A smart control method to improve the molding efficiency of injection molds

Abstract

This application provides an intelligent control method for improving the molding efficiency of injection molds, relating to the field of injection molding control technology. The method includes: performing mold flow analysis using initial experimental parameters and configuring the initial experimental parameter range; obtaining the experimental response of the quality index by executing quality index factor parameters, and obtaining the optimal combination of experimental parameters; constructing a quality index prediction model; constructing an initial population for explosive search; collecting the production response of the quality index based on the optimal process parameter combination, performing deviation analysis between the production response and the predicted response, and adjusting the optimal process parameter combination; and controlling the injection mold molding based on the actual process parameter combination. This application solves the technical problem in existing technologies where parameter settings rely on manual experience and it is difficult to effectively optimize the interaction of multiple parameters. It achieves the technical goal of optimizing and dynamically adjusting injection molding process parameters, thereby improving production efficiency.

Description

Technical Field

[0001] This application relates to the field of injection molding control technology, and in particular to an intelligent control method for improving the molding efficiency of injection molds. Background Technology

[0002] Injection molding technology is an indispensable and important process in modern industrial production, and it is widely used in the automotive, electronics, medical and consumer goods industries.

[0003] Currently, traditional technologies typically rely on manual experience to set process parameters such as injection pressure, mold temperature, filling time, and holding time. This experience-driven approach not only easily leads to inaccurate parameter settings but also requires extensive trial and error adjustments, thus prolonging product development cycles and increasing production costs. Furthermore, because manual settings struggle to simultaneously optimize the interaction of multiple parameters, the final product quality is often unstable, potentially resulting in defects such as warping, shrinkage, and core misalignment, leading to a high defect rate.

[0004] In summary, existing technologies suffer from technical problems such as time-consuming and costly process parameter adjustments and unstable product quality due to the reliance on manual experience in parameter setting and the difficulty in effectively optimizing the interaction of multiple parameters, which further affect production efficiency and final product qualification rate. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent control method to improve the molding efficiency of injection molds, in order to solve the technical problems in the prior art, which are that the parameter settings rely on human experience and it is difficult to effectively optimize the interaction of multiple parameters, resulting in long process parameter adjustment time, high cost and unstable product quality, which further affect production efficiency and final product qualification rate.

[0006] In view of the above problems, this application provides an intelligent control method for improving the molding efficiency of injection molds, comprising: performing mold flow analysis using initial experimental parameters, configuring an initial experimental parameter range based on the mold flow analysis results; extracting quality index factor parameters based on the initial experimental parameter range, executing the experiment using the quality index factor parameters to obtain a quality index experimental response, and comparing the quality index experimental response to obtain an optimal experimental parameter combination; constructing a quality index prediction model based on the optimal experimental parameter combination and the quality index experimental response; constructing an initial population and performing a burst search to obtain an optimal population, wherein the optimal population is the optimal process parameter combination; collecting the quality index production response based on the optimal process parameter combination, performing a deviation analysis between the quality index production response and the quality index prediction response predicted based on the quality index prediction model for the optimal process parameter combination, adjusting the optimal process parameter combination based on the deviation results to obtain an actual process parameter combination; and controlling the injection mold molding based on the actual process parameter combination.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Mold flow analysis is performed using initial experimental parameters, and the initial experimental parameter range is configured based on the mold flow analysis results. Quality index factor parameters are extracted based on the initial experimental parameter range, and the experiment is executed using these parameters to obtain the quality index experimental response. The optimal experimental parameter combination is obtained by comparing the quality index experimental response. A quality index prediction model is constructed based on the optimal experimental parameter combination and the quality index experimental response. An initial population is constructed and a burst search is performed to obtain the optimal population, which represents the optimal process parameter combination. The production response of the quality index is collected based on the optimal process parameter combination, and a deviation analysis is performed between the production response and the predicted response based on the quality index prediction model. The optimal process parameter combination is adjusted based on the deviation results to obtain the actual process parameter combination. Injection mold forming is controlled based on the actual process parameter combination. In other words, by optimizing and dynamically adjusting injection molding process parameters, the technical effects of improving production efficiency, reducing product defect rate, and stabilizing product quality are achieved.

[0009] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating an intelligent control method for improving the molding efficiency of injection molds according to this application.

[0012] Figure 2 This is a schematic diagram illustrating the process of obtaining the optimal combination of experimental parameters in an intelligent control method for improving the molding efficiency of injection molds, as described in this application. Detailed Implementation

[0013] This application provides an intelligent control method to improve the molding efficiency of injection molds. It solves the technical problems in existing technologies where parameter settings rely on manual experience and are difficult to effectively optimize the interaction of multiple parameters, leading to time-consuming and costly process parameter adjustments, unstable product quality, and further impacting production efficiency and final product qualification rate. The method achieves the technical goal of optimizing and dynamically adjusting injection molding process parameters, thereby improving production efficiency, reducing product defect rate, and stabilizing product quality.

[0014] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0015] Example 1, please refer to the appendix. Figure 1 This application provides an intelligent control method for improving the molding efficiency of injection molds, which specifically includes the following steps:

[0016] Step 1: Perform mold flow analysis using initial experimental parameters, and configure the initial experimental parameter range based on the mold flow analysis results.

[0017] Specifically, the initially set injection molding process parameters are input into a CAE (Computer-Aided Engineering) simulation tool for analysis, simulating factors such as flow, cooling, and pressure distribution during the process. The mold flow analysis results provide detailed data on mold performance under the initial experimental parameters, such as temperature, pressure distribution, and filling time, helping to identify potential defects or problems in the mold, such as bubbles, warpage, or core misalignment. Based on the analysis results, the initial experimental parameters can be adjusted. For example, if the analysis shows that the temperature in a certain area is too high or the filling is uneven, it may be necessary to adjust the mold temperature or injection pressure. Finally, by using feedback from the mold flow analysis results, a reasonable range of initial experimental parameters is configured to ensure that actual production within this parameter range minimizes defects and improves production stability.

[0018] Step 2: Extract quality index factor parameters based on the initial experimental parameter range, execute the experiment using the quality index factor parameters to obtain the quality index experimental response, and compare the quality index experimental response to obtain the optimal experimental parameter combination.

[0019] Specifically, based on the initial experimental parameter range, key factors affecting product quality are selected, such as injection pressure, holding time, and mold temperature. These factors are critical parameters that need to be controlled and optimized during the experiment. Next, in actual production, corresponding experiments are performed based on the extracted factors and their configured quality indicator parameters. The impact of different combinations of parameter levels on product quality is tested through actual injection molding operations, yielding the experimental response of the quality indicators, i.e., the results obtained through the experiments, such as warpage and wall thickness uniformity error. Finally, by comparing all experimental results and the experimental responses of the quality indicators, the optimal combination of experimental parameters is found. This comparison process may involve comparing quality data such as warpage and dimensional accuracy from different experimental groups to ultimately determine the optimal parameter combination, ensuring the most ideal product quality.

[0020] Step 3: Construct a quality index prediction model based on the optimal combination of experimental parameters and the experimental response of the quality index.

[0021] Specifically, the optimal combination of experimental parameters is selected as the input variable, and the experimental response of the corresponding quality index is used as the output variable, such as warpage and wall thickness error. The experimental response of the quality index is the quality result measured in actual experiments, reflecting the specific impact of the parameter combination on product performance. Then, using the input parameter combination and the output experimental response, data modeling methods, such as regression analysis or neural networks, are employed to establish a quality index prediction model. This model can quickly predict the impact of new parameter combinations on quality indicators in the future. Through this predictive capability, process parameters can be quickly adjusted during production, improving efficiency and product quality.

[0022] Step 4: Construct an initial population and perform an explosive search to obtain the optimal population, which is the optimal combination of process parameters.

[0023] Specifically, constructing an initial population for explosive search refers to generating a set of initial solutions within a defined parameter space as the initial population. Each solution corresponds to a possible combination of process parameters. The initial solutions are uniformly or randomly distributed within the parameter range. Explosive search involves expanding each initial solution according to certain rules, i.e., generating multiple new solutions (sparks). These new solutions are distributed near the original solutions, while considering the balance between local and global searches, thereby exploring better solutions and obtaining the optimal population. This means that through multiple rounds of iterative explosive search and fitness evaluation, the optimal solution is selected from all sparks. The optimal solution has a higher fitness value, indicating better performance in the process optimization objective. The selection process typically retains a fixed number of solutions to maintain the population size. The optimal population represents the optimal combination of process parameters, indicating that the selected set of optimal solutions can be directly used for production or further analysis.

[0024] Step 5: Collect the production response of quality indicators based on the optimal combination of process parameters, perform deviation analysis between the production response of quality indicators and the predicted response of quality indicators obtained by predicting the optimal combination of process parameters based on the quality indicator prediction model, and adjust the optimal combination of process parameters according to the deviation results to obtain the actual combination of process parameters.

[0025] Specifically, in actual production, trial production is conducted according to the selected optimal combination of process parameters, and product quality indicators, such as warpage, dimensional deviation, or mechanical strength, are collected using sensors or detection equipment. The production response is a collection of actual production data, reflecting the actual quality performance of the product under the current parameter conditions. The quality indicators collected in actual production are compared with the corresponding indicators given by the prediction model, the differences between the two are calculated, and the accuracy of the prediction model and whether the performance of the optimal process parameters in actual production meets the requirements are evaluated. When the deviation exceeds a preset threshold, the current process parameters need to be adjusted to reduce the deviation and improve product quality, further optimizing production efficiency. An improved set of parameter combinations is determined through adjustment and applied in actual production to ensure that the product quality indicators meet the requirements and the deviation is controlled within the preset range.

[0026] Step 6: Control the injection mold forming based on the actual process parameter combination.

[0027] Specifically, the adjusted and optimized process parameters are applied to the injection molding machine to guide the molding process, including injection pressure, mold temperature, filling time, and holding time. The control process requires inputting these parameters into the injection molding machine's operating system to ensure the equipment executes according to the set values. During production, the equipment uses sensors to monitor the molding status in real time, maintaining a stable process environment. Injection molding refers to injecting heated and molten plastic material into the mold cavity of the injection molding machine, where it cools and solidifies to form the desired product. The application of the actual process parameter combination directly affects the quality of the final product. For example, too low an injection pressure may lead to incomplete filling, while too high a mold temperature may cause warpage defects; therefore, strict control is necessary.

[0028] The aforementioned intelligent control method for improving the molding efficiency of injection molds can achieve the technical goal of optimizing and dynamically adjusting injection molding process parameters, thereby improving production efficiency, reducing product defect rate, and stabilizing product quality.

[0029] Furthermore, such as Figure 2 As shown, this application also includes:

[0030] Obtain quality index factors, and extract quality index factor parameters based on factor levels from the initial experimental parameter range, wherein the quality index factor parameters correspond to the quality index factors; enumerate and combine the quality index factor parameters to obtain quality index experimental combinations; execute the quality index experimental combinations to obtain the quality index experimental responses; compare the quality index experimental responses to obtain the optimal experimental parameter combination.

[0031] Specifically, obtaining quality index factors refers to identifying factors affecting product quality by analyzing key quality indicators (such as warpage, wall thickness uniformity, and dimensional accuracy) during the manufacturing process. Quality index factors can include injection pressure, mold temperature, and injection speed. The impact of different values ​​of these factors on product quality is evaluated, and corresponding factor levels are extracted from the initial experimental parameter range based on their influence, forming a set of quality index factor parameters. These parameters correspond to different process conditions that may occur in actual production, providing a data foundation for subsequent optimization.

[0032] Next, the quality indicator factor parameters are enumerated and combined, that is, all possible factor levels are combined to form multiple sets of experimental parameter combinations. Each set of experimental parameter combinations corresponds to a different set of process parameters, used to test and analyze their impact on product quality. By enumerating, all possible parameter configurations can be covered, thereby obtaining comprehensive data under different process conditions. For example, the experimental parameter combinations are shown in Table 1 below:

[0033] ;

[0034] ;

[0035] Next, the quality indicator test combinations are executed, which involves actual production testing based on the test combinations from the previous step. The tests will be based on different parameter combinations, with actual injection molding production to measure the impact of each parameter combination on quality indicators. For example, the warpage and dimensional accuracy of the molded product will be measured. Each test combination will generate a set of experimental response data that reflects the actual performance under those combined conditions.

[0036] Finally, by comparing the experimental responses to the quality indicators, the optimal parameter combination, which performs best across all experiments, can be determined. This optimal parameter combination maximizes product quality, reduces defects, and improves production efficiency. The comparison process analyzes the strengths and weaknesses of each group of experimental response data to determine the process parameters that best meet product quality requirements.

[0037] By acquiring quality index factors and extracting relevant parameters from the initial experimental parameter range, and through enumeration and combination and actual experiments, the optimal combination of process parameters is finally obtained. By continuously comparing experimental responses, the optimal parameter configuration is selected, thereby optimizing the production process and improving product quality.

[0038] Furthermore, this application also includes:

[0039] Initialize the parameter space, generate the initial population based on the parameter space, the initial population includes multiple initial solutions; extract the first initial solution based on the multiple initial solutions; perform an explosion search on the first initial solution to generate a first spark; evaluate the first spark through the quality index prediction model to generate a first fitness; based on the first fitness, traverse the multiple initial solutions to obtain a preset number of optimal solutions, and integrate them to obtain the optimal population.

[0040] Specifically, initializing the parameter space refers to setting the range of all possible parameters, such as the injection pressure range and mold temperature range. The parameter space defines all possible search regions, providing a basis for subsequent optimization. Multiple initial solutions are randomly generated within the parameter space until a population containing multiple initial solutions is formed.

[0041] A first initial solution is randomly extracted from multiple initial solutions. Explosive search of the first initial solution involves local perturbation in the vicinity of the first initial solution to generate multiple new solutions, i.e., sparks. For example, centered on the first initial solution, increasing or decreasing the injection pressure by 0.5 MPa and increasing or decreasing the mold temperature by 1 degree Celsius will generate multiple new spark solutions.

[0042] Evaluating the first spark through a quality index prediction model means inputting each spark solution into the model, calculating the response data of its corresponding quality index (e.g., warpage or dimensional error), and then evaluating the fitness of this response data to generate a fitness value, i.e., the first fitness. Following the method for generating the first fitness, multiple initial solutions are sequentially accessed for optimization calculations, and their fitness is evaluated. Based on these fitness values, a predetermined number of optimal solutions are selected. This involves a global comparison of all initial solutions and their generated spark solutions, selecting several solutions with higher fitness. Finally, these optimal solutions are integrated into a new optimal population for the next iteration.

[0043] Starting with the initial population generated by initializing the parameter space, the process involves gradually extracting initial solutions, performing an explosive search, evaluating spark fitness using a quality index prediction model, and finally selecting the optimal solution to construct a new population. By continuously iterating and updating the population, the process gradually approaches the global optimum, thereby finding the optimal combination of process parameters.

[0044] Furthermore, this application also includes:

[0045] An explosion is performed based on the first initial mass of the first initial solution to generate the first spark. The first spark has a first spark quantity, a first spark density, and a first spark range. The correlation coefficient between the first spark quantity and the first initial mass is positive, the correlation coefficient between the first spark density and the first initial mass is positive, and the correlation coefficient between the first spark range and the first initial mass is negative.

[0046] Specifically, "exploding based on the initial quality of the first initial solution" means triggering an explosion operation centered on the first initial solution, based on its quality (such as fitness value), to generate new solutions. The initial quality reflects the quality of the solution; for example, a higher quality indicates that the solution performs better in the optimization objective and is suitable as the basis for the explosion. Generating the first spark refers to applying a certain perturbation to the first initial solution to produce a new set of solutions (i.e., sparks). The distribution and number of sparks are controlled by the explosion parameters and are used to explore the surrounding area of ​​the solution to find potentially better solutions.

[0047] The first spark has a first spark quantity, a first spark density, and a first spark range, representing the number of sparks generated in each explosion, the spatial distribution of the sparks, and the search area for spark generation. For example, the first spark quantity determines how many new solutions the explosion produces, the first spark density determines the concentration of these new solutions within a local region, and the first spark range represents the maximum search radius of the new solutions from the initial solution. The correlation coefficient between the first spark quantity and the first initial mass is positive, meaning that the higher the quality of the initial solution, the more sparks are generated, thus allowing for a more thorough search of the area surrounding the high-quality solution.

[0048] The correlation coefficient between the first spark density and the first initial quality is positive, indicating that the higher the quality of the initial solution, the denser the distribution of sparks in its vicinity, reflecting a fine search for high-quality solutions. When the quality is low, the spark distribution will be more dispersed, allowing for a wider exploration.

[0049] The correlation coefficient between the first spark range and the first initial quality is negative, indicating that the higher the initial solution quality, the smaller the spark search range, and vice versa. This is used to increase the probability of finding a better solution in the low-quality solution region.

[0050] Sparks are generated by assessing the quality of the initial solution. By combining the control mechanisms of spark quantity, density, and range, search resources are allocated rationally. High-quality solutions generate more sparks and are searched more extensively, while low-quality solutions are explored more broadly, thereby gradually improving the overall optimization effect.

[0051] Furthermore, this application also includes:

[0052] Based on the first fitness, the first spark is iteratively exploded according to the first spark range until the exploding sparks tend to converge, generating the first exploding spark; based on the first exploding spark, the multiple initial solutions are traversed to obtain multiple exploding sparks; the fitness of the multiple exploding sparks is evaluated, and the preset number of exploding sparks is extracted based on the multiple exploding fitness to obtain the optimal solution.

[0053] Specifically, based on the first fitness, the first spark is iteratively exploded according to the first spark range. This means that after the first explosion, based on the fitness of each spark, it is determined whether further optimization of the search region is needed. If sparks with higher fitness still have potential for improvement, these sparks are exploded again to generate new solutions. The iterative explosion gradually narrows the search region according to the first spark range, eventually converging, indicating that the change in the solution is no longer significant. At this point, the explosion operation stops, and the first exploding spark is generated.

[0054] Based on the first explosion spark, multiple explosion sparks are obtained by traversing multiple initial solutions. This means that not only are the current explosion results preserved, but the search range is also expanded by combining other solutions in the initial population. Possible high-quality sparks are selected from these, ensuring that the optimization process is not limited to the vicinity of a single solution, but makes full use of the diversity of the initial population, thereby avoiding getting trapped in local optima.

[0055] Evaluating the fitness of multiple explosion sparks means predicting and evaluating the quality indicators of each generated spark, such as calculating the warpage, wall thickness uniformity, and other indicators corresponding to each spark solution, and generating a fitness value. Extracting a preset number of explosion sparks based on multiple explosion fitness means selecting the solutions with the highest fitness from all sparks as the optimal solutions, which are used in the next iteration or as the final optimization result.

[0056] By iteratively exploding the sparks to gradually refine the search, combining the traversal of the initial solution to expand the search range, and then using fitness evaluation to select the optimal solution, a gradual approximation from the initial population to the final optimization result is achieved. This ensures both a fine search for the solution and takes into account global exploration, increasing the possibility of finding the global optimum.

[0057] Furthermore, this application also includes:

[0058] The first spark is input into the quality index prediction model for response analysis, and the first quality index optimization response is output; the fitness of the first quality index optimization response is calculated to generate the first fitness.

[0059] Specifically, the spark solution generated by the first explosion is fed into the quality index prediction model. This model rapidly estimates possible quality index results based on the spark's parameter combinations, such as product warpage, wall thickness uniformity, or dimensional deviation. It then outputs the first quality index optimization response, representing the model's prediction result, used to measure the performance of each spark in the optimization objective. The optimization response can be a single index or a combined value of multiple indices; for example, lower warpage indicates better quality, or multiple indices can be combined using a weighted approach.

[0060] The optimization response based on the first quality index is converted into a fitness value, which is used to compare the quality of different sparks. For example, warpage and dimensional deviation are normalized separately, and then weighted and summed according to preset weights to generate fitness values. The higher the fitness value, the better the overall performance of the spark solution, and the more suitable it is for optimization.

[0061] The first fitness is generated by fitness calculation, which means that the fitness is used as the final score for each spark solution to evaluate the quality of the solution and select the optimal solution.

[0062] By inputting the spark solution into the prediction model for response analysis, the quality index response can be quickly obtained. Then, the fitness value is calculated based on these responses to evaluate the quality of the spark solution, thereby providing data support for the next step of selecting the optimal solution.

[0063] Furthermore, this application also includes:

[0064] Set the initial experimental parameters; perform model flow analysis on the initial experimental parameters using a CAE simulation tool to obtain the model flow analysis results; adjust the initial experimental parameters based on the model flow analysis results to determine the range of the initial experimental parameters.

[0065] Specifically, initial experimental parameters are set, including injection pressure, holding time, and mold temperature. These initial settings are determined based on past experience or engineering design requirements and are used to initially initiate the mold manufacturing process.

[0066] Next, CAE simulation tools were used to perform mold flow analysis on the initial experimental parameters, simulating the flow, cooling, and molding behaviors during the injection molding process. Mold flow analysis helps to understand the mold's performance under different parameters, such as the filling speed of the plastic melt, temperature distribution, and potential defects like bubbles and warpage. The results of the mold flow analysis provide data support and theoretical basis for subsequent parameter adjustments.

[0067] After obtaining the mold flow analysis results, the initial experimental parameters are adjusted based on these results to optimize various indicators during the injection molding process. For example, if the temperature in some areas is too high or the filling time is too long in the mold flow analysis results, the mold temperature or injection speed is adjusted. Adjustments are made based on actual performance to find the optimal process parameters.

[0068] Finally, based on the adjusted data, a preliminary parameter range was determined, providing a reasonable range of process parameters for subsequent actual production. Further testing and optimization can be carried out within this range to ultimately ensure product quality and production efficiency.

[0069] By setting initial experimental parameters and using CAE simulation tools to perform mold flow analysis, relevant data can be obtained and parameters can be adjusted to ultimately determine the effective parameter range, which can then be used to optimize the injection molding process and improve product quality and production efficiency.

[0070] Furthermore, this application also includes:

[0071] A preset deviation threshold is set; the deviation between the production response and the predicted response of the quality indicator is calculated to obtain the deviation result; if the deviation result does not meet the deviation threshold, the optimal process parameter combination is adjusted to obtain the actual process parameter combination.

[0072] Specifically, a preset deviation threshold refers to setting an allowable error range in actual production to measure whether the deviation between the actual and predicted results of quality indicators is within an acceptable range. For example, for product dimensional deviations, a deviation threshold of less than 5% might be set, meaning the error between the actual size and the target size must not exceed 5%. The preset deviation threshold serves as the criterion for subsequent adjustments, and its value directly relates to production accuracy and the difficulty of adjustment.

[0073] Deviation calculation of the production response and predicted response of quality indicators involves comparing the quality indicators obtained in actual production (such as warpage, dimensional deviation, etc.) with the quality indicators given by the prediction model and calculating the difference between the two. The purpose of deviation calculation is to quantify the degree of agreement between the production results and the prediction model, and to determine whether further optimization of process parameters is needed.

[0074] Obtaining a deviation result means that, after calculation, a numerical value is obtained for evaluation. The deviation result indicates the deviation status of the current production state. For example, if the deviation result is 6% and the deviation threshold is 5%, it means that the current production state has not met the preset quality requirements and adjustments are needed. If the deviation result is less than or equal to the threshold, it means that the current process parameters can meet the production requirements.

[0075] If the deviation result does not meet the deviation threshold, the optimal process parameter combination is adjusted. This means that when the deviation exceeds the threshold, the previously determined optimal process parameters need to be readjusted to further optimize production results. For example, the adjustment process may be as shown in Table 2 below, ensuring the efficiency and effectiveness of the adjustment.

[0076] ;

[0077] Obtaining the actual process parameter combination means that, after adjustments, an improved set of parameters has been determined. This actual process parameter combination is used in actual production to further reduce deviations and improve product quality.

[0078] By setting a preset deviation threshold, calculating the deviation between actual and predicted results, and adjusting parameters when the deviation exceeds the standard, the process combination is gradually optimized to ensure production quality and achieve a high degree of consistency between actual production and the prediction model.

[0079] In summary, the intelligent control method for improving the molding efficiency of injection molds provided in this application has the following technical effects:

[0080] Mold flow analysis is performed using initial experimental parameters, and the initial experimental parameter range is configured based on the mold flow analysis results. Quality index factor parameters are extracted based on the initial experimental parameter range, and the experiment is executed using these parameters to obtain the quality index experimental response. The optimal experimental parameter combination is obtained by comparing the quality index experimental response. A quality index prediction model is constructed based on the optimal experimental parameter combination and the quality index experimental response. An initial population is constructed and a burst search is performed to obtain the optimal population, which represents the optimal process parameter combination. The production response of the quality index is collected based on the optimal process parameter combination, and a deviation analysis is performed between the production response and the predicted response based on the quality index prediction model. The optimal process parameter combination is adjusted based on the deviation results to obtain the actual process parameter combination. Injection mold forming is controlled based on the actual process parameter combination. In other words, by optimizing and dynamically adjusting injection molding process parameters, the technical effects of improving production efficiency, reducing product defect rate, and stabilizing product quality are achieved.

[0081] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. An intelligent control method for improving the molding efficiency of injection molds, characterized in that, include: Mold flow analysis is performed using initial experimental parameters, and the range of initial experimental parameters is configured based on the results of the mold flow analysis. Based on the initial experimental parameter range, extract the quality index factor parameters, execute the experiment using the quality index factor parameters to obtain the quality index experimental response, and compare the quality index experimental response to obtain the optimal experimental parameter combination. A quality index prediction model is constructed based on the optimal combination of experimental parameters and the experimental response of the quality index. An initial population is constructed and a burst search is performed to obtain the optimal population, which is the optimal combination of process parameters, including: Initialize the parameter space, and generate the initial population based on the parameter space. The initial population includes multiple initial solutions. Extract the first initial solution based on the plurality of initial solutions; An explosion search is performed on the first initial solution to generate the first spark; The first spark is evaluated using the quality index prediction model to generate a first fitness. Based on the first fitness, the multiple initial solutions are traversed to obtain a preset number of optimal solutions, which are then integrated to obtain the optimal population. Specifically, the explosion is performed based on the first initial mass of the first initial solution to generate the first spark. The first spark has a first spark quantity, a first spark density, and a first spark range. The correlation coefficient between the first spark quantity and the first initial mass is positive. The correlation coefficient between the first spark density and the first initial mass is positive. The correlation coefficient between the first spark range and the first initial mass is negative. The production response of quality indicators is collected based on the optimal combination of process parameters. The deviation analysis is performed between the production response of quality indicators and the predicted response of quality indicators obtained by predicting the optimal combination of process parameters based on the prediction model of quality indicators. The optimal combination of process parameters is adjusted according to the deviation results to obtain the actual combination of process parameters. The injection mold forming is controlled based on the actual combination of process parameters.

2. The intelligent control method for improving the molding efficiency of injection molds as described in claim 1, characterized in that, The process of extracting quality index factor parameters based on the initial experimental parameter range, executing the experiment using the quality index factor parameters to obtain the quality index experimental response, and comparing the quality index experimental response to obtain the optimal experimental parameter combination includes: Obtain quality index factors, and extract quality index factor parameters based on factor levels from the initial experimental parameter range, wherein the quality index factor parameters correspond to the quality index factors. The quality index factor parameters are enumerated and combined to obtain the experimental combination of quality indexes; The experiment was conducted using the combination of the quality indicators, and the experimental responses for the quality indicators were obtained. The experimental responses to the quality indicators are compared to obtain the optimal combination of experimental parameters.

3. The intelligent control method for improving the molding efficiency of injection molds as described in claim 1, characterized in that, The step of obtaining a preset number of optimal solutions by traversing the plurality of initial solutions based on the first fitness includes: Based on the first fitness, the first spark is iteratively exploded according to the first spark range until the exploding sparks tend to converge, thus generating the first exploding spark. Based on the first explosion spark, multiple explosion sparks are obtained by traversing the multiple initial solutions; The fitness of the multiple explosion sparks is evaluated, and the preset number of explosion sparks is extracted based on the multiple explosion fitness to obtain the optimal solution.

4. The intelligent control method for improving the molding efficiency of injection molds as described in claim 1, characterized in that, The step of evaluating the first spark using the quality index prediction model and generating a first fitness includes: The first spark is input into the quality index prediction model for response analysis, and the first quality index optimization response is output. The fitness of the first quality index optimization response is calculated to generate the first fitness.

5. The intelligent control method for improving the molding efficiency of injection molds as described in claim 1, characterized in that, The process of performing model flow analysis using initial experimental parameters and configuring the range of initial experimental parameters based on the model flow analysis results includes: Set the initial experimental parameters; The initial experimental parameters were analyzed using CAE simulation tools to obtain the model flow analysis results. The initial experimental parameters are adjusted based on the model flow analysis results to determine the range of the initial experimental parameters.

6. The intelligent control method for improving the molding efficiency of injection molds as described in claim 1, characterized in that, The process of obtaining the actual combination of process parameters includes: Preset deviation threshold; The deviation between the production response to the quality indicator and the predicted response to the quality indicator is calculated to obtain the deviation result. If the deviation result does not meet the deviation threshold, the optimal process parameter combination is adjusted to obtain the actual process parameter combination.

Images