Intelligent optimization method for plastic bucket blow molding process parameters based on digital twinning

Abstract

The application relates to the technical field of plastic hollow blow molding, in particular to a plastic bucket blow molding process parameter intelligent optimization method based on digital twinning. The method comprises the following steps: acquiring mold cavity geometric data, material parameters and a target wall thickness distribution; constructing a blow molding digital twinning model, establishing an internal correlation mapping between process parameters and the wall thickness distribution; taking the mapping as a forward model, and according to the target wall thickness distribution, the blow molding process parameters are inversely optimized; judging whether the model output wall thickness distribution meets the target wall thickness distribution; when the condition is met, the optimized process parameters are determined as to-be-executed process parameters and are issued to a blow molding device. The application realizes the feedforward inversion optimization of the target wall thickness, avoids repeated mold testing, and improves the wall thickness uniformity and production efficiency.

Description

Technical Field

[0001] This application relates to the field of plastic hollow blow molding technology, and in particular to an intelligent optimization method for plastic bucket blow molding process parameters based on digital twins. Background Technology

[0002] Blow molding is a primary method for producing hollow plastic products, offering advantages such as low production cost and good molding performance. Products like plastic buckets have specific requirements for structural strength and pressure resistance, and wall thickness uniformity has always been a crucial indicator of product quality. However, blow-molded products commonly suffer from uneven wall thickness, particularly prominent in large, complex-shaped products.

[0003] The main reasons for this problem are: the difference in the blow-up ratio of different cross sections of the part causes inconsistent deformation of the parison; the parison is axially thinned due to gravity after extrusion; and there are many process parameters such as blow-up time, mold temperature, and parison wall thickness that are coupled with each other, making wall thickness control extremely difficult.

[0004] To address this issue, various improvement methods have been developed, including axial wall thickness control, the preform temperature difference method, and numerical simulation, which have improved wall thickness uniformity to some extent. However, most of these methods are based on operational experience or simplified physical models, failing to systematically reveal the intrinsic relationship between multiple process parameters and wall thickness distribution. Therefore, establishing this intrinsic relationship and efficiently optimizing process parameters accordingly is a technical problem that needs to be solved.

[0005] In view of the above, this application is hereby submitted. Summary of the Invention

[0006] The purpose of this application is to propose an intelligent optimization method for plastic bucket blow molding process parameters based on digital twins, which aims to establish an inherent correlation and optimize process parameters efficiently accordingly.

[0007] To address the aforementioned technical problems, this application provides a method for intelligent optimization of process parameters in plastic bucket blow molding based on digital twins, employing the following technical solution: Obtain the geometric data of the blow molding mold cavity for the plastic bucket, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket; Based on cavity geometry data, as well as blow molding material parameters and blow molding process parameters, a digital twin model of the blow molding process of plastic buckets is constructed, and an intrinsic correlation mapping between blow molding process parameters and plastic bucket wall thickness distribution is established in the digital twin model. Using the intrinsic correlation mapping as the forward model, and based on the target wall thickness distribution, the optimized blow molding process parameters that make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution are obtained by inversion. Determine whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution; When the conditions are met, the optimized blow molding process parameters are determined as the process parameters to be executed, and the process parameters to be executed are sent to the blow molding equipment.

[0008] Furthermore, an intrinsic mapping between blow molding process parameters and plastic barrel wall thickness distribution is established in the digital twin model, including: Obtain the initial outer radius of the preform, and based on the cavity geometry data, obtain the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle; The ratio of the cavity development radius to the initial outer radius of the preform is determined as the local inflation ratio; Based on the parameters of the blow molding material and the blow molding process, calculate the axial wall thickness reduction of the preform under gravity. The wall thickness distribution of the plastic bucket is obtained by the axial wall thickness reduction and the local inflation ratio.

[0009] Furthermore, the inversion yields optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution, including: Using the intrinsic correlation mapping as the forward model, the blow molding process parameters are adjusted according to the preset adjustment step size. The digital twin model is called to output the plastic barrel wall thickness distribution under the current blow molding process parameters. The output plastic barrel wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current blow molding process parameters are determined as the optimized blow molding process parameters.

[0010] Furthermore, the axial wall thickness reduction of the blank under gravity is calculated, including: The extrusion speed, melt temperature, and time interval from extrusion to mold closing in the blow molding process parameters are obtained. Based on the extrusion speed, melt temperature, and time interval, the axial wall thickness reduction is obtained by a reduced-order empirical relationship.

[0011] Furthermore, based on the cavity geometry data, the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle is obtained, including: The inner surface contour of the plastic bucket cavity is determined based on the cavity geometry data, and the inner surface contour is unfolded along the axial and circumferential directions to obtain the cavity unfolding radius.

[0012] Furthermore, the inversion yields optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution, including: The physical information proxy model is invoked to perform forward calculations, and the blow molding process parameters are adjusted according to the preset adjustment step size. The physical information proxy model is then invoked to output the plastic barrel wall thickness distribution obtained under the current blow molding process parameters. The output plastic barrel wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current blow molding process parameters are determined as the optimized blow molding process parameters.

[0013] Furthermore, determining whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution includes: Calculate the deviation between the wall thickness distribution of the plastic bucket and the target wall thickness distribution, and determine that the target wall thickness distribution is met when the deviation is within the preset tolerance range.

[0014] Furthermore, after the process parameters to be executed are sent to the blow molding equipment, this includes: Acquire online sensor data of the blow molding process, and recalibrate the digital twin model and its intrinsic correlation mapping based on the online sensor data.

[0015] Furthermore, the process parameters to be executed are sent to the blow molding equipment, including: The process parameters to be executed are converted into execution instructions for the blow molding equipment, and the execution instructions are sent to the actuator in the blow molding equipment to execute the process parameters to be executed.

[0016] Furthermore, the blow molding process parameters are adjusted according to the preset adjustment step size, including: Calculate the amount of material required to mold a plastic bucket under the current blow molding process parameters; Compare the calculated material usage with the preset upper limit of material usage; When the material usage does not exceed the preset upper limit of material usage, the current blow molding process parameters are maintained and continue to participate in the inversion. When the amount of material used exceeds the preset upper limit, the blow molding process parameters are adjusted in the direction of reducing the amount of material, while maintaining the plastic bucket wall thickness distribution to meet the target wall thickness distribution.

[0017] To address the aforementioned technical problems, this application also provides a technical solution employing the following description: A digital twin-based intelligent optimization system for plastic bucket blow molding process parameters includes: The data acquisition module is used to acquire the geometric data of the blow molding mold cavity of the plastic bucket, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket; The model building module is used to construct a digital twin model of the plastic bucket blow molding process based on cavity geometry data, blow molding material parameters, and blow molding process parameters, and to establish an intrinsic correlation mapping between blow molding process parameters and plastic bucket wall thickness distribution in the digital twin model; The parameter inversion module is used to obtain optimized blow molding process parameters that make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution, based on the intrinsic correlation mapping as the forward model and the target wall thickness distribution. The wall thickness determination module is used to determine whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution. The parameter distribution module is used to determine the optimized blow molding process parameters as the process parameters to be executed when the conditions are met, and then distribute the process parameters to be executed to the blow molding equipment.

[0018] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution: A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the intelligent optimization method for plastic bucket blow molding process parameters based on digital twins as described above.

[0019] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below: A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the intelligent optimization method for plastic bucket blow molding process parameters based on digital twins as described above.

[0020] Compared with the prior art, this application has the following main advantages: The intelligent optimization method for plastic bucket blow molding process parameters based on digital twin disclosed in this application obtains the geometric data of the blow molding mold cavity, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket. The geometric, material and target constraints required for optimization are digitally determined in one go, establishing a unified input benchmark for subsequent construction of digital twin model and establishment of correlation mapping between process parameters and wall thickness distribution. This eliminates the defects such as uneven wall thickness, long trial molding cycle and material waste caused by relying on manual experience to trial and error to adjust process parameters from the source.

[0021] Based on cavity geometry data, blow molding material parameters, and blow molding process parameters, a digital twin model of the blow molding process of plastic buckets is constructed. An intrinsic correlation mapping between blow molding process parameters and plastic bucket wall thickness distribution is established in the digital twin model. The complex nonlinear relationship between process parameters and wall thickness distribution during blow molding is solidified into a computable forward model, enabling the wall thickness distribution to be predicted positively from the process parameters. This solves the problem that existing technologies can only monitor offline or provide feedback after the fact, and cannot predict the wall thickness distribution positively, thus making it difficult to control the uniformity of wall thickness.

[0022] Using intrinsic correlation mapping as the forward model, and based on the target wall thickness distribution, the optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution are obtained through inversion. This realizes the process optimization by forward feedforward inversion of process parameters from the target wall thickness, solving the shortcomings of existing technologies that lack feedforward optimization methods, can only passively provide feedback, have long trial molding cycles, and waste materials.

[0023] The system determines whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution. A closed-loop verification of the process parameters was performed before distribution, which avoids the direct distribution of unqualified process parameters leading to batch scrap. This solves the defects of existing technologies that lack a pre-distribution verification process and are prone to waste due to improper parameters.

[0024] When the conditions are met, the optimized blow molding process parameters are determined as the process parameters to be executed, and the process parameters to be executed are sent to the blow molding equipment. The verified optimization results are directly converted into process instructions that can be executed by the equipment, realizing an automatic closed loop from model optimization to equipment execution, and solving the defects of existing technology process debugging that rely on manual labor, have poor consistency, and are inefficient. Attached Figure Description

[0025] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is an exemplary system architecture diagram to which this application can be applied; Figure 2 This is a flowchart of an embodiment of the intelligent optimization method for plastic bucket blow molding process parameters based on digital twin according to this application; Figure 3 This is a structural schematic diagram according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0027] 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 pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0030] like Figure 1 As shown, the system architecture 100 may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0031] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0032] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 (Moving Picture Experts Group Audio Layer Ⅲ) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptops, and desktop computers, etc.

[0033] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

[0034] It should be noted that the intelligent optimization method for plastic bucket blow molding process parameters based on digital twins provided in this application embodiment is generally executed by the terminal device, and correspondingly, it is generally set in the terminal device.

[0035] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0036] Continue to refer to Figure 2 The diagram illustrates a flowchart of an embodiment of the intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to this application. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins includes the following steps: Step S201: Obtain the geometric data of the blow molding mold cavity of the plastic bucket, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket.

[0037] In this embodiment, the intelligent optimization method for plastic bucket blow molding process parameters based on digital twins runs on electronic devices (e.g., Figure 1 The terminal device shown can send or receive data via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, Wi-Fi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wide band) connections, and other currently known or future wireless connection methods.

[0038] Blow mold cavity geometry data refers to the three-dimensional geometric shape data of the blow mold cavity, including the cavity's contour coordinates in the axial and circumferential directions. It defines the final shape of the plastic bucket and the cavity's unfolded dimensions at each location, serving as the fundamental input for subsequent calculations of the local blow-up ratio and wall thickness distribution. Blow molding material parameters refer to the physical properties of the polymer material used in blow molding, such as melt flow rate, density, and viscoelastic parameters. These parameters determine the flow and deformation behavior of the preform during extrusion and blow-up. The target wall thickness distribution of the plastic bucket refers to the set of wall thickness values ​​that the plastic bucket should achieve at various locations in the axial and circumferential directions, pre-set according to product strength and pressure requirements. It is typically determined based on the principle of ensuring that the minimum wall thickness meets the lower pressure limit and is as uniform as possible.

[0039] In this embodiment, the geometric data of the blow molding die cavity can be extracted from the 3D computer-aided design (CAD) model of the die. The blow molding material parameters are obtained from the material data sheet provided by the material supplier or through actual measurement using a rheometer. The target wall thickness distribution is determined during the product design stage based on the strength and weight indicators of the barrel. The reason for obtaining these three types of data first is that subsequent construction of the digital twin model, establishment of the correlation between process parameters and wall thickness distribution, and inversion optimization must all be based on real geometry, materials, and target constraints as boundary conditions; otherwise, the inverted process parameters will lose their physical basis. Its function is to anchor the optimization problem to specific product and material conditions, providing definite input for the entire optimization chain.

[0040] Step S202: Based on the cavity geometry data, blow molding material parameters, and blow molding process parameters, construct a digital twin model of the plastic bucket blow molding process, and establish an intrinsic correlation mapping between the blow molding process parameters and the plastic bucket wall thickness distribution in the digital twin model.

[0041] A digital twin model is a high-fidelity simulation model of the entire blow molding process of plastic buckets, established in virtual space. It maintains real-time data mapping with the physical production line, simulating the actual processes of preform extrusion, blow molding, and cooling / solidification. Blow molding process parameters refer to adjustable process variables during the blow molding process, including blow molding time, blow molding pressure, die temperature, initial preform wall thickness, extrusion speed, and melt temperature. These parameters are coupled and jointly determine the final wall thickness distribution. The intrinsic correlation mapping refers to the non-linear correspondence between blow molding process parameters and the wall thickness distribution of the plastic bucket; that is, a given set of process parameters can uniquely determine a corresponding wall thickness distribution.

[0042] In this embodiment, a full three-dimensional geometric model including the extruder head, preform, and blow molding die is first established based on the cavity geometry data. The viscoelastic constitutive equation, heat conduction equation, and fluid-structure interaction (FSI) algorithm are integrated to accurately describe the nonlinear viscoelastic behavior of the melt under tension and shear, the heat exchange during mold cooling and solidification, and the large interface deformation between compressed air and the softened preform. Subsequently, the blow molding process parameters are changed in a virtual environment, and the corresponding wall thickness distribution is simulated, thus obtaining the mapping from process parameters to wall thickness distribution. This mapping can be directly constructed from high-fidelity simulation or from a surrogate model trained from simulation data. The reason for constructing a digital twin model and establishing an intrinsic mapping is that traditional methods rely on experience or simplified physical models, failing to systematically reveal the coupling laws between multiple parameters and wall thickness. Its role is to encapsulate the complex physical process from process parameters to wall thickness distribution into a deterministic relationship that can be repeatedly invoked and inverted, providing a computational basis for subsequent process parameter optimization.

[0043] Step S203: Using the intrinsic correlation mapping as the forward model, and based on the target wall thickness distribution, the optimized blow molding process parameters are obtained by inversion to make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution.

[0044] The forward model refers to the forward calculation relationship from process parameters to wall thickness distribution; that is, inputting a set of blow molding process parameters will output the corresponding plastic bucket wall thickness distribution through the inherent correlation mapping. The inversion model refers to using the target wall thickness distribution as a known objective and solving in reverse to optimize the blow molding process parameters so that the plastic bucket wall thickness distribution output by the forward model approximates the target wall thickness distribution.

[0045] In this embodiment, a forward model is used as the core of the calculation. Starting from a set of initial blow molding process parameters, the process parameters are gradually changed according to a preset adjustment step size. After each change, the forward model is called to output the current wall thickness distribution of the plastic bucket, and this output is compared with the target wall thickness distribution. When the two are consistent or sufficiently close, the current blow molding process parameters are determined as the optimized blow molding process parameters. The reason for using a forward model plus inversion method is that directly determining parameters by experience or trial molding is inefficient and makes it difficult to guarantee uniform wall thickness. Its function is to transform how to obtain qualified process parameters into a mathematical solution that can be automatically iterated in a virtual environment, avoiding repeated physical trial molding and significantly improving optimization efficiency.

[0046] Step S204: Determine whether the plastic bucket wall thickness distribution output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution.

[0047] Judgment refers to the process of comparing the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters with the target wall thickness distribution position by position to confirm whether the two are consistent or sufficiently close.

[0048] In this embodiment, a forward model constructed from a digital twin model or the intrinsic correlation mapping is invoked, using optimized blow molding process parameters as input, to output the corresponding plastic bucket wall thickness distribution. Then, the output wall thickness distribution is compared position-by-position with the target wall thickness distribution. This judgment step is necessary because the solution obtained through inversion needs to pass a consistency check to confirm its qualification; its function is to prevent process parameters that have not yet reached the target accuracy from being issued, ensuring that the process parameters entering the execution stage can indeed make the wall thickness distribution meet the requirements.

[0049] Step S205: When the conditions are met, the optimized blow molding process parameters are determined as the process parameters to be executed, and the process parameters to be executed are sent to the blow molding equipment.

[0050] The process parameters to be executed refer to the set of process parameters that are ready to be delivered to the blow molding equipment after it has been determined and confirmed that the target wall thickness distribution is met. Blow molding equipment refers to the physical production equipment that completes the blow molding of plastic buckets, including but not limited to extruders, blow molding mechanisms, and molds.

[0051] In this embodiment, when the judgment result is satisfactory, the optimized blow molding process parameters are solidified into process parameters to be executed and transmitted to the blow molding equipment, so that the physical production line can form plastic buckets according to these parameters. The reason for issuing the parameters only after confirming that they are satisfactory is that only parameters that have undergone virtual verification can ensure that the wall thickness of the actual product is qualified, avoiding defective products caused by using faulty parameters. Its function is to establish a closed loop from virtual optimization to physical execution, so that the digital optimization results are put into practice.

[0052] This application obtains the geometric data of the blow molding mold cavity of the plastic bucket, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket; it digitally determines the geometry, material and target constraints required for optimization in one go, and establishes a unified input benchmark for the subsequent construction of digital twin model and the establishment of the correlation mapping between process parameters and wall thickness distribution. It eliminates the defects such as uneven wall thickness, long trial molding cycle and material waste caused by relying on manual experience to trial and error to obtain process parameters from the source.

[0053] Based on cavity geometry data, blow molding material parameters, and blow molding process parameters, a digital twin model of the blow molding process of plastic buckets is constructed. An intrinsic correlation mapping between blow molding process parameters and plastic bucket wall thickness distribution is established in the digital twin model. The complex nonlinear relationship between process parameters and wall thickness distribution during blow molding is solidified into a computable forward model, enabling the wall thickness distribution to be predicted positively from the process parameters. This solves the problem that existing technologies can only monitor offline or provide feedback after the fact, and cannot predict the wall thickness distribution positively, thus making it difficult to control the uniformity of wall thickness.

[0054] Using intrinsic correlation mapping as the forward model, and based on the target wall thickness distribution, the optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution are obtained through inversion. This realizes the process optimization by forward feedforward inversion of process parameters from the target wall thickness, solving the shortcomings of existing technologies that lack feedforward optimization methods, can only passively provide feedback, have long trial molding cycles, and waste materials.

[0055] The system determines whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution. A closed-loop verification of the process parameters was performed before distribution, which avoids the direct distribution of unqualified process parameters leading to batch scrap. This solves the defects of existing technologies that lack a pre-distribution verification process and are prone to waste due to improper parameters.

[0056] When the conditions are met, the optimized blow molding process parameters are determined as the process parameters to be executed, and the process parameters to be executed are sent to the blow molding equipment. The verified optimization results are directly converted into process instructions that can be executed by the equipment, realizing an automatic closed loop from model optimization to equipment execution, and solving the defects of existing technology process debugging that rely on manual labor, have poor consistency, and are inefficient.

[0057] In some optional implementations of this embodiment, the steps described above for establishing the intrinsic correlation mapping between blow molding process parameters and plastic barrel wall thickness distribution in the digital twin model include: Obtain the initial outer radius of the preform, and based on the cavity geometry data, obtain the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle; The ratio of the cavity development radius to the initial outer radius of the preform is determined as the local inflation ratio; Based on the parameters of the blow molding material and the blow molding process, calculate the axial wall thickness reduction of the preform under gravity. The wall thickness distribution of the plastic bucket is obtained by the axial wall thickness reduction and the local inflation ratio.

[0058] The initial outer radius of the preform refers to its outer radius in the free section after extrusion and before blow-in; it reflects the initial cross-sectional dimensions of the preform. The cavity unfolded radius refers to the radius corresponding to the circumference of the inner surface contour of the blow molding die cavity at a certain axial position and circumferential angle; it represents the final cross-sectional radius of the plastic bucket at that position. The local blow-in ratio is the ratio of the cavity unfolded radius to the initial outer radius of the preform, characterizing the factor by which the preform at that position is inflated and enlarged; it is the dominant factor in wall thickness reduction during blow-in. Axial wall thickness reduction refers to the amount of wall thickness reduction in the axial direction caused by the preform's own weight sag after extrusion and before mold closing.

[0059] In this embodiment, the initial outer radius of the preform is first read, and the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle is calculated based on the cavity geometry data. Then, the cavity unfolding radius at each position is divided by the initial outer radius of the preform to obtain the local blow-up ratio at that position. Simultaneously, the axial wall thickness reduction of the preform under gravity is calculated based on the blow molding material parameters and blow molding process parameters. Finally, the wall thickness distribution of the plastic bucket is obtained from the axial wall thickness reduction and the local blow-up ratio. Specifically, the local blow-up ratio is equal to the cavity unfolding radius divided by the initial outer radius of the preform; the local wall thickness is equal to the axial wall thickness of the preform minus the axial wall thickness reduction, then divided by the local blow-up ratio.

[0060] This application decomposes the wall thickness distribution into two physical factors coupled with vertical thinning and local inflation ratio. It establishes the intrinsic correlation mapping between multiple process parameters and wall thickness distribution on an interpretable vertical-inflation coupling mechanism, so that the mapping has both physical basis and is easy to solve by inversion, thereby improving the accuracy of wall thickness distribution prediction and the targeting of optimization.

[0061] In some optional implementations of this embodiment, the steps of obtaining optimized blow molding process parameters that make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution include: Using the intrinsic correlation mapping as the forward model, the blow molding process parameters are adjusted according to the preset adjustment step size. The digital twin model is called to output the plastic barrel wall thickness distribution under the current blow molding process parameters. The output plastic barrel wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current blow molding process parameters are determined as the optimized blow molding process parameters.

[0062] The preset adjustment step size refers to the fixed or adaptive increment used each time the blow molding process parameters are changed during the inversion iteration process. For example, the blow pressure is adjusted by 0.02 MPa each time, and the mold temperature is adjusted by 1 degree each time. The size of the step size affects the convergence speed and the stability of the solution.

[0063] In this embodiment, the inherent correlation mapping is used as the forward model. Starting from the initial process parameters, the blow molding process parameters are changed one by one according to the preset adjustment step size. Each time the parameters are changed, the digital twin model or surrogate model is called to output the plastic barrel wall thickness distribution obtained under the current process parameters, and the output is compared with the target wall thickness distribution. When the output wall thickness distribution is consistent with the target wall thickness distribution or falls within the allowable deviation, the current blow molding process parameters are determined as the optimized blow molding process parameters.

[0064] This application concretizes the inversion step into an optimization process that can be completed automatically without relying on manual trial molding by iteratively adjusting, outputting, comparing and determining the preset adjustment step size. This improves the efficiency of process parameter optimization and shortens the new product development cycle.

[0065] In some optional implementations of this embodiment, the step of calculating the axial wall thickness reduction of the blank under gravity includes: The extrusion speed, melt temperature, and time interval from extrusion to mold closing in the blow molding process parameters are obtained. Based on the extrusion speed, melt temperature, and time interval, the axial wall thickness reduction is obtained by a reduced-order empirical relationship.

[0066] Extrusion speed refers to the linear velocity of the parison as it is extruded from the die head; melt temperature refers to the melt temperature during parison extrusion; and the time interval from parison exit to die closing refers to the time elapsed from the completion of extrusion to die closure. The longer this interval, the more fully the parison sags. Reduced-order empirical relationships are simplified correlations derived from a large amount of simulation or experimental data, which quickly estimate the axial wall thickness reduction using a small number of independent variables. They belong to an empirical form of reduced-order models (ROM) and are used to replace time-consuming full-physics simulations.

[0067] In this embodiment, the extrusion speed, melt temperature, and time interval from extrusion to mold closing in the blow molding process parameters are obtained. These three parameters are then substituted into a reduced-order empirical relationship to obtain the axial wall thickness reduction of the preform under gravity. This reduction increases with decreasing extrusion speed, increasing melt temperature, or extending the time interval. The relationship can be naturally expressed as follows: the axial wall thickness reduction is directly proportional to the material density, gravitational acceleration, vertical extension height, and the square of the time interval from extrusion to mold closing, and inversely proportional to twice the apparent melt viscosity.

[0068] This application uses a reduced-order empirical relation to estimate the axial wall thickness reduction. While maintaining physical rationality, it reduces the acquisition of the vertical thinning amount from hourly full simulation to millisecond-level table lookup or calculation, thus balancing estimation accuracy and calculation speed and significantly improving inversion efficiency.

[0069] In some optional implementations of this embodiment, the step of obtaining the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle based on cavity geometry data includes: The inner surface contour of the plastic bucket cavity is determined based on the cavity geometry data, and the inner surface contour is unfolded along the axial and circumferential directions to obtain the cavity unfolding radius.

[0070] The inner surface profile refers to the three-dimensional curved surface profile of the inner wall of the blow molding mold cavity, which determines the actual shape and size of the plastic bucket at various locations.

[0071] In this embodiment, the inner surface contour of the plastic bucket cavity is determined based on the cavity geometry data, and the inner surface contour is unfolded along the axial direction by height and along the circumferential direction by angle to obtain the cavity unfolding radius corresponding to each axial position and circumferential angle.

[0072] This application improves the calculation accuracy of localized inflation ratio and wall thickness distribution by determining the cavity expansion radius through an implementation method that expands the inner surface profile of the cavity along the axial and circumferential directions.

[0073] In some optional implementations of this embodiment, the steps of obtaining optimized blow molding process parameters that make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution include: The physical information proxy model is invoked to perform forward calculations, and the blow molding process parameters are adjusted according to the preset adjustment step size. The physical information proxy model is then invoked to output the plastic barrel wall thickness distribution obtained under the current blow molding process parameters. The output plastic barrel wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current blow molding process parameters are determined as the optimized blow molding process parameters.

[0074] The Physics-Informed Surrogate Model (PSM) is a fast surrogate model that is constrained by physical laws and trained from simulation or experimental data. It retains the forward computation capability of the digital twin model and outputs the wall thickness distribution much faster than full simulation, and can be used to perform forward computation in real time at the edge.

[0075] In this embodiment, the forward calculation is performed by calling the physical information proxy model. That is, the forward model is used as a framework and the proxy model outputs the wall thickness distribution of the plastic bucket according to the current process parameters. Then, the blow molding process parameters are adjusted according to the preset adjustment step size, and the proxy model is called again to output a new wall thickness distribution. This new wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current process parameters are determined as the optimized blow molding process parameters.

[0076] This application proposes an implementation method that replaces the full digital twin simulation with a physical information proxy model to perform forward computation. While preserving the mainstream physical laws, it compresses a single forward computation to the millisecond level, enabling the inversion to be completed in real time at the edge without relying on remote high-fidelity simulation. This gives the optimization of process parameters both real-time performance and deployment flexibility.

[0077] In some optional implementations of this embodiment, the step of determining whether the plastic bucket wall thickness distribution output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution includes: Calculate the deviation between the wall thickness distribution of the plastic bucket and the target wall thickness distribution, and determine that the target wall thickness distribution is met when the deviation is within the preset tolerance range.

[0078] Deviation refers to the difference between the output wall thickness distribution and the target wall thickness distribution at corresponding locations. It can be expressed as an overall measure of the difference in wall thickness at each point, such as the root mean square deviation. The preset tolerance range refers to the maximum allowable deviation of the output wall thickness distribution from the target wall thickness distribution, used to determine whether a quantization threshold is met.

[0079] In this embodiment, the deviation between the plastic barrel wall thickness distribution output by the digital twin model based on the optimized blow molding process parameters and the target wall thickness distribution is calculated, and the deviation is compared with a preset tolerance range. When the deviation is within the preset tolerance range, it is determined that the target wall thickness distribution is met; otherwise, it is determined that it is not met and adjustment continues.

[0080] This application adopts a quantitative judgment method by introducing deviation and preset tolerance range, which quantifies the judgment of whether it meets the requirements into an operable judgment criterion, avoiding misjudgment and unnecessary repeated iterations, thereby improving the robustness and operability of the judgment.

[0081] In some optional implementations of this embodiment, the steps following the sending of the process parameters to be executed to the blow molding equipment include: Acquire online sensor data of the blow molding process, and recalibrate the digital twin model and its intrinsic correlation mapping based on the online sensor data.

[0082] Online sensor data refers to multi-source physical data collected in real time by sensors during the actual operation of blow molding equipment, such as melt temperature, blowing pressure curve, and mold temperature field. Recalibration refers to correcting the parameters of the digital twin model and its inherent correlation mapping using online sensor data as a reference, so that the virtual model is re-fitted to the actual production state.

[0083] In this embodiment, after the process parameters to be executed are sent to the blow molding equipment, online sensor data of the blow molding process is continuously acquired, and the digital twin model and its inherent correlation mapping are recalibrated based on these online sensor data. For example, the measured melt temperature and blowing pressure are used as boundary conditions to backfill the model and correct the material or equipment parameters in the mapping.

[0084] This application utilizes real production line data to continuously correct the virtual model by recalibrating the model based on online sensor data after the parameters are issued. This forms a continuous closed loop of optimization, execution, feedback, and correction, thereby maintaining the long-term predictive accuracy of the digital twin model and adapting to production fluctuations.

[0085] In some optional implementations of this embodiment, the step of sending the process parameters to be executed to the blow molding equipment includes: The process parameters to be executed are converted into execution instructions for the blow molding equipment, and the execution instructions are sent to the actuator in the blow molding equipment to execute the process parameters to be executed.

[0086] Execution instructions refer to a sequence of commands that the blow molding equipment can directly recognize and execute, derived from the process parameters to be executed, such as the blow pressure and mold temperature setpoints arranged along a time axis. The execution mechanism refers to the physical component in the blow molding equipment that actually performs the process actions, such as the mechanisms for driving blow inflation, temperature control, and mold closing.

[0087] In this embodiment, the process parameters to be executed are converted into corresponding execution instructions according to the data interface and communication protocol of the blow molding equipment, and the execution instructions are sent to the execution mechanism in the blow molding equipment that executes the process parameters to be executed. The execution mechanism completes actions such as blowing, temperature control and mold closing according to the instructions.

[0088] This application achieves a closed-loop execution from digital optimization to physical production by first converting process parameters into execution instructions and then sending them for execution. This ensures that the optimization results can be implemented and that the production line can stably produce according to the optimized parameters.

[0089] In some optional implementations of this embodiment, the step of adjusting the blow molding process parameters according to a preset adjustment step size includes: Calculate the amount of material required to mold a plastic bucket under the current blow molding process parameters; Compare the calculated material usage with the preset upper limit of material usage; When the material usage does not exceed the preset upper limit of material usage, the current blow molding process parameters are maintained and continue to participate in the inversion. When the amount of material used exceeds the preset upper limit, the blow molding process parameters are adjusted in the direction of reducing the amount of material, while maintaining the plastic bucket wall thickness distribution to meet the target wall thickness distribution.

[0090] Material consumption refers to the mass or volume of raw materials consumed in molding a single plastic bucket. It can be estimated by the sum of the products of the surface area of ​​each micro-element of the plastic bucket, the local wall thickness, and the material density. The relationship can be expressed as: material consumption equals the sum of the surface area of ​​each micro-element multiplied by the local wall thickness and then multiplied by the material density. The preset upper limit of material consumption refers to the maximum value of raw material consumption per bucket set in advance to control costs.

[0091] In this embodiment, during the process of adjusting the blow molding process parameters according to the preset adjustment step size, the amount of material required to form a plastic bucket under the current process parameters is calculated, and the amount of material is compared with the preset upper limit of material usage. When the amount of material usage does not exceed the preset upper limit of material usage, the current process parameters are maintained and continue to participate in the inversion. When the amount of material usage exceeds the preset upper limit of material usage, while maintaining the plastic bucket wall thickness distribution to meet the target wall thickness distribution, the process parameters are adjusted in the direction of reducing the amount of material usage, such as reducing the overall wall thickness setting or optimizing the preform wall thickness curve.

[0092] This application expands the inversion process from a single objective to a multi-objective optimization that achieves the required wall thickness while minimizing material usage by simultaneously constraining material consumption during the inversion process. This ensures strength while reducing raw material consumption, thereby balancing product quality and manufacturing costs and improving economic efficiency.

[0093] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0094] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0095] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0096] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0097] Further reference Figure 3 As a response to the above Figure 2 The implementation of the method shown in this application provides an embodiment of an intelligent optimization system for plastic bucket blow molding process parameters based on digital twins. This system embodiment is similar to... Figure 2 Corresponding to the method embodiments shown, the system can be specifically applied to various electronic devices.

[0098] like Figure 3 As shown, the 300 described in this embodiment includes: a data acquisition module 301, a model construction module 302, a parameter inversion module 303, a wall thickness judgment module 304, and a parameter distribution module 305. Wherein: The data acquisition module 301 is used to acquire the geometric data of the blow molding mold cavity of the plastic bucket, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket. The model building module 302 is used to build a digital twin model of the plastic bucket blow molding process based on cavity geometry data, blow molding material parameters, and blow molding process parameters, and to establish an intrinsic correlation mapping between blow molding process parameters and plastic bucket wall thickness distribution in the digital twin model. The parameter inversion module 303 is used to invert the optimized blow molding process parameters that make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution, using the intrinsic correlation mapping as the forward model and based on the target wall thickness distribution. The wall thickness judgment module 304 is used to determine whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution. The parameter sending module 305 is used to determine the optimized blow molding process parameters as the process parameters to be executed when the conditions are met, and to send the process parameters to be executed to the blow molding equipment.

[0099] The intelligent optimization system for plastic bucket blow molding process parameters based on digital twin provided in this application acquires the geometric data of the blow molding mold cavity, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket. It digitally determines the geometry, material and target constraints required for optimization in one go, establishing a unified input benchmark for subsequent construction of digital twin model and establishment of correlation mapping between process parameters and wall thickness distribution. This eliminates the defects such as uneven wall thickness, long trial molding cycle and material waste caused by relying on manual experience to trial and error to adjust process parameters from the source.

[0100] Based on cavity geometry data, blow molding material parameters, and blow molding process parameters, a digital twin model of the blow molding process of plastic buckets is constructed. An intrinsic correlation mapping between blow molding process parameters and plastic bucket wall thickness distribution is established in the digital twin model. The complex nonlinear relationship between process parameters and wall thickness distribution during blow molding is solidified into a computable forward model, enabling the wall thickness distribution to be predicted positively from the process parameters. This solves the problem that existing technologies can only monitor offline or provide feedback after the fact, and cannot predict the wall thickness distribution positively, thus making it difficult to control the uniformity of wall thickness.

[0101] Using intrinsic correlation mapping as the forward model, and based on the target wall thickness distribution, the optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution are obtained through inversion. This realizes the process optimization by forward feedforward inversion of process parameters from the target wall thickness, solving the shortcomings of existing technologies that lack feedforward optimization methods, can only passively provide feedback, have long trial molding cycles, and waste materials.

[0102] The system determines whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution. A closed-loop verification of the process parameters was performed before distribution, which avoids the direct distribution of unqualified process parameters leading to batch scrap. This solves the defects of existing technologies that lack a pre-distribution verification process and are prone to waste due to improper parameters.

[0103] When the conditions are met, the optimized blow molding process parameters are determined as the process parameters to be executed, and the process parameters to be executed are sent to the blow molding equipment. The verified optimization results are directly converted into process instructions that can be executed by the equipment, realizing an automatic closed loop from model optimization to equipment execution, and solving the defects of existing technology process debugging that rely on manual labor, have poor consistency, and are inefficient.

[0104] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0105] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41, 42, and 43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0106] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0107] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for a digital twin-based intelligent optimization method for plastic bucket blow molding process parameters. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0108] In some embodiments, the processor 42 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute the computer-readable instructions of the intelligent optimization method for plastic bucket blow molding process parameters based on digital twins.

[0109] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0110] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the above-described intelligent optimization method for plastic bucket blow molding process parameters based on digital twins.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0112] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method for intelligent optimization of process parameters in plastic bucket blow molding based on digital twins, characterized in that, Includes the following steps: Obtain the geometric data of the blow molding mold cavity for the plastic bucket, as well as the parameters of the blow molding material and the target wall thickness distribution of the plastic bucket; Based on the cavity geometry data, the blow molding material parameters, and the blow molding process parameters, a digital twin model of the plastic bucket blow molding process is constructed, and an intrinsic correlation mapping between the blow molding process parameters and the plastic bucket wall thickness distribution is established in the digital twin model. Using the intrinsic correlation mapping as the forward model, and based on the target wall thickness distribution, the optimized blow molding process parameters that make the plastic bucket wall thickness distribution output by the digital twin model approximate the target wall thickness distribution are obtained by inversion. Determine whether the plastic bucket wall thickness distribution output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution; When the conditions are met, the optimized blow molding process parameters are determined as the process parameters to be executed, and the process parameters to be executed are sent to the blow molding equipment.

2. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 1, characterized in that, The process of establishing an intrinsic mapping between blow molding process parameters and plastic barrel wall thickness distribution in the digital twin model includes: Obtain the initial outer radius of the preform, and based on the cavity geometry data, obtain the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle; The ratio of the cavity development radius to the initial outer radius of the preform is determined as the local inflation ratio; Based on the blow molding material parameters and blow molding process parameters, calculate the axial wall thickness reduction of the preform under gravity. The wall thickness distribution of the plastic bucket is obtained by the axial wall thickness reduction and the local inflation ratio.

3. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 1, characterized in that, The inversion yields optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution, including: Using the intrinsic correlation mapping as the forward model, the blow molding process parameters are adjusted according to a preset adjustment step size. The digital twin model is then called to output the plastic barrel wall thickness distribution obtained under the current blow molding process parameters. The output plastic barrel wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current blow molding process parameters are determined as the optimized blow molding process parameters.

4. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 2, characterized in that, The calculation of the axial wall thickness reduction of the blank under gravity includes: The extrusion speed, melt temperature, and time interval from extrusion to mold closing in the blow molding process parameters are obtained, and the axial wall thickness reduction is obtained by a reduced-order empirical relationship based on the extrusion speed, melt temperature, and time interval.

5. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 2, characterized in that, The step of obtaining the cavity unfolding radius of the plastic bucket at each axial position and circumferential angle based on the cavity geometry data includes: Based on the cavity geometry data, the inner surface contour of the plastic bucket cavity is determined, and the inner surface contour is unfolded along the axial and circumferential directions to obtain the cavity unfolding radius.

6. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 3, characterized in that, The inversion yields optimized blow molding process parameters that make the wall thickness distribution of the plastic bucket output by the digital twin model approximate the target wall thickness distribution, including: The forward calculation is performed by calling the physical information proxy model, the blow molding process parameters are adjusted according to the preset adjustment step size, and the plastic barrel wall thickness distribution obtained under the current blow molding process parameters is output by calling the physical information proxy model. The output plastic barrel wall thickness distribution is compared with the target wall thickness distribution. When the two are consistent, the current blow molding process parameters are determined as the optimized blow molding process parameters.

7. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 1, characterized in that, The step of determining whether the wall thickness distribution of the plastic bucket output by the digital twin model based on the optimized blow molding process parameters meets the target wall thickness distribution includes: Calculate the deviation between the wall thickness distribution of the plastic bucket and the target wall thickness distribution, and determine that the target wall thickness distribution is met when the deviation is within a preset tolerance range.

8. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 1, characterized in that, After sending the process parameters to be executed to the blow molding equipment, the process includes: Acquire online sensor data of the blow molding process, and recalibrate the digital twin model and the intrinsic correlation mapping based on the online sensor data.

9. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 1, characterized in that, The step of sending the process parameters to be executed to the blow molding equipment includes: The process parameters to be executed are converted into execution instructions for the blow molding equipment, and the execution instructions are sent to the actuator in the blow molding equipment that executes the process parameters to be executed.

10. The intelligent optimization method for plastic bucket blow molding process parameters based on digital twins according to claim 3, characterized in that, The step of adjusting the blow molding process parameters according to the preset adjustment step size includes: Calculate the amount of material required to mold the plastic bucket under the current blow molding process parameters; Compare the calculated material usage with the preset upper limit of material usage; When the amount of material used does not exceed the preset upper limit of material usage, the current blow molding process parameters are maintained and continue to participate in the inversion. When the amount of material used exceeds the preset upper limit of material usage, the blow molding process parameters are adjusted in the direction of reducing material usage, while maintaining the wall thickness distribution of the plastic bucket to meet the target wall thickness distribution.

Images