Device and method for monitoring quality of FDM 3D printing

Abstract

The invention provides an FDM 3D printing quality monitoring device and method, and relates to the technical field of 3D printing, the device comprises a multispectral sensor module, a dynamic calibration module, an edge calculation module, a multi-parameter cooperative execution mechanism and an emergency intervention module, the multispectral sensor module is used for collecting multispectral sensor data of the surface appearance, the temperature field and the microscopic layer thickness distribution of the printing wire in real time; surface topography data collected by a laser microspur scanner is used for correcting illumination distortion of visible light camera images, measurement errors caused by thermal expansion of materials are dynamically compensated based on temperature field data provided by an infrared thermal imager, and defects are detected and printed in a classified mode in real time. Printing parameters of the extrusion rate, the nozzle temperature and the platform moving speed are calculated and dynamically adjusted in real time; the six-axis linkage motion platform regulates and controls rotation of the spray head and inclination of the platform, a control instruction is responded in real time, support-free printing of a complex curved surface is supported, and therefore the printing quality is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of 3D printing, and particularly to an apparatus and method for monitoring the quality of FDM 3D printing. Background Art

[0002] FDM (Fused Deposition Modeling) 3D printing technology is a commonly used additive manufacturing method, which is widely applied in fields such as prototyping, medical devices, and aerospace. Although the FDM technology has great advantages in rapid manufacturing, it still faces many technical challenges, especially in the control and optimization of printing quality. Most existing FDM printing devices rely on static control parameters and lack comprehensive monitoring and adjustment of various factors (such as temperature, interlayer adhesion, surface quality, etc.) during the real-time printing process.

[0003] The existing FDM 3D printing technology has the following problems: 1. Lack of real-time quality monitoring: Existing technologies can usually only check the results after printing is completed, and it is difficult to detect and adjust defects in the printing process in real time. In this way, if problems occur during the printing process (such as nozzle clogging, material breakage, or layer misalignment), it may affect the printing quality and even lead to printing failure.

[0004] 2. Limited sensor information: Traditional FDM printers generally use simple sensors, such as temperature sensors and position sensors, but the data of these sensors is not comprehensive enough to accurately detect key information such as the temperature distribution of the printing filament, microscopic deformation, and surface defects.

[0005] 3. Lag in adjusting printing parameters: Traditional FDM printers usually cannot automatically adjust printing parameters (such as nozzle temperature, extrusion rate, etc.) according to real-time conditions during the printing process. The influence of changes in the external environment (such as fluctuations in temperature and humidity) on the printing quality often cannot be compensated in a timely manner. 4. Lack of self-repair mechanism: The current FDM printing technology often cannot automatically repair faults that occur (such as nozzle clogging or material breakage). Once a problem occurs, manual intervention is usually required to resume the printing process.

[0006] In order to solve the above problems, there is an urgent need for an FDM 3D printing quality monitoring system based on advanced sensing technology and adaptive control algorithms to improve printing quality, reduce waste, increase the printing success rate, and be able to cope with various environmental changes and faults. Summary of the Invention

[0007] In view of this, the purpose of the present invention is to propose an apparatus and method for monitoring the quality of FDM 3D printing, which can detect, monitor, and adjust printing parameters in real time during the printing process, thereby effectively improving printing quality, reducing the occurrence of faults, and providing self-repair capabilities.

[0008] To achieve the above object, the present invention provides the following technical solutions: Based on the above object, in a first aspect, the present invention provides a device for monitoring the quality of FDM 3D printing, including the following components: A multispectral sensor module, which includes a visible light camera, an infrared thermal imager, and a laser macro scanner, and is used to collect the surface topography of the printing filament in real time, monitor the temperature field of the printing area in real time, and collect the microscopic layer thickness distribution data of the printing filament; A dynamic calibration module, which is used to correct the illumination distortion of the visible light image with the laser scanning data, and compensate for the measurement error caused by the thermal expansion of the material based on the thermal imaging data, so as to ensure the consistency and accuracy of the multi-sensor data; An edge computing module, which is used to deploy a lightweight neural network model, perform real-time fusion analysis on the data collected by the multispectral sensor module in real time, generate control instructions, and identify defects that occur during the printing process in real time; A multi-parameter collaborative actuator, which includes a motor speed control module, a nozzle temperature PID controller, and a six-axis motion platform, supports nozzle rotation and platform tilting, and performs support-free printing of complex curved surfaces; An emergency intervention module, which includes a piezoelectric ceramic vibrator, and is used to start the high-frequency oscillation nozzle when detecting the risk of nozzle clogging, and synchronously reduce the extrusion pressure to avoid material accumulation.

[0009] As a further solution of the present invention, the accuracy of the visible light camera for collecting the surface topography of the printing filament in real time is ±0.02 mm; the working band of the infrared thermal imager is 8-14 μm, the spatial resolution is ≤0.1 mm / pixel, the frame rate is ≥60 Hz, and the temperature resolution for monitoring the temperature field of the printing area in real time is ±1 °C.

[0010] As a further solution of the present invention, the edge computing module integrates a dynamic focusing unit, predicts the moving trajectory of the nozzle according to the printing path, and adjusts the sensor focal length in advance to ensure the clarity and accuracy of image acquisition; a YOLOv5s network after transfer learning is deployed in the edge computing module to identify 12 common printing defects that occur during the printing process in real time, such as broken filaments, bubbles, layer misalignment, etc., and the recognition accuracy is ≥98%.

[0011] As a further solution of the present invention, the six-axis motion platform supports nozzle rotation of ±180° and platform tilting of ±30°.

[0012] As a further aspect of the present invention, the multi-parameter collaborative actuator includes a piezoelectric ceramic vibrator that can clear nozzle blockages and resume printing within 0.1 second, ensuring the continuity and efficiency during the printing process; the multi-parameter collaborative actuator supports a fully automated nozzle self-calibration mechanism, including an automatic detection and adjustment unit for nozzle position, ensuring the precise positioning and stable operation of the nozzle during the printing process.

[0013] As a further aspect of the present invention, the multi-parameter collaborative actuator integrates a piezoelectric ceramic vibrator for clearing nozzle blockages and resuming printing within 0.1 second, ensuring continuity and error-free during the printing process.

[0014] As a further aspect of the present invention, the device for monitoring the quality of FDM 3D printing supports co-extrusion printing of multiple materials, uses laser-induced graphene for directional alignment, realizes local thermal conductivity regulation, and thus optimizes the printing effects and performance of different materials.

[0015] As a further aspect of the present invention, the device for monitoring the quality of FDM 3D printing further includes a cloud collaborative learning module that aggregates the operation data of multiple devices through federated learning, continuously optimizes the global regulation strategy, and realizes cross-device quality management and improvement.

[0016] As a further aspect of the present invention, the laser macro scanner in the multi-spectral sensor module has an accuracy of ±0.01 mm, and is used to accurately capture the detailed changes in the microscopic layer thickness.

[0017] In a second aspect, the present invention also provides a method for monitoring the quality of FDM 3D printing, including the following steps: By deploying a visible light camera, an infrared thermal imager, and a laser macro scanner on the side of the printing nozzle, multi-spectral sensor data of the surface topography, temperature field, and microscopic layer thickness distribution of the printing filament are collected in real time; Using the surface topography data collected by the laser macro scanner to correct the illumination distortion of the visible light camera image, and based on the temperature field data provided by the infrared thermal imager, dynamically compensate for the measurement error caused by the thermal expansion of the material; Through a lightweight neural network model in the edge computing unit, feature fusion is performed on the multi-spectral data, printing defects are detected and classified in real time, and printing parameters such as the extrusion rate, nozzle temperature, and platform movement speed are calculated and dynamically adjusted in real time by combining particle swarm optimization and PID control; Regulate the rotation of the nozzle and the tilt of the platform through a six-axis linkage motion platform, respond to control commands in real time, and support the printing of complex curved surfaces without supports; When a nozzle blockage risk is detected, start the piezoelectric ceramic vibrator to oscillate the nozzle at high frequency and simultaneously reduce the extrusion pressure to prevent material accumulation.

[0018] As a further solution of the present invention, the working band of the infrared thermal imager is 8 - 14 μm, with a spatial resolution ≤ 0.1 mm / pixel and a frame rate ≥ 60 Hz, which is used to monitor the temperature field of the printing area in real time to ensure the temperature control accuracy.

[0019] Compared with the prior art, a device and method for monitoring the quality of FDM 3D printing proposed by the present invention have the following beneficial effects: 1. Precision improvement: Through multi-spectral fusion perception and dynamic calibration mechanism, the control precision of the printing filament width is significantly improved, from ±0.1 mm to ±0.03 mm, and the interlayer bonding strength is increased by 30% at the same time.

[0020] 2. Material adaptability expansion: It supports the printing of full-spectrum materials such as PLA to graphene composite materials (thermal conductivity > 200 W / m·K), meets the needs of different fields, and is especially suitable for the printing of complex components with high thermal conductivity and high strength requirements.

[0021] 3. Energy consumption optimization: By adopting the technology of dynamic matching of the thermal field, it can effectively reduce the ineffective energy consumption of the heating module, and the energy-saving effect reaches 25%.

[0022] 4. Quality control precision and real-time performance: Through accurate sensor data acquisition and real-time feedback mechanism, the system can respond and adjust the printing parameters within a time shorter than 0.15 seconds to ensure the high-precision control of the printing process.

[0023] 5. Automation and self-adaptability: The system can automatically detect and repair the defects that may occur during the printing process, reduce manual intervention, and improve the production efficiency and printing success rate.

[0024] 6. Intelligent decision-making and optimization: Combining the YOLOv5s network and the particle swarm optimization algorithm, the system can identify various printing defects in real time and precisely control various parameters during the printing process to further optimize the printing quality.

[0025] The device is applicable to high-value-added fields such as aerospace, precision medical devices, complex biological printing, etc., providing a strong technical guarantee for the printing process with high quality requirements.

[0026] These aspects or 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 only exemplary and explanatory, and cannot limit the present application. Brief Description of the Drawings

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the related art, the following will briefly introduce the drawings required for the description of the exemplary embodiments or the related art. The drawings are used to provide a further understanding of the present invention and constitute a 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 to the present invention. In the drawings: Figure 1 It is a structural block diagram of a device for monitoring the quality of FDM 3D printing according to an embodiment of the present invention.

[0028] Figure 2 It is a flowchart of a method for monitoring the quality of FDM 3D printing according to an embodiment of the present invention. Detailed implementation manners

[0029] Next, in combination with the drawings and the specific implementation manners, the present application will be further described. It should be noted that, on the premise of no conflict, the following-described embodiments or technical features can be combined arbitrarily to form new embodiments.

[0030] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following will further elaborate on the embodiments of the present invention in detail with reference to the specific embodiments and the drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0031] It should be noted that all the expressions using "first" and "second" in the embodiments of the present invention are used to distinguish two non-identical entities or non-identical parameters with the same name. It can be seen that "first" and "second" are only for the convenience of expression and should not be construed as a limitation to the embodiments of the present invention. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units inherently includes other steps or units.

[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0033] The flowchart shown in the drawings is only an example illustration and does not necessarily include all the content and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, combined, or partially merged. Therefore, the actual execution order may change according to the actual situation.

[0034] The following will, in conjunction with the accompanying drawings, elaborate on some embodiments of the present application. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0035] Due to the problems of the existing FDM 3D printing technology, such as the lack of real-time quality monitoring, limited sensor information, lag in adjusting printing parameters, and lack of self-repair mechanism, the present invention proposes a device and method for monitoring the quality of FDM 3D printing, so as to improve the printing quality, reduce waste, increase the printing success rate, and be able to cope with various environmental changes and failures. The present invention can detect, monitor, and adjust printing parameters in real time during the printing process, thereby effectively improving the printing quality, reducing the occurrence of failures, and providing self-repair ability.

[0036] See Figure 1 As shown, an embodiment of the present invention provides a device for monitoring the quality of FDM 3D printing. The device includes a multispectral sensor module 100, a dynamic calibration module 200, an edge computing module 300, a multi-parameter collaborative actuator 400, and an emergency intervention module 500. The multispectral sensor module 100 includes a visible light camera 101, an infrared thermal imager 102, and a laser macro scanner 103, which are used to collect the surface topography of the printing filament in real time, monitor the temperature field of the printing area in real time, and collect data on the microscopic layer thickness distribution of the printing filament.

[0037] In this embodiment, the visible light camera 101 is equipped with a 12-megapixel CMOS sensor, with a resolution of 2592×1944, supporting macro shooting. When the working distance is 50 mm, the resolution accuracy of the visible light camera 101 for collecting the surface topography of the printing filament in real time is ±0.02 mm. When printing PLA material, surface ripples at the 0.1 mm level can be captured.

[0038] The working band of the infrared thermal imager 102 is 8 - 14 μm, the spatial resolution ≤0.1 mm / pixel, and the frame rate ≥60 Hz. The infrared thermal imager 102 uses a non-cooled detector. The 8 - 14 μm band covers the infrared radiation characteristics of common polymer materials. The temperature resolution for monitoring the temperature field of the printing area in real time is ±1℃. Taking PEEK printing as an example, its melting temperature window is 370 - 400℃, and the thermal imager can monitor the nozzle temperature gradient (±1℃) in real time to avoid carbonization of the material caused by local overheating.

[0039] The laser macro scanner 103 realizes continuous measurement of the layer thickness of 0.05 - 0.3 mm through the projection of a laser with a wavelength of 905 nm and CMOS reception. When printing a porous scaffold, layer collapse caused by material shrinkage can be detected.

[0040] Taking the printing of carbon fiber reinforced nylon (PA6-CF) as an example, the visible light camera 101 detects stripes on the surface, and infrared thermal imaging finds that the temperature on the right side of the nozzle is abnormal: locally reaching 220°C, exceeding the set value by ±5°C. The laser scanner identifies layer thickness fluctuations, and the layer thickness suddenly increases to 0.25 mm. After fusing the three sets of data, it is determined that the material feeding is uneven, and the actuator is triggered to adjust the extrusion pressure.

[0041] The dynamic calibration module 200 is used to correct the illumination distortion of the visible light image with the laser scan data and compensate for the measurement error caused by the thermal expansion of the material based on the thermal imaging data to ensure the consistency and accuracy of the multi-sensor data. In this embodiment, when the dynamic calibration module 200 performs illumination distortion correction, a checkerboard calibration board (20×20 mm, 50 mm spacing) is used to perform geometric correction on the visible light camera 101. For example, when the nozzle moves to the edge of the hot bed, the ambient light reflection causes uneven image brightness, which is corrected by the adaptive histogram equalization algorithm (CLAHE) to ensure the consistency of the surface topography data. When the dynamic calibration module 200 performs thermal expansion compensation, a material thermal expansion model is established based on ANSYS simulation (such as the linear expansion coefficient of PLA is 6×10-5 / °C). When the infrared detects a change in the ambient temperature of ±2°C, the layer thickness measurement value is automatically compensated. For example, when printing a titanium alloy support structure, the temperature rise causes the support layer to expand by 0.03 mm, and the actual layer thickness error is controlled within ±0.01 mm after compensation.

[0042] Taking the printing of superalloy Inconel 718 as an example, the nozzle temperature rises to 420°C, and the thermal expansion reduces the distance between the nozzle and the hot bed by 0.05 mm. The dynamic calibration module 200 calculates the compensation value according to the thermal expansion coefficient (12×10 -6 / °C) and adjusts the initial position of the Z-axis to avoid adhesion failure caused by over-extrusion in the first layer.

[0043] The edge computing module 300 is used to deploy a lightweight neural network model, perform real-time fusion analysis on the data collected in real time by the multi-spectral sensor module 100, generate control commands, and identify defects that occur during the printing process in real time.

[0044] In this embodiment, the edge computing module 300 integrates a dynamic focusing unit 301, predicts the movement trajectory of the nozzle according to the printing path, and adjusts the sensor focal length in advance to ensure the clarity and accuracy of image acquisition; a YOLOv5s network after transfer learning is deployed in the edge computing module 300 to identify 12 common printing defects that occur during the printing process in real time, such as filament breakage, bubbles, layer misalignment, etc., and the recognition accuracy rate is ≥98%.

[0045] Among them, the dynamic focusing unit 301 integrates a liquid lens (MT-26AUJ) driven by a stepper motor, with a focal length adjustment range of 50 - 200 mm and a response time < 50 ms. For example, when the nozzle prints along a spiral path, the focal point position is predicted 0.2 seconds in advance to ensure clear images in the curved surface area. When performing transfer learning in the edge computing module 300 with the YOLOv5s network after transfer learning, 2000 labeled datasets (including 12 types of defects such as wire breakage, bubbles, and layer misalignment) are used for fine-tuning. The input size of the model is 640×640, and the mAP@0.5 reaches 98.3%. For example, when printing TPU flexible components, bubbles of 0.5 mm² can be identified (confidence > 0.9), and a speed reduction instruction (from 60 mm / s to 20 mm / s) is triggered to fill the defect.

[0046] Taking the printing of medical-grade 316L stainless steel bone nails as an example, when the YOLO model detects layer misalignment (displacement > 0.1 mm), the edge computing unit immediately sends a G-code instruction to pause the printing, and calls historical data to match similar faults (such as nozzle offset), and recommends adjusting the XY-axis synchronous error compensation parameters.

[0047] The multi-parameter collaborative actuator 400 includes a motor speed regulation module 401, a nozzle temperature PID controller 402, and a six-axis motion platform 403, which supports nozzle rotation and platform tilting for unsupported printing of complex curved surfaces. In this embodiment, the multi-parameter collaborative actuator 400 includes a piezoelectric ceramic vibrator 501 that can clear nozzle blockage and resume printing within 0.1 second to ensure the continuity and efficiency of the printing process; the multi-parameter collaborative actuator 400 supports a fully automated nozzle self-calibration mechanism, including an automatic detection and adjustment unit for nozzle position to ensure accurate positioning and stable operation of the nozzle during the printing process. Among them, the six-axis motion platform 403 supports nozzle rotation of ±180° and platform tilting of ±30°. The multi-parameter collaborative actuator 400 integrates a piezoelectric ceramic vibrator 501 for clearing nozzle blockage and resuming printing within 0.1 second to ensure continuity and error-free during the printing process.

[0048] The emergency intervention module 500 includes a piezoelectric ceramic vibrator 501, which is used to start high-frequency oscillation of the nozzle when a nozzle blockage risk is detected, and simultaneously reduce the extrusion pressure to avoid material accumulation. Among them, the piezoelectric ceramic vibrator 501 uses PZT-5H material, with a vibration frequency of 20 - 200 kHz and an amplitude of ±5 μm. When a nozzle blockage risk occurs, high-frequency vibration is started within 0.1 second, combined with the feedback of the pressure sensor, with an accuracy of ±0.1 MPa, to achieve closed-loop control. For example, when printing carbon fiber composite materials, 0.05 seconds before nozzle blockage, an abnormal torque (> 8 N·m) is detected, the vibrator is started and the extrusion pressure is simultaneously reduced from 12 MPa to 8 MPa, and the material flow is restored within 3 seconds.

[0049] For example, when printing a titanium alloy impeller for aerospace, the six-axis platform is tilted by 25°, and the nozzle rotates by 150°, and support-free printing is achieved with the assistance of centrifugal force. During the process, when the laser scanner detects uneven layer thickness, the edge computing module 300 sends an instruction to adjust the nozzle rotation speed (from 1200 rpm to 1000 rpm), and at the same time, the PID controller raises the hot bed temperature from 60 °C to 65 °C to enhance the interlayer bonding force.

[0050] In this embodiment, the device for monitoring the quality of FDM 3D printing supports co-extrusion printing of multiple materials, and uses laser-induced graphene for directional alignment to achieve local regulation of the thermal conductivity coefficient, thereby optimizing the printing effects and performance of different materials. The device for monitoring the quality of FDM 3D printing further includes a cloud collaborative learning module, which aggregates the operation data of multiple devices through federated learning, continuously optimizes the global regulation strategy, and realizes cross-device quality management and improvement. The laser macro scanner 103 in the multispectral sensor module 100 has an accuracy of ±0.01 mm, and is used to accurately capture the detailed changes in the microscopic layer thickness.

[0051] See Figure 2 As shown, the embodiment of the present invention further provides a method for monitoring the quality of FDM 3D printing, and the method includes the following steps: Step S10: By deploying a visible light camera, an infrared thermal imager, and a laser macro scanner on the side of the printing nozzle, multispectral sensor data of the surface topography, temperature field, and microscopic layer thickness distribution of the printing filament are collected in real time; wherein, the working band of the infrared thermal imager is 8-14 μm, and it has a spatial resolution ≤0.1 mm / pixel and a frame rate ≥60 Hz, and is used to monitor the temperature field of the printing area in real time to ensure the temperature control accuracy.

[0052] Step S20: Use the surface topography data collected by the laser macro scanner to correct the illumination distortion of the visible light camera image, and based on the temperature field data provided by the infrared thermal imager, dynamically compensate for the measurement error caused by the thermal expansion of the material; Step S30: Perform feature fusion on the multispectral data through a lightweight neural network model in the edge computing unit, detect and classify printing defects in real time, and combine particle swarm optimization and PID control to calculate and dynamically adjust the printing parameters such as the extrusion rate, nozzle temperature, and platform movement speed in real time; Step S40: Regulate the nozzle rotation and platform tilt through a six-axis linkage motion platform, respond to control instructions in real time, and support support-free printing of complex curved surfaces; Step S50: When the risk of nozzle blockage is detected, start the piezoelectric ceramic vibrator to oscillate the nozzle at high frequency, and synchronously reduce the extrusion pressure to prevent material accumulation.

[0053] Among them, the working band of the infrared thermal imager is 8-14μm, with a spatial resolution of ≤0.1mm / pixel and a frame rate of ≥60Hz, which is used to monitor the temperature field of the printing area in real time to ensure the temperature control accuracy.

[0054] Through the multi-spectral fusion perception and dynamic calibration mechanism, the present invention significantly improves the control accuracy of the printing filament width, which is reduced from ±0.1mm to ±0.03mm, and at the same time the interlayer bonding strength is increased by 30%; it supports the printing of full-spectrum materials such as PLA to graphene composite materials (thermal conductivity >200 W / m·K), meeting the needs of different fields, especially suitable for the printing of complex components with high thermal conductivity and high strength requirements. By adopting the thermal field dynamic matching technology, it can effectively reduce the ineffective energy consumption of the heating module, and the energy-saving effect reaches 25%. Through accurate sensor data acquisition and real-time feedback mechanism, the system can respond and adjust the printing parameters within a time shorter than 0.15 seconds to ensure the high-precision control of the printing process. Combining the YOLOv5s network with the particle swarm optimization algorithm, the system can identify various printing defects in real time and precisely control various parameters in the printing process to further optimize the printing quality.

[0055] It should be noted that the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, rather than for limiting purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0056] It should be understood that although the above is described in a certain order, these steps are not necessarily executed in the above order successively. Unless there is a clear indication in this article, the execution of these steps has no strict order limitation, and these steps can be executed in other orders. Moreover, a part of the steps of this embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0057] The above are the exemplary embodiments disclosed by the present invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present invention defined by the claims. The functions, steps, and / or actions of the method claims according to the disclosed embodiments here do not need to be executed in any specific order. In addition, although the elements disclosed in the embodiments of the present invention can be described or claimed in individual form, they can also be understood as multiple unless clearly limited to the singular.

[0058] It should be understood that, as used herein, unless the context clearly supports the exception, the singular form "a" is intended to also include the plural form. It should also be understood that the "and / or" used herein refers to any and all possible combinations of one or more of the associated listed items. The serial numbers of the disclosed embodiments of the present invention above are only for description and do not represent the advantages or disadvantages of the embodiments.

[0059] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the embodiments of the present invention as above, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the embodiments of the present invention.

Claims

1. An apparatus for monitoring the quality of FDM 3D printing, characterized in that, It includes the following components: A multi-spectral sensor module, including a visible light camera, an infrared thermal imager, and a laser macro scanner, which is used to collect the surface topography of the printing filament in real time, monitor the temperature field of the printing area in real time, and collect the microscopic layer thickness distribution data of the printing filament; A dynamic calibration module, which is used to correct the illumination distortion of the visible light image with the laser scanning data and compensate for the measurement error caused by the thermal expansion of the material based on the thermal imaging data; An edge computing module, which is used to deploy a lightweight neural network model, perform real-time fusion analysis on the data collected by the multi-spectral sensor module in real time, generate control instructions, and identify defects that occur during the printing process in real time; A multi-parameter collaborative actuator, including a motor speed regulation module, a nozzle temperature PID controller, and a six-axis motion platform, which supports nozzle rotation and platform tilt for unsupported printing of complex curved surfaces; An emergency intervention module, including a piezoelectric ceramic vibrator, which is used to start the high-frequency oscillation nozzle when the risk of nozzle clogging is detected and synchronously reduce the extrusion pressure.

2. The device for monitoring the quality of FDM 3D printing according to claim 1, wherein, The accuracy of the visible light camera when collecting the surface topography of the printing filament in real time is ±0.02 mm; the working band of the infrared thermal imager is 8-14 μm, the spatial resolution ≤0.1 mm / pixel, the frame rate ≥60 Hz, and the temperature resolution when monitoring the temperature field of the printing area in real time is ±1 °C.

3. The device for monitoring the quality of FDM 3D printing according to claim 2, wherein The edge computing module integrates a dynamic focusing unit, predicts the moving trajectory of the nozzle according to the printing path, and adjusts the sensor focal length in advance; The edge computing module deploys a YOLOv5s network after transfer learning to identify printing defects that occur during the printing process in real time.

4. The device for monitoring the quality of FDM 3D printing according to claim 1, wherein, The six-axis motion platform supports nozzle rotation of ±180° and platform tilt of ±30°.

5. The method for monitoring the quality of FDM 3D printing according to claim 4, characterized in that, The multi-parameter collaborative actuator includes a piezoelectric ceramic vibrator for clearing nozzle blockages and resuming printing; the multi-parameter collaborative actuator supports a fully automated nozzle self-calibration mechanism, including an automatic detection and adjustment unit for nozzle position.

6. The device for monitoring the quality of FDM 3D printing according to claim 5, characterized in that, The multi-parameter collaborative actuator integrates a piezoelectric ceramic vibrator, which can clear nozzle blockages and resume printing within 0.1 seconds.

7. The device for monitoring the quality of FDM 3D printing according to claim 1, characterized in that, Laser-induced graphene is used for directional alignment to achieve local thermal conductivity regulation.

8. The device for monitoring the quality of FDM 3D printing according to claim 1, characterized in that, The accuracy of the laser macro scanner in the multi-spectral sensor module reaches ±0.01 mm.

9. A method for monitoring the quality of FDM 3D printing, characterized in that, Based on the device for monitoring the quality of FDM 3D printing according to any one of claims 1-8, this method is implemented, and the method includes the following steps: By deploying a visible light camera, an infrared thermal imager, and a laser macro scanner on the side of the printing nozzle, multi-spectral sensor data of the surface topography, temperature field, and microscopic layer thickness distribution of the printing filament are collected in real time; Use the surface topography data collected by the laser macro scanner to correct the illumination distortion of the visible light camera image, and based on the temperature field data provided by the infrared thermal imager, dynamically compensate for the measurement error caused by the thermal expansion of the material; Perform feature fusion on the multi-spectral data through the lightweight neural network model in the edge computing unit, detect and classify printing defects in real time, and combine particle swarm optimization and PID control to calculate and dynamically adjust printing parameters such as extrusion rate, nozzle temperature, and platform moving speed in real time; The rotation of the nozzle and the tilt of the platform are regulated by a six-axis linkage motion platform, which can respond to control commands in real time and support the unsupported printing of complex curved surfaces; When the risk of nozzle clogging is detected, the piezoelectric ceramic vibrator is activated to oscillate the nozzle at high frequency, and the extrusion pressure is synchronously reduced.

10. The method for monitoring the quality of FDM 3D printing according to claim 9, characterized in that, The working band of the infrared thermal imager is 8-14μm, with a spatial resolution ≤0.1mm / pixel and a frame rate ≥60Hz, and is used to monitor the temperature field of the printing area in real time.

Images