight of injection molding efficiency indicators, is the empirical evaluation function of injection molding efficiency, is the weight of injection molding cost index, is the injection molding cost empirical evaluation function, , and The sum of the weights is 1, is the error empirical constant.

Specifically, the evaluation function construction module in this embodiment is used to extract indicators, including an indicator extraction module and a function construction module. Specifically, the injection molding quality indicator measures the quality factors such as the appearance, dimensional accuracy, and structural integrity of the final product. The injection molding efficiency indicator considers the efficiency of the production process, including the production cycle, machine utilization, etc. The injection molding cost indicator focuses on the material cost, labor cost, and equipment depreciation costs in the production process. The injection molding effect incentive evaluation function is specifically, ;in, Characterize the weight of injection molding quality indicators, is the injection molding quality empirical evaluation function, is the i-th group of injection molding control parameters, Characterize the weight of injection molding efficiency indicators, is the empirical evaluation function of injection molding efficiency, is the weight of injection molding cost index, is the injection molding cost empirical evaluation function, , and The sum of the weights is 1, is the error empirical constant.

Furthermore, the system further comprises:

An evaluation and calculation module, used to evaluate and calculate each parameter solution in the injection molding characteristic parameter solution space by using the injection molding effect excitation degree evaluation function to obtain an injection molding effect excitation degree set;

A parameter partitioning module, used for screening the centers of parameter clusters in the injection molding characteristic parameter solution space based on the injection molding effect excitation degree set, and then performing parameter solution partitioning and clustering according to the centers of the parameter clusters to determine a plurality of injection molding characteristic parameter clusters;

A parameter cluster acquisition module, used for setting a learning factor, and performing parameter iterative optimization toward the center of the parameter cluster in the plurality of injection molding characteristic parameter clusters based on the learning factor, until a preset convergence requirement is met, so as to obtain a plurality of injection molding optimization parameter clusters;

The comparison and optimization module is used to calculate the sum of the excitation degrees of the plurality of injection molding optimization parameter clusters, and perform parameter cluster comparison and optimization based on the calculation result of the sum of the excitation degrees to obtain the injection molding control parameter memory library.

Specifically, the memory library acquisition module in this embodiment is used for parameter evaluation calculation, obtaining multiple parameter clusters, and obtaining parameter memory libraries, including an evaluation calculation module, a parameter division module, a parameter cluster acquisition module, and a comparison and optimization module. Specifically, the injection molding effect excitation evaluation function is used to evaluate and calculate each parameter solution in the injection molding characteristic parameter solution space. This process will assign an excitation value to each parameter solution, and these values constitute the injection molding effect excitation set. Based on the injection molding effect excitation set, the parameter solution space can be screened for the parameter cluster center. By finding a parameter solution with a higher excitation as the center of the cluster. Then, according to these cluster centers, the parameter solution space is divided and clustered to form multiple injection molding characteristic parameter clusters. A learning factor is set, which determines the step size and speed of parameter optimization. In each injection molding characteristic parameter cluster, the learning factor is used to perform parameter iterative optimization toward the parameter cluster center. This process is to gradually adjust the parameter value so that the parameter solution in each parameter cluster gradually approaches the parameter configuration of the cluster center until the preset convergence requirements are met. In this way, multiple injection molding optimization parameter clusters can be obtained. For the optimized multiple injection molding optimization parameter clusters, the sum of the excitation degrees of each parameter cluster is calculated. This sum reflects the comprehensive effect of all parameter solutions in the parameter cluster. Based on the calculation results of these excitation degree sums, the parameter clusters are compared and optimized. Finally, the parameter solution in the parameter cluster with the highest excitation degree sum is selected as the content of the injection molding control parameter memory library. Through the above steps, a set of optimized and compared injection molding control parameters is obtained. These parameters are stored in the injection molding control parameter memory library for future reuse and reference in similar injection molding tasks.

Furthermore, the system further comprises:

A learning optimization module, configured to perform parameter learning optimization on the remaining injection molding control parameters in the plurality of injection molding characteristic parameter clusters toward the center of the parameter cluster based on the learning factor, so as to obtain a plurality of injection molding learning parameter clusters;

An interactive learning module, used for randomly selecting other parameter solutions from the plurality of injection molding learning parameter clusters to perform excitation degree comparison and interactive learning, so as to obtain a plurality of injection molding interactive parameter clusters;

A parameter updating module is used to update and iteratively optimize the parameter cluster center based on the multiple injection molding interactive parameter clusters until the preset convergence requirement is met to obtain the multiple injection molding optimization parameter clusters.

Specifically, the parameter division module in this embodiment is used to perform parameter learning optimization, excitation comparison and interactive learning, including a learning optimization module, an interactive learning module, and a parameter updating module. Specifically, a preset learning factor is used to optimize the remaining injection molding control parameters in multiple injection molding feature parameter clusters toward the center of their respective parameter clusters. This learning factor determines the speed and amplitude of parameter adjustment. Through this process, the parameter solution in each parameter cluster will gradually approach the parameter configuration of its cluster center, forming multiple injection molding learning parameter clusters. In the multiple injection molding learning parameter clusters formed, the remaining parameter solutions are randomly selected for excitation comparison. The injection molding effects of different parameter solutions are evaluated, and which parameter solutions perform better in the injection molding effect by comparing their excitation values. Based on the results of the excitation comparison, interactive learning is performed. The advantages of the parameter solutions with better performance will be borrowed and learned to improve other parameter solutions. In this way, the parameter solutions can learn and learn from each other, thereby improving the injection molding effect as a whole. This process will form multiple injection molding interactive parameter clusters, in which the parameter solutions have been interactively learned and improved. Based on the above interactive parameter clusters, the original parameter cluster centers are updated. The center point of each parameter cluster is recalculated to reflect the overall trend and change of the parameter solution after interactive learning. Then, the updated parameter cluster center is used to perform parameter iterative optimization again until the preset convergence requirements are met. Through the above iteration and optimization process, when the preset convergence requirements are met, for example, when the improvement of the optimization effect is less than a certain threshold, or the number of iterations reaches a certain upper limit, it can be considered that multiple injection molding optimization parameter clusters have been found. The parameter solutions in these parameter clusters have reached a relatively optimal state in terms of injection molding effect.

Furthermore, the system further comprises:

A compensation analysis module, used for performing parameter compensation analysis on the injection molding product test performance information to obtain a control parameter variation direction if the injection molding product test performance information does not achieve a preset injection molding effect;

The parameter variation module is used to set the parameter variation rule according to the variation direction of the control parameter. The parameter variation rule is specifically: ,in, is the parameter position after Gaussian mutation, is the position of the original control parameter, represents a normal distribution with a mean of 0 and a variance of 1;

An evaluation and optimization module is used to mutate and update the multiple suboptimal injection molding control parameters based on the parameter variation rule, and perform parameter evaluation and optimization on the multiple suboptimal injection molding control parameters after the variation update to determine the target injection molding control parameters.

Specifically, the molding control module in this embodiment is used to obtain the direction of control parameter variation, set parameter variation rules, and perform parameter evaluation and optimization, including a compensation analysis module, a parameter variation module, and an evaluation and optimization module. Specifically, the test performance information of the injection molded product is analyzed to determine the specific reasons why it fails to achieve the preset molding effect. By comparing the preset effect with the actual test effect, the performance gap is identified to determine the direction of variation of the control parameters. This direction indicates how the control parameters should be adjusted in order to improve product performance. For the production performance of injection molded products that do not achieve the preset injection molding effect, the molding control parameters associated with it are analyzed to determine the direction of variation adjustment, such as increasing the injection molding pressure. According to the direction of variation of the control parameters, a parameter variation rule is set. This rule guides how to fine-tune the current suboptimal injection molding control parameters. The parameter variation rule is specifically: ,in, is the parameter position after Gaussian mutation, is the position of the original control parameter, Represents a normal distribution with a mean of 0 and a variance of 1. Based on the above parameter variation rules, multiple suboptimal injection molding control parameters are mutated and updated. The value of each parameter is randomly adjusted according to the variation rules to explore possible better parameter combinations. Use the multiple suboptimal injection molding control parameters after variation update to conduct actual injection molding tests, and evaluate the product performance corresponding to each parameter combination. By comparing the product performance under different parameter combinations, determine which parameter combinations are closer to the preset molding effect. Select the parameter combination with the best performance as the new target injection molding control parameters. If the preset effect is still not achieved after one variation and evaluation, the above process can be repeated for multiple iterative optimizations until the target injection molding control parameters that meet the requirements are found.

The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims (5)

1. A material molding control system for an injection mold, the system comprising:

A request information acquisition module, configured to execute step S1: obtaining production requirement information of a target injection molding product, extracting injection molding elements from the production requirement information to obtain injection molding production element information, wherein the injection molding production element information comprises structural dimensions, product appearance and material properties;

The attribute classification module is configured to execute step S2: classifying attributes of a target injection mold, acquiring injection mold application attribute information, defining molding parameters of the injection mold application attribute information based on the injection production element information, and determining selectable injection molding control parameter species;

The matching optimizing module is used for executing the step S3: performing traversal search in an injection molding parameter library based on the selectable injection molding control parameter species, constructing an injection molding mold molding space, and performing matching optimization in the injection molding mold molding space by taking the injection molding production element information as a constraint parameter to obtain an injection molding control parameter memory library;

The molding control module is used for executing the step S4: performing a preforming test on the target injection product based on the injection molding control parameter memory library to obtain injection product test performance information, performing parameter error compensation analysis through the injection product test performance information, and determining target injection molding control parameters to perform injection molding control;

The matching optimizing module further comprises:

The arbiter construction module is configured to execute step S31: constructing an injection molding production feature discriminator, and classifying and integrating the injection molding mold forming space based on the injection molding production feature discriminator to obtain a mold forming feature parameter space;

The similarity screening module is configured to execute step S32: taking the injection molding production element information as a constraint parameter and carrying out similarity screening on the constraint parameter and the mold molding characteristic parameter space to obtain an injection molding characteristic parameter solution space;

The evaluation function construction module is configured to execute step S33: performing multivariate evaluation fitting on the injection molding effect data in the injection molding characteristic parameter solution space, and constructing an injection molding effect excitation evaluation function;

the memory bank obtaining module is configured to execute step S34: performing optimizing analysis in the injection molding characteristic parameter solution space based on the injection molding effect excitation degree evaluation function to obtain an injection molding control parameter memory bank, wherein the injection molding control parameter memory bank comprises optimal injection molding control parameters and a plurality of suboptimal injection molding control parameters;

The evaluation function construction module further includes:

The index extraction module is used for extracting indexes of the injection molding effect data and determining an injection molding effect evaluation index set, wherein the injection molding effect evaluation index set comprises injection molding quality, injection molding efficiency and injection molding cost;

The function construction module is used for constructing an injection molding effect excitation degree evaluation function based on the injection molding effect evaluation index set, wherein the injection molding effect excitation degree evaluation function specifically comprises the following steps:

wherein, The quality index weight of the injection molding is represented,For the injection molding quality experience evaluation function,For the i-th set of injection molding control parameters,The index weight of the injection molding efficiency is represented,For the empirical evaluation of the function of injection molding efficiency,For the cost index weight of injection molding,For the empirical evaluation function of the injection molding cost,、AndThe sum of the weights of (2) is 1,Is an empirical constant of error.

2. The system of claim 1, wherein the attribute classification module further comprises:

a control attribute acquisition module for executing step S21: obtaining injection molding control attributes, wherein the injection molding control attributes comprise temperature control attributes, pressure control attributes, speed control attributes and time control attributes;

the parameter set obtaining module is configured to execute step S22: matching and mapping the injection molding production element information and the injection molding control attribute to obtain a production element-control attribute mapping relation;

The control analysis module is configured to execute step S22: performing molding parameter control analysis on the application attribute information of the injection mold and the injection molding control attribute respectively to obtain a mold molding controllable attribute parameter set;

a parameter configuration module, configured to execute step S24: and carrying out associated control parameter configuration on the die molding controllable attribute parameter set based on the production element-control attribute mapping relation, and determining the selectable injection molding control parameter species.

3. The system of claim 1, wherein the memory bank acquisition module further comprises:

The evaluation calculation module is used for performing evaluation calculation on each parameter solution in the injection molding characteristic parameter solution space by using the injection molding effect excitation degree evaluation function to obtain an injection molding effect excitation degree set;

The parameter dividing module is used for screening parameter cluster centers from the injection molding characteristic parameter solution space based on the injection molding effect excitation degree set, and then carrying out parameter solution dividing clustering according to the parameter cluster centers to determine a plurality of injection molding characteristic parameter clusters;

the parameter cluster acquisition module is used for setting a learning factor, and respectively carrying out parameter iterative optimization on the centers of the parameter clusters in the plurality of injection molding characteristic parameter clusters based on the learning factor until the preset convergence requirement is met to obtain a plurality of injection molding optimized parameter clusters;

and the comparison optimization module is used for calculating the sum of the excitation degrees of the injection molding optimization parameter clusters, and performing parameter cluster comparison optimization based on the calculation result of the sum of the excitation degrees to obtain the obtained injection molding control parameter memory bank.

4. The system of claim 3, wherein the parameter partitioning module further comprises:

The learning optimization module is used for carrying out parameter learning optimization on the rest injection molding control parameters in the injection molding characteristic parameter clusters based on the learning factors to the center of the parameter cluster so as to obtain a plurality of injection molding learning parameter clusters;

the interactive learning module is used for randomly selecting other parameter solutions from the injection molding learning parameter clusters to perform excitation degree comparison and interactive learning to obtain a plurality of injection molding interactive parameter clusters;

And the parameter updating module is used for updating, iterating and optimizing the parameter cluster center based on the injection molding interaction parameter clusters until the preset convergence requirement is met, so as to obtain the injection molding optimization parameter clusters.

5. The system of claim 1, wherein the molding control module further comprises:

The compensation analysis module is used for carrying out parameter compensation analysis on the injection molding product test performance information if the injection molding product test performance information does not reach a preset injection molding effect, and obtaining a control parameter variation direction;

The parameter variation module is configured to set a parameter variation rule according to the control parameter variation direction, where the parameter variation rule specifically is: wherein, the method comprises the steps of, wherein, The position of the parameter after the Gaussian variation is determined,Is the position of the original control parameter,Represents a normal distribution with a mean value of 0 and a variance of 1;

And the evaluation optimizing module is used for carrying out mutation updating on the plurality of sub-optimal injection molding control parameters based on the parameter mutation rule, carrying out parameter evaluation optimizing on the plurality of sub-optimal injection molding control parameters after mutation updating, and determining the target injection molding control parameters.