Extrusion quality control method and device

Abstract

The invention provides an extrusion quality control method and device, and relates to the technical field of extrusion molding.The method comprises the steps that an annular array type multispectral thermal imaging module is used, and thermal field distribution in the extrusion process is monitored in real time; the displacement of the thermal imager generated in the moving process of the nozzle is compensated through the laser-assisted positioning system, so that a thermal imaging image is strictly synchronized with the axis of the extrusion nozzle; thermal imaging data is processed through three-dimensional dynamic reconstruction, a three-dimensional temperature field is generated, a shielding area in the thermal imaging data is repaired through a transfer learning frame, the thermal imaging module is composed of at least six groups of micro-distance thermal imagers, each group is provided with short-wave infrared and medium-wave infrared double-spectrum channels, the micro-distance thermal imagers are symmetrically distributed around the axis of an extrusion nozzle, and the medium-wave infrared and short-wave infrared double-spectrum channels are communicated with the thermal imaging module. And the distance between the device and the deposition layer is dynamically adjusted through the hydraulic driving telescopic mechanism, so that the spatial resolution is self-adaptive, accurate control, real-time defect detection and self-adaptive adjustment of the extrusion process are realized, and the production efficiency, the product quality and the material utilization rate are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of extrusion molding, and in particular to a method and device for extrusion quality control. Background Art

[0002] Current extrusion quality control mainly relies on thermal imaging technology, sensors, temperature, pressure monitoring and digital processing methods, but these methods have the following disadvantages: 1. Thermal imaging occlusion and insufficient spatial resolution: During the dynamic extrusion process, existing thermal imaging systems suffer from image information loss due to nozzle movement or deposition layer occlusion, making it impossible to accurately obtain global thermal field data. 2. Slow defect detection response: Traditional defect detection methods, such as X-ray inspection, have problems such as slow response and difficulty in predicting potential defects in real time, which affects production efficiency. 3. Single process parameter optimization: Most existing process optimization methods rely only on simple PID adjustment, which makes it difficult to achieve comprehensive optimization of multiple variables and cannot adapt to complex process requirements.

[0003] Therefore, how to effectively use real-time data to optimize the extrusion process and improve product quality has become a key issue facing current technology. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to propose a method and device for extrusion quality control. By combining multimodal sensors, embedded edge computing and dynamic feedback control technology, a breakthrough extrusion quality control solution is provided, which not only solves the defects in the existing technology, improves the thermal imaging resolution and defect detection response speed, but also greatly improves the process accuracy and production efficiency through multivariable optimization and adaptive control.

[0005] To achieve the above object, the present invention provides the following technical solutions: Based on the above objectives, in a first aspect, the present invention provides a method for extrusion quality control, comprising the following steps: Use a ring array multi-spectral thermal imaging module to monitor the thermal field distribution during the extrusion process in real time; The laser-assisted positioning system compensates for the displacement of the thermal imager during nozzle movement, ensuring that the thermal imaging image is strictly synchronized with the extrusion nozzle axis. The thermal imaging data is processed through three-dimensional dynamic reconstruction to generate a three-dimensional temperature field, and the occluded areas in the thermal imaging data are repaired using a transfer learning framework.

[0006] As a further solution of the present invention, the thermal imaging module is composed of at least six groups of macro thermal imagers, each group is equipped with short-wave infrared (SWIR) and medium-wave infrared (MWIR) dual spectral channels, which are symmetrically distributed around the axis of the extrusion nozzle and dynamically adjust the distance from the deposition layer through a hydraulically driven telescopic mechanism, making the spatial resolution adaptive.

[0007] As a further solution of the present invention, the three-dimensional dynamic reconstruction includes parallax compensation and point cloud registration steps. The point cloud registration uses an improved ICP point cloud registration algorithm. The update frequency of the reconstructed three-dimensional temperature field is at least 30 Hz.

[0008] As a further embodiment of the present invention, the method for extrusion quality control further comprises the following steps: Using an embedded multi-physics sensor array to monitor melt pressure, temperature gradient, and shear rate during extrusion, wherein the sensor array includes a fiber Bragg grating (FBG) sensor, a flexible piezoelectric film array, and a microwave dielectric spectrum online detection module; The fiber Bragg grating sensor is used to monitor the melt pressure (0-50 MPa), temperature gradient (±0.1°C) and shear rate in real time, and the piezoelectric film array is used to detect microcracks under the deposited layer; The crystallinity and molecular orientation of the material are analyzed through the microwave dielectric spectroscopy online detection module.

[0009] As a further solution of the present invention, the frequency range of the microwave dielectric spectrum online detection module is 1-10 GHz, and the data collected by the sensor array is used together with the thermal imaging data for defect detection and feature extraction.

[0010] As a further embodiment of the present invention, the method for extrusion quality control further comprises: Use a multi-scale feature pyramid network (FPN) to simultaneously process thermal imaging, acoustic emission, and dielectric spectroscopy data to extract defect features such as interlayer bonding strength, porosity, and crystallinity anomalies. A defect propagation model is constructed using graph neural networks to predict the potential defect types and locations of the next few deposition layers based on current process parameters.

[0011] As a further solution of the present invention, the defect propagation model predicts defect types including cracks, pores and delamination through graph neural networks, and provides the defect location and severity during real-time monitoring.

[0012] As a further embodiment of the present invention, the method for extrusion quality control further comprises the following steps: Establishing a multi-objective optimization engine based on the response surface model to optimize multiple process parameters, including but not limited to extrusion speed, temperature, and pressure; Use NSGA-III to find the Pareto optimal solution set in the multi-objective space to achieve balanced optimization of different process objectives; Use the digital twin system to preview the adjustment effects of different process parameters in virtual space and predict the effects in actual production, thereby reducing trial and error costs.

[0013] As a further solution of the present invention, the digital twin system simulates the extrusion process in real time, and dynamically adjusts the extrusion temperature and pressure parameters based on changes in process parameters to optimize the quality stability during the production process.

[0014] As a further embodiment of the present invention, the method for extrusion quality control further comprises the following steps: Use adaptive PID-MPC hybrid controller to control temperature and pressure during extrusion; The PID-MPC hybrid controller optimizes the temperature control of the heating section through model predictive control (MPC) and dynamically adjusts the extrusion speed in combination with the fuzzy PID algorithm to ensure a response time of no more than 50ms. Among them, the MPC controller performs rolling time domain optimization control based on the real-time feedback data of the current temperature field and pressure field, eliminates the coupling interference between multiple heating sections, and ensures the precise adjustment and stability of process parameters. This extrusion quality control method is applied to the 3D printing process of polymer materials, which can effectively improve printing accuracy, reduce the standard deviation of interlayer bonding strength and material waste rate, and has high industrial application value.

[0015] In a second aspect, the present invention provides an extrusion quality control device comprising the following components: A ring-shaped multispectral thermal imaging module is used to monitor the thermal field distribution during the extrusion process in real time. The module consists of at least six groups of macro thermal imagers, each equipped with short-wave infrared (SWIR) and medium-wave infrared (MWIR) dual spectral channels. These are symmetrically distributed around the axis of the extrusion nozzle and dynamically adjust the distance between the thermal imagers and the deposited layer through a hydraulically driven telescopic mechanism, making the spatial resolution adaptive. Laser-assisted positioning system, used to compensate for the displacement of the thermal imager during nozzle movement, ensuring that the thermal image is strictly synchronized with the extrusion nozzle axis; A data processing unit is used to receive and process the thermal imaging data from the thermal imaging module, generate a three-dimensional temperature field using a three-dimensional dynamic reconstruction algorithm, perform parallax compensation and point cloud registration, and use a transfer learning framework to repair occluded areas in the thermal imaging data.

[0016] As a further embodiment of the present invention, the extrusion quality control device further comprises: An embedded multi-physics sensor array for monitoring melt pressure, temperature gradient, and shear rate. The sensor array includes a fiber Bragg grating (FBG) sensor, a flexible piezoelectric film array, and a microwave dielectric spectrum online detection module. The data acquisition and processing unit is connected to the embedded multi-physics field sensor array, collects sensor data in real time and performs defect detection and feature extraction together with thermal imaging data.

[0017] As a further embodiment of the present invention, the extrusion quality control device further comprises: A multi-objective optimization engine for optimizing multiple process parameters, including but not limited to extrusion speed, temperature, and pressure; Response surface model, used to generate multi-objective optimization solutions based on process parameter optimization results; The digital twin system is connected to the optimization engine and is used to simulate the influence of different process parameters on the extrusion process in a virtual space and adjust the actual process parameters in production according to the simulation results.

[0018] As a further embodiment of the present invention, the extrusion quality control device further comprises: Adaptive PID-MPC hybrid controller for controlling temperature and pressure during extrusion; Model Predictive Control (MPC) unit, used to optimize the temperature control of the heating section, and dynamically adjust the extrusion speed in combination with the fuzzy PID algorithm to ensure a response time of no more than 50ms; The pressure regulating unit is used to automatically adjust the extrusion pressure according to real-time feedback data to ensure accurate adjustment of process parameters.

[0019] Compared with the prior art, the method and device for extrusion quality control proposed by the present invention have the following beneficial effects: The present invention realizes real-time monitoring of multiple key parameters such as temperature field, pressure field, shear rate, etc. during the extrusion process through an annular array multi-spectral thermal imaging module, a laser-assisted positioning system, and an embedded multi-physics field sensor array. Combining thermal imaging data with multi-physics field sensor data, the present invention can accurately capture abnormal fluctuations, uneven temperature distribution, pores, cracks and other defects in the extrusion process, and then adjust the process parameters in time through the data processing unit to ensure the high quality and stability of the extrusion process. Through the multi-scale feature pyramid network and graph neural network, it is possible to synchronously process a variety of sensor data, extract material defect characteristics, and predict potential defect types and locations in real time. Compared with traditional methods, the defect detection of the present invention can not only detect quality problems in a timely manner during the production process, but also provide an accurate basis for subsequent defect repair and optimization, thereby greatly reducing the scrap rate and improving the overall quality of the product.

[0020] Moreover, the present invention also integrates an adaptive PID-MPC hybrid controller and a response surface model optimization engine. The present invention can dynamically adjust process parameters such as temperature, pressure and extrusion speed during the extrusion process according to real-time feedback data, thereby achieving precise control. The method of the present invention can automatically adjust the control strategy according to changes in the process, eliminate coupling interference between multiple heating sections, and effectively eliminate quality fluctuations that may occur during the production process, thereby achieving automated and intelligent production process control; by introducing a digital twin system, the extrusion process can be simulated in a virtual space, and the production process parameters can be optimized through comparative analysis with actual production data. Through a multi-objective optimization engine and the NSGA-III algorithm, the present invention can balance optimization among multiple objectives, such as reducing material waste, improving production efficiency and improving the quality of the final product. This optimization capability significantly improves the efficiency and stability of production and reduces the cost of experiments and debugging.

[0021] Through the extrusion quality control method of the present invention, abnormal phenomena in the production process can be discovered and corrected in time, avoiding waste due to quality problems. In addition, the present invention improves the utilization rate of materials and reduces production costs through precise control of the extrusion process. This is particularly important for fields such as 3D printing and film manufacturing of polymer materials, and can greatly improve the performance stability of products and reduce the occurrence of defective products. Therefore, the extrusion quality control method and device of the present invention, through the combination of multimodal sensors, dynamic feedback control and intelligent algorithms, realizes precise control of the extrusion process, real-time defect detection and adaptive adjustment, significantly improves production efficiency, product quality and material utilization, reduces scrap rate and cost, and has broad industrial application prospects.

[0022] These and other aspects of the present application will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for the exemplary embodiments or related technical descriptions. The drawings are used to provide a further understanding of the present invention and constitute part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings: Figure 1 The present invention is a flowchart of a method for extrusion quality control according to an embodiment of the present invention.

[0024] Figure 2 The present invention is a flowchart of a method for extrusion quality control according to a further embodiment of the present invention. DETAILED DESCRIPTION

[0025] Below, the present application is further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0026] To make the purpose, technical solutions and advantages of the present invention more clearly understood, the following is a further detailed description of the embodiments of the present invention in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0027] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are intended to distinguish two non-identical entities or non-identical parameters with the same name. Therefore, "first" and "second" are used for convenience of expression only and should not be understood as limitations on the embodiments of the present invention. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, other steps or units inherent to a process, method, system, product, or device that includes a series of steps or units.

[0028] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0029] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0030] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0031] Since current extrusion quality control methods have problems such as thermal imaging occlusion and insufficient spatial resolution, slow defect detection response, and single process parameter optimization, the present invention proposes a method and device for extrusion quality control. By combining multimodal sensors, embedded edge computing and dynamic feedback control technology, a breakthrough extrusion quality control solution is provided. This solution not only solves the defects of the existing technology, improves the thermal imaging resolution and defect detection response speed, but also greatly improves process accuracy and production efficiency through multivariable optimization and adaptive control.

[0032] See also Figure 1 As shown, an embodiment of the present invention provides a method for extrusion quality control, the method comprising the following steps: Step S10: Using a ring array multispectral thermal imaging module to monitor the thermal field distribution during the extrusion process in real time.

[0033] In this step, the thermal imaging module consists of at least six groups of macro thermal imagers, each equipped with short-wave infrared (SWIR) and medium-wave infrared (MWIR) dual spectral channels, symmetrically distributed around the axis of the extrusion nozzle, and dynamically adjusts the distance from the deposition layer through a hydraulically driven telescopic mechanism, making the spatial resolution adaptive.

[0034] During the extrusion process, a ring-shaped multispectral thermal imaging module is first used to monitor the extrusion nozzle in real time. This thermal imaging module consists of at least six sets of macro thermal imagers, each equipped with dual spectral channels for shortwave infrared (SWIR) and mediumwave infrared (MWIR), and is symmetrically distributed around the extrusion nozzle. Each set of thermal imagers uses a hydraulically driven telescopic mechanism to dynamically adjust its distance from the deposition layer to accommodate variations in the deposition layer, ensuring high spatial resolution and achieving adaptive thermal imaging.

[0035] Step S20: Compensating the displacement of the thermal imager during the movement of the nozzle by using a laser-assisted positioning system, so that the thermal imaging image is strictly synchronized with the axis of the extrusion nozzle.

[0036] In this step, the three-dimensional dynamic reconstruction includes parallax compensation and point cloud registration steps. The point cloud registration uses an improved ICP point cloud registration algorithm. The update frequency of the reconstructed three-dimensional temperature field is at least 30 Hz.

[0037] Because the extrusion nozzle moves during the production process, a laser-assisted positioning system is used to compensate for the thermal imager's displacement to ensure the accuracy of the thermal imaging data. The laser-assisted system corrects the thermal image in real time, ensuring that it is always strictly synchronized with the nozzle axis. The thermal imaging data is then processed using 3D dynamic reconstruction technology to generate a 3D temperature field. This process includes: Parallax compensation: eliminates image deviation caused by changes in camera position; Point cloud registration: An improved ICP point cloud registration algorithm is used to achieve accurate 3D temperature field reconstruction, with an update frequency of at least 30Hz to ensure the timeliness of temperature data.

[0038] The occluded areas in the thermal imaging data are repaired using a transfer learning framework to ensure the continuity and accuracy of the temperature field.

[0039] Step S30: Process the thermal imaging data through three-dimensional dynamic reconstruction to generate a three-dimensional temperature field, and use the transfer learning framework to repair the occluded areas in the thermal imaging data.

[0040] In some embodiments, see Figure 2 As shown, the method for extrusion quality control further includes the following steps: Step S11: using an embedded multi-physics field sensor array to monitor melt pressure, temperature gradient, and shear rate during the extrusion process, wherein the sensor array includes a fiber Bragg grating (FBG) sensor, a flexible piezoelectric film array, and a microwave dielectric spectrum online detection module; Step S12: using the fiber Bragg grating sensor to monitor the melt pressure (0-50 MPa), temperature gradient (±0.1°C) and shear rate in real time, and detecting microcracks below the deposited layer through a piezoelectric film array; Step S13: analyzing the crystallinity and molecular orientation of the material through a microwave dielectric spectroscopy online detection module.

[0041] The frequency range of the microwave dielectric spectrum online detection module is 1-10 GHz, and the data collected by the sensor array is used together with the thermal imaging data for defect detection and feature extraction.

[0042] During the extrusion process, an embedded multi-physics field sensing array is used, including fiber Bragg grating (FBG) sensors, flexible piezoelectric film arrays, and microwave dielectric spectrum online detection modules. These sensors monitor the melt's pressure, temperature gradient, shear rate, and other physical quantities: Fiber Bragg Grating (FBG) sensor: real-time monitoring of melt pressure (range: 0-50MPa), temperature gradient (±0.1°C) and shear rate; Flexible piezoelectric film arrays: Detect microcracks beneath the deposited layer to ensure structural integrity; Microwave Dielectric Spectroscopy Online Detection Module: Analyzes the crystallinity and molecular orientation of materials. Operating in the 1-10 GHz frequency range, this module is used to accurately assess the physical properties of materials.

[0043] The data collected by these sensors is used together with thermal imaging data for defect detection and feature extraction. A multi-scale feature pyramid network (FPN) is used to simultaneously process thermal imaging, acoustic emission, and dielectric spectroscopy data to extract key defect characteristics such as interlayer bonding strength, porosity, and crystallinity anomalies.

[0044] In some embodiments, the method for extrusion quality control further comprises: Use a multi-scale feature pyramid network (FPN) to simultaneously process thermal imaging, acoustic emission, and dielectric spectroscopy data to extract defect features such as interlayer bonding strength, porosity, and crystallinity anomalies. A defect propagation model is constructed using graph neural networks to predict the potential defect types and locations of the next few deposition layers based on current process parameters.

[0045] Among them, the defect propagation model predicts defect types including cracks, pores and delamination through graph neural networks, and gives the defect location and severity during real-time monitoring.

[0046] In some embodiments, a multi-objective optimization engine is established using a response surface model to optimize multiple process parameters during the production process. The process parameters optimized by the engine include extrusion speed, temperature, pressure, etc., and the NSGA-III algorithm is used to find a Pareto optimal solution set in the multi-objective space to balance various process objectives, such as quality, efficiency, and cost. The extrusion quality control method further includes the following steps: Establishing a multi-objective optimization engine based on the response surface model to optimize multiple process parameters, including but not limited to extrusion speed, temperature, and pressure; Use NSGA-III to find the Pareto optimal solution set in the multi-objective space to achieve balanced optimization of different process objectives; Use the digital twin system to preview the adjustment effects of different process parameters in virtual space and predict the effects in actual production, thereby reducing trial and error costs.

[0047] As a further solution of the present invention, the digital twin system simulates the extrusion process in real time, and dynamically adjusts the extrusion temperature and pressure parameters based on changes in process parameters to optimize the quality stability during the production process.

[0048] Furthermore, the system uses a digital twin system to simulate the impact of different process parameters on the production process in virtual space. By previewing the effects of adjustments, it can predict actual production changes, reducing trial and error costs and improving production efficiency. The digital twin system can simulate the extrusion process in real time and dynamically adjust control parameters such as temperature and pressure based on changes in process parameters, further optimizing quality stability during production.

[0049] As a further embodiment of the present invention, the method for extrusion quality control further comprises the following steps: Use adaptive PID-MPC hybrid controller to control temperature and pressure during extrusion; The PID-MPC hybrid controller optimizes the temperature control of the heating section through model predictive control (MPC) and dynamically adjusts the extrusion speed in combination with the fuzzy PID algorithm to ensure a response time of no more than 50ms. Among them, the MPC controller performs rolling time domain optimization control based on the real-time feedback data of the current temperature field and pressure field, eliminates the coupling interference between multiple heating sections, and ensures the precise adjustment and stability of process parameters. This extrusion quality control method is applied to the 3D printing process of polymer materials, which can effectively improve printing accuracy, reduce the standard deviation of interlayer bonding strength and material waste rate, and has high industrial application value.

[0050] This invention incorporates an adaptive PID-MPC hybrid controller to precisely control temperature and pressure during the extrusion process. This controller employs model predictive control (MPC) to optimize temperature control in the heating section and dynamically adjusts the extrusion speed using a fuzzy PID algorithm, ensuring a system response time of no more than 50ms. Based on real-time feedback data (temperature and pressure fields), the MPC controller optimizes control within a rolling time domain, eliminating coupling interference between multiple heating sections and precisely adjusting process parameters. This control approach ensures precise and stable regulation of temperature and pressure, effectively improving the stability and consistency of extrusion quality during production.

[0051] The present invention provides a highly integrated extrusion quality control method. By combining multiple sensors and a control system, it is able to monitor and adjust various physical quantities during the extrusion process in real time, ensuring the quality stability of the material. During the extrusion process, the use of a ring array thermal imaging module, an embedded sensor array, three-dimensional dynamic reconstruction technology, a defect propagation prediction model, and other technical means, combined with a digital twin system and adaptive control strategy, can significantly improve production efficiency, reduce material waste, and ensure the quality and precision of the final product. This method is particularly suitable for high-precision manufacturing fields such as 3D printing of polymer materials and has broad industrial application value.

[0052] It should be noted that the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0053] It should be understood that, although the above is described in a certain order, these steps are not necessarily performed in sequence according to the above order. Unless clearly stated herein, the execution of these steps does not have strict order restrictions, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.

[0054] According to a second aspect of the embodiments of the present invention, the present invention further provides an extrusion quality control device, comprising: A ring-shaped multispectral thermal imaging module is used to monitor the thermal field distribution during the extrusion process in real time. The module consists of at least six groups of macro thermal imagers, each equipped with short-wave infrared (SWIR) and medium-wave infrared (MWIR) dual spectral channels. These are symmetrically distributed around the axis of the extrusion nozzle and dynamically adjust the distance between the thermal imagers and the deposited layer through a hydraulically driven telescopic mechanism, making the spatial resolution adaptive. Laser-assisted positioning system, used to compensate for the displacement of the thermal imager during nozzle movement, ensuring that the thermal image is strictly synchronized with the extrusion nozzle axis; A data processing unit is used to receive and process the thermal imaging data from the thermal imaging module, generate a three-dimensional temperature field using a three-dimensional dynamic reconstruction algorithm, perform parallax compensation and point cloud registration, and use a transfer learning framework to repair occluded areas in the thermal imaging data.

[0055] When selecting the hardware, six sets of FLIR Lepton 3.5 macro thermal imagers were used, with short-wave infrared (SWIR) 1.5-2.5μm and medium-wave infrared (MWIR) 3-5μm, symmetrically distributed around the axis of the 3D printing nozzle at 120° intervals. For dynamic focusing, an integrated hydraulic drive slide (stroke 0.5-3mm) combined with a laser positioning system (wavelength 905nm, accuracy ±0.01mm) compensates for nozzle movement offset in real time, achieving a spatial resolution of 5μm / pixel. For data fusion, thermal images and RGB images are collected synchronously, and the nozzle occlusion area is repaired through a transfer learning framework (pre-trained U-Net network), improving the accuracy by 42%.

[0056] In this embodiment, the extrusion quality control device further comprises: An embedded multi-physics sensor array for monitoring melt pressure, temperature gradient, and shear rate. The sensor array includes a fiber Bragg grating (FBG) sensor, a flexible piezoelectric film array, and a microwave dielectric spectrum online detection module. The data acquisition and processing unit is connected to the embedded multi-physics field sensor array, collects sensor data in real time and performs defect detection and feature extraction together with thermal imaging data.

[0057] During melt monitoring, a micro FBG sensor is integrated inside the nozzle (0-50MPa pressure monitoring, ±0.1MPa accuracy; temperature gradient ±0.1°C), and a flexible PVDF piezoelectric film array detects interlayer microcracks (sensitivity 10μm level). During material state analysis, a microwave dielectric spectroscopy module (1-10GHz) online analyzes the crystallinity (error <3%) and molecular orientation of the PLA material, and generates a crystallinity-temperature correlation curve based on thermal imaging data.

[0058] In this embodiment, the extrusion quality control device further comprises: A multi-objective optimization engine for optimizing multiple process parameters, including but not limited to extrusion speed, temperature, and pressure; Response surface model, used to generate multi-objective optimization solutions based on process parameter optimization results; The digital twin system is connected to the optimization engine and is used to simulate the influence of different process parameters on the extrusion process in a virtual space and adjust the actual process parameters in production according to the simulation results.

[0059] In this embodiment, the extrusion quality control device further comprises: Adaptive PID-MPC hybrid controller for controlling temperature and pressure during extrusion; Model Predictive Control (MPC) unit, used to optimize the temperature control of the heating section, and dynamically adjust the extrusion speed in combination with the fuzzy PID algorithm to ensure a response time of no more than 50ms; The pressure regulating unit is used to automatically adjust the extrusion pressure according to real-time feedback data to ensure accurate adjustment of process parameters.

[0060] Through the above detailed steps, the extrusion quality control device of the present invention is used to execute the steps of the extrusion quality control method in the above embodiment, which will not be repeated here. The extrusion quality control device of the present invention is particularly suitable for the 3D printing process of polymer materials. Through real-time monitoring and optimization control, the printing accuracy can be significantly improved, the standard deviation of the interlayer bonding strength can be reduced, and the material waste rate can be reduced. Especially in high-precision 3D printing, through intelligent quality control, the printing quality and material utilization efficiency are greatly improved, and it has significant industrial application value.

[0061] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope of the embodiments disclosed in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless expressly limited to the singular.

[0062] It should be understood that, as used herein, the singular form "a" or "an" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations of one or more of the items listed in association. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0063] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to limit the scope of the disclosure of the present invention (including the claims) to these examples. Within the spirit of the present invention, the technical features of the above embodiments or different embodiments may be combined, and many other variations exist in different aspects of the above embodiments, which are not provided in detail for the sake of clarity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for extrusion quality control, characterized in that, The method comprises the following steps: Use a ring array multi-spectral thermal imaging module to monitor the thermal field distribution during the extrusion process in real time; The laser-assisted positioning system compensates for the displacement of the thermal imager during nozzle movement, ensuring that the thermal imaging image is strictly synchronized with the extrusion nozzle axis. The thermal imaging data is processed through three-dimensional dynamic reconstruction to generate a three-dimensional temperature field, and the occluded areas in the thermal imaging data are repaired using a transfer learning framework.

2. The method for extrusion quality control according to claim 1, wherein: The thermal imaging module consists of at least six groups of macro thermal imagers, each equipped with short-wave infrared and medium-wave infrared dual spectral channels, symmetrically distributed around the axis of the extrusion nozzle, and dynamically adjusts the distance from the deposition layer through a hydraulically driven telescopic mechanism, making the spatial resolution adaptive.

3. The method for extrusion quality control according to claim 2, wherein: The three-dimensional dynamic reconstruction includes parallax compensation and point cloud registration steps. The point cloud registration uses an improved ICP point cloud registration algorithm. The update frequency of the reconstructed three-dimensional temperature field is at least 30 Hz.

4. The method for extrusion quality control according to claim 1, wherein: The method for extrusion quality control further comprises the following steps: Use an embedded multi-physics field sensor array to monitor melt pressure, temperature gradient, and shear rate during extrusion, wherein the sensor array includes a fiber Bragg grating sensor, a flexible piezoelectric film array, and a microwave dielectric spectrum online detection module; The fiber Bragg grating sensor is used to monitor the melt pressure, temperature gradient and shear rate in real time, and the piezoelectric film array is used to detect microcracks under the deposited layer; The crystallinity and molecular orientation of the material are analyzed through the microwave dielectric spectroscopy online detection module.

5. The method for extrusion quality control according to claim 4, wherein: The frequency range of the microwave dielectric spectrum online detection module is 1-10 GHz, and the data collected by the sensor array is used together with the thermal imaging data for defect detection and feature extraction.

6. The method for extrusion quality control according to claim 4, wherein: The method for extrusion quality control also includes: A multi-scale feature pyramid network is used to simultaneously process thermal imaging, acoustic emission, and dielectric spectroscopy data to extract defect features such as interlayer bonding strength, porosity, and crystallinity anomalies. A defect propagation model is constructed using graph neural networks to predict the potential defect types and locations of the next few deposition layers based on current process parameters.

7. The method for extrusion quality control according to claim 6, wherein: The defect propagation model predicts defect types including cracks, pores, and delamination through graph neural networks, and provides the defect location and severity during real-time monitoring.

8. The method for extrusion quality control according to claim 6, wherein: The method for extrusion quality control further comprises the following steps: Establishing a multi-objective optimization engine based on the response surface model to optimize multiple process parameters, including but not limited to extrusion speed, temperature, and pressure; Use NSGA-III to find the Pareto optimal solution set in the multi-objective space to achieve balanced optimization of different process objectives; Use the digital twin system to preview the adjustment effects of different process parameters in virtual space and predict the effects in actual production, thereby reducing trial and error costs.

9. The method for extrusion quality control according to claim 8, wherein: The method for extrusion quality control further comprises the following steps: Use adaptive PID-MPC hybrid controller to control temperature and pressure during extrusion; The PID-MPC hybrid controller optimizes the temperature control of the heating section through model predictive control and dynamically adjusts the extrusion speed in combination with the fuzzy PID algorithm to ensure that the response time does not exceed 50ms.

10. An extrusion quality control device, characterized in that: A method for performing extrusion quality control according to any one of claims 1 to 9, the device comprising: A ring-shaped multispectral thermal imaging module is used to monitor the thermal field distribution during the extrusion process in real time. The module consists of at least six groups of macro thermal imagers, each equipped with short-wave infrared and medium-wave infrared dual-spectral channels. These groups are symmetrically distributed around the axis of the extrusion nozzle. A hydraulically driven telescopic mechanism dynamically adjusts the distance between the thermal imagers and the deposited layer, making the spatial resolution adaptive. Laser-assisted positioning system, used to compensate for the displacement of the thermal imager during nozzle movement, ensuring that the thermal image is strictly synchronized with the extrusion nozzle axis; A data processing unit is used to receive and process the thermal imaging data from the thermal imaging module, generate a three-dimensional temperature field using a three-dimensional dynamic reconstruction algorithm, perform parallax compensation and point cloud registration, and use a transfer learning framework to repair occluded areas in the thermal imaging data.

Images