Parameter adjustment method of injection molding process, electronic device, and readable storage medium

Abstract

The application discloses a parameter adjustment method of an injection molding process, an electronic device and a readable storage medium, comprising: acquiring injection molding production parameters and size detection data in an injection molding production cycle; confirming main adjustment parameters and auxiliary adjustment parameters in the injection molding production parameters based on the feature importance weight of product key dimensions and the like of the injection molding production parameters; inputting parameter values corresponding to the main adjustment parameters and the auxiliary adjustment parameters in the injection molding production parameters and the size detection data into a process parameter optimization model to obtain candidate parameter adjustment results; selecting target adjustment parameter values corresponding to the main adjustment parameters and the auxiliary adjustment parameters from the candidate parameter adjustment results; generating pre-adjustment data according to the target adjustment parameter values corresponding to the main adjustment parameters and the auxiliary adjustment parameters, and controlling an injection molding device to perform corresponding parameter adjustment actions. In this way, the main and auxiliary adjustment parameters are screened out and model optimization is performed, closed-loop adaptive control of injection molding parameter adjustment is realized, and the parameter adjustment efficiency and product size precision are significantly improved.

Description

Technical Field

[0001] This invention relates to the fields of injection molding and intelligent manufacturing technology, and in particular to a method for adjusting parameters of an injection molding process, an electronic device, and a computer-readable storage medium. Background Technology

[0002] As the injection molding industry transforms towards intelligent and flexible manufacturing, downstream applications are continuously increasing their requirements for the precision and consistency of injection molded products. At the same time, efficiency, energy consumption, and cost control must be taken into account during the production process.

[0003] Traditional injection molding process parameter adjustments rely on the professional experience of operators and employ a trial-and-error approach, which has several drawbacks: First, the efficiency of parameter adjustment is low. For example, parameters such as mold temperature, hot runner temperature, and cavity pressure need to be adjusted individually, resulting in insufficient centralized control of injection molding parameters and difficulty in ensuring stability. Second, the timeliness is poor. From product NG information feedback to mold parameter confirmation and finally parameter adjustment, this process can significantly affect the equipment's U-value. Third, energy consumption and costs are high. Manual parameter adjustment makes it difficult to achieve synergistic optimization of quality, efficiency, and energy consumption, and the training cost for professional operators is high.

[0004] Therefore, there is an urgent need for a method for adjusting injection molding process parameters, electronic equipment, and computer-readable storage media to solve the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a parameter adjustment method, electronic device and computer-readable storage medium for injection molding process, which can realize closed-loop adaptive control of injection molding parameter adjustment by screening the main and auxiliary adjustment parameters and performing model optimization, thereby significantly improving the parameter adjustment efficiency and product dimensional accuracy.

[0006] To achieve the above objectives: This application provides a method for adjusting parameters in an injection molding process, comprising: acquiring multi-source data during the injection molding production cycle, wherein the multi-source data includes at least injection molding production parameters and dimensional detection data; based on the characteristic importance weights of the injection molding production parameters to key dimensions of the product, and in conjunction with preset process rules, identifying the primary and secondary adjustment parameters in the injection molding production parameters; inputting the parameter values ​​corresponding to the primary and secondary adjustment parameters in the injection molding production parameters, and the dimensional detection data, into a process parameter optimization model to obtain candidate adjustment results; verifying whether the prediction index of the candidate adjustment results meets a preset accuracy threshold; selecting the combination with the best prediction effect from the candidate adjustment results that meet the preset accuracy threshold, and determining it as the target primary adjustment parameter and the target secondary adjustment parameter; using the adjustment parameter values ​​corresponding to the target primary adjustment parameter and the target secondary adjustment parameter as the target adjustment parameter values ​​of the primary adjustment parameter and the secondary adjustment parameter, respectively; generating pre-adjustment data based on the target adjustment parameter values ​​corresponding to the primary adjustment parameter and the secondary adjustment parameter, and controlling the injection molding equipment to perform corresponding parameter adjustment actions.

[0007] In one embodiment, before assigning the characteristic importance weights of the product's critical dimensions based on the injection molding production parameters, the process includes: determining the product's critical dimensions according to product quality requirements; verifying the preset injection molding production parameters using the controlled variable method to determine the injection molding production parameters that affect the product's critical dimensions, and determining the standard values ​​and process windows of the injection molding production parameters.

[0008] In one embodiment, the parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter in the injection molding production parameters, as well as the dimensional detection data, are input into the process parameter optimization model to obtain candidate parameter tuning results. This includes: inputting the parameter values ​​and the corresponding dimensional detection data as input parameters into the process parameter optimization model constructed based on the XGBoost algorithm; controlling the process parameter optimization model to perform parameter optimization calculations within the constraint boundaries defined by the process window; and outputting multiple sets of candidate parameter tuning results.

[0009] In one embodiment, before inputting the parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter in the injection molding production parameters, as well as the dimensional detection data, into the process parameter optimization model, the method further includes: obtaining historical dimensional detection data of a preset batch of products produced immediately adjacent to the current time, and historical injection molding production parameters corresponding to the historical dimensional detection data; calculating the average value of the historical dimensional detection data to obtain a real-time compensation factor characterizing the current environmental fluctuations; and combining the historical injection molding production parameters with the real-time compensation factor to incrementally update or dynamically compensate the process parameter optimization model.

[0010] In one embodiment, after controlling the injection molding equipment to perform the corresponding parameter adjustment action, the method further includes: acquiring the actual size detection data of the product produced after parameter adjustment; calculating the actual deviation between the actual size detection data and the predicted size output by the process parameter optimization model; and updating and optimizing the parameter adjustment coefficients of the process parameter optimization model based on the actual deviation.

[0011] In one embodiment, after generating pre-adjustment data based on the target adjustment parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter, the process includes: converting the pre-adjustment data into a control message recognizable by the programmable logic controller (PLC) of the injection molding equipment; and when the injection molding equipment completes the current production cycle and is in a standby state, sending the control message to the PLC to apply the pre-adjustment data in the next production cycle.

[0012] In one embodiment, after controlling the injection molding equipment to perform the corresponding parameter adjustment action, the method further includes: acquiring the actual size detection data of the products produced in the preset batch after parameter adjustment; acquiring the corresponding preset size tolerance range based on the key dimensions of the products; comparing the actual size detection data with the preset size tolerance range, and when the actual size detection data exceeds the size tolerance range, determining that the corresponding product is unqualified, and counting the number of consecutive unqualified determinations; when the number of unqualified determinations reaches a preset abnormal threshold, generating a mistake-proof control command, which is used to lock the current injection molding production parameters or control the injection molding equipment to revert to the injection molding production parameters before parameter adjustment.

[0013] This application also provides an electronic device, including: a processor and a memory storing a computer program, wherein when the processor runs the computer program, the steps of the above method are implemented.

[0014] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0015] The parameter adjustment method, electronic device, and computer-readable storage medium for injection molding processes provided in this application include: acquiring multi-source data during the injection molding production cycle, the multi-source data including at least injection molding production parameters and dimensional detection data; identifying primary and secondary adjustment parameters in the injection molding production parameters based on the characteristic importance weights of the injection molding production parameters to key product dimensions, combined with preset process rules; inputting the parameter values ​​corresponding to the primary and secondary adjustment parameters in the injection molding production parameters, along with the dimensional detection data, into a process parameter optimization model to obtain candidate parameter adjustment results; selecting target adjustment parameter values ​​corresponding to the primary and secondary adjustment parameters from the candidate parameter adjustment results; generating pre-adjustment data based on the target adjustment parameter values ​​corresponding to the primary and secondary adjustment parameters, and controlling the injection molding equipment to perform corresponding parameter adjustment actions. Thus, by selecting the primary and secondary adjustment parameters and performing model optimization, closed-loop adaptive control of injection molding parameter adjustment is achieved, significantly improving adjustment efficiency and product dimensional accuracy. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a parameter adjustment method for an injection molding process provided in an embodiment of the present invention.

[0017] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. In the following description relating to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements.

[0019] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0020] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, can be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" as used herein are to be interpreted as inclusive, or mean any one or any combination thereof. Therefore, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C". Exceptions to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0021] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0022] It should be noted that step designations such as S1 and S2 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the protection scope of this application.

[0023] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0024] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0025] See Figure 1 This application provides a method for adjusting parameters in an injection molding process. This method can be executed by an intelligent control system for injection molding process parameters provided in this application. The system can be implemented using software and / or hardware. In this embodiment, the execution entity of the method is an IAC system. The method provided in this embodiment includes: Step S1: Obtain multi-source data during the injection molding production cycle.

[0026] The multi-source data includes at least: injection molding production parameters and dimensional inspection data.

[0027] Injection molding production parameters can be divided into injection molding machine operating parameters and mold condition parameters. Injection molding machine operating parameters include: injection speed, V / P (speed / pressure switching point), holding pressure, holding time, metering position, screw speed, back pressure, and barrel temperature, etc. Mold condition parameters include: hot runner temperature and cavity pressure, etc.

[0028] Dimensional inspection data includes: length (geometric dimensions of the product, dimensional inspection data), etc.

[0029] It should be noted that multi-source data also includes: peak pressure (usually referring to the highest value of cavity pressure or injection machine nozzle pressure during the injection molding process) and viscosity (in actual industrial AI algorithms, viscosity is usually a virtual variable (derived parameter) derived from data such as cavity pressure, injection speed and temperature through algorithm formula derivation).

[0030] Specifically, in each complete production cycle of injection molding (from mold closing, injection, pressure holding, cooling to mold opening and demolding), a comprehensive dataset (i.e., multi-source data) is collected synchronously or asynchronously from multiple heterogeneous data sources such as injection molding machines, molds (HT), AOI equipment, and Kistler monitoring systems through a data acquisition system. This dataset comprehensively reflects the current injection molding process status and product quality results.

[0031] Step S2: Based on the characteristic importance weight of injection molding production parameters to the key dimensions of the product, and in conjunction with the preset process rules, confirm the main adjustment parameters and auxiliary adjustment parameters in the injection molding production parameters.

[0032] In injection-molded products, critical dimensions are specific geometric dimensions or form and position tolerances that have a decisive impact on the final assembly performance, core functionality, overall appearance quality, or subsequent processing steps. When these dimensions exceed tolerances, it can directly lead to the product being unable to be assembled, functional failure, or serious batch quality defects.

[0033] Key product dimensions include at least one of the following: assembly fit dimensions, functional positioning dimensions, appearance critical dimensions, and process-sensitive dimensions.

[0034] Feature importance weight is a quantitative indicator that characterizes the degree of influence of each injection molding production parameter (such as temperature, pressure, speed, time, etc.) on the changes in the critical dimensions of the final product. The magnitude of this weight directly reflects the sensitivity and contribution of the injection molding process parameter to improving or worsening the critical dimensions of the product.

[0035] The main adjustment parameters have a decisive influence on the key dimensions of the product and are the core objects for the optimization model to make significant adjustments (such as injection pressure, holding time, etc.).

[0036] Auxiliary adjustment parameters have an auxiliary impact on dimensions and are mainly used for fine-tuning compensation or stabilizing the molding process (such as mold temperature, cooling time, etc.).

[0037] It should be noted that feature importance weights calculated purely from data may be affected by outliers. Therefore, they need to be combined with preset process rules (i.e., expert knowledge of the physical mechanisms of injection molding). For example, if the cooling time in the injection molding production parameters has a very high weight for a certain dimension, but the process rules determine that this dimension is mainly affected by the holding pressure in the injection molding production parameters, the system will adjust the weights or perform secondary screening based on the process rules to ensure that the final confirmed primary / secondary adjustment parameters conform to both data patterns and actual physical mechanisms.

[0038] Specifically, based on the importance of each parameter and its influence on length, the characteristic importance weight of each injection molding production parameter to the critical dimensions of the product is calculated (obtained in advance through DOE (Design of Experiments) data validation of the injection molding production parameters). This weight characterizes the statistical contribution and influence of a single parameter on the variation of product dimensions. Then, the characteristic importance weight is combined with preset process rules (i.e., expert knowledge of the physical mechanisms of injection molding) for cross-comparison. If the two are consistent, the weight is maintained; if the weight of a non-sensitive parameter obtained from DOE validation is abnormally high due to noise or other interference, a penalty attenuation (mechanism correction) can be applied according to the preset process rules. Additionally, if a critical parameter in the injection molding production parameters is missed in DOE validation due to a small range of historical data variation, a basic minimum weight can be assigned to the corresponding parameter according to the process rules (mechanism supplementation). Finally, based on the final weight after fusion and correction, it can be graded according to preset thresholds. If the final weight is higher than the first preset threshold (e.g., the proportion > 30%), it is confirmed as the main adjustment parameter (e.g., holding pressure) and used as the core of optimization; if it is lower than the first preset threshold, it is confirmed as the auxiliary adjustment parameter (e.g., mold temperature, cooling time) and used to assist in fine-tuning compensation.

[0039] Step S3: Input the parameter values ​​corresponding to the main adjustment parameters and auxiliary adjustment parameters in the injection molding production parameters, as well as the dimensional detection data, into the process parameter optimization model to obtain the candidate parameter adjustment results.

[0040] The process parameter optimization model is a nonlinear mapping and inverse solution system built based on machine learning algorithms. This model takes injection molding production parameters (such as temperature, pressure, and speed) as input features and the product's key dimensions as output targets. By learning from massive amounts of historical production data, it establishes a complex nonlinear mapping relationship between injection molding production parameters and dimensional results. During actual parameter tuning, the model can, based on the current dimensional deviation and within the preset process window constraints, inversely derive and output multiple sets of candidate parameter tuning results that allow the dimensions to revert to the target values.

[0041] Step S4: Select the target adjustment parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter from the candidate parameter tuning results.

[0042] Specifically, after the process parameter optimization model outputs multiple sets of candidate parameter tuning results that meet the dimensional accuracy requirements, the optimal parameter combination is selected from the candidate results based on a preset comprehensive evaluation strategy. This combination includes the target adjustment values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter, aiming to make the product's key dimensions stably return to the target value with minimal production fluctuations and the lowest adjustment cost.

[0043] Step S5: Generate pre-adjustment data based on the target adjustment parameter values ​​corresponding to the main adjustment parameter and auxiliary adjustment parameter, and control the injection molding equipment to perform the corresponding parameter adjustment actions.

[0044] The pre-adjustment data is calculated by the process parameter optimization model and is the final injection molding production parameter value (i.e., the target main adjustment parameter and the target auxiliary adjustment parameter) after verification and optimization.

[0045] Specifically, after completing the optimization calculation and determining the optimal combination of main and auxiliary adjustment parameters, the target adjustment parameter values ​​are converted into standardized control instructions (i.e., pre-adjustment data) that can be recognized and executed by the injection molding machine's underlying controller (such as a PLC or dedicated control board). These instructions are then precisely issued and executed while ensuring the equipment is in a safe and ready state, thereby achieving automated closed-loop adjustment of the injection molding process parameters. In this embodiment, the injection molding equipment includes at least an injection molding machine and an injection mold.

[0046] The above method first identifies the primary and secondary adjustment parameters in injection molding production. Then, using a process parameter optimization model, it reverse-engineers the parameter value combinations that meet product quality requirements. Subsequently, through standardized instruction conversion and a strict safety triggering mechanism, automated closed-loop adjustment of injection molding equipment parameters is achieved. This solution effectively overcomes the shortcomings of traditional parameter adjustment, which relies excessively on manual experience, and significantly improves adjustment efficiency and product dimensional accuracy.

[0047] In one embodiment, prior to assigning feature importance weights to critical dimensions of the product based on injection molding production parameters, the following steps are included: Determine the key dimensions of the product based on product quality requirements; The preset injection molding production parameters were verified by using the controlled variable method to determine the injection molding production parameters that affect the critical dimensional accuracy of the product, and to determine the standard values ​​and process windows of the injection molding production parameters.

[0048] Controlled variable method: In injection molding process verification, this method refers to artificially changing only one preset injection molding production parameter (such as holding pressure) while keeping all other injection molding production parameters (such as injection speed, cooling time, etc.) constant. The actual impact of the change of this single variable on the accuracy of the product's key dimensions is observed and recorded, thereby scientifically identifying the parameter that truly plays a decisive role.

[0049] Standard values ​​for injection molding production parameters: These are the optimal set of process parameters (e.g., optimal holding pressure of 80 MPa) determined after verification using the controlled variable method or scientific trial molding, which enables the product's key dimensions to reach their best target values ​​and achieves the highest overall yield. This serves as the reference center point for subsequent mass production.

[0050] It should be noted that the standard value is the theoretically optimal solution obtained using the controlled variable method under specific conditions of time, material batch, and temperature and humidity. It assumes that the production environment is absolutely constant. However, in a real injection molding workshop, ambient temperature and humidity vary, raw materials exhibit batch-to-batch differences, molds experience continuous wear, and even hydraulic oil temperature can rise with operating time. These uncontrollable dynamic disturbances can cause the originally perfect standard value to gradually become invalid, resulting in drift in critical product dimensions. Therefore, dynamic adjustments are necessary using a process parameter optimization model.

[0051] Process window: The safe range (i.e., upper and lower limits) within which injection molding production parameters are allowed to fluctuate reasonably, based on standard values. Within this process window, even if there are minor fluctuations in the production environment or materials, the critical dimensions of the product can still be stably maintained within tolerance requirements without causing secondary defects such as flash or insufficient glue.

[0052] For example, a process parameter optimization model might calculate extremely high holding pressures or extremely high melt temperatures to address the issue of undersized dimensions. If these exceed the process window, while the dimensions may meet the requirements, it can lead to serious secondary defects such as burrs, material degradation (burning), and excessive internal residual stress in the product. Therefore, it is necessary to use a defined process window to ensure that the parameter tuning scheme provided by the model is comprehensively acceptable.

[0053] The following explanation uses the injection molding production of a precision electronic housing for automobiles as an example: Determine the product's critical dimensions: During the drawing evaluation phase, if engineers discover that the spacing of the internal positioning clip holes in the housing directly affects the subsequent installation of the PCB board, and that exceeding the tolerance will cause assembly jamming; while other parts do not affect functionality, then the clip hole spacing is defined as the product's critical dimension, and its strict tolerance requirement is set at ±0.05mm.

[0054] Parameter verification was performed using the controlled variable method: Engineers first obtained preset injection molding production parameters (i.e., all injection molding production parameters related to the shell's injection molding, such as holding pressure, mold temperature, and cooling time). Then, the mold temperature and cooling time were locked at fixed values, with only the holding pressure adjusted (e.g., gradually increasing from 60MPa to 100MPa in 10MPa increments). After testing the holding pressure, the mold temperature and cooling time were tested and verified sequentially. If measurements showed that changes in holding pressure or mold temperature caused changes in the hole spacing (with little or no effect from cooling time), then the holding pressure and mold temperature were determined to be the core injection molding production parameters affecting the accuracy of this critical dimension.

[0055] In addition, based on the above verification results, standard values ​​for injection molding production parameters are determined (e.g., standard holding pressure: 80MPa). Taking into account flash risk and dimensional lower limits, a safe fluctuation range for injection molding production parameters is set (e.g., holding pressure from 75MPa to 85MPa), i.e., the process window for these parameters.

[0056] In one embodiment, the parameter values ​​corresponding to the main and auxiliary adjustment parameters in the injection molding production parameters, along with dimensional inspection data, are input into the process parameter optimization model to obtain candidate parameter tuning results, including: The parameter values ​​and corresponding dimensional detection data are input as input parameters into the process parameter optimization model built based on the XGBoost algorithm; The process parameter optimization model performs parameter optimization calculations within the constraint boundaries defined by the process window and outputs multiple sets of candidate parameter tuning results.

[0057] Process parameter optimization model: A mathematical mapping model built based on machine learning algorithms (specifically XGBoost algorithm in this embodiment). This model is trained using a large amount of historical injection molding production parameter data (including injection molding production parameter settings and corresponding product dimension detection results), and can accurately fit the nonlinear and complex relationship between injection molding production parameters and key product dimensions. Upon receiving the current injection molding production parameters and dimensional deviations, the model can perform back-calculation or grid search internally to predict and output the optimal parameter combination that allows the dimensions to revert to the target value.

[0058] The constraint boundary, or process window, is the specific manifestation of the process window at the algorithm level. It is the absolute physical and safety boundary that the process parameter optimization model must adhere to during calculation. During the optimization process, the values ​​of the primary and secondary adjustment parameters of any generated candidate parameter combination must strictly fall within this boundary range to ensure that the output parameter tuning scheme is safe, compliant, and will not cause secondary defects in actual production.

[0059] Candidate parameter tuning results: After the process parameter optimization model performs calculations within the constraint boundaries, it outputs one or more parameter adjustment schemes that meet the dimensional accuracy requirements. Because the model may output multiple parameter combinations that can achieve the dimensional targets, it is necessary to further select the optimal set as the final target adjustment parameter value based on comprehensive evaluation indicators such as minimum adjustment cost and minimum equipment fluctuation.

[0060] Specifically, assuming that in the current production cycle, the main adjustment parameter (holding pressure) of the injection molding machine is set to 80MPa, and the auxiliary adjustment parameter (mold temperature) is set to 60℃. AOI inspection equipment confirms that the snap-hole spacing of the products produced in this cycle is 0.03mm too small. These three data points are used as input parameters to the model: [holding pressure: 80MPa, mold temperature: 60℃, dimensional deviation: -0.03mm], and input into a pre-trained process parameter optimization model based on the XGBoost algorithm. After receiving the data, the model begins its internal calculations (the model confirms that the current dimension is too small, requiring an increase in holding pressure or an appropriate increase in mold temperature to compensate for shrinkage). At this point, the constraint boundaries (process window) come into play. Assuming the process window for this product specifies that the safe range for holding pressure is 75MPa - 85MPa, and the safe range for mold temperature is 55℃ - 65℃, the model, based on these constraint boundaries, searches within this three-dimensional space (holding pressure, mold temperature, dimension) during calculation, and forcibly filters out all parameter combinations that exceed these boundaries. For example, the model calculated that the dimensional compensation effect was best at a holding pressure of 88 MPa, but this exceeded the upper limit of 85 MPa, so this combination was directly discarded by the model. After rigorous calculations within the safety boundaries, the model finally output three sets of candidate parameter tuning results that could bring the dimensional deviation back to 0: A (holding pressure adjusted to 82 MPa, mold temperature maintained at 60°C), B (holding pressure maintained at 80 MPa, mold temperature adjusted to 62°C), and C (holding pressure adjusted to 81 MPa, mold temperature adjusted to 61°C).

[0061] By leveraging the powerful nonlinear mapping capabilities of the XGBoost algorithm, the complex coupling relationship between injection molding process parameters and product dimensions was accurately fitted, effectively overcoming the limitations of traditional manual parameter tuning that relies on experience. Simultaneously, by using the process window as a rigid constraint boundary, it was ensured that the multiple candidate parameter tuning results output by the model remained within a safe and compliant operating space, fundamentally eliminating the risk of secondary defects or equipment damage caused by out-of-bounds parameter tuning. Furthermore, the output of multiple candidate results broke the limitations of a single solution, providing reliable decision support for subsequent comprehensive evaluation and selection of the optimal parameter combination that balances dimensional compliance and stable production.

[0062] In one embodiment, before inputting the parameter values ​​corresponding to the main and auxiliary adjustment parameters in the injection molding production parameters, as well as the dimensional inspection data, into the process parameter optimization model, the method further includes: Obtain historical dimensional inspection data of products produced in a preset batch immediately before the current time, as well as the historical injection molding production parameters corresponding to the historical dimensional inspection data; Calculate the average value of historical size detection data to obtain a real-time compensation factor characterizing current environmental fluctuations; By combining historical injection molding production parameters with real-time compensation factors, the process parameter optimization model is incrementally updated or dynamically compensated.

[0063] Real-time compensation factor: A quantitative indicator extracted from recent historical dimensional inspection data (such as calculating the average value or mean drift) to characterize the impact of current production environment fluctuations (such as material batch differences, workshop temperature and humidity changes, mold thermal expansion, etc.) on product quality.

[0064] Specifically, assuming the 1000th mold is currently being produced, production data from the 20 most recent molds (molds 980 to 999) immediately preceding the current moment can be automatically extracted. This production data includes historical injection molding parameters such as holding pressure and melt temperature for these 20 molds, as well as historical dimensional inspection data (generally inspection data for critical product dimensions) obtained through AOI equipment. By calculating the historical dimensional inspection data from these 20 molds, it is confirmed that their average value is 0.02mm smaller than the target center value, and this -0.02mm can be used as a real-time compensation factor.

[0065] Before inputting the parameters of the current 1000th mold into the model, a compensation factor of -0.02mm can be used to process the model. In the dynamic compensation method, -0.02mm is directly input as a baseline deviation into the model, telling it, "The current environment has caused the overall product to be 0.02mm smaller; please take this environmental error into account in subsequent optimization." In the incremental update method, if similar dimensional drift is found in 50 consecutive molds, it indicates a substantial change in the environment. In this case, the data from these 50 molds needs to be fed into the model for incremental learning, fine-tuning the decision tree weights within the model so that the model as a whole recognizes that the current material or temperature conditions are different from those during previous mold trials.

[0066] After the aforementioned dynamic compensation or incremental updates, the model has acquired the ability to cope with current environmental fluctuations. At this point, inputting the current parameter and dimension data into the model will allow it to provide extremely accurate parameter tuning suggestions.

[0067] In one embodiment, selecting target adjustment parameter values ​​corresponding to the primary adjustment parameter and the secondary adjustment parameter from the candidate adjustment results includes: Verify whether the prediction metrics of the candidate parameter tuning results meet the preset accuracy threshold; Among the candidate parameter tuning results that meet the preset accuracy threshold, the combination with the best prediction effect is selected and determined as the target main adjustment parameter and the target auxiliary adjustment parameter; The adjustment parameter values ​​corresponding to the target primary adjustment parameter and the target secondary adjustment parameter are used as the target adjustment parameter values.

[0068] Predictive metrics, typically referring to the compensation amount for dimensional deviations predicted by the model or the expected dimensional accuracy, are the direct basis for measuring whether the set of candidate parameters can effectively solve the current dimensional problem.

[0069] The preset accuracy threshold is a pre-set minimum quality standard for determining whether candidate parameter tuning results are usable (e.g., size deviation must be controlled within ±0.01mm). Only candidate results with predicted indicators better than this threshold can enter the next round of optimization, thereby ensuring that the issued parameter tuning scheme has absolute quality assurance.

[0070] The target parameter values ​​are adjusted, and after verification and optimization, the final parameter settings are determined and prepared to be issued to the actuators of the injection molding equipment.

[0071] Specifically, if in the previous step, the model output three sets of candidate parameter tuning results: A, expected size deviation of +0.005mm; B, expected size deviation of +0.025mm; and C, expected size deviation of +0.008mm, with a preset accuracy threshold of ±0.01mm, and after verification, candidate parameter tuning result B's deviation (0.025mm) exceeds the threshold and is directly eliminated, while candidate parameter tuning results A and C both exceed the threshold and can proceed to the next round of optimization. The optimization strategy here is to "prioritize the scheme with the smallest change in the main control parameter, under the premise of meeting accuracy requirements, to reduce system wear." However, candidate parameter tuning result A requires increasing the holding pressure (main control parameter) from 80MPa to 83MPa (a change of 3MPa), while candidate parameter tuning result C only requires increasing the holding pressure to 81MPa (a change of 1MPa). Therefore, after comprehensive evaluation, candidate parameter tuning result C is determined to be the combination with the best prediction effect, ensuring both extremely high dimensional accuracy and maximizing the stable operation of the equipment. After determining the final parameter adjustment result as candidate parameter adjustment result C (holding pressure 81MPa, mold temperature 61℃), the two specific values ​​in candidate parameter adjustment result C are formally determined as target adjustment parameter values ​​and encapsulated as control instructions, ready to be automatically sent to the injection molding machine controller for execution at the start of the next injection molding cycle.

[0072] The above method rigorously filters candidate solutions by setting a precision threshold and comprehensively optimizes them by combining actual engineering needs (such as equipment stability and adjustment costs), ultimately establishing the optimal target adjustment parameter value that balances dimensional compliance and stable production.

[0073] In one embodiment, after controlling the injection molding equipment to perform the corresponding parameter adjustment action, the method further includes: Obtain actual size inspection data of the manufactured products after parameter adjustment; Calculate the actual deviation between the actual size inspection data and the predicted size output by the process parameter optimization model; Based on the actual deviation, the parameter tuning coefficients of the process parameter optimization model are updated and optimized.

[0074] Actual deviation is the difference between the predicted size output by the process parameter optimization model and the actual size measured after production. This deviation objectively reflects the model's prediction accuracy and fitting error under the current operating conditions.

[0075] Parameter tuning coefficients are mathematical weights, split nodes, or bias parameters used within the process parameter optimization model to describe the mapping relationship between injection molding production parameters and product dimensions. These coefficients determine the model's sensitivity to input data and the accuracy of its predicted output.

[0076] For example, in the previous round of parameter adjustments, the model recommended increasing the holding pressure from 80MPa to 82MPa to achieve the optimal target value for the product's critical dimensions. After the injection molding equipment implemented this adjustment, the next batch of products was produced. Inspection by AOI equipment such as high-precision sensors or coordinate measuring machines confirmed that the actual dimension of the product was 50.015mm (the optimal target value on the drawing was 50.000mm).

[0077] The previous model predicted a product dimension of 50.005 mm under a holding pressure of 82 MPa. The actual deviation is calculated as follows: Actual dimension (50.015 mm) - Predicted dimension (50.005 mm) = +0.010 mm. This indicates that while the model correctly determined the direction of adjustment, it underestimated the nonlinear coupling between the holding pressure and the dimension, resulting in excessive compensation and a positive prediction error of 0.010 mm.

[0078] After obtaining the aforementioned actual deviation, the model update and optimization mechanism is triggered. Based on the actual deviation, the gradient is calculated and the parameter tuning coefficients inside the model are corrected in reverse (for example, reducing the weight sensitivity of the holding pressure feature in the model under the current temperature conditions).

[0079] By iteratively correcting the model in the above manner, when the model encounters similar situations where the size is too small and compensation is needed, the pressure recommendation given by the model will be more accurate (for example, only recommending to increase it to 81.5MPa), thereby minimizing the prediction error and realizing the continuous self-evolution of the model.

[0080] In one embodiment, after generating pre-adjustment data based on the target adjustment parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter, the process includes: Convert the pre-adjustment data into control messages that can be recognized by the programmable logic controller of the injection molding equipment; When the injection molding equipment completes the current production cycle and is in standby mode, a control message is sent to the programmable logic controller to apply the pre-adjustment data in the next production cycle.

[0081] A Programmable Logic Controller (PLC) is the core, low-level control hub of an injection molding machine, responsible for directly driving the machine's hydraulic valves, heating coils, servo motors, and other hardware actuators. PLCs operate according to strict timing logic and typically can only recognize digital signals or control instructions in specific formats; they cannot directly understand upper-level business data.

[0082] Control messages are binary or structured data frames generated by encoding and packaging pre-adjustment data according to the underlying communication protocol of the injection molding equipment PLC (such as Modbus, OPC UA, or proprietary protocol customized by the equipment manufacturer).

[0083] In standby mode, the injection molding equipment completes the current cycle's mold opening, ejection, and mold closing actions, but has not yet triggered the next injection action within a short time window.

[0084] Specifically, after parameter optimization and screening in the preceding steps, the optimal parameters for the next cycle are finally determined (e.g., the main regulating parameter / holding pressure is set to 81.5MPa, and the auxiliary regulating parameter / barrel temperature is set to 265℃). The multiple values ​​corresponding to the optimal parameters constitute the current pre-adjustment data. Then, through the Modbus TCP protocol, 81.5MPa is converted into an integer value (e.g., 8150, unit is 0.01MPa) at the corresponding register address (e.g., address 4001), and 265℃ is converted into a value (2650) at address 4002, thus forming a control message. When the injection molding machine is executing the process of the Xth mold product ejection being completed, the moving platen retracting into place, and the equipment entering the mold-open and stationary standby state, the host computer system sends a control message to the PLC via Ethernet. After receiving the message, the PLC quickly updates the settings of its internal registers to adjust the injection molding production parameters.

[0085] In one implementation, after controlling the injection molding equipment to perform the corresponding parameter adjustment actions, it also includes: Obtain the actual size detection data of the products produced in the preset batch after parameter adjustment; Based on the product's key dimensions, obtain the corresponding preset dimensional tolerance range; The actual size inspection data is compared with the preset size tolerance range. When the actual size inspection data exceeds the size tolerance range, the corresponding product is judged as unqualified, and the number of consecutive unqualified judgments is counted. When the number of non-compliances reaches the preset abnormal threshold, a mistake-proof control instruction is generated.

[0086] Among them, the foolproof control command is used to lock the current injection molding production parameters or control the injection molding equipment to revert to the injection molding production parameters before the parameter adjustment.

[0087] The preset dimensional tolerance range, based on the product design drawings or quality standards (i.e., the optimal target values ​​of the aforementioned products), is the allowable fluctuation range (i.e., the upper and lower limits) set for the key dimensions of the product. It is the absolute physical standard for determining whether the product is qualified. Any actual dimensional inspection data that exceeds this range is considered unqualified.

[0088] Abnormal threshold yes A preset warning threshold for the number of consecutive parameter tuning failures. This threshold is set to distinguish between occasional process fluctuations and systemic process failures. Only when the actual dimensions still exceed the tolerance range after parameter adjustments over multiple consecutive cycles, and the cumulative number of failures reaches this threshold, is it determined that the model's current optimization strategy has failed or that an irreversible change has occurred in the production environment.

[0089] The error-proof control command is the highest-level safety intervention mechanism triggered after continuous parameter tuning of the model has been confirmed to have failed, in order to prevent the injection molding equipment from continuing to blindly try and make mistakes, resulting in batch scrap. Its core function is to forcibly disconnect the model's automatic optimization authority, forcibly pull the production status back to the safety baseline, or stop the machine and wait for manual intervention.

[0090] For example, suppose the model adjusts the holding pressure from 80MPa to 82MPa to compensate for undersized dimensions. However, the next batch produced still has dimensions that are too small or too large (exceeding the preset dimensional tolerance range). In this case, the system will not immediately alarm and stop the machine, but will instead feed back this still unacceptable result to the model. The model will then continue to try adjusting the parameters based on the new data (for example, further adjusting the holding pressure to 83.5MPa, or simultaneously fine-tuning the mold temperature, etc.).

[0091] The model underwent multiple adjustments (e.g., 82MPa - 83.5MPa - 84.5MPa), but the dimensions of the produced products consistently exceeded the tolerance range. At this point, the system's count of consecutive non-conformities reached the preset anomaly threshold (3 times). This indicates that the current dimensional deviation cannot be compensated for by fine-tuning conventional injection molding production parameters. Therefore, the model's parameter adjustment strategy is deemed ineffective, and a foolproof control command is immediately generated and executed: automatically reverting parameters such as holding pressure to the baseline value before adjustment (80MPa), or displaying an alarm on the screen to lock the current parameters and forcibly suspend the model's automatic parameter adjustment function.

[0092] The above methods not only provide the model with ample room for adaptive adjustment, but also completely eliminate the risk of batch scrapping caused by the model getting stuck in a local dead loop, perfectly balancing the intelligence and safety of production; at the same time, it can also remind on-site engineers: "There may be wear on the mold inserts or abnormal material batches. The model can no longer repair itself automatically. Please intervene manually."

[0093] In summary, the method provided in the above embodiments accurately fits the complex nonlinear coupling relationship between injection molding production parameters and product dimensions using a process parameter optimization model. Combined with real-time environmental compensation factors and process window constraints, this ensures the scientific rigor, high precision, and absolute safety of parameter tuning decisions. Furthermore, a dual-check mechanism of precision threshold filtering and engineering optimal selection achieves a smooth transition from theoretical feasibility to engineering practicality. Message conversion and standby state delivery technologies ensure seamless and secure execution of parameter tuning commands in the underlying equipment. Finally, a model incremental update mechanism based on measured deviations is established, enabling the process optimization model to continuously self-evolve. Simultaneously, an intelligent error-proofing strategy of "model parameter tuning and repair first, then triggering a safety fallback" is introduced. This provides the model with ample adaptive adjustment space while completely eliminating the risk of batch scrap due to continuous parameter tuning failures, perfectly balancing the high efficiency and intelligence of injection molding production with industrial-grade high reliability.

[0094] Based on the same inventive concept as the foregoing embodiments, the foregoing embodiments will be described in detail below through a specific application scenario.

[0095] For example, firstly, based on the customer's product quality requirements, identify the key dimensions of the product that require focused control. Then, based on the requirements of these key dimensions, verify the injection molding production parameters that can affect the accuracy of these dimensions (e.g., injection speed, V / P, holding pressure, holding time, metering position, screw speed, back pressure, barrel temperature, hot runner temperature, cavity pressure, length, peak pressure, viscosity, etc.). Next, using the controlled variable method, verify each of these injection molding production parameters one by one to identify the target injection molding production parameters affecting the dimensional accuracy and their upper and lower limits of standard values.

[0096] Then, the data from the injection molding machine (mold number, V / P, HP, BT, holding pressure, barrel temperature), mold (HT), AOI equipment (dimensional inspection data), and Kistler monitoring system are transmitted to the injection molding machine's PLC via TCP communication protocol, OPC-UA communication protocol, OPC-UA communication protocol, and TCP communication protocol, respectively. The data is then sent to the factory's MES system, where the IAC control system communicates with the MES system and retrieves the injection molding production parameter data.

[0097] Then, based on the importance of the aforementioned injection molding production parameters, injection molding experience, and the degree of influence of these parameters on product dimensions and length, the Top 10 influencing factors were selected to further reduce data and computational load. After obtaining the corresponding factors, one was chosen as the primary adjustment parameter, and the remainder as auxiliary adjustment parameters. A corresponding AI algorithm model (i.e., a process parameter optimization model) was established based on the XGBoost model. The parameters corresponding to the influencing factors were substituted into the AI ​​algorithm model to output candidate parameter tuning results, verifying whether these results met expectations. From the candidate parameter tuning results that met expectations, the primary and auxiliary factor parameters (i.e., primary and auxiliary adjustment parameters) with the best processing results were selected.

[0098] The AI ​​algorithm model then processes the results into pre-adjustment data for the injection molding parameters of the next mold, and transmits this data to the PLC. The PLC then executes the parameter adjustment action according to the defined parameter adjustment logic. The AI ​​algorithm model captures the AOI data (i.e., dimensional detection data) of the next mold product after parameter adjustment, compares it with the expected results, and adjusts the coefficients in real time to optimize the parameter adjustment algorithm for the next mold product.

[0099] The AI ​​algorithm model also has the ability to learn in real time, and can capture the average value of the most recent 20 sets of data to compensate for external influences.

[0100] In addition, upper and lower limits for parameter tuning can be set simultaneously, and the number of NGs after parameter tuning can be limited for error prevention control, ensuring that the parameter tuning of the IAC control system is stable and controllable.

[0101] Finally, without manual operation, the IAC system automatically adjusts and controls the parameters, ensuring that the product parameter test results remain stable within the test standards, and the IAC system completes the operation cycle.

[0102] Based on the same inventive concept as the foregoing embodiments, this invention provides an electronic device, such as... Figure 2 As shown, the device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 2 The processor 310 shown in the diagram does not indicate that there is only one processor 310, but only indicates the positional relationship of the processor 310 relative to other devices. In practical applications, there can be one or more processors 310; similarly, Figure 2 The memory 311 illustrated herein has the same meaning, that is, it is only used to indicate the positional relationship of memory 311 relative to other devices. In practical applications, there can be one or more memories 311. When the processor 310 runs the computer program, the method applied to the above-mentioned device is implemented.

[0103] The device may also include at least one network interface 312. The various components of the device are coupled together via a bus system 313. It is understood that the bus system 313 is used to implement communication between these components. In addition to a data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 2 The general designated all buses as Bus System 313.

[0104] The memory 311 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memory 311 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0105] The memory 311 in this embodiment of the invention is used to store various types of data to support the operation of the device. Examples of this data include: any computer programs used to operate on the device, such as operating systems and applications; contact data; phonebook data; messages; pictures; videos, etc. The operating system includes various system programs, such as the framework layer, core library layer, driver layer, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications, such as media players, browsers, etc., used to implement various application services. Here, the program implementing the method of this embodiment of the invention can be included in the application.

[0106] Based on the same inventive concept as the foregoing embodiments, this embodiment also provides a computer-readable storage medium storing a computer program. The computer-readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM), etc.; it can also be various devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc. When the computer program stored in the computer-readable storage medium is run by a processor, it implements the above method. For the specific steps implemented when the computer program is executed by the processor, please refer to [link to relevant documentation]. Figure 1 The description of the illustrated embodiments will not be repeated here.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0109] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for adjusting parameters in an injection molding process, characterized in that, include: Acquire multi-source data during the injection molding production cycle, wherein the multi-source data includes at least injection molding production parameters and dimensional detection data; Determine the key dimensions of the product based on product quality requirements; The preset injection molding production parameters are verified by using the controlled variable method to determine the injection molding production parameters that affect the key dimensions of the product, and to determine the standard values ​​and process windows of the injection molding production parameters. Based on the characteristic importance weights of the injection molding production parameters to the key dimensions of the product, and in conjunction with the preset process rules, the main adjustment parameters and auxiliary adjustment parameters in the injection molding production parameters are identified. The parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter in the injection molding production parameters, as well as the size detection data, are input as input parameters into the process parameter optimization model constructed based on the XGBoost algorithm; The process parameter optimization model is controlled to perform parameter optimization calculations within the constraint boundaries defined by the process window, and outputs multiple sets of candidate parameter tuning results; Verify whether the prediction index of the candidate parameter tuning results meets the preset accuracy threshold; Among the candidate parameter tuning results that meet the preset accuracy threshold, the combination with the best prediction effect is selected and determined as the target main adjustment parameter and the target auxiliary adjustment parameter; The adjustment parameter values ​​corresponding to the target primary adjustment parameter and the target secondary adjustment parameter are respectively used as the target adjustment parameter values ​​of the primary adjustment parameter and the secondary adjustment parameter; Pre-adjustment data is generated based on the target adjustment parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter, and the injection molding equipment is controlled to perform corresponding parameter adjustment actions.

2. The parameter adjustment method for injection molding process as described in claim 1, characterized in that, Before inputting the parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter in the injection molding production parameters, as well as the dimensional detection data, into the process parameter optimization model, the method further includes: Obtain historical dimension detection data of products produced in a preset batch immediately adjacent to the current time, as well as historical injection molding production parameters corresponding to the historical dimension detection data; Calculate the average value of the historical size detection data to obtain a real-time compensation factor characterizing the current environmental fluctuations; By combining the historical injection molding production parameters with the real-time compensation factor, the process parameter optimization model is incrementally updated or dynamically compensated.

3. The parameter adjustment method for injection molding process as described in claim 1, characterized in that, After the injection molding equipment is controlled to perform the corresponding parameter adjustment actions, the method further includes: Obtain actual size inspection data of the products produced after parameter adjustment; Calculate the actual deviation between the actual size detection data and the predicted size output by the process parameter optimization model; Based on the actual deviation, the parameter tuning coefficients of the process parameter optimization model are updated and optimized.

4. The parameter adjustment method for injection molding process as described in claim 1, characterized in that, After generating the pre-adjustment data based on the target adjustment parameter values ​​corresponding to the main adjustment parameter and the auxiliary adjustment parameter, the process includes: The pre-adjustment data is converted into a control message that can be recognized by the programmable logic controller of the injection molding equipment; When the injection molding equipment completes the current production cycle and is in standby mode, the control message is sent to the programmable logic controller to apply the pre-adjustment data in the next production cycle.

5. The parameter adjustment method for injection molding process as described in claim 1, characterized in that, After the injection molding equipment is controlled to perform the corresponding parameter adjustment actions, the method further includes: Obtain the actual size detection data of the products produced in the preset batch after parameter adjustment; Based on the key dimensions of the product, obtain the corresponding preset dimensional tolerance range; The actual size detection data is compared with the preset size tolerance range. When the actual size detection data exceeds the size tolerance range... When the product is found to be defective, the number of consecutive defective products is counted. When the number of non-conforming items reaches a preset abnormal threshold, a mistake-proof control command is generated. The mistake-proof control command is used to lock the current injection molding production parameters or control the injection molding equipment to revert to the injection molding production parameters before parameter adjustment.

6. An electronic device, characterized in that, include: The processor and the memory storing a computer program implement the steps of the parameter adjustment method for the injection molding process according to any one of claims 1 to 5 when the processor runs the computer program.

7. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, implements the steps of the parameter adjustment method for the injection molding process according to any one of claims 1 to 5.

Images