Multi-control parameter collaborative optimization method and system in plastic product production

Abstract

The invention relates to the technical field of plastic product auxiliary manufacturing, and provides a multi-control parameter collaborative optimization method and system in plastic product production. The method comprises the following steps: acquiring component characteristics; traversing the material components to obtain the crystal porosity; performing weighted adjustment to obtain the porosity of the target crystal; dynamically monitoring the processing record; screening a predetermined index to obtain a control index parameter time sequence; determining a target component and recording the target component as an index parameter; forming a processing control strategy based on the average index parameters; matching to obtain a target historical processing strategy; performing weighted adjustment on the historical porosity fitness to obtain a target porosity; and if the target porosity does not conform to the threshold value, optimizing and adjusting the processing control strategy. According to the method and the device, the technical problem that the product quality and the processing efficiency are influenced due to inaccurate processing parameter setting caused by material characteristic difference in the plastic product processing process is solved, and the effects of realizing accurate matching and weighted adjustment based on material component characteristic information and improving the processing precision and the processing efficiency of the plastic product are achieved.

Description

Technical Field

[0001] This application relates to the field of materials processing technology, specifically to the field of auxiliary manufacturing technology for plastic products, and particularly to a method and system for collaborative optimization of multiple control parameters in the production of plastic products. Background Technology

[0002] With the increasing demand for plastic products and the rising quality requirements of consumers, parameter optimization in the plastic product processing process has become particularly important. However, traditional auxiliary processing methods for plastic products often neglect the influence of material properties on processing parameters, leading to inaccurate parameter settings and consequently affecting product quality and processing efficiency. Material properties are a crucial factor that cannot be ignored in the processing of plastic products. Different materials have different physical and chemical properties, such as density, hardness, and thermal conductivity, which directly determine the material's behavior during processing. Therefore, accurately understanding material properties and optimizing processing parameters based on these properties is key to improving the processing precision and efficiency of plastic products. Summary of the Invention

[0003] This application provides a method and system for collaborative optimization of multiple control parameters in the production of plastic products, aiming to solve the technical problem that inaccurate setting of processing parameters due to differences in material properties during the processing of plastic products, thereby affecting product quality and processing efficiency.

[0004] In view of the above problems, this application provides a method and system for collaborative optimization of multiple control parameters in the production of plastic products.

[0005] The first aspect disclosed in this application provides a method for collaborative optimization of multiple control parameters in the production of plastic products. The method includes: acquiring target component characteristic information of a target material, the target component characteristic information including multiple material components with proportion identifiers; traversing and matching a first material component among the multiple material components with proportion identifiers in a material component database to obtain a first crystal porosity; using a first proportion of the first material component as a weighting coefficient to weight and adjust the first crystal porosity to obtain the target crystal porosity of the target material; dynamically monitoring and obtaining a first product processing control record, the first product processing control record referring to the processing record of the target material in a first predetermined processing cycle; and traversing and screening a first predetermined indicator among predetermined processing control indicators in the first product processing control record. The first control index parameter time series is obtained by selecting and combining it with the first predetermined processing cycle; the first target component of the first control index parameter time series is compared and determined, and the first average control index parameter of the first target component is recorded as the index parameter of the first predetermined index; a first target processing control strategy is formed based on the first average control index parameter, and the first target processing control strategy is traversed and matched in the processing control database to obtain the target historical processing control strategy; the target crystal porosity is weighted and adjusted using the target historical porosity fitness of the target historical processing control strategy as a weighting coefficient to obtain the target porosity; when the target porosity is not at the predetermined porosity threshold, a processing adjustment command is issued, and the first target processing control strategy is optimized and adjusted based on the processing adjustment command.

[0006] Another aspect of this application discloses a multi-control parameter collaborative optimization system for plastic product manufacturing. The system includes: a characteristic information acquisition module for acquiring target component characteristic information of a target material, the target component characteristic information including multiple material components with proportion identifiers; a material component traversal matching module for traversing and matching a first material component among the multiple material components with proportion identifiers in a material component database to obtain a first crystal porosity; a first porosity weighted adjustment module for using a first proportion of the first material component as a weighting coefficient to weight and adjust the first crystal porosity to obtain the target crystal porosity of the target material; a dynamic monitoring module for dynamically monitoring and obtaining a first product processing control record, the first product processing control record referring to the processing record of the target material in a first predetermined processing cycle; and a traversal screening module for selecting a first predetermined indicator from predetermined processing control indicators in the first product processing control record. The system iterates through the processing control records and combines them with the first predetermined processing cycle to obtain the timing sequence of the first control index parameter; a parameter comparison module is used to compare and determine the first target component of the timing sequence of the first control index parameter, and record the first average control index parameter of the first target component as the index parameter of the first predetermined index; a processing control traversal matching module is used to form a first target processing control strategy based on the first average control index parameter, and traverse and match the first target processing control strategy in the processing control database to obtain the target historical processing control strategy; a target porosity weighted adjustment module is used to use the target historical porosity fitness of the target historical processing control strategy as a weighting coefficient to perform weighted adjustment on the target crystal porosity to obtain the target porosity; an optimization adjustment module is used to issue a processing adjustment command when the target porosity is not at a predetermined porosity threshold, and perform optimization adjustment on the first target processing control strategy based on the processing adjustment command.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The aforementioned method for collaborative optimization of multiple control parameters in the production of plastic products first obtains specific component characteristic information of the target material, including various material components with different proportions. Then, it searches a material component database for crystal porosity data matching these material components. Using one material component and its proportion as a reference, a first crystal porosity is obtained through database matching. The proportion of this material component is then used as a weighting coefficient to adjust the first crystal porosity, thereby obtaining the target crystal porosity of the target material. During the processing of plastic products, processing control data is recorded in real time, including various parameter changes within the processing cycle. Predetermined key control indicators are selected from the real-time monitored data, and a time-series variation graph of the control indicator parameters is formed by combining the processing cycle. The target component is then determined from these time-series variations, and its average control indicator parameter is calculated, which serves as the indicator parameter for that indicator. Finally, based on the obtained indicator parameters, a target processing control strategy is generated, and a matching historical processing control strategy is searched in the processing control database. Then, using the porosity fitness from the found historical processing control strategies as a new weighting coefficient, the previously calculated target crystal porosity is re-weighted and adjusted to obtain the final target porosity. If the target porosity does not meet the predetermined porosity threshold, a processing adjustment command is issued, and the current processing control strategy is optimized according to this command to ensure that the porosity of the final product meets the predetermined requirements. This achieves precise optimization of the processing parameters of plastic products, improving product quality and processing efficiency.

[0008] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating a method for collaborative optimization of multiple control parameters in the production of plastic products, as shown in one embodiment.

[0011] Figure 2 This is a system architecture diagram for collaborative optimization of multiple control parameters in the production of plastic products in one embodiment.

[0012] Figure labeling: 1. Characteristic information acquisition module; 2. Material composition traversal matching module; 3. First porosity weighted adjustment module; 4. Dynamic monitoring module; 5. Traversal screening module; 6. Parameter comparison module; 7. Processing control traversal matching module; 8. Target porosity weighted adjustment module; 9. Optimization adjustment module. Detailed Implementation

[0013] This application provides a method and system for collaborative optimization of multiple control parameters in the production of plastic products, which solves the technical problem that inaccurate setting of processing parameters due to differences in material properties during the processing of plastic products, thereby affecting product quality and processing efficiency.

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below 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. 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.

[0015] It should be noted that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0016] Example 1, as Figure 1 As shown, this application provides a method for collaborative optimization of multiple control parameters in the production of plastic products, the method comprising: Obtain target component characteristic information of the target material, wherein the target component characteristic information includes a variety of material components with proportioning identifiers.

[0017] In this embodiment, during the processing of plastic products, to ensure product quality and processing efficiency, the system terminal acquires specific component characteristic information of the target material. This information includes various different material components constituting the target material, each with its unique proportion identifier. These proportion identifiers indicate the percentage of each material component in the target material. By accurately understanding these material components and their proportions, a scientific basis can be provided for setting subsequent processing parameters, ensuring that the processing fully considers the material's characteristics, thereby obtaining higher quality and more efficient plastic products.

[0018] The first material component among the various material components with proportioning identifiers is matched by traversing the material component database to obtain the first crystal porosity.

[0019] In one embodiment, after obtaining multiple material components with proportion identifiers, the system terminal extracts these components sequentially to obtain the first material component. This first material component is then used to traverse and compare data in a material component database to find matching crystal porosity data. The material component database is pre-established and contains detailed composition information for various materials. The system terminal uses the proportion identifier of the first material component to search for corresponding crystal porosity data in the material component database to obtain the first crystal porosity, providing foundational data for subsequent optimization and adjustments.

[0020] Using the first ratio of the first material components as a weighting coefficient, the porosity of the first crystal is adjusted by weighting to obtain the target crystal porosity of the target material.

[0021] In one embodiment, during the processing of plastic products, after determining the first material component in the target material, the system terminal acquires the proportion data of this first material component and uses this proportion data as the first proportion. Subsequently, the proportion of the first material component in the target material is used as a weighting coefficient. For example, if the proportion of the first material component in the target material is 30%, the weighting coefficient is 0.3. Then, the first crystal porosity is adjusted using the weighting coefficient, that is, the weighting coefficient is multiplied by the first crystal porosity. The first crystal porosity refers to the inherent porosity characteristics of the first material component itself; these pores are inherent within the material and typically do not disappear. Through weighted adjustment, the system terminal considers the influence of different material components and their proportions on the overall material porosity, thereby obtaining a more accurate target crystal porosity, which represents the expected porosity level of the target material after processing.

[0022] Dynamic monitoring yields the processing control record of the first product, which refers to the processing record of the target material in the first predetermined processing cycle.

[0023] In one embodiment, during the first predetermined processing cycle, the system terminal continuously collects various data related to the processing process, including key parameters such as processing temperature, pressure, and speed, as well as information such as material usage and equipment operating status. This data is recorded in detail to generate a first product processing control record. The first predetermined processing cycle is a pre-set period of periodic monitoring and control, designed to continuously optimize the processing process through real-time monitoring and data analysis, ensuring the quality and performance of the product. After the first predetermined processing cycle ends, the system terminal performs in-depth analysis of the data from that cycle. This analysis assesses the stability of the processing process and the consistency of product quality, i.e., whether the processing effect meets expectations. Simultaneously, it predicts potential issues in the second predetermined processing cycle, providing a reference for developing a more reasonable processing strategy. Based on the data analysis results of the first predetermined processing cycle, the system terminal determines whether to change the processing strategy for the second predetermined processing cycle. If the processing process in the first predetermined processing cycle is stable and the product quality is good, the system terminal continues to use the current processing strategy; if there are many problems in the first predetermined processing cycle or the product quality is unstable, the processing strategy is adjusted and optimized to improve the processing effect and product quality in the second cycle.

[0024] The first predetermined indicator in the predetermined processing control indicators is traversed and filtered in the first product processing control record, and the timing sequence of the first control indicator parameter is obtained by combining it with the first predetermined processing cycle.

[0025] In one embodiment, during the processing of the work-in-process, to ensure processing stability and product quality controllability, the system terminal sets a series of predetermined processing control indicators. Then, a control indicator is randomly selected from these predetermined indicators as the first predetermined indicator. To understand the specific performance of this indicator during processing, the system terminal extracts the work-in-process processing control records for the first predetermined processing cycle from the first work-in-process processing control records, i.e., the first cycle work-in-process processing control records. Afterwards, the system terminal iterates through and filters the first cycle work-in-process processing control records according to the first predetermined indicator, examining each record during the processing of the first predetermined processing cycle to obtain the timing sequence of the first control indicator parameter. This timing sequence of the first control indicator parameter demonstrates the changes of the first predetermined indicator within the first predetermined processing cycle, including the initial value, intermediate changes, and final value.

[0026] Furthermore, this application provides predetermined processing control indicators, including: The predetermined processing control parameters include at least injection speed, injection pressure, melt temperature, mold temperature, cooling time, screw speed, back pressure, and material dryness.

[0027] Preferably, in the processing of plastic products, the predetermined processing control indicators set by the system terminal refer to key factors affecting material porosity and are adjustable. These indicators aim to minimize material porosity through precise control, thereby effectively reducing bubbles during processing and improving the overall quality of the plastic products. These predetermined processing control indicators include, but are not limited to, injection speed, injection pressure, melt temperature, mold temperature, cooling time, screw speed, back pressure, and material dryness. Specifically, injection speed refers to the speed at which the molten plastic is injected into the mold, ensuring uniform flow of the melt within the mold and reducing the generation of bubbles and pores. Injection pressure refers to the pressure applied per unit area of ​​the molten material by the screw or plunger end face, ensuring that the melt fully fills the mold and reduces porosity. Melt temperature refers to the temperature of the plastic in its molten state, used to control the fluidity of the plastic and the quality of the product. Mold temperature refers to the surface temperature of the mold cavity in contact with the product, affecting the flow behavior of the melt within the mold cavity and the cooling rate of the product. Cooling time refers to the time required for the product to cool to a predetermined temperature in the mold, ensuring complete solidification of the product and improving its performance. Screw speed refers to the rotational speed of the screw, which affects the mixing effect and conveying speed of the plastic melt. Back pressure is the pressure applied to the screw during retraction to prevent the melt from flowing out of the nozzle, used to reduce porosity and air bubbles in the finished product. Material dryness refers to the degree of dryness of the plastic raw material before processing, used to ensure melt quality and reduce the formation of air bubbles and porosity.

[0028] The first target component of the first control index parameter time series is determined by comparison, and the first average control index parameter of the first target component is recorded as the index parameter of the first predetermined index.

[0029] In one embodiment, to more precisely control the processing, the system terminal performs modal decomposition on the time series of the first control index parameter, and then analyzes the modal decomposition results using a modal component weight evaluation function to determine the first target component. Subsequently, a weighted average is calculated for multiple modal decomposition results of the first target component with their corresponding weights to obtain the first average control index parameter of the first target component. This first average control index parameter reflects the overall performance of the index within a first predetermined processing cycle. This first average control index parameter is then used as the index parameter of the first predetermined index. In this way, the system terminal obtains a specific, quantified value to guide subsequent strategy generation.

[0030] Furthermore, this application provides a method for determining the first target component, including: The first control index parameter time series is subjected to modal decomposition to obtain a first modal decomposition result, which includes multiple modal components; a modal component weight evaluation function is introduced to evaluate the weights of the multiple modal components in sequence to obtain multiple weights; the multiple weights are compared and the first target component is determined.

[0031] Preferably, during the processing control process, the system terminal sets key parameters in the Variational Mode Decomposition (VMD) algorithm based on parameter characteristics and actual needs, including the number of modes K, the center frequency of each mode, and the bandwidth. Subsequently, the VMD algorithm is applied to decompose the time series of the first control index parameter, yielding K BLIMFs, i.e., multiple modal components. These modal components are then extracted from the decomposition results of the VMD algorithm. Each modal component represents the characteristics of different time scales in the time series of the first control index parameter. Next, to determine which modal components have a more significant impact on the processing, the system terminal introduces a modal component weight evaluation function. This function evaluates the weight of each modal component and assigns different weight values. Then, based on the weight values ​​calculated by comparing with preset weights, weight values ​​greater than or equal to these preset weights are selected. These selected weight values ​​represent the modes among all modal components that have an impact on the processing. Finally, the system terminal matches the selected modal components with their corresponding weight values ​​and summarizes the matching results to form the first target component. The first target component represents the features that can influence the processing, helping the system terminal to understand the processing more accurately and providing an important basis for subsequent strategy generation.

[0032] Furthermore, this application provides a modal component weighting evaluation function, including: The expression for the modal component weight evaluation function is as follows: ; Optionally, the modal component weighting evaluation function is used to quantify the importance of each modal component in the overall analysis. The modal component weighting evaluation function is as follows: ;in, Characterizing the first of the multiple modal components Modal components The Each modal component has a weight; the larger the weight, the greater the influence of that modal component. Characterizing the first Modal components The amount of feature information. The total characteristic information quantity representing the time series of the first control index parameter is the sum of the characteristic information quantities of all modal components. Characterizing the first Modal components The correlation coefficient value between the modal components and the timing of the first control index parameter measures the linear correlation between the modal components and the timing of the first control index parameter. and These are the first coefficient and the second coefficient, respectively. The first coefficient is used to adjust the weighting of feature information in the weighting calculation, and the second coefficient is used to adjust the weighting of the correlation coefficient in the weighting calculation. This is to ensure the normalization of weights.

[0033] A first target processing control strategy is formed based on the first average control index parameters, and the first target processing control strategy is traversed and matched in the processing control database to obtain the target historical processing control strategy.

[0034] In one embodiment, the system terminal formulates a first target processing control strategy based on a first average control index parameter, combined with the actual needs and objectives of the processing process. This strategy describes how to set and control relevant parameters to achieve or maintain a specific processing effect, efficiency, or quality. Subsequently, the system terminal connects to a processing control database, which contains various control strategies used in past processing processes, along with their corresponding processing results, conditions, and other information. After connecting to the processing control database, the system terminal uses the first target processing control strategy to traverse the database and match historical processing control strategies that are highly similar to the first target processing control strategy. This matching process involves calculating the angle between each historical processing control strategy and the first target processing control strategy based on cosine similarity, quantifying the similarity between the two processing control strategies, and extracting the historical processing control strategy corresponding to the maximum similarity. The system terminal uses this extracted historical processing control strategy as the target historical processing control strategy for subsequent weighted adjustments.

[0035] Using the target historical porosity fitness of the target historical processing control strategy as a weighting coefficient, the target crystal porosity is weighted and adjusted to obtain the target porosity.

[0036] In one embodiment, after obtaining the target historical processing control strategy, the system terminal extracts the target historical porosity fitness from the strategy. This target historical porosity fitness represents the degree of matching between the target historical porosity and the expected effect during actual processing. A higher fitness indicates a better effect of the historical porosity in practical applications, and a closer approximation to or achievement of the expected processing target. Therefore, after determining the target historical processing control strategy, the system terminal uses the target historical porosity fitness as a weighting coefficient to adjust the current target crystal porosity, i.e., multiplying the weighting coefficient by the target crystal porosity. Through this weighted adjustment, the system terminal obtains a more reasonable and reliable target porosity, which is based not only on the analysis of current processing conditions but also incorporates historical successful experiences, thereby improving the controllability and success rate of the processing process.

[0037] Furthermore, this application provides a method for obtaining the fitness of the target historical porosity, including: Read the predetermined strategy vectorization scheme; based on the predetermined strategy vectorization scheme, vectorize the first target processing control strategy and the first historical processing control strategy in sequence to obtain the first target vector and the first historical vector, respectively, wherein the first historical processing control strategy is any historical processing control strategy in the processing control database.

[0038] Preferably, the system terminal reads a predefined strategy vectorization scheme. This scheme is used to convert various elements in the machining control strategy, such as parameter settings and machining conditions, into numerical vectors. These vectors represent the positions and characteristics of different strategies in a multi-dimensional space. After obtaining the predefined strategy vectorization scheme, the system terminal performs vectorization of the first target machining control strategy and the first historical machining control strategy according to the rules in the predefined strategy vectorization scheme. The first historical machining control strategy refers to any historical machining control strategy in the machining control database. Specifically, the system terminal first extracts all key elements from the first target machining control strategy. Then, based on the type of these key elements, it matches the corresponding vectorization method in the predefined strategy vectorization scheme. For example, for numerical parameters, the system terminal performs vectorization according to the numerical vectorization sub-scheme in the predefined strategy vectorization scheme, that is, it directly uses the parameter itself for quantization. For discrete parameters, the system terminal performs vectorization according to the discrete vectorization sub-scheme in the predefined strategy vectorization scheme, that is, it assigns a unique integer value to it; for example, tool type A can be converted to 1, tool type B can be converted to 2, and so on. For text-based parameters, the system terminal performs text-based vectorization according to the predefined strategy vectorization sub-scheme, that is, using one-hot encoding to create a new binary column for each parameter. Then, following the arrangement in the first target processing control strategy, these values ​​are combined into a vector, namely the first target vector. For the first historical processing control strategy, the system terminal uses the same method to obtain the first historical vector. This vectorization process facilitates the comparison and analysis of processing control strategies, providing strong support for strategy optimization.

[0039] A first similarity is obtained by comparing and analyzing the first target vector and the first historical vector; when the first similarity reaches a predetermined similarity threshold, the first historical porosity fitness of the matched first historical processing control strategy is recorded as the target historical porosity fitness.

[0040] Preferably, after obtaining the first target vector and the first historical vector, the system terminal uses cosine similarity to calculate the similarity between the first target vector and the first historical vector, obtaining a first similarity. If the calculated first similarity reaches a predetermined similarity threshold, the system terminal determines that the first target processing control strategy and the first historical processing control strategy have high similarity in features. At this point, the system terminal can conclude that the two strategies may also have similar processing effects. Therefore, the system terminal records the historical porosity fitness of the matched first historical processing control strategy as the target historical porosity fitness.

[0041] Furthermore, this application provides a method for obtaining the first historical porosity fitness, including: Obtain the first historical initial crystal porosity; monitor the first real-time historical material porosity under the first historical processing control strategy; take the first real-time historical ratio of the first real-time historical material porosity to the first historical initial crystal porosity as the first real-time historical porosity fitness; perform periodic analysis on the first fitness time series generated based on the first real-time historical porosity fitness to obtain the first historical porosity fitness.

[0042] Optionally, before processing begins, to assess the impact of the processing control strategy on material porosity, the system terminal retrieves the first historical initial crystal porosity under the first historical processing control strategy from the processing control database. This porosity, measured before processing begins, represents the initial state of the material. Subsequently, pre-deployed monitoring sensors are used to measure the changes in material porosity in real time. This real-time measured porosity reflects the dynamic change of material porosity over time under the first historical processing control strategy. Then, the ratio between the real-time measured material porosity and the initial crystal porosity is calculated, and this ratio is used as the real-time historical porosity fitness. This ratio intuitively reflects the degree of influence of the processing control strategy on material porosity; if the ratio is close to 1, it indicates that the processing control strategy has a small impact on material porosity; if the ratio is far from 1, it indicates that the processing control strategy has a large impact on material porosity. To more comprehensively assess the impact of the processing control strategy on material porosity, the system terminal performs periodic analysis on the real-time historical porosity fitness. This process involves collecting real-time historical porosity fitness data at multiple time points, organizing this data to form a first fitness time series. Statistical analysis is then performed on this first fitness time series, calculating the average of these fitness data points to reflect the overall porosity fitness performance. By calculating statistical indicators, the system terminal can obtain a comprehensive evaluation result, namely the first historical porosity fitness. This evaluation result helps to understand the performance of the historical processing control strategy in controlling material porosity and provides a reference for optimizing subsequent processing control strategies.

[0043] When the target porosity is not at the predetermined porosity threshold, a processing adjustment command is issued, and the first target processing control strategy is optimized and adjusted based on the processing adjustment command.

[0044] In one embodiment, when the obtained target porosity fails to reach the predetermined porosity threshold, it indicates that the current processing control strategy may not be ideal and needs to be adjusted to optimize the material's porosity. At this point, the system terminal issues a processing adjustment command, which guides the system terminal to use a tabu optimization algorithm to optimize and adjust the current processing control strategy to obtain a processing control strategy that meets the predetermined porosity threshold requirement.

[0045] Furthermore, this application provides processing control for performing a second predetermined processing cycle, including: An optimization space is constructed based on the predetermined thresholds of each predetermined indicator in the predetermined processing control index; taboo optimization is performed in the optimization space using porosity fitness as the optimization index to obtain the target optimal processing control strategy; the target material is processed and controlled for a second predetermined processing cycle according to the target optimal processing control strategy.

[0046] Preferably, the system terminal constructs an optimization space based on the threshold values ​​of each predetermined indicator in the predetermined processing control indicators. This optimization space contains all possible combinations of processing control strategies, and the parameter values ​​of these combinations are all within the set threshold range. Subsequently, the system terminal uses a tabu search algorithm to search within this optimization space, aiming to find a processing control strategy that maximizes porosity fitness. In this process, the system terminal first sets a tabu list to record solutions that have already been searched or the characteristics of solutions, to avoid repeated searches and improve search efficiency. Then, an initial solution set is randomly generated, representing different combinations of processing control strategies, and the porosity fitness of each solution in the initial solution set is evaluated using cosine similarity, i.e., the degree of matching between the porosity of the material under their corresponding processing control strategy and the target porosity. After that, the solution with the best fitness is selected from the current solution set as the current optimal solution. Then, it is checked whether the current optimal solution is in the tabu list; if so, the solution is skipped, and the second-best solution is selected. Then, the current optimal solution is mutated or adjusted to generate a new solution. This is done by changing the values ​​of the processing control parameters or adjusting the combination of parameters. After generating a new solution, the system terminal evaluates the porosity fitness of the new solution. If the new solution has better fitness, the solution set and the current optimal solution are updated. The current optimal solution or its characteristics are then added to the tabu list to avoid redundant searches in subsequent iterations. These steps are repeated until the predetermined number of iterations is reached. When the termination condition is met, the search process stops, and the final optimal solution, i.e., the target optimal processing control strategy, is output. This strategy, within the optimization space, uses the optimal combination of processing control parameters searched through a tabu optimization algorithm based on the porosity fitness index, enabling the target material's porosity to reach or approach the optimal fitness. Finally, the system terminal performs processing control on the target material for a second predetermined processing cycle according to this target optimal processing control strategy. During this process, processing is strictly performed according to the parameter settings in the optimal strategy to ensure that the porosity of the final product meets the predetermined requirements.

[0047] In summary, the embodiments of this application have at least the following technical effects: This application first obtains the target component characteristic information of the target material and matches the crystal porosity of each component in the material component database. Then, based on the component ratio as a weighting coefficient, the crystal porosity is adjusted to obtain the target crystal porosity of the target material. Next, the processing control records of the target material in the first predetermined processing cycle are dynamically monitored and recorded, including multiple key processing control indicators. By analyzing the time series of these indicator parameters, the parameter parameters of each predetermined indicator are determined. Then, based on the target processing control strategy, the target historical processing control strategy is matched in the processing control database, and its historical porosity fitness is used as a weighting coefficient to further adjust the target crystal porosity. When the target porosity does not reach a predetermined threshold, a tabu search algorithm is used to find the optimal processing control strategy within a preset optimization space to meet the target porosity requirement. Finally, the target material is processed in a second predetermined processing cycle according to the optimized processing control strategy to ensure product quality and processing efficiency. These technologies collectively solve the technical problem of inaccurate processing parameter settings caused by differences in material properties during the processing of plastic products, which in turn affects product quality and processing efficiency. They achieve precise matching and weighted adjustment based on material component characteristic information, thereby improving the processing accuracy and efficiency of plastic products.

[0048] Example 2, based on the same inventive concept as the method for collaborative optimization of multiple control parameters in the production of plastic products in the foregoing examples, such as... Figure 2 As shown, this application provides a multi-control parameter collaborative optimization system for plastic product manufacturing, the system comprising: Characteristic information acquisition module 1: The characteristic information acquisition module 1 is used to acquire the target component characteristic information of the target material, and the target component characteristic information includes a variety of material components with proportioning identifiers; Material composition traversal and matching module 2: The material composition traversal and matching module 2 is used to traverse and match the first material component among the multiple material components with proportioning identifiers in the material composition database to obtain the first crystal porosity; First porosity weighted adjustment module 3: The first porosity weighted adjustment module 3 is used to use the first ratio of the first material component as a weighting coefficient to adjust the porosity of the first crystal to obtain the target crystal porosity of the target material. Dynamic monitoring module 4: The dynamic monitoring module 4 is used to dynamically monitor and obtain the processing control record of the first product, which refers to the processing record of the target material in the first predetermined processing cycle; Traversal and filtering module 5: The traversal and filtering module 5 is used to traverse and filter the first predetermined indicator in the predetermined processing control indicators in the first product processing control record, and combine it with the first predetermined processing cycle to obtain the timing sequence of the first control indicator parameter. Parameter comparison module 6: The parameter comparison module 6 is used to compare and determine the first target component of the timing sequence of the first control index parameter, and record the first average control index parameter of the first target component as the index parameter of the first predetermined index. Processing control traversal matching module 7: The processing control traversal matching module 7 is used to form a first target processing control strategy based on the first average control index parameters, and to traverse and match the first target processing control strategy in the processing control database to obtain the target historical processing control strategy. Target porosity weighted adjustment module 8: The target porosity weighted adjustment module 8 is used to adjust the target crystal porosity by using the target historical porosity fitness of the target historical processing control strategy as a weighting coefficient to obtain the target porosity; Optimization adjustment module 9: When the target porosity is not at a predetermined porosity threshold, the optimization adjustment module 9 issues a processing adjustment command and optimizes the first target processing control strategy based on the processing adjustment command.

[0049] Furthermore, the traversal filtering module 5 is also used to perform the following method: The predetermined processing control parameters include at least injection speed, injection pressure, melt temperature, mold temperature, cooling time, screw speed, back pressure, and material dryness.

[0050] Furthermore, the parameter comparison module 6 is also used to perform the following method: The first control index parameter time series is subjected to modal decomposition to obtain a first modal decomposition result, which includes multiple modal components; a modal component weight evaluation function is introduced to evaluate the weights of the multiple modal components in sequence to obtain multiple weights; the multiple weights are compared and the first target component is determined.

[0051] Furthermore, the parameter comparison module 6 is also used to perform the following method: The expression for the modal component weight evaluation function is as follows: ;in, Characterizing the first of the multiple modal components Modal components The Each weight, Characterizing the first Modal components The amount of feature information, The total amount of characteristic information representing the time series of the first control index parameter. Characterizing the first Modal components The correlation coefficient value between the first control index parameter and the time series. and They are the first coefficient and the second coefficient, respectively, and .

[0052] Furthermore, the target porosity weighted adjustment module 8 is also used to perform the following method: Read the predetermined strategy vectorization scheme; based on the predetermined strategy vectorization scheme, vectorize the first target processing control strategy and the first historical processing control strategy sequentially to obtain the first target vector and the first historical vector, respectively, wherein the first historical processing control strategy is any historical processing control strategy in the processing control database; compare and analyze the first target vector and the first historical vector to obtain the first similarity; when the first similarity reaches the predetermined similarity threshold, record the first historical porosity fitness of the matched first historical processing control strategy as the target historical porosity fitness.

[0053] Furthermore, the target porosity weighted adjustment module 8 is also used to perform the following method: Obtain the first historical initial crystal porosity; monitor the first real-time historical material porosity under the first historical processing control strategy; take the first real-time historical ratio of the first real-time historical material porosity to the first historical initial crystal porosity as the first real-time historical porosity fitness; perform periodic analysis on the first fitness time series generated based on the first real-time historical porosity fitness to obtain the first historical porosity fitness.

[0054] Furthermore, the optimization adjustment module 9 is also used to perform the following method: An optimization space is constructed based on the predetermined thresholds of each predetermined indicator in the predetermined processing control index; taboo optimization is performed in the optimization space using porosity fitness as the optimization index to obtain the target optimal processing control strategy; the target material is processed and controlled for a second predetermined processing cycle according to the target optimal processing control strategy.

[0055] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0056] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0057] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for collaborative optimization of multiple control parameters in the production of plastic products, characterized in that, include: Obtain target component characteristic information of the target material, wherein the target component characteristic information includes multiple material components with proportioning identifiers; The first material component among the various material components with proportioning identifiers is matched by traversing and matching in the material component database to obtain the first crystal porosity; Using the first ratio of the first material components as a weighting coefficient, the porosity of the first crystal is adjusted by weighting to obtain the target crystal porosity of the target material; Dynamic monitoring yields the processing control record of the first product, which refers to the processing record of the target material in the first predetermined processing cycle; The first predetermined indicator in the predetermined processing control indicators is traversed and filtered in the first product processing control record, and the timing sequence of the first control indicator parameter is obtained by combining it with the first predetermined processing cycle. The first target component of the first control index parameter time series is determined by comparison, and the first average control index parameter of the first target component is recorded as the index parameter of the first predetermined index. A first target processing control strategy is formed based on the first average control index parameters, and the first target processing control strategy is traversed and matched in the processing control database to obtain the target historical processing control strategy. Using the target historical porosity fitness of the target historical processing control strategy as a weighting coefficient, the target crystal porosity is weighted and adjusted to obtain the target porosity; When the target porosity is not at the predetermined porosity threshold, a processing adjustment command is issued, and the first target processing control strategy is optimized and adjusted based on the processing adjustment command.

2. The method for collaborative optimization of multiple control parameters in the production of plastic products according to claim 1, characterized in that, The predetermined processing control parameters include at least injection speed, injection pressure, melt temperature, mold temperature, cooling time, screw speed, back pressure, and material dryness.

3. The method for coordinated optimization of multiple control parameters in the production of plastic products according to claim 1, characterized in that, include: The timing sequence of the first control index parameter is subjected to modal decomposition to obtain a first modal decomposition result, which includes multiple modal components; A modal component weight evaluation function is introduced to sequentially evaluate the weights of the multiple modal components, resulting in multiple weights; The multiple weights are compared and the first target component is determined.

4. The method for coordinated optimization of multiple control parameters in the production of plastic products according to claim 3, characterized in that, The expression for the modal component weight evaluation function is as follows: ； in, Characterizing the first of the multiple modal components Modal components The Each weight, Characterizing the first Modal components The amount of feature information, The total amount of characteristic information representing the time series of the first control index parameter. Characterizing the first Modal components The correlation coefficient value between the first control index parameter and the time series. and They are the first coefficient and the second coefficient, respectively, and .

5. The method for collaborative optimization of multiple control parameters in the production of plastic products according to claim 1, characterized in that, include: Read the predefined strategy vectorization scheme; Based on the predetermined strategy vectorization scheme, the first target processing control strategy and the first historical processing control strategy are vectorized sequentially to obtain the first target vector and the first historical vector, respectively. The first historical processing control strategy is any historical processing control strategy in the processing control database. The first similarity is obtained by comparing and analyzing the first target vector and the first historical vector. When the first similarity reaches a predetermined similarity threshold, the first historical porosity fitness of the matched first historical processing control strategy is recorded as the target historical porosity fitness.

6. The method for collaborative optimization of multiple control parameters in the production of plastic products according to claim 5, characterized in that, include: Obtain the initial crystal porosity in the first historical period; The first real-time historical material porosity under the first historical processing control strategy was obtained through monitoring; The first real-time historical ratio of the first real-time historical material porosity to the first real-time initial crystal porosity is taken as the first real-time historical porosity fitness. Periodic analysis is performed on the time series of the first fitness generated based on the first real-time historical porosity fitness to obtain the first historical porosity fitness.

7. The method for collaborative optimization of multiple control parameters in the production of plastic products according to claim 1, characterized in that, include: An optimization space is constructed based on the predetermined threshold values ​​of each predetermined indicator in the predetermined processing control indicators; Using porosity fitness as the optimization index, tabu search is performed in the optimization space to obtain the target optimal processing control strategy; The target material is processed and controlled for a second predetermined processing cycle according to the target optimal processing control strategy.

8. A multi-control parameter collaborative optimization system for plastic product manufacturing, characterized in that, The steps for implementing the multi-control parameter collaborative optimization method in the production of plastic products according to any one of claims 1 to 7 include: Characteristic information acquisition module: acquires the target component characteristic information of the target material, wherein the target component characteristic information includes multiple material components with proportioning identifiers; Material composition traversal and matching module: Traverses and matches the first material component among the multiple material components with proportioning identifiers in the material composition database to obtain the first crystal porosity; First porosity weighted adjustment module: Using the first ratio of the first material component as a weighting coefficient, the first crystal porosity is weighted and adjusted to obtain the target crystal porosity of the target material; Dynamic monitoring module: Dynamic monitoring obtains the first product processing control record, which refers to the processing record of the target material in the first predetermined processing cycle; Traversal and filtering module: Traversal and filtering of the first predetermined indicator in the predetermined processing control indicators in the first product processing control record, and obtaining the timing sequence of the first control indicator parameter by combining the first predetermined processing cycle; Parameter comparison module: compares and determines the first target component of the timing sequence of the first control index parameter, and records the first average control index parameter of the first target component as the index parameter of the first predetermined index; Processing control traversal matching module: Based on the first average control index parameters, a first target processing control strategy is formed, and the first target processing control strategy is traversed and matched in the processing control database to obtain the target historical processing control strategy; Target porosity weighted adjustment module: Using the target historical porosity fitness of the target historical processing control strategy as a weighting coefficient, the target crystal porosity is weighted and adjusted to obtain the target porosity; Optimization and adjustment module: When the target porosity is not at the predetermined porosity threshold, a processing adjustment command is issued, and the first target processing control strategy is optimized and adjusted based on the processing adjustment command.

Images