Intelligent production process optimization method for medical polymer material

Abstract

The invention discloses an intelligent production process optimization method for a medical high polymer material, and relates to the technical field of data processing, and the method comprises the following steps: collecting original production process parameters of syringe production by using polyethylene; performing performance analysis, and classifying to obtain a fusion optimization step length, a forming optimization step length and a cooling optimization step length; obtaining a first production process parameter; constructing first syringe twinborn model distribution, and obtaining a first dose performance parameter, a first strength performance parameter and a first push performance parameter; and outputting the optimal production process parameter with the maximum injector fitness as a production process optimization result. The technical problems that the consistency and stability of product performance quality are insufficient and the production efficiency is low due to the fact that accurate control and optimization of production process parameters and performance prediction are difficult to achieve in an existing production process of the medical polymer material are solved. The technical effects of improving the production efficiency, the product quality and the product performance are achieved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method for optimizing intelligent manufacturing processes for medical polymer materials. Background Technology

[0002] With the rapid development of intelligent manufacturing technology, especially the advancements in data analysis and machine learning, new ideas and methods have been provided for optimizing the production process of medical polymer materials. In the medical field, polymer materials are widely used in the manufacture of various medical devices and instruments, such as syringes, due to their unique physical and chemical properties. However, the production process parameters of polymer materials directly determine the performance and quality of the products. In the production process of syringes, polyethylene, as a commonly used polymer material, directly affects the molding quality, dimensional accuracy, and performance of the syringes when its production process parameters are set. Traditional production process optimization methods often rely on experience and trial and error, making it difficult to achieve precise control and optimization of production process parameters and accurately predict the performance distribution of the products, thus affecting the production efficiency and performance quality of syringes.

[0003] Therefore, in the current production technology of medical polymer materials, there are technical problems such as difficulty in accurately controlling and optimizing production process parameters and predicting performance, which leads to insufficient consistency and stability of product performance and quality, as well as low production efficiency. Summary of the Invention

[0004] This application provides an intelligent manufacturing process optimization method for medical polymer materials. By employing performance analysis, parameter optimization, and other technical means, it solves the technical problems existing in the manufacturing process of medical polymer materials, such as the difficulty in achieving precise control and optimization of manufacturing process parameters and performance prediction, which leads to insufficient consistency and stability of product performance and quality, as well as low production efficiency. The method achieves the technical effects of improving production efficiency, product quality, and enhancing product performance.

[0005] This application provides a method for optimizing the intelligent manufacturing process of medical polymer materials. The method includes: collecting original manufacturing process parameters for syringes produced using polyethylene, wherein the original manufacturing process parameters include original melting process parameters, original molding process parameters, and original cooling process parameters; collecting test data of syringes produced according to the original manufacturing process parameters, performing performance analysis, and classifying and obtaining melting optimization step size, molding optimization step size, and cooling optimization step size; adjusting the original manufacturing process parameters using the melting optimization step size, molding optimization step size, and cooling optimization step size to obtain first manufacturing process parameters, and predicting and obtaining a first uniformity distribution, a first crystallization defect distribution, and a first bubble probability distribution, wherein the first bubble probability distribution includes the probability of bubbles appearing at multiple locations of the syringe; constructing a first syringe twin model distribution based on the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution, performing performance analysis, obtaining a first dose performance parameter, a first strength performance parameter, and a first delivery performance parameter, and classifying and obtaining a first syringe fitness; continuing to optimize the manufacturing process parameters until the optimization requirements are met, and outputting the optimal manufacturing process parameters that maximize the syringe fitness as the manufacturing process optimization result.

[0006] In a possible implementation, test data of syringes produced according to the original production process parameters is collected, performance analysis is performed, and the melt optimization step size, molding optimization step size, and cooling optimization step size are obtained by classification. The following processing is also performed: Test data of syringes produced according to the original production process parameters is collected; dosage performance parameters, strength performance parameters, and delivery performance parameters are extracted from the test data to obtain original dosage performance parameters, original strength performance parameters, and original delivery performance parameters; based on the original dosage performance parameters, original strength performance parameters, and original delivery performance parameters, the melt optimization step size, molding optimization step size, and cooling optimization step size are obtained to adjust and optimize the original melt process parameters, original molding process parameters, and original cooling process parameters.

[0007] In a possible implementation, based on the original dose performance parameters, original strength performance parameters, and original delivery performance parameters, a melt optimization step size, a forming optimization step size, and a cooling optimization step size are obtained to adjust and optimize the original melt process parameters, original forming process parameters, and original cooling process parameters. The following processing is also performed: Based on historical performance test data of syringes, a set of sample dose performance parameters, a set of sample strength performance parameters, and a set of sample delivery performance parameters are collected, along with a set of sample syringe performance parameters. Using the collected set of sample dose performance parameters, sample strength performance parameters, and sample delivery performance parameters as classification inputs, and using the set of sample syringe performance parameters as classification outputs, a syringe performance analyzer is constructed. Using the syringe performance analyzer, the original dose performance parameters, original strength performance parameters, and original delivery performance parameters are classified to obtain syringe performance parameters. Based on the deviation between the syringe performance parameters and preset performance parameters, the preset step sizes for adjusting the original melt process parameters, original forming process parameters, and original cooling process parameters are adjusted respectively to obtain the melt optimization step size, the forming optimization step size, and the cooling optimization step size.

[0008] In a possible implementation, the original production process parameters are adjusted using the aforementioned melt optimization step size, molding optimization step size, and cooling optimization step size to obtain first production process parameters. A first uniformity distribution, a first crystallization defect distribution, and a first bubble probability distribution are predicted and obtained. The following processing is also performed: The original melt process parameters, original molding process parameters, and original cooling process parameters within the original production process parameters are adjusted using the aforementioned melt optimization step size, molding optimization step size, and cooling optimization step size to obtain first melt process parameters, first molding process parameters, and first cooling process parameters, which serve as the first production process parameters. Based on historical production data of polyethylene syringes, a sample production process parameter set is collected, along with production... The test obtains a set of sample uniformity distributions, a set of sample crystallization defect distributions, and a set of sample bubble probability distributions. Each sample bubble probability distribution includes the probability of bubbles appearing at multiple locations on the syringe. Each sample uniformity distribution and sample crystallization defect distribution includes the component uniformity parameters and the number of crystallization defects at multiple locations on the syringe. Using the set of sample production process parameters as training input and the set of sample uniformity distributions, sample crystallization defect distributions, and sample bubble probability distributions as training output, a syringe feature predictor is trained. Using the syringe feature predictor, production prediction is performed on the first production process parameters to obtain the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution.

[0009] In a possible implementation, a first syringe twin model distribution is constructed based on the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution. Performance analysis is performed to obtain first dose performance parameters, first intensity performance parameters, and first delivery performance parameters. The fitness of the first syringe is calculated. The following processing is also performed: a first basic syringe twin model is constructed based on the first uniformity distribution and the first crystallization defect distribution; the first basic syringe twin model is supplemented using the probabilities of bubbles appearing at multiple locations within the first bubble probability distribution to obtain multiple first syringe twin models and multiple production probabilities, resulting in a first syringe twin model distribution, wherein bubbles exist at different locations within each first syringe twin model; performance analysis is performed based on the first syringe twin model distribution to obtain first dose performance parameters, first intensity performance parameters, and first delivery performance parameters, and the fitness of the first syringe is determined by classification.

[0010] In a possible implementation, performance analysis is performed based on the distribution of the first syringe twin models to obtain first dose performance parameters, first intensity performance parameters, and first delivery performance parameters. The following processing is also performed: Simulated injection tests are conducted on multiple first syringe twin models within the distribution of the first syringe twin models to obtain multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first delivery performance parameters; Based on multiple production probabilities within the distribution of the first syringe twin models, the multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first delivery performance parameters are weighted and calculated to obtain first comprehensive dose performance parameters, first comprehensive intensity performance parameters, and first comprehensive delivery performance parameters; Based on the first comprehensive dose performance parameters, first comprehensive intensity performance parameters, and first comprehensive delivery performance parameters, first syringe performance parameters are classified and obtained as the fitness of the first syringe.

[0011] In a possible implementation, the production process parameters are further optimized until the optimization requirements are met, and the optimal production process parameters that maximize the syringe fitness are output. The following processing is also performed: the first production process parameters are adjusted using the aforementioned melt optimization step size, molding optimization step size, and cooling optimization step size to obtain second production process parameters; based on the second production process parameters, a second uniformity distribution, a second crystallization defect distribution, and a second bubble probability distribution are predicted and processed to obtain a second syringe fitness; when the second syringe fitness is greater than the first syringe fitness, the second production process parameters are retained, and the first production process parameters are deleted; when the second syringe fitness is not greater than the first syringe fitness, a judgment is made according to the bubble probability discrimination rule, and either the first or second production process parameter is retained. Continue iterative optimization until the optimization requirements are met, and output the optimal production process parameters that maximize the adaptability of the syringe.

[0012] In a possible implementation, in addition to the discrimination according to the bubble probability discrimination rule, the following processing is also performed: calculate the first total bubble probability based on the first bubble probability distribution, calculate the second total bubble probability based on the second bubble probability distribution; calculate the absolute value of the difference between the second total bubble probability and the first total bubble probability as the discrimination threshold, randomly generate a random number between 0 and 1, and determine whether the random number is greater than the discrimination threshold. If it is, the second production process parameter is retained; if not, the first production process parameter is retained.

[0013] This application proposes a smart manufacturing process optimization method for medical polymer materials. The method involves collecting original manufacturing process parameters for syringes made from polyethylene; collecting syringe test data, performing performance analysis, and classifying the parameters to obtain melt optimization step size, molding optimization step size, and cooling optimization step size; adjusting the original manufacturing process parameters to obtain first manufacturing process parameters, and predicting the first uniformity distribution, first crystallization defect distribution, and first bubble probability distribution; constructing a first syringe twin model distribution to obtain first dosage performance parameters, first strength performance parameters, and first delivery performance parameters; continuing to optimize the manufacturing process parameters until the optimization requirements are met, and outputting the optimal manufacturing process parameters that maximize syringe adaptability as the manufacturing process optimization result. This method solves the technical problems of existing medical polymer material manufacturing processes, which struggle to achieve precise control and optimization of manufacturing process parameters and performance prediction, leading to insufficient consistency and stability of product performance and quality, as well as low production efficiency. It achieves the technical effects of improving production efficiency, product quality, and enhancing product performance. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0015] Figure 1 A schematic diagram of the intelligent manufacturing process optimization method for medical polymer materials provided in this application embodiment; Figure 2 This is a schematic flowchart illustrating the method for optimizing the intelligent manufacturing process of medical polymer materials provided in this application to obtain the optimal manufacturing process parameters. Detailed Implementation

[0016] The above description is only 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, the following are specific embodiments of this application.

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. 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 explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0019] This application provides an intelligent manufacturing process optimization method for medical polymer materials, such as... Figure 1 As shown, the method includes: Step S100: Collect the original production process parameters for syringe production using polyethylene, wherein the original production process parameters include the original melting process parameters, the original molding process parameters, and the original cooling process parameters. Polyethylene is a thermoplastic resin synthesized by polymerizing ethylene monomers under high or low pressure using different catalyst systems (such as Ziegler-Natta catalysts). It is mainly used to manufacture films, packaging materials, containers, pipes, monofilaments, wires and cables, and daily necessities. It can also be used as a high-frequency insulating material for televisions, radar, etc. Ultra-high molecular weight polyethylene (UHMWPE) is suitable for manufacturing medical polymer materials, such as syringes. The original process parameters for syringe production include original melt processing parameters, original molding process parameters, and original cooling process parameters. Specifically, melt processing refers to heating the polyethylene raw material to its melting point or semi-molten state, making it flowable, and then using specific molding equipment to process the material (through extrusion, injection molding, blow molding, etc.) into the required shape. The original melt processing parameters mainly include melt temperature, melt time, and melt pressure. Melt temperature refers to the temperature at which the polyethylene material begins to melt. The selection of melt temperature is crucial for ensuring sufficient melting, fluidity, and avoiding overheating and degradation. Melt time refers to the time required to ensure complete melting after the material reaches the melt temperature. The time required to maintain a uniform molten state is considered the molding process parameters. Molding pressure refers to the pressure applied during the melting process to promote material flow within the equipment or to remove air bubbles. The primary molding process parameters include molding pressure, molding temperature, and molding time. Specifically, molding pressure refers to the pressure applied during syringe molding to ensure that molten polyethylene is fully filled into all parts of the mold when injected into the mold. Molding temperature ensures rapid cooling and solidification of the material within the mold, significantly impacting the product's molding quality and dimensional accuracy. Molding time refers to the time required from material injection into the mold to complete product solidification. The primary cooling process parameters include cooling rate, cooling medium, and cooling time. Cooling rate refers to the time required for cooling after product solidification within the mold; its speed directly affects the product's shrinkage rate, dimensional accuracy, and surface quality. Cooling medium refers to the medium used for cooling (such as water, air, coolant, etc.) and its corresponding temperature and flow rate parameters. Cooling time refers to the time required for subsequent cooling after the syringe is removed from the mold to ensure the product reaches a stable temperature and reduces deformation.

[0020] Step S200: Collect test data of syringes produced according to the original production process parameters, perform performance analysis, and classify and obtain melt optimization step length, molding optimization step length, and cooling optimization step length. Based on the test data of syringes produced according to the original production process parameters (including dosage performance parameters, strength performance parameters, and delivery performance parameters, reflecting the accuracy of dosage, strength during use, and the accuracy of resistance during delivery compared to standard resistance), specifically referring to producing syringes according to the original production process parameters and conducting performance tests, recording and acquiring test data, including using appropriate equipment to collect data on syringe dimensional accuracy, shape stability, strength and toughness, sealing and drug delivery smoothness, heat resistance, corrosion resistance, etc., analyze the test data to find the relationship between performance and process parameters, and determine the process parameters that have a significant impact on performance. Specifically, the melt optimization step length refers to gradually adjusting the melt parameters, adjusting them in small increments each time (e.g., adjusting the melt temperature by 5°C each time, and the melt time by 10 seconds each time), observing their impact on syringe performance. The optimal melt optimization step length was determined to improve the melt efficiency and melt quality of polyethylene, ensuring that the polyethylene material melts fully and has good fluidity. The optimal molding step length was determined by gradually adjusting molding parameters, making small adjustments each time (e.g., adjusting pressure by 5 MPa, temperature by 5°C, time by 1 second, etc.), observing their impact on performance, and ultimately determining the optimal molding step length. The goal is to ensure uniform material filling, appropriate shrinkage, and stable shape during the syringe molding process. The optimal cooling step length was determined by gradually adjusting cooling parameters, making small adjustments each time (e.g., adjusting cooling rate by 10%, medium temperature by 1°C, time by 5 seconds, etc.), observing their impact on performance, and ultimately determining the optimal cooling step length. The goal is to ensure that the syringe cools quickly and uniformly during the cooling process, reducing deformation and internal stress.

[0021] In one possible implementation, step S200 further includes step S210, collecting test data of syringes manufactured according to the original production process parameters. The syringes manufactured according to the original production process parameters are tested, and various performance index data of these syringes are collected, including dosage performance, strength performance, and delivery performance. Step S220 further includes extracting the dosage performance parameters, strength performance parameters, and delivery performance parameters from the test data to obtain original dosage performance parameters, original strength performance parameters, and original delivery performance parameters. The original dosage performance parameters may include the deviation between the actual dose administered by the syringe and the set dose, dose repeatability (i.e., consistency of dose administered multiple times by the syringe), etc.; the original strength performance parameters may include the syringe's pressure resistance, material strength, etc.; and the original delivery performance parameters may include delivery resistance, delivery smoothness, etc.

[0022] Step S200 further includes step S230, which, based on the original dosage performance parameters, original strength performance parameters, and original delivery performance parameters, classifies and obtains melt optimization step size, molding optimization step size, and cooling optimization step size for adjusting and optimizing the original melting process parameters, original molding process parameters, and original cooling process parameters. The original dosage performance parameters, original strength performance parameters, and original delivery performance parameters are analyzed to assess whether they meet preset requirements. If the original dosage performance parameters do not meet the requirements, the melting process parameters (such as melting temperature, time, pressure, etc.) need to be adjusted to obtain more accurate dosage performance. If the original strength performance parameters do not meet the requirements, the molding process parameters (such as molding pressure, temperature, time, etc.) may need to be adjusted to improve the structural strength of the syringe. If the original delivery performance parameters are unsatisfactory, the cooling process parameters (such as cooling rate, cooling time, etc.) may need to be optimized to improve the delivery performance of the syringe.

[0023] In one possible implementation, step S230 further includes step S231, which involves collecting a set of sample dose performance parameters, a set of sample strength performance parameters, and a set of sample delivery performance parameters based on historical performance test data of the syringe, and also collecting a set of sample syringe performance parameters. The set of sample dose performance parameters refers to the set of parameters related to dose performance extracted from historical performance test data, such as the deviation between the actual administered dose and the set dose, and dose repeatability. The set of sample strength performance parameters is the set of parameters related to strength performance, such as pressure resistance and material strength. The set of sample delivery performance parameters is the set of parameters related to delivery performance, such as delivery resistance and delivery smoothness. The set of sample syringe performance parameters consists of classification labels or results corresponding to the above performance parameters, typically representing the overall performance level or classification of the syringe.

[0024] Step S230 further includes step S232, which uses the collected sample dose performance parameter set, sample intensity performance parameter set, and sample push performance parameter set as classification input, and the sample syringe performance parameter set as classification output to construct a syringe performance analyzer. A classification model is constructed using machine learning (such as decision trees, random forests, neural networks, etc.). The collected sample dose performance parameter set, sample intensity performance parameter set, and sample push performance parameter set are used as classification input features and input to the constructed classification model for training, resulting in the syringe performance analyzer. This model can predict the performance classification of the syringe based on the input performance parameters. Step S233 further includes using the syringe performance analyzer to perform performance classification on the original dose performance parameters, original intensity performance parameters, and original push performance parameters to obtain syringe performance parameters. Using the trained syringe performance analyzer, the original dose performance parameters, intensity performance parameters, and push performance parameters are classified, that is, by applying the analyzer to the original parameters, the predicted classification of the syringe in these performance aspects is obtained, resulting in the corresponding syringe performance parameters.

[0025] Step S230 further includes step S234, which adjusts the preset step size of the original melting process parameters, the original molding process parameters, and the original cooling process parameters according to the deviation between the syringe performance parameters and the preset performance parameters, so as to obtain the melting optimization step size, the molding optimization step size, and the cooling optimization step size. Preset performance parameters are expected performance parameter values ​​set according to product quality requirements. By comparing the syringe performance parameters with the preset performance parameters, the deviation or difference between the two is determined. Then, based on the magnitude and direction of the performance deviation, it is determined whether the preset step size needs to be adjusted, as well as the direction and magnitude of the adjustment. For example, if the performance deviation is large, the step size may need to be increased to speed up the optimization process. If the performance deviation is within an acceptable range but the direction is opposite to the target, the step size may need to be fine-tuned to gradually approach the target. If the performance deviation is already small and close to the target, the step size may need to be reduced to avoid over-adjustment. Specifically, based on the deviation of the dosage performance, strength performance, and / or delivery performance from the preset values, the preset step size of the original melting process parameters is adjusted to obtain a new melting process parameter adjustment step size. Based on the performance deviation, the preset step size of the original molding process parameters is adjusted to obtain an optimized molding process parameter step size. Based on the performance deviation, the preset step size of the original cooling process parameters is adjusted to obtain an optimized cooling process parameter step size.

[0026] Step S300: Using the melt optimization step size, molding optimization step size, and cooling optimization step size, the original production process parameters are adjusted to obtain the first production process parameters. A first uniformity distribution, a first crystallization defect distribution, and a first bubble probability distribution are predicted. The first bubble probability distribution includes the probability of bubbles appearing at multiple locations on the syringe. Adjusting the original production process parameters using the melt optimization step size, molding optimization step size, and cooling optimization step size specifically refers to adjusting the melt temperature, melt time, melt pressure, molding pressure, molding temperature, molding time, and optimizing the cooling process to ensure rapid and uniform cooling of the product. For example, starting from the initial temperature (e.g., 150°C), the temperature is gradually adjusted to the optimal temperature (e.g., 160°C) according to the melt optimization step size (e.g., adjusting by 5°C each time). The melt time is gradually adjusted according to the material's melting characteristics to ensure complete melting. The melt pressure is adjusted according to the performance of the melting equipment and the melting state to promote material flow and venting, thereby obtaining the first production process parameters. The first production process parameters refer to the adjusted original production process parameters. The corresponding syringe manufacturing process parameters obtained after the calculation are as follows: Specifically, the first uniformity distribution refers to the prediction of the uniformity of the syringe in terms of material distribution and density by observing the material distribution and density of the product in various parts through simulation or actual production; the first crystallization defect distribution refers to the prediction of defects that may occur in the product during the crystallization process, such as point defects and line defects, based on materials science knowledge and production experience, combined with the product structure and production process; the first bubble rate distribution refers to the prediction of the probability of bubbles appearing in multiple locations of the syringe, such as identifying key locations in the syringe where bubbles may be generated, such as weld lines and edges, and assessing the probability of bubbles appearing at each location based on factors such as raw material quality, injection molding machine parameters, mold design and production environment.

[0027] In one possible implementation, step S300 further includes step S310, which involves adjusting the original melting process parameters, original forming process parameters, and original cooling process parameters within the original production process parameters using the melt optimization step size, forming optimization step size, and cooling optimization step size to obtain first melting process parameters, first forming process parameters, and first cooling process parameters, which serve as the first production process parameters. Using the calculated melt optimization step size, forming optimization step size, and cooling optimization step size, the original melting process parameters, original forming process parameters, and original cooling process parameters within the original production process parameters are adjusted to obtain the first melting process parameters, first forming process parameters, and first cooling process parameters. These parameters, combined, constitute the first production process parameters.

[0028] Step S300 further includes step S320, which involves collecting a set of sample production process parameters, a set of sample uniformity distributions, a set of sample crystallization defect distributions, and a set of sample bubble probability distributions obtained from production tests, based on historical production data of polyethylene syringes. Each sample bubble probability distribution includes the probability of bubbles appearing at multiple locations on the syringe, and each sample uniformity distribution and sample crystallization defect distribution includes the compositional uniformity parameters and the number of crystallization defects at multiple locations on the syringe. The set of sample production process parameters refers to the set of different production process parameters used in the historical production of polyethylene. The production test data refers to data related to product quality obtained through production tests, including the set of sample uniformity distributions, the set of sample crystallization defect distributions, and the set of sample bubble probability distributions. Specifically, the sample uniformity distribution represents the compositional uniformity parameters at different locations on the syringe, reflecting the uniformity of material distribution; the sample crystallization defect distribution represents the number of crystallization defects at different locations on the syringe, reflecting the integrity and quality of material crystallization; and the sample bubble probability distribution includes the probability of bubbles appearing at multiple locations on the syringe, reflecting the possibility and location of bubble generation during the product production process.

[0029] Step S300 further includes step S330, which uses the set of sample production process parameters as training input and the set of sample uniformity distribution, sample crystallization defect distribution, and sample bubble probability distribution as training output to train the syringe feature predictor. A prediction model is constructed based on machine learning algorithms (such as neural networks, random forests, etc.). The prediction model is trained under supervision using the set of sample production process parameters as training input and the set of sample uniformity distribution, sample crystallization defect distribution, and sample bubble probability distribution as output, resulting in the syringe feature predictor, which can predict the uniformity distribution, crystallization defect distribution, and bubble probability distribution of the product based on the production process parameters.

[0030] Step S300 further includes step S340, which uses the syringe feature predictor to predict the production based on the first production process parameters, obtaining the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution. Using the first production process parameters as input, the trained syringe feature predictor outputs the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution, representing the expected product quality and potential problems when producing using the first production process parameters.

[0031] Step S400: Based on the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution, construct the first syringe twin model distribution, perform performance analysis, obtain the first dose performance parameter, the first intensity performance parameter, and the first delivery performance parameter, and classify to obtain the first syringe fitness. The first syringe twin model refers to a digital simulation of the syringe manufacturing process based on first production process parameters. Specifically, a basic syringe twin model is constructed by combining a first uniformity distribution and a first crystallization defect distribution. Then, based on the first bubble probability distribution, including the probability of bubbles appearing at multiple locations in the syringe, bubbles are added to multiple locations within the basic syringe twin model to obtain multiple first syringe twin models. Multiple production probabilities are then assigned according to the probability of bubbles appearing at multiple locations, forming a distribution of first syringe twin models that can be obtained by producing syringes according to the first production process parameters. Simulation performance tests are then conducted to obtain multiple sets of first dose performance parameters, first strength performance parameters, and first delivery performance parameters. Among them, the first dose performance parameter is used to evaluate the dosage accuracy and consistency of the syringe during drug administration; the first strength performance parameter is used to evaluate the structural strength and durability of the syringe; and the first delivery performance parameter is used to evaluate the smoothness and resistance of the syringe during drug delivery. Finally, based on the first dose performance parameter, first strength performance parameter, and first delivery performance parameter, the performance of the first syringe is weighted according to the importance of syringe production, and the performance is classified to obtain the first syringe fitness.

[0032] In one possible implementation, step S400 further includes step S410, constructing a first basic syringe twin model based on the first uniformity distribution and the first crystallization defect distribution. Based on the first uniformity distribution and the first crystallization defect distribution, a basic digital twin model is constructed to simulate the physical characteristics of the syringe, representing the expected performance and quality of the syringe in the absence of air bubbles.

[0033] Step S400 further includes step S420, which supplements the first basic syringe twin model using the probabilities of bubbles appearing at multiple locations within the first bubble probability distribution, obtaining multiple first syringe twin models and multiple production probabilities, thus obtaining a first syringe twin model distribution. In each first syringe twin model, bubbles exist at different locations. Supplementing the first basic syringe twin model using the probabilities of bubbles appearing at multiple locations within the first bubble probability distribution means simulating the presence of bubbles at different locations in the basic model to reflect various situations that may occur in actual production. Based on the bubble probability distribution, multiple first syringe twin models can be generated, each model containing bubbles at different locations. Simultaneously, the production probability corresponding to each model is calculated, i.e., the likelihood of that model appearing in actual production. These models with different bubble locations and production probabilities constitute a distribution, namely the first syringe twin model distribution, representing various syringe states and quality levels that may occur in actual production.

[0034] Step S400 further includes step S430, which involves performing performance analysis based on the distribution of the first syringe twin models to obtain first dose performance parameters, first intensity performance parameters, and first delivery performance parameters, and classifying them to obtain the fitness of the first syringe. The performance analysis based on the distribution of the first syringe twin models specifically refers to simulating or calculating the performance of each model in terms of dose performance, intensity performance, and delivery performance. Through analysis, the first dose performance parameters, first intensity performance parameters, and first delivery performance parameters are obtained, representing the expected performance of the syringe in these aspects in actual production based on current production process parameters. Based on the first dose performance parameters, first intensity performance parameters, and first delivery performance parameters, the fitness of each model in the distribution of the first syringe twin models is evaluated. Based on the results of the fitness evaluation, the first syringe twin models can be classified, providing a more intuitive understanding of the performance level of the syringe under different production process parameters.

[0035] In one possible implementation, step S430 further includes step S431, which involves performing simulated injection tests on multiple first syringe twin models within the distribution of the first syringe twin models to obtain multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first push performance parameters. Based on the multiple first syringe twin models within the distribution of the first syringe twin models, simulated injection tests are performed to simulate the syringe's performance in terms of dose, intensity, and push during actual injection, resulting in multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first push performance parameters, representing the performance of the syringe under different twin models (i.e., different bubble positions and distributions).

[0036] Step S430 further includes step S432, which involves weighting the multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first push performance parameters according to multiple production probabilities within the distribution of the first syringe twin model, to obtain the first comprehensive dose performance parameter, the first comprehensive intensity performance parameter, and the first comprehensive push performance parameter. By weighting the performance parameters obtained from each simulation test according to multiple production probabilities within the distribution of the first syringe twin model, the first comprehensive dose performance parameter, the first comprehensive intensity performance parameter, and the first comprehensive push performance parameter are obtained. These comprehensive performance parameters comprehensively consider all possible twin models (i.e., all possible bubble positions and distributions) and their corresponding production probabilities, thereby more accurately reflecting the overall performance of the syringe in actual production. The production probability reflects the likelihood of each twin model (i.e., each bubble position and distribution) occurring in actual production.

[0037] Step S433: Based on the first comprehensive dose performance parameter, the first comprehensive intensity performance parameter, and the first comprehensive delivery performance parameter, the first syringe performance parameters are classified and obtained as the first syringe fitness. The performance of the syringe is comprehensively evaluated based on the first comprehensive dose performance parameter, the first comprehensive intensity performance parameter, and the first comprehensive delivery performance parameter. The results of the comprehensive evaluation are classified to obtain the first syringe performance parameters, which serve as the first syringe fitness, reflecting the overall performance and reliability of the syringe in practical applications.

[0038] Step S500: Continue optimizing the production process parameters until the optimization requirements are met. Output the optimal production process parameters that maximize the syringe's adaptability as the production process optimization result. Set specific optimization requirements or standards for each performance parameter, such as dosage error range, structural strength index, and push resistance limit. Gradually adjust the production process parameters, such as melting temperature, time, and pressure; molding pressure, temperature, and time; and cooling rate and time. After each parameter adjustment, evaluate the syringe's performance, including dosage performance, strength performance, and push performance. Based on the set optimization requirements, calculate the syringe's adaptability after each iteration. Compare the adaptability of the current iteration with that of the previous iteration to determine if the optimization direction is correct. If the syringe's adaptability after the current iteration meets or exceeds the set optimization requirements, terminate the iteration, select the production process parameters with the highest adaptability as the optimal production process parameters, and output the optimal production process parameters as the production process optimization result. Use this result for the actual production of syringes to improve syringe performance.

[0039] In one possible implementation, such as Figure 2As shown, step S500 further includes step S510, continuing to use the melt optimization step size, molding optimization step size, and cooling optimization step size to adjust the first production process parameters to obtain second production process parameters. The second production process parameters refer to the syringe production process parameters obtained after adjusting the first production process parameters according to the melt optimization step size, molding optimization step size, and cooling optimization step size. It also includes step S520, where, based on the second production process parameters, a second uniformity distribution, a second crystallization defect distribution, and a second bubble probability distribution are predicted, and then processed to obtain the second syringe fitness. Based on the second production process parameters, the second uniformity distribution, the second crystallization defect distribution, and the second bubble probability distribution are predicted. Based on these predicted distributions, a second syringe twin model is constructed and simulated to obtain the second syringe fitness.

[0040] Step S500 further includes step S530, where, when the adaptability of the second syringe is greater than that of the first syringe, the second production process parameter is retained and the first production process parameter is deleted. The adaptability of the second syringe is compared with that of the first syringe. If the adaptability of the second syringe is greater than that of the first syringe, it indicates that the adjusted production process parameter has brought better performance; therefore, the second production process parameter is retained and the first production process parameter is deleted. Step S540 further includes, where, when the adaptability of the second syringe is not greater than that of the first syringe, a judgment is made according to the bubble probability discrimination rule, retaining either the first or second production process parameter. If the adaptability of the second syringe is not greater than that of the first syringe, it indicates that the adjusted production process parameter has not brought better performance; in this case, a judgment is made according to the bubble probability discrimination rule. The bubble probability discrimination rule is another evaluation criterion used to select a better production process parameter when performance is similar. For example, the influence of bubble distribution: if bubbles are located in critical areas (such as the exit of the injection needle), it affects the accuracy of the dosage and the smoothness of the injection; the influence of the number of bubbles: the more bubbles there are, the greater the impact on the performance of the syringe; the influence of bubble size: the larger the bubbles, the greater the impact on the performance of the syringe. It also includes step S550, which continues iterative optimization until the optimization requirements are met, and outputs the optimal production process parameters that maximize the adaptability of the syringe.

[0041] In one possible implementation, step S540 further includes step S541, calculating a first total bubble probability based on the first bubble probability distribution, and calculating a second total bubble probability based on the second bubble probability distribution. Calculating the first total bubble probability based on the first bubble probability distribution (i.e., the distribution of bubbles in the syringe predicted based on the first production process parameters) typically means adding all bubble probabilities in the distribution or merging them according to certain weights; similarly, calculating the second total bubble probability based on the second bubble probability distribution (i.e., the bubble distribution predicted based on the second production process parameters).

[0042] Step S540 further includes step S542, which involves calculating the absolute value of the difference between the total probability of the second bubble and the total probability of the first bubble, using this as a discrimination threshold. A random number between 0 and 1 is randomly generated, and it is determined whether the random number is greater than the discrimination threshold. If so, the second production process parameter is retained; otherwise, the first production process parameter is retained. Calculating the absolute value of the difference between the total probability of the second bubble and the total probability of the first bubble reflects the magnitude of the difference in bubble probability between the two production process parameters. This absolute value of the difference is used as the discrimination threshold. Then, a random number between 0 and 1 is randomly generated, and it is determined whether the generated random number is greater than the discrimination threshold. If the generated random number is greater than the discrimination threshold, it indicates that the current preference is to choose the second production process parameter with a higher total bubble probability (possibly fewer bubbles or a more uniform distribution), and the second production process parameter is retained. If the generated random number is not greater than the discrimination threshold, it indicates that the current preference is to choose the first production process parameter, and the first production process parameter is retained.

[0043] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for optimizing the intelligent manufacturing process of medical polymer materials, characterized in that, The method includes: The original production process parameters for syringe production using polyethylene were collected, including original melting process parameters, original molding process parameters, and original cooling process parameters. Test data of syringes produced according to the original production process parameters were collected, performance analysis was performed, and the melt optimization step length, molding optimization step length and cooling optimization step length were obtained by classification. The original production process parameters are adjusted using the melt optimization step size, molding optimization step size and cooling optimization step size to obtain the first production process parameters, and the first uniformity distribution, the first crystallization defect distribution and the first bubble probability distribution are predicted. The first bubble probability distribution includes the probability of bubbles appearing at multiple locations of the syringe. Based on the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution, a first syringe twin model distribution is constructed, performance analysis is performed, and first dose performance parameters, first intensity performance parameters, and first delivery performance parameters are obtained. The fitness of the first syringe is then classified. Continue to optimize the production process parameters until the optimization requirements are met, and output the optimal production process parameters that maximize the adaptability of the syringe as the production process optimization result.

2. The intelligent manufacturing process optimization method for medical polymer materials according to claim 1, characterized in that, Test data of syringes produced according to the original production process parameters were collected, performance analysis was performed, and the melt optimization step length, molding optimization step length, and cooling optimization step length were obtained by classification, including: Collect test data for syringes produced according to the original production process parameters; The dose performance parameters, intensity performance parameters, and push performance parameters in the test data are extracted to obtain the original dose performance parameters, original intensity performance parameters, and original push performance parameters. Based on the original dosage performance parameters, original strength performance parameters, and original delivery performance parameters, the melt optimization step size, molding optimization step size, and cooling optimization step size are obtained by classifying and optimizing the original melt process parameters, original molding process parameters, and original cooling process parameters.

3. The intelligent manufacturing process optimization method for medical polymer materials according to claim 2, characterized in that, Based on the original dosage performance parameters, original strength performance parameters, and original delivery performance parameters, the melt optimization step size, molding optimization step size, and cooling optimization step size for adjusting and optimizing the original melt process parameters, original molding process parameters, and original cooling process parameters are obtained, including: Based on the historical performance test data of syringes, a set of sample dose performance parameters, a set of sample intensity performance parameters, and a set of sample delivery performance parameters are collected, as well as a set of sample syringe performance parameters. A syringe performance analyzer is constructed by using the set of sample dose performance parameters, the set of sample intensity performance parameters, and the set of sample delivery performance parameters as classification inputs and the set of sample syringe performance parameters as classification outputs. The syringe performance analyzer is used to classify the original dose performance parameters, original intensity performance parameters, and original delivery performance parameters to obtain the syringe performance parameters. Based on the deviation between the syringe performance parameters and the preset performance parameters, the preset step sizes for adjusting the original melting process parameters, the original molding process parameters, and the original cooling process parameters are adjusted respectively to obtain the melt optimization step size, the molding optimization step size, and the cooling optimization step size.

4. The intelligent manufacturing process optimization method for medical polymer materials according to claim 1, characterized in that, The original production process parameters are adjusted using the aforementioned melt optimization step size, molding optimization step size, and cooling optimization step size to obtain first production process parameters, and first uniformity distribution, first crystallization defect distribution, and first bubble probability distribution are predicted, including: Using the aforementioned melt optimization step size, molding optimization step size, and cooling optimization step size, the original melt process parameters, original molding process parameters, and original cooling process parameters within the original production process parameters are adjusted to obtain the first melt process parameters, the first molding process parameters, and the first cooling parameters, which are then used as the first production process parameters. Based on historical production data of polyethylene syringes, a set of sample production process parameters, as well as a set of sample uniformity distribution, sample crystallization defect distribution, and sample bubble probability distribution obtained from production tests were collected. Among them, each sample bubble probability distribution includes the probability of bubbles appearing at multiple locations of the syringe, and each sample uniformity distribution and sample crystallization defect distribution includes the composition uniformity parameters and the number of crystallization defects at multiple locations of the syringe. The syringe feature predictor is trained using the set of sample production process parameters as training input and the set of sample uniformity distribution, sample crystallization defect distribution, and sample bubble probability distribution as training output. Using the syringe feature predictor, production prediction is performed on the first production process parameters to obtain the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution.

5. The intelligent manufacturing process optimization method for medical polymer materials according to claim 1, characterized in that, Based on the first uniformity distribution, the first crystallization defect distribution, and the first bubble probability distribution, a first syringe twin model distribution is constructed, performance analysis is performed, and first dose performance parameters, first intensity performance parameters, and first delivery performance parameters are obtained. The fitness of the first syringe is then calculated, including: Based on the first uniformity distribution and the first crystallization defect distribution, a first basic syringe twin model is constructed; The first basic syringe twin model is supplemented by using the probability of bubbles appearing at multiple locations within the first bubble probability distribution to obtain multiple first syringe twin models and multiple production probabilities, and to obtain the distribution of first syringe twin models, wherein bubbles exist at different locations within each first syringe twin model; Based on the distribution of the first syringe twin model, performance analysis is performed to obtain the first dose performance parameter, the first intensity performance parameter, and the first delivery performance parameter, and the fitness of the first syringe is obtained by classification.

6. The intelligent manufacturing process optimization method for medical polymer materials according to claim 5, characterized in that, Based on the distribution of the first syringe twin model, performance analysis is performed to obtain the first dose performance parameter, the first intensity performance parameter, and the first delivery performance parameter, including: Based on multiple first syringe twin models within the distribution of the first syringe twin model, simulated injection tests are performed to obtain multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first delivery performance parameters. Based on multiple production probabilities within the distribution of the first syringe twin model, the multiple first dose performance parameters, multiple first intensity performance parameters, and multiple first push performance parameters are weighted and calculated to obtain the first comprehensive dose performance parameter, the first comprehensive intensity performance parameter, and the first comprehensive push performance parameter. Based on the first comprehensive dose performance parameter, the first comprehensive intensity performance parameter, and the first comprehensive delivery performance parameter, the first syringe performance parameters are classified and obtained as the first syringe fitness.

7. The intelligent manufacturing process optimization method for medical polymer materials according to claim 1, characterized in that, Continue optimizing the production process parameters until the optimization requirements are met, and output the optimal production process parameters that maximize the syringe's adaptability, including: The first production process parameters are adjusted by continuing to use the melt optimization step size, molding optimization step size and cooling optimization step size to obtain the second production process parameters; Based on the second production process parameters, a second uniformity distribution, a second crystallization defect distribution, and a second bubble probability distribution are predicted and obtained, and then processed to obtain the second syringe fitness. When the adaptability of the second syringe is greater than that of the first syringe, the second production process parameter is retained and the first production process parameter is deleted. When the fitness of the second syringe is not greater than that of the first syringe, the bubble probability discrimination rule is used to make a judgment and the first or second production process parameter is retained. Continue iterative optimization until the optimization requirements are met, and output the optimal production process parameters that maximize the adaptability of the syringe.

8. The intelligent manufacturing process optimization method for medical polymer materials according to claim 7, characterized in that, The discrimination is performed according to the bubble probability discrimination rule, including: Based on the first bubble probability distribution, the first total bubble probability is calculated, and based on the second bubble probability distribution, the second total bubble probability is calculated. Calculate the absolute value of the difference between the total probability of the second bubble and the total probability of the first bubble, and use it as a discrimination threshold. Randomly generate a random number between 0 and 1, and determine whether the random number is greater than the discrimination threshold. If it is, the second production process parameter is retained; if not, the first production process parameter is retained.

Images