Blueberry bottle opening sealing performance optical nondestructive testing device and method

Abstract

The invention relates to the technical field of optical nondestructive testing equipment for the sealing performance of a blueberry bottle opening, in particular to an optical nondestructive testing device and method for the sealing performance of the blueberry bottle opening. According to the technical scheme, the optical nondestructive testing device for the sealing performance of the blueberry bottle opening comprises an optical testing device, mounting grooves, a lead screw, a mounting support, a mounting ring, a Fresnel lens, a micrometer caliper, a double-color laser line light source and a rotating motor, and the mounting grooves are formed in the two sides of the interior of the optical testing device; compared with a traditional optical nondestructive testing device for the sealing performance of the blueberry bottle opening, a single light source or a simple lens group is mostly adopted, a 360-degree annular area of the bottle opening is difficult to cover, illumination on the edge of the bottle opening or a complex curved surface area is insufficient, and tiny defects are prone to being omitted; according to the optical nondestructive testing device for the sealing performance of the blueberry bottle opening, the double-color laser line light source is matched with the Fresnel lens array, multispectral reflection data are synchronously collected, the surface micro-mark contrast is enhanced by utilizing wavelength difference, and the monochromatic light detection sensitivity is effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of optical nondestructive testing equipment for sealing properties of blueberry bottle openings, and in particular to an optical nondestructive testing device and method for sealing properties of blueberry bottle openings. Background Art

[0002] The optical non-destructive testing device for the sealing of blueberry bottle mouth is a device specially used to detect the sealing of the bottle mouth of blueberry bottles. It adopts optical non-destructive testing technology and can quickly and accurately detect the sealing performance of the bottle mouth without damaging the bottle mouth.

[0003] Existing optical nondestructive testing devices for the sealing of blueberry bottle mouths mostly use a single light source or a simple lens group, which makes it difficult to cover the 360° annular area of ​​the bottle mouth, resulting in insufficient lighting at the edge of the bottle mouth or complex curved areas, and small defects are easily missed. At the same time, they rely on monochromatic light or low-resolution sensors, and are unable to obtain the multi-spectral reflectance characteristics of the bottle mouth surface. It is difficult to distinguish between the texture of the material itself and the defect characteristics, and the false detection rate is high.

[0004] In view of the problem that the existing optical non-destructive testing devices for the sealing of blueberry bottle mouths mostly use single light sources or simple lens groups, which are difficult to cover the 360° annular area of ​​the bottle mouth, resulting in insufficient lighting at the edge of the bottle mouth or complex curved surface areas, and small defects are easily missed, the optical non-destructive testing device for the sealing of blueberry bottle mouths uses wafer defect / particle monitoring related technologies, a two-color laser line light source and a Fresnel lens array to synchronously collect multi-spectral reflection data, and use wavelength differences to enhance the surface micro-trace contrast, effectively improving the sensitivity of monochromatic light detection. At the same time, combined with structured light triangulation and spiral micrometer encoding data, the three-dimensional point cloud of the bottle mouth sealing surface is reconstructed to achieve quantitative judgment of multi-parameters of flatness, greatly improving the detection accuracy. Summary of the invention

[0005] In order to overcome the existing optical non-destructive testing devices for the sealing of blueberry bottle mouths, most of them use a single light source or a simple lens group, which is difficult to cover the 360° annular area of ​​the bottle mouth, resulting in insufficient lighting at the edge of the bottle mouth or complex curved surface areas, and small defects are easily missed. At the same time, they rely on monochromatic light or low-resolution sensors, and cannot obtain the multi-spectral reflectance characteristics of the bottle mouth surface. It is difficult to distinguish between the texture of the material itself and the defect characteristics, resulting in a high false detection rate.

[0006] The technical scheme of the present invention is: an optical nondestructive testing device for the sealing of a blueberry bottle mouth, comprising an optical testing device, a reflection component, a mounting groove, a screw, a mounting bracket, a mounting ring, a Fresnel lens, a screw micrometer, a two-color laser line light source, a rotating motor and an analysis component, wherein the top surface of the optical testing device is provided with a reflection component, mounting grooves are provided on both sides of the interior of the optical testing device, a screw is provided inside the mounting groove, a mounting bracket is provided on the outside of the screw, mounting rings are provided at both ends of the mounting bracket, a plurality of groups of Fresnel lenses are provided on the surface of the mounting ring, and the Fresnel lenses are distributed in an array, a screw micrometer is provided on one side of the mounting bracket, a two-color laser line light source is provided above the screw micrometer, a rotating motor is provided on the top surface of the optical testing device, and an analysis component is provided on one side of the optical testing device.

[0007] Preferably, the detection light source inside the optical detection device is refracted by a reflection component to ensure that the light can evenly cover the 360° annular area of ​​the bottle mouth, the screw rod is installed through the mounting groove, the screw rod is driven to rotate by a rotating motor, the mounting bracket is driven to move up and down by the screw rod, the mounting ring is installed through the mounting bracket, the Fresnel lens is installed through the mounting ring, the light source inside the optical detection device is refracted by the Fresnel lens, the Fresnel lens can effectively collect and converge light, and illuminate and refract tiny fine scratches on the surface of the blueberry bottle mouth, the position distance between the mounting ring and the blueberry bottle is detected by a screw micrometer, the two-color laser line light source provides stable and uniform light, the two-color laser line is evenly irradiated to the bottle mouth, the refracted light is analyzed by the analysis component to determine whether there is a defect in the bottle mouth.

[0008] Preferably, the reflective assembly includes an installation card box, a replaceable top plate, a light-transmitting mirror, an electric telescopic rod, a reflective mounting plate and an annular microprism array. The top surface of the optical detection device is provided with an installation card box, the interior of the installation card box is provided with a replaceable top plate, the bottom surface of the replaceable top plate is provided with a light-transmitting mirror, the bottom surface of the replaceable top plate is provided with an electric telescopic rod, multiple groups of electric telescopic rods are provided, a reflective mounting plate is provided at the bottom end of the electric telescopic rod, and the bottom surface of the reflective mounting plate is provided with an annular microprism array.

[0009] Preferably, the analysis component includes a light-transmitting base plate, a CMOS sensor array, a light source amplifying channel, a light source receiver and a non-destructive testing analyzer. A light-transmitting base plate is arranged on the inner side of the optical detection device, a CMOS sensor array is arranged on the surface of the light-transmitting base plate, and the CMOS sensor array is arranged in multiple groups. A light source amplifying channel is arranged on one side of the optical detection device, a light source receiver is arranged at one end of the light source amplifying channel, and a non-destructive testing analyzer is arranged on the other side of the optical detection device.

[0010] The optical non-destructive testing method for the sealing of blueberry bottle mouth includes the following methods:

[0011] S101: First, the system is initialized and the bottle is positioned;

[0012] S102: modulating the two-color laser line light source, and dynamically calibrating the micrometer screw and the dynamic light field;

[0013] S103: adapting the environmental micro-prism array;

[0014] S104: Collect multispectral data;

[0015] S105: Intelligently identify defects of the mouth of the blueberry bottle;

[0016] S106: Output the test results and trace the quality.

[0017] Preferably, when performing system initialization and bottle positioning, the following steps are included:

[0018] S201: Turn on the power of the optical detection device, and the system automatically performs hardware self-test to check the power stability of the dual-color laser line light source, the error must be ≤±2%, the step accuracy of the rotating motor, the step angle error ≤0.1°, and the dark current noise of the CMOS sensor array, the dark current noise <0.05e- / pixel / s;

[0019] S202: Input the specification parameters of the blueberry bottle through the control terminal, including the bottle mouth diameter, height and material refractive index, and the system automatically matches the preset annular microprism array tilt angle, using the formula: θ = arcsin (n 1 / n 2 ) to calculate the curvature of the bottle mouth, where n 1 is the refractive index of air, n 2 is the refractive index of the bottle material;

[0020] S203: The conveyor belt transports the blueberry bottle to the inspection station, and the pneumatic grippers clamp the bottle body from both sides. The laser distance sensor measures the deviation between the axis of the bottle mouth and the center line of the inspection device. The position of the bottle body is fine-tuned through the six-axis correction platform to ensure that the overlap between the center of the bottle mouth and the optical axis of the two-color laser line light source is ≤0.1mm.

[0021] Preferably, when performing light source configuration and dynamic calibration, the following steps are included:

[0022] S301: Two-color laser line source emission wavelength λ 1 =450nm (blue light) and λ 2 =660nm (red light) laser line, which is expanded into a circular light curtain covering 360° of the bottle mouth through the Fresnel lens array, and the light intensity ratio is set to I 1 / I 2=1.5, optimize surface micro-trace contrast;

[0023] S302: rotating the micrometer screw to drive the mounting ring to move along the axial direction of the screw rod, so that the working distance between the Fresnel lens and the end face of the bottle mouth is adjusted to D=bottle mouth radius×0.8, ensuring that the incident angle of the light θ≤30° to avoid total reflection;

[0024] S303: The motor drives the mounting bracket to rotate, and the CMOS sensor array collects the distribution of light intensity reflected from the bottle mouth in real time. The system automatically adjusts the extension amount of the electric telescopic rod of the reflective mounting plate through the PID algorithm, with an adjustment accuracy of ±0.02mm, so that the standard deviation of light intensity in the annular area is ≤5%.

[0025] Preferably, when adapting the annular microprism array, the following steps are included:

[0026] S401: The visual recognition system scans the shape of the bottle mouth, selects a matching model from the replaceable top plate library, and completes the top plate replacement within 15 seconds through the magnetic quick replacement mechanism;

[0027] S402: According to the parameters of the bottle mouth thread, the electric telescopic rod is controlled to adjust the height H of the reflective mounting plate so that the prism vertex of the annular microprism array and the root of the bottle mouth thread are in the same phase plane;

[0028] S403: Test laser pulses are emitted, and after passing through the light-transmitting mirror and the annular microprism array, evenly distributed diffuse reflection spots are formed at the bottle mouth to verify that there are no blind spots in the coverage area and the spot density is ≥200 points / cm 2 .

[0029] Preferably, when performing multispectral data collection, the following steps are included:

[0030] S501: The two-color laser line source emits alternately at a frequency of 1kHz, and the CMOS sensor array uses a double exposure mode to synchronously capture λ 1 and λ 2 The exposure time is set as t 1 =5μs (blue light), t 2 =8μs (red light);

[0031] S502: Perform Fourier transform on the original signal through the light source amplification channel, extract the spatial frequency f=1 / (2Δx), Δx is the high-frequency component of the pixel spacing, and enhance the edge contrast of the surface micro-scratches;

[0032] S503: Combine the position encoding data of the micrometer screw and use the principle of structured light triangulation to reconstruct the three-dimensional point cloud of the bottle mouth with a resolution of ≤50μm, focusing on extracting the geometric deviation of the sealing surface in the area of ​​0-1mm from the bottle mouth end face.

[0033] Preferably, when performing intelligent defect identification, the following steps are included:

[0034] S601: Extract 6 types of features from the 3D point cloud, including texture roughness (Ra, μm level), edge sharpness (gradient amplitude ≥ threshold T 1 ), surface continuity (curvature change rate ≤ T 2 ), sealing surface flatness (PV value ≤ λ / 10), laser line break length (threshold L ≥ 0.2 mm) and refraction angle abnormal area (Δθ ≥ 0.5°);

[0035] S602: Input the feature vector into a pre-trained convolutional neural network, which includes 5 convolutional layers and 3 fully connected layers, and outputs a probability distribution of defect types, including four categories: cracks, scratches, deformation, and poor sealing;

[0036] S603: Perform Delaunay triangulation on the identified defect area to generate a three-dimensional coordinate tag cloud, accurately marking the defect position (polar coordinate accuracy ±0.1°), size (error ≤5%) and depth (resolution ≤20μm).

[0037] Preferably, when outputting the results and tracing the quality, the following steps are included:

[0038] S701: Automatic classification according to defect type:

[0039] Grade A: No defects or Ra<0.5μm

[0040] Class B: 0.5μm≤Ra<1.0μm, no structural damage

[0041] Grade C: Ra ≥ 1.0 μm or crack / scratch depth > 50 μm;

[0042] S702: If there is a continuous defect area on the sealing surface > 1mm 2 , automatically marked as unqualified;

[0043] S703: Generate a test report, including a three-dimensional defect distribution thermogram, key dimension measurement data, a defect type statistical histogram, and a quality grade certificate;

[0044] S704: Upload the hash value of the test data to the blockchain node to ensure that the test record cannot be tampered with, and support the query of the original data by scanning the code during subsequent quality traceability.

[0045] Beneficial effects of the present invention:

[0046] 1. Compared with the traditional blueberry bottle mouth sealing optical non-destructive testing device, which mostly uses a single light source or a simple lens group, it is difficult to cover the 360° annular area of ​​the bottle mouth, resulting in insufficient illumination at the edge of the bottle mouth or the complex curved surface area, and small defects are easily missed. At the same time, it relies on monochromatic light or low-resolution sensors, and cannot obtain the multi-spectral reflection characteristics of the bottle mouth surface. It is difficult to distinguish the texture of the material itself from the defect characteristics, and the false detection rate is high. The blueberry bottle mouth sealing optical non-destructive testing device uses a two-color laser line light source with a Fresnel lens array to synchronously collect multi-spectral reflection data, and uses wavelength differences to enhance the surface micro-trace contrast, effectively improving the monochromatic light detection sensitivity. At the same time, it combines structured light triangulation and spiral micrometer encoding data to reconstruct the three-dimensional point cloud of the bottle mouth sealing surface, realize the quantitative determination of multi-parameters of flatness, and greatly improve the detection accuracy;

[0047] 2. Refract the detection light source inside the optical detection device through the reflection component to ensure that the light can evenly cover the 360° annular area of ​​the bottle mouth, install the screw rod through the mounting groove, drive the screw rod to rotate through the rotating motor, drive the mounting bracket to move up and down through the screw rod, install the mounting ring through the mounting bracket, install the Fresnel lens through the mounting ring, refract the light source inside the optical detection device through the Fresnel lens, the Fresnel lens can effectively collect and converge light, illuminate and refract the tiny fine scratches on the surface of the blueberry bottle mouth, detect the position distance between the mounting ring and the blueberry bottle through the micrometer, provide stable and uniform light through the two-color laser line light source, evenly irradiate the two-color laser line to the bottle mouth, analyze the refracted light through the analysis component to determine whether there is a defect in the bottle mouth. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 Shown is a first three-dimensional structural schematic diagram of the optical nondestructive testing device for sealing of a blueberry bottle mouth of the present invention;

[0049] Figure 2 Shown is a second three-dimensional structure schematic diagram of the optical nondestructive testing device for sealing of a blueberry bottle mouth of the present invention;

[0050] Figure 3 Shown is a schematic diagram of the bottom three-dimensional structure of the optical non-destructive testing device for the sealing of a blueberry bottle mouth of the present invention;

[0051] Figure 4 Shown is a schematic diagram of the internal three-dimensional structure of the optical non-destructive testing device for the sealing of a blueberry bottle mouth of the present invention;

[0052] Figure 5 Shown is a partial three-dimensional structure schematic diagram of the optical non-destructive testing device for the sealing property of a blueberry bottle mouth of the present invention;

[0053] Figure 6The schematic diagram of the process framework of the optical nondestructive testing method for the sealing property of the blueberry bottle mouth of the present invention is shown;

[0054] Explanation of the reference numerals: 1. optical detection device; 201. mounting card box; 202. replaceable top plate; 203. light-transmitting mirror; 204. electric telescopic rod; 205. reflective mounting plate; 206. annular microprism array; 301. mounting groove; 302. lead screw; 303. mounting bracket; 304. mounting ring; 305. Fresnel lens; 306. micrometer screw; 307. two-color laser line light source; 308. rotating motor; 401. light-transmitting bottom plate; 402. CMOS sensor array; 403. light source amplification channel; 404. light source receiver; 405. non-destructive detection analyzer. DETAILED DESCRIPTION

[0055] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0056] See also Figure 1-Figure 5 The present invention provides an embodiment: an optical nondestructive testing device for the sealing of a blueberry bottle mouth, comprising an optical testing device 1, a reflection component, a mounting groove 301, a screw 302, a mounting bracket 303, a mounting ring 304, a Fresnel lens 305, a screw micrometer 306, a two-color laser line light source 307, a rotating motor 308 and an analysis component, wherein the top surface of the optical testing device 1 is provided with a reflection component, the inner sides of the optical testing device 1 are provided with mounting grooves 301, and the inner side of the mounting groove 301 is provided with A screw rod 302 is provided with a mounting bracket 303 on the outside of the screw rod 302, mounting rings 304 are provided at both ends of the mounting bracket 303, a plurality of groups of Fresnel lenses 305 are provided on the surface of the mounting ring 304, and the Fresnel lenses 305 are distributed in an array, a micrometer screw 306 is provided on one side of the mounting bracket 303, a two-color laser line light source 307 is provided above the micrometer screw 306, a rotating motor 308 is provided on the top surface of the optical detection device 1, and an analysis component is provided on one side of the optical detection device 1.

[0057] Preferably, the detection light source inside the optical detection device 1 is refracted by a reflection component to ensure that the light can evenly cover the 360° annular area of ​​the bottle mouth, the screw rod 302 is installed through the installation groove 301, the screw rod 302 is driven to rotate by the rotating motor 308, the mounting bracket 303 is driven to move up and down by the screw rod 302, the mounting ring 304 is installed by the mounting bracket 303, the Fresnel lens 305 is installed by the mounting ring 304, the light source inside the optical detection device 1 is refracted by the Fresnel lens 305, the Fresnel lens 305 can effectively collect and converge light, and refract light to tiny fine scratches on the surface of the blueberry bottle mouth, the position distance between the mounting ring 304 and the blueberry bottle is detected by the micrometer screw 306, the two-color laser line light source 307 provides stable and uniform light, and the two-color laser line is evenly irradiated to the bottle mouth, and the refracted light is analyzed by the analysis component to determine whether there is a defect in the bottle mouth.

[0058] Preferably, the reflective assembly includes an installation card box 201, a replaceable top plate 202, a light-transmitting mirror 203, an electric telescopic rod 204, a reflective mounting plate 205 and an annular microprism array 206. The top surface of the optical detection device 1 is provided with an installation card box 201, the interior of the installation card box 201 is provided with a replaceable top plate 202, the bottom surface of the replaceable top plate 202 is provided with a light-transmitting mirror 203, the bottom surface of the replaceable top plate 202 is provided with an electric telescopic rod 204, the electric telescopic rod 204 is provided with multiple groups, the bottom end of the electric telescopic rod 204 is provided with a reflective mounting plate 205, and the bottom surface of the reflective mounting plate 205 is provided with an annular microprism array 206. The optical detection device 1 is provided with an annular microprism array 206. When in use, the replaceable top plate 202 is installed by installing the card box 201, and the light-transmitting mirror 203 is installed by the replaceable top plate 202. The replaceable top plate 202 can be replaced at any time according to different bottle types to meet the needs of different bottle types. The light-transmitting mirror 203 is used to strengthen the refraction of the light source inside the optical detection device 1. The reflective mounting plate 205 is driven to rise and fall by the electric telescopic rod 204. The annular microprism array 206 is installed by the reflective mounting plate 205. The annular microprism array 206 ensures that the light can evenly cover the 360° annular area of ​​the bottle mouth.

[0059] Preferably, the analysis component includes a light-transmitting bottom plate 401, a CMOS sensor array 402, a light source amplifying channel 403, a light source receiver 404 and a non-destructive testing analyzer 405. A light-transmitting bottom plate 401 is arranged on the inner side of the optical detection device 1, a CMOS sensor array 402 is arranged on the surface of the light-transmitting bottom plate 401, and multiple groups of CMOS sensor arrays 402 are arranged. A light source amplifying channel 403 is arranged on one side of the optical detection device 1, a light source receiver 404 is arranged at one end of the light source amplifying channel 403, and a non-destructive testing analyzer 405 is arranged on the other side of the optical detection device 1. When in use, the CMOS sensor array 402 is installed through the light-transmitting bottom plate 401, the refracted light source is received through the CMOS sensor array 402, the electrical signal of the received light source is amplified through the light source amplifying channel 403, the amplified light source is converted into a signal through the light source receiver 404, and the tiny defects of the bottle mouth are detected and analyzed through the non-destructive testing analyzer 405.

[0060] See also Figure 6 In this embodiment, the optical nondestructive testing method for the sealing of the blueberry bottle mouth includes the following methods:

[0061] S101: First, the system is initialized and the bottle is positioned;

[0062] S102: modulating the two-color laser line light source 307, and dynamically calibrating the micrometer screw 306 and the dynamic light field;

[0063] S103: adapting the environmental micro-prism array 206;

[0064] S104: Collect multispectral data;

[0065] S105: Intelligently identify defects of the mouth of the blueberry bottle;

[0066] S106: Output the test results and trace the quality.

[0067] Preferably, when performing system initialization and bottle positioning, the following steps are included:

[0068] S201: Turn on the power of the optical detection device 1, and the system automatically performs a hardware self-test to check the power stability of the two-color laser line light source 307, the error must be ≤±2%, the step accuracy of the rotating motor 308, the step angle error ≤0.1°, and the dark current noise of the CMOS sensor array 402, the dark current noise <0.05e- / pixel / s;

[0069] S202: Input the blueberry bottle specification parameters through the control terminal, including the bottle mouth diameter, height and material refractive index, and the system automatically matches the preset annular microprism array 206 tilt angle, using the formula: θ = arcs in (n 1 / n 2 ) to calculate the curvature of the bottle mouth, where n 1 is the refractive index of air, n 2 is the refractive index of the bottle material;

[0070] S203: The conveyor belt transports the blueberry bottle to the inspection station, the pneumatic grippers clamp the bottle body from both sides, the laser distance sensor measures the deviation between the axis of the bottle mouth and the center line of the inspection device, and the position of the bottle body is fine-tuned through the six-axis correction platform to ensure that the overlap degree between the center of the bottle mouth and the optical axis of the two-color laser line light source 307 is ≤0.1mm.

[0071] Preferably, when performing light source configuration and dynamic calibration, the following steps are included:

[0072] S301: Two-color laser line source 307 emission wavelength λ 1 =450nm (blue light) and λ 2 =660nm (red light) laser line, which is expanded into a ring light curtain covering 360° of the bottle mouth through the Fresnel lens 305 array, and the light intensity ratio is set to I 1 / I 2 =1.5, optimize surface micro-trace contrast;

[0073] S302: Rotate the micrometer screw 306 to drive the mounting ring 304 to move axially along the screw rod 302, so that the working distance between the Fresnel lens 305 and the end face of the bottle mouth is adjusted to D=bottle mouth radius×0.8, ensuring that the incident angle of the light θ≤30° to avoid total reflection;

[0074] S303: The rotating motor 308 drives the mounting bracket 303, and the CMOS sensor array 402 collects the distribution of the reflected light intensity of the bottle mouth in real time. The system automatically adjusts the extension amount of the electric telescopic rod 204 of the reflective mounting plate 205 through the PID algorithm, and the adjustment accuracy is ±0.02mm, so that the standard deviation of the light intensity in the annular area is ≤5%.

[0075] Preferably, when adapting the annular microprism array, the following steps are included:

[0076] S401: The visual recognition system scans the shape of the bottle mouth, selects a matching model from the replaceable top plate library, and replaces the top plate 202 within 15 seconds through a magnetic quick replacement mechanism;

[0077] S402: According to the parameters of the bottle mouth thread, the electric telescopic rod 204 is controlled to adjust the height H of the reflective mounting plate 205 so that the prism vertex of the annular microprism array 206 and the root of the bottle mouth thread are in the same phase plane;

[0078] S403: Test laser pulses are emitted, and after passing through the light-transmitting mirror 203 and the annular microprism array 206, evenly distributed diffuse reflection spots are formed at the bottle mouth, verifying that there is no blind spot in the coverage area and the spot density is ≥200 points / cm 2 .

[0079] Preferably, when performing multispectral data collection, the following steps are included:

[0080] S501: The two-color laser line light source 307 emits alternately at a frequency of 1kHz, and the CMOS sensor array 402 uses a double exposure mode to synchronously capture λ 1 and λ 2 The exposure time is set as t 1 =5μs (blue light), t 2 =8μs (red light);

[0081] S502: Perform Fourier transform on the original signal through the light source amplification channel 403 to extract the spatial frequency f=1 / (2Δx), where Δx is the high-frequency component of the pixel spacing, and enhance the edge contrast of the surface micro-scratches;

[0082] S503: Combined with the position coding data of the micrometer screw 306, the three-dimensional point cloud of the bottle mouth is reconstructed using the principle of structured light triangulation, with a resolution of ≤50μm, and the geometric deviation of the sealing surface in the area of ​​0-1mm from the bottle mouth end face is extracted in particular.

[0083] Preferably, when performing intelligent defect identification, the following steps are included:

[0084] S601: Extract 6 types of features from the 3D point cloud, including texture roughness (Ra, μm level), edge sharpness (gradient amplitude ≥ threshold T 1 ), surface continuity (curvature change rate ≤ T 2 ), sealing surface flatness (PV value ≤ λ / 10), laser line break length (threshold L ≥ 0.2 mm) and refraction angle abnormal area (Δθ ≥ 0.5°);

[0085] S602: Input the feature vector into a pre-trained convolutional neural network, which includes 5 convolutional layers and 3 fully connected layers, and outputs a probability distribution of defect types, including four categories: cracks, scratches, deformation, and poor sealing;

[0086] S603: Perform Delaunay triangulation on the identified defect area to generate a three-dimensional coordinate tag cloud, accurately marking the defect position (polar coordinate accuracy ±0.1°), size (error ≤5%) and depth (resolution ≤20μm).

[0087] Preferably, when outputting the results and tracing the quality, the following steps are included:

[0088] S701: Automatic classification according to defect type:

[0089] Grade A: No defects or Ra<0.5μm

[0090] Class B: 0.5μm≤Ra<1.0μm, no structural damage

[0091] Grade C: Ra ≥ 1.0 μm or crack / scratch depth > 50 μm;

[0092] S702: If there is a continuous defect area on the sealing surface > 1mm 2 , automatically marked as unqualified;

[0093] S703: Generate a test report, including a three-dimensional defect distribution thermogram, key dimension measurement data, a defect type statistical histogram, and a quality grade certificate;

[0094] S704: Upload the hash value of the test data to the blockchain node to ensure that the test record cannot be tampered with, and support the query of the original data by scanning the code during subsequent quality traceability.

[0095] Verification of the effectiveness of the optical nondestructive testing device and method for the sealing of blueberry bottle mouth

[0096] 1. Experimental design

[0097] Objective: To verify the ability of the six-step test process to identify blueberry bottle seal defects and quantify the improvement in test accuracy and efficiency.

[0098] Sample: Bottle type: 3 specifications (diameter 38mm / 42mm / 48mm, height 80mm / 100mm / 120mm)

[0099] Material: Soda-lime glass (n=1.52), borosilicate glass (n=1.47), PET plastic (n=1.58)

[0100] Artificial defects: Scratches on sealing surface (depth 20μm / 50μm / 80μm)

[0101] Edge crack (length 0.3mm / 0.5mm / 1.0mm)

[0102] Thread deformation (offset 0.1mm / 0.2mm / 0.3mm)

[0103] Simulation of loose sealing (gap 50μm / 100μm / 150μm)

[0104] 2. Equipment configuration

[0105]

[0106]

[0107] 3. Experimental steps

[0108] S801: Input bottle parameters: diameter 42mm, height 100mm, material refractive index 1.52 (corresponding to high borosilicate glass); six-axis calibration platform adjustment time: 8.2 seconds (the overlap between the center of the bottle mouth and the optical axis is 0.05mm);

[0109] S802: Angle of annular light curtain coverage: 360°±0.3° (verified by laser power meter); Fresnel lens working distance D=16.8mm (bottle mouth radius 21mm×0.8); Light intensity standard deviation: 4.1% (after PID adjustment);

[0110] S803: Top plate replacement time: 12 seconds; Phase difference between prism vertex and thread root: 0.02 mm (measured by laser interferometer); Diffuse reflection spot density: 220 points / cm 2 (uniformity 98.7%);

[0111] S804: Double exposure image synchronization error: 1.5μs; 3D point cloud reconstruction time: 0.8 seconds / bottle; Sealing surface geometric deviation detection accuracy: ±8μm;

[0112] S805: CNN training data set: 20,000 defect images; test set recognition rate: crack 99.2%, scratch 98.5%, deformation 97.8%, poor sealing 99.5%; defect positioning error: position ±0.08°, size error 4.2%, depth resolution 15μm;

[0113] S806: Test report generation time: 3.1 seconds / bottle; quality grade determination accuracy: 100%.

[0114] 4. Results Analysis

[0115]

[0116]

[0117] 5. Conclusion

[0118] The annular microprism array + dynamic light field calibration technology reduces the detection blind area from 12% of the traditional method to 0.3%. The two-color laser line fusion detection increases the recognition rate of tiny defects by 42%. The blockchain traceability function shortens the quality traceability time by 80%, increases the detection efficiency by 5-8 times, and the sealing judgment accuracy is ≥99.8%.

[0119] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. An optical nondestructive testing device and method for the sealing of a blueberry bottle, characterized in that: The optical detection device (1) comprises an optical detection device (1), a reflection component, a mounting groove (301), a screw (302), a mounting bracket (303), a mounting ring (304), a Fresnel lens (305), a screw micrometer (306), a two-color laser line light source (307), a rotating motor (308) and an analysis component. The top surface of the optical detection device (1) is provided with a reflection component. Both sides of the interior of the optical detection device (1) are provided with mounting grooves (301). The interior of the mounting groove (301) is provided with a screw (302). The screw (302) A mounting bracket (303) is arranged on the outside, mounting rings (304) are arranged at both ends of the mounting bracket (303), a plurality of groups of Fresnel lenses (305) are arranged on the surface of the mounting ring (304), and the Fresnel lenses (305) are arranged in an array. A micrometer screw (306) is arranged on one side of the mounting bracket (303), and a two-color laser line light source (307) is arranged above the micrometer screw (306). A rotating motor (308) is arranged on the top surface of the optical detection device (1), and an analysis component is arranged on one side of the optical detection device (1).

2. The optical nondestructive testing device and method for the sealing property of a blueberry bottle mouth according to claim 1, characterized in that: The reflective component comprises a mounting card box (201), a replaceable top plate (202), a light-transmitting mirror (203), an electric telescopic rod (204), a reflective mounting plate (205) and an annular micro-prism array (206); the top surface of the optical detection device (1) is provided with a mounting card box (201); the interior of the mounting card box (201) is provided with a replaceable top plate (202); the bottom surface of the replaceable top plate (202) is provided with a light-transmitting mirror (203); the bottom surface of the replaceable top plate (202) is provided with an electric telescopic rod (204); a plurality of electric telescopic rods (204) are provided; the bottom end of the electric telescopic rod (204) is provided with a reflective mounting plate (205); and the bottom surface of the reflective mounting plate (205) is provided with an annular micro-prism array (206).

3. The optical nondestructive testing device and method for sealing of blueberry bottle mouth according to claim 1, characterized in that: The analysis component comprises a light-transmitting bottom plate (401), a CMOS sensor array (402), a light source amplifying channel (403), a light source receiver (404) and a non-destructive testing analyzer (405); the light-transmitting bottom plate (401) is arranged on the inner side of the optical testing device (1); the CMOS sensor array (402) is arranged on the surface of the light-transmitting bottom plate (401); the CMOS sensor array (402) is arranged in multiple groups; the light source amplifying channel (403) is arranged on one side of the optical testing device (1); the light source receiver (404) is arranged at one end of the light source amplifying channel (403); and the non-destructive testing analyzer (405) is arranged on the other side of the optical testing device (1).

4. The optical nondestructive testing device for sealing of blueberry bottle mouth according to claims 1-3, characterized in that: The optical non-destructive testing method for the sealing of blueberry bottle mouth includes the following methods: S101: First, the system is initialized and the bottle is positioned; S102: modulating the two-color laser line light source (307) and dynamically calibrating the micrometer screw (306) and the dynamic light field; S103: adapting the environmental micro-prism array (206); S104: Collect multispectral data; S105: Intelligently identify defects of the mouth of the blueberry bottle; S106: Output the test results and trace the quality.

5. The optical nondestructive testing device and method for the sealing property of a blueberry bottle mouth according to claim 4, characterized in that: When initializing the system and positioning the bottle, the following steps are included: S201: Turn on the power of the optical detection device 1, and the system automatically performs a hardware self-test to check the power stability of the two-color laser line light source (307), the error must be ≤±2%, the step accuracy of the rotating motor (308), the step angle error ≤0.1°, and the dark current noise of the CMOS sensor array (402), the dark current noise <0.05e- / pixel / s; S202: Inputting the specification parameters of the blueberry bottle through the control terminal, including the diameter, height and refractive index of the bottle mouth, the system automatically matches the preset inclination angle of the annular microprism array (206), and calculates the curvature of the bottle mouth using the formula: θ=arcsin(n1 / n2), where n1 is the refractive index of air and n2 is the refractive index of the bottle body material; S203: The conveyor belt transports the blueberry bottle to the inspection station, and the pneumatic grippers clamp the bottle body from both sides. The laser distance sensor measures the deviation between the axis of the bottle mouth and the center line of the inspection device. The position of the bottle body is fine-tuned through the six-axis correction platform to ensure that the overlap between the center of the bottle mouth and the optical axis of the two-color laser line light source (307) is ≤0.1mm.

6. The optical nondestructive testing device and method for sealing of blueberry bottle mouth according to claim 4, characterized in that: When performing light source configuration and dynamic calibration, the following steps are included: S301: a two-color laser line light source (307) emits laser lines with wavelengths λ1=450nm (blue light) and λ2=660nm (red light), which are expanded into an annular light curtain covering 360° of the bottle mouth through a Fresnel lens (305) array, and the light intensity ratio is set to I1 / I2=1.5 to optimize the surface micro-trace contrast; S302: rotating the micrometer screw (306) to drive the mounting ring (304) to move axially along the screw rod (302), so that the working distance between the Fresnel lens (305) and the end face of the bottle mouth is adjusted to D=bottle mouth radius×0.8, ensuring that the incident angle of the light θ≤30° to avoid total reflection; S303: The motor (308) is rotated to drive the mounting bracket (303), and the CMOS sensor array (402) collects the distribution of light intensity reflected from the bottle mouth in real time. The system automatically adjusts the extension amount of the electric telescopic rod (204) of the reflective mounting plate (205) through a PID algorithm, with an adjustment accuracy of ±0.02mm, so that the standard deviation of the light intensity in the annular area is ≤5%.

7. The optical nondestructive testing device and method for sealing of blueberry bottle mouth according to claim 4, characterized in that: When adapting the annular microprism array, the following steps are included: S401: The visual recognition system scans the shape of the bottle mouth, selects a matching model from a replaceable top plate library, and replaces the top plate (202) within 15 seconds through a magnetic quick replacement mechanism; S402: According to the parameters of the bottle mouth thread, the electric telescopic rod (204) is controlled to adjust the height H of the reflective mounting plate (205) so that the prism apex of the annular microprism array (206) and the root of the bottle mouth thread are in the same phase plane; S403: emitting a test laser pulse, which passes through the light-transmitting mirror (203) and the annular microprism array (206), and forms evenly distributed diffuse reflection spots at the bottle mouth, verifying that there is no blind spot in the coverage area and the spot density is ≥200 dots / cm 2 .

8. The optical nondestructive testing device and method for sealing of blueberry bottle mouth according to claim 4, characterized in that: When performing multispectral data acquisition, the following steps are included: S501: The two-color laser line light source (307) emits alternately at a frequency of 1 kHz, and the CMOS sensor array (402) uses a double exposure mode to synchronously capture the reflection images of λ1 and λ2, and the exposure time is set to t1 = 5 μs (blue light) and t2 = 8 μs (red light), respectively; S502: Performing Fourier transform on the original signal through the light source amplification channel (403), extracting the spatial frequency f=1 / (2Δx), where Δx is the high-frequency component of the pixel spacing, and enhancing the edge contrast of the surface micro-scratches; S503: combining the position coding data of the micrometer screw (306), using the principle of structured light triangulation, reconstructing the three-dimensional point cloud of the bottle mouth with a resolution of ≤50 μm, and focusing on extracting the geometric deviation of the sealing surface in the area of ​​0-1 mm from the bottle mouth end face.

9. The optical nondestructive testing device and method for sealing of blueberry bottle mouth according to claim 4, characterized in that: When performing intelligent defect identification, the following steps are included: S601: Extract 6 types of features from the 3D point cloud, including texture roughness (Ra, μm level), edge sharpness (gradient amplitude ≥ threshold T1), surface continuity (curvature change rate ≤ T2), sealing surface flatness (PV value ≤ λ / 10), laser line break length (threshold L ≥ 0.2 mm) and refraction angle abnormal area (Δθ ≥ 0.5°); S602: Input the feature vector into a pre-trained convolutional neural network, which includes 5 convolutional layers and 3 fully connected layers, and outputs a probability distribution of defect types, including four categories: cracks, scratches, deformation, and poor sealing; S603: Perform Delaunay triangulation on the identified defect area to generate a three-dimensional coordinate tag cloud, accurately marking the defect position (polar coordinate accuracy ±0.1°), size (error ≤5%) and depth (resolution ≤20μm).

10. The optical nondestructive testing device and method for sealing of blueberry bottle mouth according to claim 4, characterized in that: When outputting results and tracing quality, the following steps are included: S701: Automatic classification according to defect type: Grade A: No defects or Ra<0.5μm Class B: 0.5μm≤Ra<1.0μm, no structural damage Grade C: Ra ≥ 1.0 μm or crack / scratch depth > 50 μm; S702: If there is a continuous defect area on the sealing surface > 1mm 2 , automatically marked as unqualified; S703: Generate a test report, including a three-dimensional defect distribution thermogram, key dimension measurement data, a defect type statistical histogram, and a quality grade certificate; S704: Upload the hash value of the test data to the blockchain node to ensure that the test record cannot be tampered with, and support the query of the original data by scanning the code during subsequent quality traceability.

Images