A 3D simulation-driven method for precision molding of plastic packaging bottles

Abstract

This application relates to the field of plastic packaging bottle processing technology, providing a method for precise molding of plastic packaging bottles driven by three-dimensional simulation analysis. The method includes: interactive processing orders to extract basic molding information and construct a three-dimensional simulation model; fitting the precision of the production line equipment to generate a first molding influence coefficient; setting a molding tolerance bandwidth; deriving a three-dimensional simulation model based on the influence coefficient and tolerance bandwidth; processing samples according to preset parameters; acquiring simulated molding samples using multi-point images; matching the derived model to obtain a target model; generating adjustment parameters through twin analysis; and controlling the molding of the target plastic bottle. This application solves the technical problem of low control efficiency in existing technologies that adjust based solely on the three-dimensional simulation model of the finished product, ignoring the influence of the processing line's own processing capacity. It achieves improved control efficiency by comprehensively considering the processing line's processing capacity and the finished product's quality tolerance range when determining molding adjustment parameters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of plastic processing, specifically to the technical field of plastic packaging bottle processing, and particularly to a three-dimensional simulation analysis driven plastic packaging bottle precise forming method. BACKGROUND

[0002] With the rapid development of the medical industry and the increasing demand of patients for drug safety and quality, the processing and forming control technology of plastic packaging bottles for infusion plays a crucial role in the field of medical packaging. However, with the continuous expansion of the infusion product market and the increasing concern of consumers for the safety of drug packaging, the traditional plastic packaging bottle processing and forming control method has been difficult to meet the high standard requirements of modern medical industry for high efficiency, precision and safety. When dealing with packaging bottles for infusion, the traditional plastic packaging bottle processing and forming control method usually faces problems such as low control precision, slow response speed and poor stability. These problems not only affect the production efficiency of packaging bottles for infusion, but also may pose potential threats to the quality and safety of drugs. For example, insufficient control precision may lead to uneven bottle wall thickness, thereby affecting the shelf life and stability of the drug; slow response speed may make it difficult for the production process to respond to unexpected situations, increasing the production risk. SUMMARY

[0003] The present application provides a three-dimensional simulation analysis driven plastic packaging bottle precise forming method, which aims to solve the technical problem of low control efficiency caused by the fact that the existing technology only adjusts according to the three-dimensional simulation model of the finished product, ignoring the influence of the processing capacity of the production line itself.

[0004] In view of the above problems, the present application provides a three-dimensional simulation analysis driven plastic packaging bottle precise forming method.

[0005] The application provides a three-dimensional simulation analysis driven plastic packaging bottle precise forming method, the method comprises the following steps: interacting a target processing order, extracting basic forming information of a target plastic packaging bottle, and constructing a three-dimensional simulation model of the target plastic packaging bottle according to the basic forming information; fitting the production line processing precision according to the control precision of a plurality of processing equipment of a target processing forming production line, generating a first forming influence coefficient; configuring a forming tolerance bandwidth of the target plastic packaging bottle, wherein the forming tolerance bandwidth is set according to a forming index qualified parameter interval in the basic forming information; deriving and expanding the three-dimensional simulation model based on the first forming influence coefficient and the forming tolerance bandwidth, obtaining a three-dimensional derived simulation model set; processing a sample of the target plastic packaging bottle according to a preset forming control parameter, generating a plurality of forming samples; using a multi-point image acquisition device to perform three-dimensional point cloud simulation on the plurality of forming samples, generating a plurality of forming sample simulation models; using the plurality of forming sample simulation models to perform similarity matching on the three-dimensional derived simulation model set, taking the three-dimensional derived simulation model with the highest matching degree as a target three-dimensional simulation model; performing twin analysis based on the plurality of forming sample simulation models and the target three-dimensional simulation model, generating an adjusted forming control parameter according to the analysis result, and using the adjusted forming control parameter to control the processing and forming of the target plastic packaging bottle.

[0006] One or more technical solutions provided in the application have at least the following technical effects or advantages:

[0007] The above-mentioned three-dimensional simulation analysis driven plastic packaging bottle precise forming method receives and analyzes the target processing order, extracts the basic forming information of the plastic packaging bottle, and constructs a three-dimensional simulation model accordingly. This model provides intuitive and accurate reference for the subsequent production process. Then, according to the control accuracy of each processing equipment on the production line, the processing capacity of the whole production line is simulated and evaluated, and a first forming influence coefficient is generated. This coefficient reflects the potential capacity and limitation of the production line in processing the plastic packaging bottle. Then, a forming tolerance bandwidth is configured for the target plastic packaging bottle. This bandwidth is set based on the qualified parameter interval in the basic forming information, ensuring that the product still meets the quality requirements even in slight deviation. With the first forming influence coefficient and the forming tolerance bandwidth, the initial three-dimensional simulation model is derived and expanded to generate a set of three-dimensional derivative simulation models containing multiple possibilities. These models represent the possible product forms under different conditions. Then, according to the preset forming control parameters, the actual sample is processed, and a multi-point image acquisition device is used to simulate the three-dimensional point cloud of the sample, generating multiple forming sample simulation models. These simulation models are highly consistent with the actual sample, providing accurate data for subsequent matching and analysis. Then, the simulation model of the actual sample is matched with the set of three-dimensional derivative simulation models, and the model with the highest matching degree is selected as the target three-dimensional simulation model. This model best represents the product form that can be obtained under actual production conditions. Finally, the multiple forming sample simulation models and the target three-dimensional simulation model are analyzed to reveal the deviation and potential problems in the actual production process, and the adjusted forming control parameters are generated accordingly. These adjusted parameters will be used to guide the subsequent production process, ensuring that the plastic packaging bottle is processed more precisely, efficiently and safely.

[0008] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the content of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0010] Figure 1 A flowchart of a three-dimensional simulation analysis driven plastic packaging bottle precise forming method in an embodiment.

[0011] Figure 2A flowchart of a process for generating a first forming influence coefficient of a three-dimensional simulation analysis driven plastic packaging bottle precision forming method in an embodiment. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a three-dimensional simulation analysis driven plastic packaging bottle precision forming method, which solves the technical problem of low control efficiency caused by adjusting only according to a three-dimensional simulation model of a finished product and ignoring the influence of the processing capacity of a processing line in the prior art.

[0013] The technical solutions in the embodiments of the present application will be clearly and completely described in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0014] 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 including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0015] An embodiment, as shown in the accompanying drawings, the present application provides a three-dimensional simulation analysis driven plastic packaging bottle precision forming method, the method comprises: Figure 1

[0016] The interactive target processing order extracts the basic forming information of the target plastic packaging bottle, and constructs a three-dimensional simulation model of the target plastic packaging bottle according to the basic forming information.

[0017] In the current plastic packaging bottle processing industry for infusion, with the continuous growth of demand for pharmaceuticals, higher requirements for manufacturing precision and quality control of packaging bottles for infusion are put forward. However, the traditional processing method often relies on the adjustment of the three-dimensional simulation model of the finished product. Although this method can ensure the appearance and quality of the product to a certain extent, it ignores the influence of the processing capacity of the processing line itself. This practice often leads to low control efficiency in the production process, which is difficult to meet the demand of the medical industry for high-precision and high-quality pharmaceutical packaging.

[0018] ​In the embodiments of the present application, the system terminal interacts with the transaction platform to obtain a target processing order, which contains information such as the specifications and quantity of plastic packaging bottles for infusion that need to be processed. This plastic packaging bottle for infusion is the target plastic packaging bottle. Subsequently, the system terminal extracts the specifications of the target plastic packaging bottle, i.e. the basic forming information, from the target processing order, which includes key parameters such as size, shape, and material requirements. Once these basic forming information is obtained, the system terminal activates the three-dimensional modeling component, and inside the three-dimensional modeling component, the system terminal uses a similar basic geometric body as a starting point to begin constructing a basic model of the target plastic packaging bottle according to the extracted basic forming information. Then, according to the size information of the bottle, the size parameters of the basic model are adjusted to match the actual size of the target plastic packaging bottle. Based on the basic model, the system terminal adds the detailed features of the bottle, such as the mouth, bottom, label area, etc. These detailed features are based on actual needs and design requirements. After that, the basic model with detailed features is polished, such as adjusting the surface smoothness, adding texture, etc., to improve the realism of the basic model. Then, according to the material requirements in the basic forming information, the corresponding material properties of the basic model are set, such as plastic type, color, transparency, etc. These properties will affect the rendering effect of the basic model and the appearance of the final product. When the material properties are set, the system terminal constructs a three-dimensional simulation model of the target plastic packaging bottle. This three-dimensional simulation model can help the system terminal understand the final form of the product and possible problems more intuitively. In this way, a series of verification and optimization can be carried out before formal production, to ensure that the final produced target plastic packaging bottle can meet the requirements and standards of the target processing order.

[0019] According to the control accuracy of the plurality of processing equipment of the target processing forming production line, the production line processing precision fitting is performed to generate a first forming influence coefficient.

[0020] In one embodiment, on a target machining forming production line, each machining device has its specific control accuracy, which directly determines the machining accuracy they can achieve in the production process. In order to evaluate the machining accuracy of the entire production line, the system terminal performs production line machining accuracy fitting. The core of this fitting process is to comprehensively consider the control accuracy of each device and analyze how they jointly affect the forming quality of the final product. Specifically, the system terminal first acquires a plurality of machining record data sets of a plurality of machining devices in the target machining forming production line, and then constructs a plurality of machining box plots of the plurality of machining devices based on these sets. Subsequently, discrete analysis is performed on the plurality of machining box plots to obtain a plurality of control accuracies of the plurality of machining devices. These accuracy data include the positioning accuracy, cutting accuracy, forming error, etc. of the device. Then, the system terminal sets a corresponding weight for the control accuracy data of each device according to the importance of each device on the production line and the degree of influence on the forming quality of the final product. The weight is determined according to historical experience, expert advice and historical data. The system terminal will give a higher weight to the device that has a greater impact on the final product quality. Then, the control accuracy data of each device is multiplied by the corresponding weight, and the results are added to obtain a weighted sum. This weighted sum is the first forming influence coefficient, which represents the machining accuracy level of the entire production line, can help production managers understand the performance of the production line, find potential problems, and provide a basis for subsequent optimization and improvement.

[0021] Further, as shown in Figure 2 The present application provides a method for performing production line machining accuracy fitting according to the control accuracy of a plurality of machining devices of a target machining forming production line, generating a first forming influence coefficient, the method further comprising:

[0022] Acquiring a plurality of machining record data sets of a plurality of machining devices in the target machining forming production line; retrieving the plurality of machining record data sets with machining deviation values as indexes to generate a plurality of machining deviation value sets.

[0023] Preferably, when evaluating the machining accuracy of the target machining forming production line, the system terminal first acquires the machining record data sets of the plurality of machining devices in the production line. These data sets contain the machining result information of the devices under different times and different conditions. Subsequently, the machining record data sets are retrieved with machining deviation values as the key indexes. The machining deviation value is set based on the actual production requirements, describes the difference between the actual machining result and the expected result, and reflects the machining accuracy and stability of the device. By indexing retrieval with machining deviation values, the system terminal can extract the data subset related to a specific deviation value from the massive machining record data to form a plurality of machining deviation value sets. The data in these sets will help the system terminal to more clearly understand the machining performance of the device within a specific deviation range, and further analyze the control accuracy of the production line.

[0024] constructing a plurality of processing box plots of the plurality of processing devices based on the plurality of sets of processing deviation values; and performing dispersion analysis on the plurality of processing box plots to obtain a plurality of control precisions of the plurality of processing devices.

[0025] Preferably, when evaluating the control precision of the plurality of processing devices, the system terminal constructs a processing box plot of each device based on the collected plurality of sets of processing deviation values. The box plot is a commonly used statistical graph for displaying the dispersion of a set of data, especially the distribution range, median, and outliers of the data. For each processing device, the system terminal processes its corresponding set of processing deviation values according to the construction rules of the box plot, and draws a box plot containing the minimum value, the first quartile (Q1), the median (Q2), the third quartile (Q3), and the maximum value. This box plot intuitively shows the distribution of the processing results of the device, especially the dispersion degree and possible outliers of the data. Subsequently, dispersion analysis is performed on the constructed plurality of processing box plots. Dispersion analysis mainly focuses on the dispersion degree and distribution characteristics of the data, including the range and interquartile range (IQR) of the data. The interquartile range reflects the dispersion degree of the data set, especially the dispersion degree of the middle 50% of the data in the data set. The interquartile range measures the distance between the first quartile and the third quartile, i.e., the third quartile minus the first quartile. By analyzing these statistical quantities, the control precision of each processing device can be evaluated. If the box of the box plot is narrow, it indicates that the processing results of the device are concentrated. In this case, the system terminal calculates the mean of each set of processing deviation values and performs a ratio operation with the sum of the deviation values of each set of processing deviation values to obtain a plurality of processing control precisions. Conversely, if the box is wide, it indicates that the processing results of the device are dispersed. In this case, the system terminal extracts a plurality of deviation values between the first quartile and the third quartile, and performs control precision analysis on these deviation values to generate a plurality of processing control precisions. Through this method, the system terminal can construct a processing box plot based on the set of processing deviation values and obtain the control precision evaluation results of the plurality of processing devices through dispersion analysis. This provides an important basis for subsequent process adjustment.

[0026] Further, the present application provides that when the plurality of interquartile ranges is less than or equal to a preset interquartile range threshold, the method comprises:

[0027] extracting a plurality of interquartile ranges of the plurality of processing box plots and performing dispersion verification on the plurality of interquartile ranges; when the plurality of interquartile ranges is less than or equal to a preset interquartile range threshold, performing mean calculation on the plurality of sets of processing deviation values, and performing a ratio operation on the calculation results and the sum of the deviation values of the plurality of sets of processing deviation values to obtain a plurality of processing control precisions.

[0028] Optionally, when evaluating the control precision of multiple machining processes, the system terminal extracts the interquartile ranges of the machining box plots. Subsequently, the interquartile ranges are subjected to dispersion verification, i.e., checking whether they meet a preset interquartile range threshold. The purpose of dispersion verification is to determine whether the data is sufficiently concentrated to meet the expected machining control requirements. The preset interquartile range threshold is set according to historical data and industry standards. When the multiple interquartile ranges are less than or equal to the preset threshold, it indicates that the data sets representing the machining processes are relatively concentrated, and the machining control is relatively stable. Subsequently, the system terminal calculates the mean values of the multiple sets of machining deviation values, and then divides each mean value by the sum of the deviation values of the corresponding set of machining deviation values to obtain the multiple machining control precision metrics. This step aims to evaluate the stability and accuracy of the machining processes by comparing the relative sizes of the mean values and the sum of the deviations. In this way, the control precision of different machining processes can be quantified, providing important reference for production management and quality control.

[0029] Further, the present application provides that when the multiple interquartile ranges are greater than the preset interquartile range threshold, the method further comprises:

[0030] When the multiple interquartile ranges are greater than the preset interquartile range threshold, the multiple filtered machining deviation values located between the first quartile and the third quartile in the multiple machining box plots are extracted and added to the multiple target machining deviation value sets; control precision analysis is performed based on the multiple target machining deviation value sets to generate multiple machining control precisions.

[0031] Optionally, when the extracted interquartile ranges of the multiple machining box plots are greater than the preset interquartile range threshold, it indicates that there is a large dispersion in the data, which may be caused by noise or outliers. In order to more accurately evaluate the control precision of the machining processes, it is necessary to eliminate these noises. Specifically, the system terminal extracts the multiple machining deviation values located between the first quartile and the third quartile from each machining box plot as the multiple filtered machining deviation values. These filtered values are considered to be relatively concentrated and less affected by noise, and therefore are added to the multiple target machining deviation value sets. Subsequently, control precision analysis is performed based on these target machining deviation value sets. The system terminal randomly selects a target machining deviation value set from the multiple target machining deviation value sets, and then sorts the target machining deviation value set in ascending order. Subsequently, the median is extracted from the ascending sequence, the absolute deviations of each deviation value from the median are calculated, and the median of these deviations is taken to obtain the machining control precision of the target machining deviation value set. Then, the system terminal repeats the above process to perform control precision analysis on the remaining target machining deviation value sets, thereby obtaining multiple machining control precisions.

[0032] The forming tolerance bandwidth of the target plastic packaging bottle is configured, wherein the forming tolerance bandwidth is set according to the forming index qualified parameter interval in the basic forming information.

[0033] In one embodiment, in order to obtain more accurate forming control parameters, the system terminal sets the forming tolerance bandwidth of the plastic packaging bottle, which is a range of process parameter fluctuations allowed in the manufacturing process to ensure product quality, and is a qualified parameter interval set based on the forming indexes of the target plastic packaging bottle, such as size, weight, strength, etc.

[0034] The three-dimensional simulation model set is obtained by deriving and expanding the three-dimensional simulation model based on the first forming influence coefficient and the forming tolerance bandwidth.

[0035] In one embodiment, the system terminal uses the obtained first forming influence coefficient and forming tolerance bandwidth to derive and expand the initially constructed three-dimensional simulation model. The derivation and expansion process is a series of adjustments and optimizations of the original three-dimensional simulation model to simulate the packaging bottle structure under different forming conditions. The adjustment and optimization process is iterated until a preset iteration number is met. Through this derivation and expansion method, the system terminal can obtain a three-dimensional simulation model set containing multiple three-dimensional simulation models. Each model in the set represents the packaging bottle structure under a specific forming condition and meets the set forming tolerance bandwidth.

[0036] Further, the application provides a method for obtaining the three-dimensional simulation model set, which further comprises:

[0037] The basic forming indexes are adjusted multiple times according to a preset adjustment mode to obtain multiple initial adjustment forming indexes, wherein the preset adjustment mode is to increase or decrease different basic forming indexes according to a preset adjustment step; and the multiple initial adjustment forming indexes are constrained by the forming tolerance bandwidth to obtain multiple adjustment forming indexes.

[0038] Preferably, in order to ensure that the manufactured target plastic packaging bottle can meet the requirements and conditions, the system terminal will adjust the basic molding indicators. This adjustment is made in accordance with the preset adjustment method, specifically, the system terminal increases or decreases different basic molding indicators according to the preset adjustment step. In this way, a plurality of initial adjustment molding indicators can be obtained, which represent potential parameter combinations under different molding conditions. For example, the preset adjustment step of the density is set to 0.1 g / cm³, and the system terminal increases or decreases the density in the basic molding indicators by this preset adjustment step each time to obtain the initial adjustment densities in the plurality of initial adjustment molding indicators, which correspond to the lightweight, durable, etc. of the target plastic packaging bottle. Subsequently, the system terminal uses the molding tolerance bandwidth to constrain the initial adjustment molding indicators, ensuring that these adjusted indicators are still within the acceptable range. During the constraint process, the system terminal checks each initial adjustment molding indicator to determine whether it is outside the range of the molding tolerance bandwidth. If a certain indicator is outside this range, the system terminal will eliminate this indicator, so that the system terminal can obtain a plurality of adjustment molding indicators that fully meet the requirements of the molding tolerance bandwidth. These adjustment molding indicators will serve as an important reference for generating the adjusted three-dimensional simulation model subsequently.

[0039] Based on the first molding influence coefficient and the plurality of adjustment molding indicators, a three-dimensional simulation is performed to generate a set of adjusted three-dimensional simulation models; the historical processing data set of the target processing molding production line is called to evaluate the frequency of the set of adjusted three-dimensional simulation models, and the set of adjusted three-dimensional simulation models is iteratively updated according to the evaluation results until a preset iteration number is met, and a set of three-dimensional derivative simulation models is obtained.

[0040] Preferably, in order to optimize the target plastic packaging bottle, the system terminal uses the first molding influence coefficient and a plurality of adjustment molding indexes to adjust the three-dimensional simulation model. First, in the three-dimensional simulation component, the system terminal adjusts the three-dimensional simulation model according to the influence of the first molding influence coefficient on the shape and performance of the target plastic packaging bottle, that is, to avoid the problems such as concave and convex caused by insufficient control accuracy, the three-dimensional simulation model is adjusted in the opposite direction in advance, which can offset a part of the problems caused by insufficient control accuracy. Subsequently, the three-dimensional simulation model is finely adjusted using a plurality of adjustment molding indexes. These adjustments are made by changing the parameters of the model to simulate the product shape under different molding conditions. After adjustment, the system terminal obtains a set of adjusted three-dimensional simulation models, each model in the set corresponds to an adjustment molding index. Then, the system terminal calls the historical processing data set of the target processing molding production line to evaluate the set of adjusted three-dimensional simulation models, obtains a plurality of adjustment frequency factors, and clusters a part of the larger adjustment frequency factors based on the adjustment frequency factors, to obtain a plurality of follow-up stage adjustment clusters. Larger is selected because the higher the frequency, the more representative the average level of processing. Then, adjust the adjustment clusters according to the preset adjustment mode, and update iteratively according to the adjustment result until the preset iteration number is satisfied, to obtain a set of three-dimensional derivative simulation models. These models not only consider various influencing factors in the molding process, but also are finely adjusted and optimized, providing an important reference for subsequent production.

[0041] Further, the present application provides a basic molding index, and the method further comprises:

[0042] The basic molding index includes appearance quality, tensile strength, sealing performance, and density.

[0043] Optionally, the basic molding indicators are the key factors to ensure the quality and performance of the product. These indicators include appearance quality, tensile strength, sealing performance, and density, etc. Among them, the appearance quality refers to the visual performance of the target plastic packaging bottle, including the transparency of the bottle, whether the surface is smooth, whether there are bubbles, impurities, scratches, etc. Good appearance quality not only concerns the aesthetics of the product, but more importantly, it can ensure that the state of the liquid in the bottle can be clearly seen during use, which is crucial to ensure the accuracy and safety of the injection of liquid medicine. Tensile strength refers to the ability of the target plastic packaging bottle to resist damage when subjected to tensile force. This involves various pressures that the packaging bottle may be subjected to during transportation, storage, and injection. Packaging bottles with high tensile strength can ensure that they will not break or deform during normal use, thereby preventing the leakage or contamination of the liquid medicine. Sealing performance refers to the ability of the target plastic packaging bottle to prevent external substances from entering when closed. Good sealing performance is crucial to ensure that the liquid medicine remains sterile and pure during storage and transportation. Density is an important physical parameter of the target plastic packaging bottle, reflecting the tightness and weight of the material. Proper density can ensure that the packaging bottle has sufficient strength and durability, while remaining lightweight and easy to operate.

[0044] Further, the present application provides a frequency evaluation method, which further comprises:

[0045] The historical processing data set of the target processing molding production line is called to perform frequency evaluation on the adjusted three-dimensional simulation model set, to obtain multiple adjustment frequency factors; the multiple adjustment frequency factors are sorted in descending order, and the M adjustment frequency factors corresponding to the M adjustment molding indicators located in the first m positions are taken as the M adjustment directions.

[0046] Optionally, in order to determine which adjustment directions are most important and frequent, the system terminal uses the historical processing data set to evaluate the frequency of the adjustment three-dimensional simulation model set. The core of this process is to analyze the frequency of different three-dimensional simulation models in historical processing. Higher frequency represents that these models or the forming indicators they represent are more common in actual production, and thus are more likely to represent the average level of processing or key adjustment points. Subsequently, the frequency of each model in the adjustment three-dimensional simulation model set is counted in the historical processing data set, generating a plurality of adjustment frequency factors, which are the frequencies of the corresponding models. Then, these adjustment frequency factors are sorted in descending order, so that the most frequently occurring models will be ranked first. Then, the top m positions in the sorting are selected M adjustment frequency factors, and the M adjustment forming indicators corresponding to these factors are considered as the top M adjustment directions. Wherein, m is set based on historical experience, and M has the same value as m. These adjustment directions represent the aspects that need to be paid most attention to in the production process, because they have the highest frequency in actual processing and have the greatest impact on overall processing efficiency and product quality.

[0047] The remaining plurality of adjustment forming indicators are clustered with the M adjustment forming indicators as clustering centers to generate M following adjustment clusters; and the M following adjustment clusters are adjusted based on the M adjustment directions according to the preset adjustment mode to obtain M following stage adjustment clusters.

[0048] Optionally, after determining the M adjustment forming indicators of the target processing forming production line, the system terminal uses these adjustment forming indicators as clustering centers, and then uses the Euclidean distance to calculate the distance between each remaining adjustment forming indicator and the M clustering centers. Subsequently, each remaining adjustment forming indicator is assigned to the cluster where the clustering center with the smallest distance is located, forming M following adjustment clusters. Then, based on the determined M adjustment directions, the adjustment forming indicators in each following adjustment cluster are adjusted. Here, the adjustment is based on the preset adjustment mode, that is, the adjustment forming indicators are added or subtracted according to the adjustment direction and the preset adjustment step. In this way, each following adjustment cluster will be improved according to the corresponding adjustment direction, thereby forming M following stage adjustment clusters.

[0049] Further, the application provides a method for obtaining a three-dimensional derivative simulation model set, which further comprises:

[0050] The M follow-up stage adjustment clusters are used to iteratively update the M adjustment directions, to generate M updated adjustment directions and M updated follow-up adjustment clusters; and the M updated follow-up adjustment clusters are adjusted according to the M updated adjustment directions and the preset adjustment mode, and iteratively updated according to the adjustment results until a preset iteration number is met, to obtain M target adjustment directions; and M target adjustment three-dimensional simulation models corresponding to the M target adjustment directions are taken as the set of three-dimensional derivative simulation models.

[0051] Optionally, the system terminal first associates the stage adjustment forming indicators in each follow-up stage adjustment cluster with the corresponding adjustment directions. For each follow-up stage adjustment cluster, the Euclidean distance is used to calculate the distances between the stage adjustment forming indicators in the cluster and the cluster center. At the same time, the differences between different clusters are calculated to ensure that the updated adjustment directions can distinguish different clusters. Subsequently, the corresponding adjustment directions are fine-tuned according to the distribution and characteristics of the stage adjustment forming indicators in the cluster. This involves moving, scaling, etc. of the adjustment directions. The purpose of fine-tuning is to enable the updated adjustment directions to better represent the main trends and characteristics of the stage adjustment forming indicators in the cluster. Based on the updated adjustment directions, the stage adjustment forming indicators are re-clustered to generate new M follow-up adjustment clusters. This clustering process is similar to the foregoing, except that the updated adjustment directions are used as new cluster centers. Then, the system terminal uses the same adjustment method as before to adjust the M updated follow-up adjustment clusters according to the updated adjustment directions and the preset adjustment mode. Then, the clustering and adjustment processes described above are repeated until a preset iteration number is reached. When the preset iteration number is reached, the system terminal outputs the current M updated adjustment directions to obtain M target adjustment directions. These target adjustment directions are based on a large amount of historical data and multiple iterations of optimization, and therefore they have high credibility and guiding value. Finally, the adjustment three-dimensional simulation models corresponding to the M target adjustment directions are taken as the set of three-dimensional derivative simulation models. These sets of three-dimensional derivative simulation models can intuitively show the impact and effect of each target adjustment direction on the production line, and provide intuitive references and bases for optimization of the target plastic packaging bottle production.

[0052] The sample processing of the target plastic packaging bottle is performed according to the preset forming control parameters, to generate a plurality of forming samples; and the multi-point image acquisition device is used to perform three-dimensional point cloud simulation on the plurality of forming samples, to generate a plurality of forming sample simulation models.

[0053] In one embodiment, during the production of plastic packaging bottles, in order to verify and optimize the molding effect of the product, the system terminal manufactures samples of target plastic packaging bottles according to preset molding control parameters to generate a plurality of molding samples. Once the molding samples are manufactured, the system terminal collects three-dimensional point cloud data of the molding samples using a multi-point image acquisition device to simulate a plurality of molding sample simulation models. The molding sample simulation models correspond one-to-one to the molding samples.

[0054] The plurality of molding sample simulation models are used to perform similarity matching on the set of three-dimensional derivative simulation models, and the three-dimensional derivative simulation model with the highest matching degree is selected as the target three-dimensional simulation model.

[0055] In one embodiment, the system terminal randomly selects one molding sample simulation model from the plurality of molding sample simulation models, and then performs iterative nearest point matching between the molding sample simulation model and each model in the set of three-dimensional derivative simulation models. In each iteration, the iterative nearest point algorithm finds the nearest point pair between the two point clouds and calculates a rigid transformation to align the points. The iteration process continues until the maximum number of iterations is reached. At the end of each iteration, the system terminal calculates the root mean square error between the aligned point clouds and takes this error as a similarity score. Repeat the above process for the remaining molding sample simulation models to obtain a plurality of similarity scores for each molding sample simulation model. Then, the three-dimensional derivative simulation models are sorted according to the similarity scores. The lower the score, the higher the matching degree. Then, the three-dimensional derivative simulation model with the lowest similarity score is selected as the target three-dimensional simulation model. This model represents the most similar adjustment parameters to the actual molding sample.

[0056] Based on the plurality of molding sample simulation models and the target three-dimensional simulation model, perform twin analysis to generate adjusted molding control parameters based on the analysis results, and use the adjusted molding control parameters for the processing and molding control of the target plastic packaging bottle.

[0057] In one embodiment, after obtaining the target 3D simulation model, the system terminal performs a twin analysis on multiple molded sample simulation models based on this target 3D simulation model. During this twin analysis, the system terminal extracts the similarity scores between the target 3D simulation model and the corresponding 3D derived simulation model and these molded sample simulation models. These similarity scores represent the errors between the target 3D simulation model and the multiple molded sample simulation models. Subsequently, the system terminal calculates the average difference of these errors. Then, the system terminal inputs this average difference and preset molding control parameters into a pre-constructed difference control network. Based on learned knowledge, the difference control network generates adjusted molding control parameters. Finally, the system terminal uses the adjusted molding control parameters to control the processing and molding of the target plastic packaging bottle. By applying these adjusted molding control parameters in actual production, plastic packaging bottles that more closely resemble the target 3D simulation model can be obtained.

[0058] For the differential control network, the system terminal first acquires a large number of sample differential averages, preset sample shaping control parameters, and sample adjusted shaping control parameters. These sample data are then divided into training and testing sets. Subsequently, based on the complexity of the problem and the characteristics of the data, a neural network structure is constructed, including the number of neurons in the input, hidden, and output layers. Next, the weights and biases of the neural network are initialized using random numbers, and the initialized neural network is trained using the training set. After each iteration, the system terminal uses the mean squared error loss function to calculate the error between the predicted adjusted shaping control parameters and the sample adjusted shaping control parameters. Then, based on the calculated error, the Adam optimizer is used to update the weights of the neural network. This process is repeated until the maximum number of iterations is met. When the maximum number of iterations is met, the system terminal evaluates the trained neural network using the testing set and calculates the accuracy of the neural network. If the accuracy is higher than expected, the current neural network is output, generating the differential control network. Otherwise, the neural network is optimized by increasing its depth, modifying its structure, etc., and retrained until the expected accuracy is met.

[0059] In summary, the embodiments of this application have at least the following technical effects:

[0060] This application's embodiments interactively acquire target processing orders and extract basic molding information of target plastic packaging bottles, then construct a three-dimensional simulation model based on this information. Subsequently, the control precision of processing equipment in the production line is analyzed, a first molding influence coefficient is generated through data fitting, and a molding tolerance bandwidth is set based on the qualified parameter range of the basic molding information. Then, these parameters are used to derive and expand the three-dimensional simulation model, resulting in a set of derived three-dimensional simulation models. To verify and adjust these simulation models, samples are processed according to preset molding control parameters, and a multi-point image acquisition device is used to perform three-dimensional point cloud simulation, generating a molded sample simulation model. By performing similarity matching between these simulation models and the set of derived simulation models, the three-dimensional simulation model that best matches the target is found. After obtaining the target three-dimensional simulation model, twin analysis is performed using multiple molded sample simulation models to identify the control parameters that need adjustment. Simultaneously, combined with historical processing data from the production line, the molding indicators are iteratively updated and optimized until a preset number of iterations is met. These technologies collectively solve the problem of low control efficiency caused by existing technologies that adjust based solely on the three-dimensional simulation model of the finished product during processing, ignoring the influence of the processing line's own processing capacity. They achieve the effect of comprehensively considering the processing line's processing capacity and the tolerance range of the finished product's quality to determine the molding adjustment parameters, thereby improving control efficiency.

[0061] 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.

[0062] 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.

[0063] 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 precision molding method of a plastic packaging bottle driven by three-dimensional simulation analysis, characterized by, The method comprises: interacting with the target processing order, extracting the basic forming information of the target plastic packaging bottle, and constructing a three-dimensional simulation model of the target plastic packaging bottle according to the basic forming information; According to the control accuracy of the plurality of processing equipment of the target processing forming production line, the production line processing precision fitting is carried out, and the first forming influence coefficient is generated; Configure the forming tolerance bandwidth of the target plastic packaging bottle, wherein the forming tolerance bandwidth is set according to the forming index qualified parameter interval in the basic forming information; Based on the first forming influence coefficient and the forming tolerance bandwidth, the three-dimensional simulation model is derived and expanded to obtain a three-dimensional derived simulation model set; According to the preset forming control parameter, the sample processing of the target plastic packaging bottle is carried out, and a plurality of forming samples are generated; Use a multi-point image acquisition device to simulate a three-dimensional point cloud of the plurality of forming samples, and generate a plurality of forming sample simulation models; Using the plurality of forming sample simulation models, the three-dimensional derived simulation model set is matched, and the three-dimensional derived simulation model with the highest matching degree is taken as the target three-dimensional simulation model; Based on the plurality of forming sample simulation models and the target three-dimensional simulation model, twin analysis is carried out, and the adjustment forming control parameter is generated according to the analysis result, and the target plastic packaging bottle is processed and formed by using the adjustment forming control parameter; The method comprises: Adjust the basic forming index according to the preset adjustment mode for multiple times to obtain a plurality of initial adjustment forming indexes, wherein the preset adjustment mode is to increase or decrease the different basic forming indexes according to the preset adjustment step; Constrain the plurality of initial adjustment forming indexes by using the forming tolerance bandwidth to obtain a plurality of adjustment forming indexes; Based on the first forming influence coefficient and the plurality of adjustment forming indexes, a three-dimensional simulation model set is generated, specifically, first, in the three-dimensional simulation component, according to the influence of the first forming influence coefficient on the shape and performance of the target plastic packaging bottle, the three-dimensional simulation model is adjusted accordingly, and the three-dimensional simulation model is adjusted in the opposite direction in advance, then, the three-dimensional simulation model is finely adjusted using the plurality of adjustment forming indexes; Call the historical processing data set of the target processing forming production line to evaluate the adjustment three-dimensional simulation model set, and update the adjustment three-dimensional simulation model set according to the evaluation result until the preset iteration number is satisfied, and obtain the three-dimensional derived simulation model set; The method comprises: Call the historical processing data set of the target processing forming production line to evaluate the adjustment three-dimensional simulation model set, and obtain a plurality of adjustment frequency factors; Sort the plurality of adjustment frequency factors in descending order, and take the M adjustment forming indexes corresponding to the M adjustment frequency factors located in the first m positions as the M adjustment directions; Take the M adjustment forming indexes as the clustering center, and cluster the remaining plurality of adjustment forming indexes to generate M following adjustment clusters; Adjust the M follow-up adjustment clusters according to the preset adjustment mode based on the M adjustment directions, to obtain M follow-up stage adjustment clusters; The method comprises: Iteratively update the M adjustment directions using the M follow-up stage adjustment clusters, to generate M updated adjustment directions and M updated follow-up adjustment clusters; Adjust the M updated follow-up adjustment clusters according to the preset adjustment mode based on the M updated adjustment directions, and iteratively update the adjustment results until a preset iteration number is met, to obtain M target adjustment directions; Take the M target adjustment three-dimensional simulation models corresponding to the M target adjustment directions as the three-dimensional derivative simulation model set.

2. The three-dimensional simulation analysis driven precision molding method of plastic packaging bottles according to claim 1, wherein, According to the control accuracy of the plurality of processing equipment of the target processing forming production line, the processing precision of the production line is fitted, and a first forming influence coefficient is generated. The method comprises: Obtain a plurality of processing record data sets of a plurality of processing equipment in the target processing forming production line; Retrieving the plurality of processing record data sets with the processing deviation value as the index, to generate a plurality of processing deviation value sets; Based on the plurality of processing deviation value sets, a plurality of processing box plots of the plurality of processing equipment are constructed; Discrete analysis is performed on the plurality of processing box plots to obtain a plurality of control accuracies of the plurality of processing equipment.

3. The three-dimensional simulation analysis driven precision molding method of plastic packaging bottles according to claim 2, wherein, The method comprises: Extracting the plurality of quartile ranges of the plurality of processing box plots, and performing discrete verification on the plurality of quartile ranges; When the plurality of quartile ranges are less than or equal to a preset quartile range threshold, the mean value of the plurality of processing deviation value sets is calculated, and the calculation result is compared with the sum of the deviation values of the plurality of processing deviation value sets, to obtain a plurality of processing control accuracies.

4. The three-dimensional simulation analysis driven precision molding method of plastic packaging bottles according to claim 3, wherein, The method comprises: When the plurality of quartile ranges are greater than the preset quartile range threshold, a plurality of filtered processing deviation values between the first quartile and the third quartile in the plurality of processing box plots are extracted and added to a plurality of target processing deviation value sets; Based on the plurality of target processing deviation value sets, control accuracy analysis is performed to generate a plurality of processing control accuracies.

5. The three-dimensional simulation analysis driven precision molding method of plastic packaging bottles according to claim 1, wherein, The basic forming indicators include appearance quality, tensile strength, sealing performance, and density.

Images