Nondestructive testing system based on fluorescence imaging principle

Abstract

The invention discloses a nondestructive testing system based on a fluorescence imaging principle, and belongs to the technical field of nondestructive testing. Comprising a hardware system and a software system. The hardware system comprises an excitation module, an imaging module, an adjusting module, a loading module and a control module; the software system comprises an image processing unit, a defect identification unit, a parameter management unit and a report generation unit, and the software system runs in the control module and is used for processing images, identifying defects, managing parameters and generating reports. By means of multi-wavelength switchable light sources and automatic optical filter switching, the system can adapt to workpieces made of various materials such as metal, ceramic and composite materials, the problem that an existing system is poor in adaptability is solved, the double-camera linkage assembly is matched with the three-dimensional translation table and the rotating shaft, all-directional coverage of workpieces in complex shapes can be achieved, the detection integrity is improved, and the detection efficiency is improved. The distance sensing unit is linked with the control module, so that the relative positions of the workpiece, the light source and the camera are automatically and accurately adjusted, manual adjustment errors are eliminated, and the detection precision is improved.

Description

Technical Field

[0001] This invention relates to the field of nondestructive testing technology, and more specifically, to a nondestructive testing system based on the principle of fluorescence imaging. Background Technology

[0002] Non-destructive testing (NDT) technology is a key technology for ensuring the quality of components in industrial production. Among them, fluorescence imaging-based testing technology is widely used due to its advantages such as high sensitivity and intuitive detection. However, existing fluorescence imaging NDT systems have the following shortcomings: First, the excitation light source is mostly a single wavelength, which cannot be adapted to workpieces of different materials (e.g., short wavelength excitation is required for metal workpieces, while long wavelength excitation is required for composite materials), resulting in poor adaptability. Second, the imaging module mostly adopts a single-camera design, which easily leads to imaging blind spots when inspecting workpieces with complex shapes (such as curved surfaces and irregular shapes), making it impossible to fully capture the fluorescence signal. Third, the relative positions of the workpiece, light source, and camera need to be manually adjusted during the inspection process, which is not only cumbersome but also prone to affecting the inspection accuracy due to adjustment errors. Fourth, the influence of ambient temperature on the fluorescence signal is not considered; when the ambient temperature fluctuates, the fluorescence intensity easily changes, leading to a decrease in the accuracy of defect identification.

[0003] Existing inspection systems use only a single laser light source, which cannot be adapted to the inspection of composite materials. Furthermore, the use of single-sided array cameras results in blind spots when inspecting curved workpieces. These systems have not solved the problems of multi-material adaptation, blind-spot-free inspection of complex workpieces, automatic position adjustment, and elimination of temperature interference, making it difficult to meet the inspection requirements for high precision and multiple scenarios.

[0004] In view of this, the present invention is proposed to solve the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this invention is to provide a non-destructive testing system based on the principle of fluorescence imaging to solve the proposed technical problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: The non-destructive testing system based on fluorescence imaging principle includes a hardware system and a software system. The hardware system includes an excitation module, an imaging module, an adjustment module, a material loading module, and a control module. The software system includes an image processing unit, a defect identification unit, a parameter management unit, and a report generation unit. The excitation module is electrically connected to the control module and is used to emit excitation light of switchable wavelengths to the fluorescent penetrant on the surface of the workpiece. The imaging module is electrically connected to the control module and is used to acquire fluorescence signals excited on the surface of the workpiece and convert them into digital image signals; The adjustment module is electrically connected to the control module and is used to adjust the relative position of the workpiece with the excitation module and the imaging module. The loading module is electrically connected to the control module and is used to fix the workpiece and maintain the workpiece temperature stability. The software system runs in the control module and is used to process images, identify defects, manage parameters, and generate reports.

[0007] Furthermore, the excitation module includes a multi-wavelength switchable light source, a beam shaper, and a light source driving unit; The multi-wavelength switchable light source has built-in laser generators with three wavelengths: 405nm, 532nm, and 635nm. The beam shaper is set on the light output path of the multi-wavelength switchable light source to shape the laser into a rectangular spot. The light source driving unit is electrically connected to the control module and is used to drive the laser generator to switch wavelengths.

[0008] Furthermore, the imaging module includes a dual-camera linkage assembly, a filter assembly, and an image acquisition unit; The dual-camera linkage assembly includes an area scan camera and a line scan camera. The area scan camera and the line scan camera are connected by a mechanical linkage frame, which is electrically connected to the control module. The filter assembly includes multiple narrowband filters and an automatic filter switcher, which is electrically connected to the control module. The image acquisition unit is electrically connected to the dual-camera linkage assembly and is used to convert optical images into digital image signals.

[0009] Furthermore, the adjustment module includes a three-dimensional translation stage, a rotation axis, and a distance sensing unit; The X, Y, and Z axis displacement accuracy of the three-dimensional translation stage is 0.01 mm, and the drive unit of the three-dimensional translation stage is electrically connected to the control module. The rotation angle range of the rotating shaft is 0°-360°, and it is electrically connected to the control module through a rotation drive unit; The distance sensing unit includes two laser distance sensors, which are respectively mounted on the excitation module and the imaging module, and are used to detect distance and transmit signals to the control module.

[0010] Furthermore, the loading module includes an adjustable clamp, a temperature control component, and a loading stage body; The adjustable clamp includes two electric grippers with elastic rubber pads on the inside of the grippers. The electric grippers are electrically connected to the control module. The temperature control component includes a heating element, a cooling element, and a temperature sensor, with the temperature sensor electrically connected to the control module; The platform body is made of heat-insulating material.

[0011] Furthermore, the image processing unit includes an adaptive noise reduction module, a fluorescence enhancement module, and an image stitching module; The adaptive noise reduction module extracts the time-domain attenuation characteristics of the fluorescence signal and uses a wavelet transform algorithm to filter noise; The fluorescence enhancement module enhances image contrast through a grayscale stretching algorithm; The image stitching module uses the SIFT feature point matching algorithm to stitch images together.

[0012] Furthermore, the defect identification unit includes a deep learning model and a defect classification module; The deep learning model is built based on the improved YOLOv8 algorithm; The defect classification module categorizes defects into four types based on their characteristics: cracks, porosity, inclusions, and delamination, and labels the defect level accordingly.

[0013] Furthermore, the parameter management unit includes a parameter database and a parameter calling module; The parameter database stores the detection parameters corresponding to different workpiece materials; The parameter calling module supports automatic parameter calling or manual parameter adjustment.

[0014] Furthermore, the report generation unit includes a data integration module and a report export module; The data integration module integrates detection parameters, defect information, and detection images; The report export module supports exporting reports.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Multi-material compatibility: Through multi-wavelength switchable light source and automatic filter switching, it can be adapted to workpieces of various materials such as metal, ceramics, and composite materials, solving the problem of poor compatibility of existing systems.

[0016] 2. Blind-spot-free detection: The dual-camera linkage component, together with the three-dimensional translation stage and rotation axis, can achieve all-round coverage of complex-shaped workpieces, avoid imaging blind spots, and improve detection integrity.

[0017] 3. High-precision automatic adjustment: The distance sensing unit and the control module work together to achieve automatic and precise adjustment of the relative position of the workpiece, the light source, and the camera, eliminating manual adjustment errors and improving detection accuracy.

[0018] 4. Resistance to temperature interference: The temperature control component of the loading module maintains the workpiece temperature stably, avoiding the influence of temperature fluctuations on the fluorescence signal and improving the accuracy of defect identification.

[0019] 5. Intelligent Detection: The software system's adaptive noise reduction, deep learning defect identification, and automatic report generation functions simplify the operation process, improve detection efficiency, and reduce reliance on manual labor. Attached Figure Description

[0020] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention, but do not constitute an undue limitation of the invention. Obviously, the drawings described below are merely some embodiments, and those skilled in the art can obtain other drawings based on these drawings without creative effort. In the drawings: Figure 1 This is a flowchart of the non-destructive testing system based on fluorescence imaging principle provided in this embodiment of the application. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0022] See Figure 1 As shown in the embodiments of this application, a non-destructive testing system based on the principle of fluorescence imaging is provided, including a hardware system and a software system. The hardware system includes an excitation module, an imaging module, an adjustment module, a loading module, and a control module. The software system includes an image processing unit, a defect identification unit, a parameter management unit, and a report generation unit. The excitation module is electrically connected to the control module and is used to emit excitation light of switchable wavelengths to the fluorescent penetrant on the surface of the workpiece. The imaging module is electrically connected to the control module and is used to collect the fluorescence signal excited on the surface of the workpiece and convert it into a digital image signal. The adjustment module is electrically connected to the control module and is used to adjust the relative position of the workpiece with the excitation module and the imaging module. The loading module is electrically connected to the control module and is used to fix the workpiece and maintain the workpiece temperature stability. The software system runs in the control module and is used to process images, identify defects, manage parameters, and generate reports.

[0023] In the above scheme, the control module serves as the core control unit of the system, including an industrial controller (using a PLC, model S7-1200), a touch screen display, and a data interface. The industrial controller is electrically connected to the excitation module, imaging module, adjustment module, object carrier module, and software system, respectively, and is used to receive signals from each module and send control commands. The touch screen display is used to display system operating parameters (such as excitation wavelength, camera parameters, temperature, distance, etc.) and detection images, and also supports manual input of control commands. The data interface includes a USB interface and an Ethernet interface for data export and system networking.

[0024] The excitation module includes a multi-wavelength switchable light source, a beam shaper, and a light source driving unit. The multi-wavelength switchable light source has built-in laser generators with three wavelengths: 405nm (suitable for metal workpieces), 532nm (suitable for ceramic workpieces), and 635nm (suitable for composite material workpieces). Each laser generator is electrically connected to the control module through the light source driving unit, and the switching can be controlled by the control module according to the workpiece material. The beam shaper is set on the light output path of the multi-wavelength switchable light source to shape the laser into a rectangular spot (the spot size can be adjusted by the control module, with an adjustment range of 5mm×5mm-50mm×50mm), avoiding the problem of weak local fluorescence signal caused by uneven spot size. The light source driving unit is electrically connected to the control module and is used to drive the laser generator to switch wavelengths.

[0025] The imaging module includes a dual-camera linkage assembly, a filter assembly, and an image acquisition unit. The dual-camera linkage assembly includes an area scan camera and a line scan camera, which are connected by a mechanical linkage frame. The mechanical linkage frame is electrically connected to the control module. The filter assembly includes multiple narrowband filters and an automatic filter switcher, which is electrically connected to the control module. The image acquisition unit is electrically connected to the dual-camera linkage assembly and is used to convert optical images into digital image signals.

[0026] In the above scheme, the area scan camera has 5 million pixels and a frame rate of 30fps, used to capture local detail defects of the workpiece, while the line scan camera has 2048 pixels and a scanning speed of 1m / s, used to scan large areas of the workpiece. The relative angle (adjustment range 0°-90°) and height (adjustment range 50mm-300mm) of the two cameras can be adjusted by the control module to achieve blind-spot-free coverage of complex-shaped workpieces. The filter assembly is set in front of the lens of the dual-camera linkage assembly. The narrowband filter matching the excitation wavelength corresponds to the excitation wavelengths of 405nm, 532nm, and 635nm, and the filter wavelengths are 520nm, 620nm, and 720nm, respectively. The automatic filter switcher can automatically switch the corresponding filter according to the excitation wavelength to filter ambient stray light and improve the purity of the fluorescence signal. The image acquisition unit is electrically connected to the dual-camera linkage assembly and is used to convert the optical image acquired by the camera into a digital image signal and transmit it to the control module.

[0027] The adjustment module is used to adjust the relative position of the workpiece with the excitation module and imaging module. The adjustment module includes a 3D translation stage, a rotation axis, and a distance sensing unit. The X, Y, and Z axis displacement accuracy of the 3D translation stage is 0.01mm, and the displacement range is 0-500mm. The drive unit of the 3D translation stage is electrically connected to the control module, enabling precise movement of the workpiece in the horizontal and vertical directions. The rotation axis is located between the 3D translation stage and the loading module, and its rotation angle range is 0°-360°. Through a rotation drive unit electrically connected to the control module, it can drive the workpiece to rotate. Combined with the dual-camera linkage assembly, it achieves full-range... The distance sensing unit includes two laser distance sensors, respectively mounted on the excitation module and the imaging module, used to detect distances and transmit signals to the control module. This allows for real-time detection of the distance from the light source's emission end to the workpiece surface, with a detection range of 10mm-200mm and an accuracy of 0.05mm, as well as the distance from the camera lens to the workpiece surface, with a detection range of 20mm-300mm and an accuracy of 0.05mm. The control module automatically controls the three-dimensional translation stage and rotation axis to adjust their positions based on a preset distance threshold (50mm) and a preset distance of 100mm between the camera and the workpiece, thus avoiding errors from manual adjustments.

[0028] The loading module is used to fix the workpiece and maintain a stable temperature in the testing environment. The module includes an adjustable clamp, a temperature control component, and a stage body. The adjustable clamp includes two motorized grippers with elastic rubber pads on their inner sides. The motorized grippers are electrically connected to the control module via electric actuators and can automatically adjust the clamping width according to the workpiece size (compatible with workpiece sizes ranging from 50mm×50mm×5mm to 400mm×400mm×50mm). The elastic rubber pads on the inner sides of the motorized grippers prevent damage to the workpiece surface. The temperature control component includes heating elements and cooling elements. The stage body is equipped with a heating element and a cooling element. The heating element and cooling element are embedded inside the stage body. The temperature sensor is located on the surface of the stage body and is electrically connected to the control module. It can detect the surface temperature of the stage body in real time (detection range 0-50℃, accuracy 0.5℃). The control module controls the heating element or cooling element to work according to the preset temperature (25℃±2℃) to maintain the surface temperature of the workpiece and avoid temperature fluctuations affecting the fluorescence signal intensity. The stage body is made of heat-insulating material (polytetrafluoroethylene) to reduce the influence of external temperature on the stage body.

[0029] The image processing unit processes the digital image signals transmitted by the imaging module. It includes an adaptive noise reduction module, a fluorescence enhancement module, and an image stitching module. The adaptive noise reduction module extracts the temporal decay characteristics of the fluorescence signal (fluorescence signal decay time is 100ns-1ns, ambient stray light decay time is <10ns) to distinguish between fluorescence signals and stray light noise. It uses a wavelet transform algorithm to filter noise, avoiding fluorescence signal loss caused by traditional fixed threshold noise reduction. The fluorescence enhancement module enhances image contrast using a grayscale stretching algorithm, adjusting the grayscale value range of the fluorescence signal from 0-255 to 50-200, thus enhancing the contrast between defective and normal areas. The image stitching module uses the SIFT feature point matching algorithm to stitch the images, achieving a stitching accuracy error of <0.1mm, forming a complete workpiece inspection image.

[0030] The defect identification unit is used to identify defects in the processed image. The defect identification unit includes a deep learning model and a defect classification module. The deep learning model is built based on the improved YOLOv8 algorithm. The training dataset contains fluorescence images of 10 types of defects, such as metal cracks, composite material delamination, and ceramic pores. The number of images for each type of defect is ≥1000. The model input is the processed complete workpiece image, and the output is the position coordinates of the defect with an accuracy of ±0.5mm, the size (length accuracy ±0.1mm, width accuracy ±0.05mm), and the confidence score. The confidence score threshold is set to 0.8. If the score is lower than the threshold, it is marked as a suspected defect. The defect classification module classifies defects into four categories: cracks, pores, inclusions, and delamination, and labels the defect level according to the defect characteristics.

[0031] The parameter management unit includes a parameter database and a parameter calling module. The parameter database stores the detection parameters (excitation wavelength, spot size, camera exposure time, temperature preset value, etc.) corresponding to different workpiece materials (metal, ceramic, composite materials). It supports users to add, modify and delete parameters. The parameter calling module supports automatic calling or manual adjustment of parameters.

[0032] The report generation unit includes a data integration module and a report export module. The data integration module integrates inspection parameters, defect information, and inspection images to form structured data. The report export module supports exporting reports in PDF format. The report includes inspection time, workpiece information, system parameters, defect list, inspection images, and conclusions. It also supports adding a signature column for the inspection personnel.

[0033] Work process I. Testing Preparation Workpiece type: Aviation aluminum alloy component (size 200mm×150mm×10mm), surface crack defects to be inspected; System parameter call: Input "aviation aluminum alloy" through the touch screen of the control module, and the parameter management unit will automatically call the corresponding optimal parameters: excitation wavelength 405nm, spot size 20mm×20mm, area scan camera exposure time 10ms, line scan camera scanning speed 0.5m / s, stage temperature preset 25℃; Workpiece fixing: Place the workpiece on the platform body of the loading module. The control module controls the electric push rod of the adjustable clamp to move. The gripper automatically adjusts the clamping width to 200mm to clamp the workpiece. The elastic rubber pad is in contact with the workpiece surface. Temperature adjustment: The temperature sensor of the loading module detects that the surface temperature of the loading stage is 22℃. The control module controls the heating element to work. When the temperature reaches 25℃, the heating element stops working, and the temperature control component maintains the temperature at 25℃±2℃.

[0034] II. Testing Process Excitation light emission: The control module sends a command to the excitation module, and the light source drive unit starts the 405nm laser generator. The multi-wavelength switchable light source emits 405nm laser. The laser is shaped into a uniform rectangular spot of 20mm×20mm by the beam shaper and irradiates the surface of the workpiece (the surface of the workpiece has been pre-coated with a fluorescent penetrant, which emits 520nm fluorescence under the excitation of the 405nm laser). Fluorescence Imaging: The control module controls the automatic filter switcher of the imaging module to switch to a 520nm narrowband filter, and simultaneously controls the mechanical linkage frame of the dual-camera linkage assembly to adjust the relative angle between the area scan camera and the line scan camera to 30° and the height to 100mm; the line scan camera scans a large area of ​​the workpiece at a speed of 0.5m / s to acquire an overall fluorescence image of the workpiece; the area scan camera acquires local detailed fluorescence images of areas prone to blind spots, such as the edges and corners of the workpiece; the image acquisition unit converts the optical images acquired by the two cameras into digital image signals and transmits them to the control module; Position adjustment: The two laser distance sensors of the adjustment module detect in real time the distance from the light source to the workpiece surface as 48mm (lower than the preset 50mm) and the distance from the camera lens to the workpiece surface as 98mm (lower than the preset 100mm). The distance signals are transmitted to the control module. The control module controls the Z-axis of the three-dimensional translation stage to move upward by 2mm, so that the distance from the light source to the workpiece reaches 50mm and the distance from the camera to the workpiece reaches 100mm. At the same time, it controls the rotation axis to drive the workpiece to rotate at a speed of 10° / s, so as to complete the all-round imaging with the dual cameras.

[0035] III. Image Processing and Defect Recognition Image Processing: The image processing unit of the software system receives digital image signals. The adaptive noise reduction module extracts the temporal attenuation characteristics of the fluorescence signal (attenuation time approximately 500 ns) and uses a wavelet transform algorithm to filter out ambient stray light noise. The fluorescence enhancement module adjusts the grayscale value of the fluorescence signal to 50-200 using a grayscale stretching algorithm, enhancing the contrast between the cracked area (higher grayscale value) and the normal area (lower grayscale value). The image stitching module uses the SIFT feature point matching algorithm to stitch together the local detail images from the area scan camera and the large-area images from the line scan camera to form a complete workpiece inspection image (stitching accuracy error 0.08 mm). Defect identification: The improved YOLOv8 model of the defect identification unit analyzes the complete detection image and outputs the location coordinates (X: 120mm, Y: 80mm), size (length 5mm, width 0.2mm), and confidence score of 0.92 (higher than the threshold of 0.8) of a defect. The defect classification module classifies the defect as a "crack" based on its linear shape and size, and marks it as a Class II defect according to the GB / T 12604.3-2005 standard.

[0036] IV. Report Generation and Data Export Report generation: The data integration module of the report generation unit integrates the detection parameters (excitation wavelength 405nm, temperature 25℃, etc.), defect information (location 120mm×80mm, size 5mm×0.2mm, level II), and complete detection images into structured data; Data Export: The inspection report is exported as a PDF via the control module's USB interface. The report includes the inspection time, workpiece model (aviation aluminum alloy component), system parameters, defect list, inspection images, and the conclusion "a Class II crack defect exists, requiring further processing." The inspection personnel sign the report in the signature column and then archive it.

[0037] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A non-destructive testing system based on fluorescence imaging principle, characterized in that, It includes a hardware system and a software system; the hardware system includes an excitation module, an imaging module, an adjustment module, a loading module, and a control module; the software system includes an image processing unit, a defect identification unit, a parameter management unit, and a report generation unit. The excitation module is electrically connected to the control module and is used to emit excitation light with switchable wavelengths to the fluorescent penetrant on the surface of the workpiece. The imaging module is electrically connected to the control module and is used to acquire fluorescence signals excited on the surface of the workpiece and convert them into digital image signals. The adjustment module is electrically connected to the control module and is used to adjust the relative position of the workpiece with the excitation module and the imaging module. The loading module is electrically connected to the control module and is used to fix the workpiece and maintain the workpiece temperature stability. The software system runs in the control module and is used to process images, identify defects, manage parameters, and generate reports.

2. The non-destructive testing system based on fluorescence imaging principle according to claim 1, characterized in that, The excitation module includes a multi-wavelength switchable light source, a beam shaper, and a light source driving unit. The multi-wavelength switchable light source has built-in laser generators with three wavelengths: 405nm, 532nm, and 635nm. The beam shaper is set on the light output path of the multi-wavelength switchable light source to shape the laser into a rectangular spot. The light source driving unit is electrically connected to the control module and is used to drive the laser generator to switch wavelengths.

3. The non-destructive testing system based on fluorescence imaging principle according to claim 2, characterized in that, The imaging module includes a dual-camera linkage component, a filter component, and an image acquisition unit; The dual-camera linkage assembly includes an area scan camera and a line scan camera. The area scan camera and the line scan camera are connected by a mechanical linkage frame, which is electrically connected to the control module. The filter assembly includes multiple narrowband filters and an automatic filter switcher, which is electrically connected to the control module. The image acquisition unit is electrically connected to the dual-camera linkage component and is used to convert optical images into digital image signals.

4. The non-destructive testing system based on fluorescence imaging principle according to claim 3, characterized in that, The adjustment module includes a three-dimensional translation stage, a rotation axis, and a distance sensing unit; The X, Y, and Z axis displacement accuracy of the three-dimensional translation stage is 0.01 mm, and the drive unit of the three-dimensional translation stage is electrically connected to the control module. The rotation angle range of the rotating shaft is 0°-360°, and it is electrically connected to the control module through a rotation drive unit; The distance sensing unit includes two laser distance sensors, which are respectively mounted on the excitation module and the imaging module, and are used to detect distance and transmit signals to the control module.

5. The non-destructive testing system based on fluorescence imaging principle according to claim 4, characterized in that, The loading module includes an adjustable clamp, a temperature control component, and a loading platform body; The adjustable clamp includes two electric grippers, with elastic rubber pads provided on the inner side of the grippers, and the electric grippers are electrically connected to the control module. The temperature control component includes a heating element, a cooling element, and a temperature sensor, with the temperature sensor electrically connected to the control module. The platform body is made of heat-insulating material.

6. The non-destructive testing system based on fluorescence imaging principle according to claim 5, characterized in that, The image processing unit includes an adaptive noise reduction module, a fluorescence enhancement module, and an image stitching module; The adaptive noise reduction module extracts the time-domain attenuation characteristics of the fluorescence signal and uses a wavelet transform algorithm to filter noise. The fluorescence enhancement module enhances image contrast through a grayscale stretching algorithm; The image stitching module uses the SIFT feature point matching algorithm to stitch images together.

7. The non-destructive testing system based on fluorescence imaging principle according to claim 6, characterized in that, The defect identification unit includes a deep learning model and a defect classification module; The deep learning model is built based on the improved YOLOv8 algorithm; The defect classification module categorizes defects into four types based on their characteristics: cracks, pores, inclusions, and delamination, and labels the defect level accordingly.

8. The non-destructive testing system based on fluorescence imaging principle according to claim 7, characterized in that, The parameter management unit includes a parameter database and a parameter calling module; The parameter database stores the detection parameters corresponding to different workpiece materials; The parameter calling module supports automatic calling or manual adjustment of parameters.

9. The non-destructive testing system based on fluorescence imaging principle according to claim 8, characterized in that, The report generation unit includes a data integration module and a report export module; The data integration module integrates detection parameters, defect information, and detection images; The report export module supports exporting reports.

Images