Glass bottle surface spraying quality detection method

Abstract

The invention relates to the technical field of optical detection, in particular to a glass bottle surface spraying quality detection method which comprises the following steps: under a specified wavelength, acquiring target incident light by adjusting a polarization angle, irradiating a glass bottle spraying layer, collecting a transmission spectrum signal to calculate parallel and vertical polarization transmissivity and ratio of the spraying layer, and generating polarization transmissivity. According to the method, the light with the polarization angle irradiates the spraying layer, the polarization component of the transmission light is obtained, the thickness uniformity and the internal structure are analyzed, weak areas, particle flaws and excessive spraying of the spraying layer are recognized, the defect detection precision is improved, multi-angle transmissivity data are collected, the change rate is calculated, and color deviation and thickness abnormity are accurately positioned; through cross analysis of multiple optical parameters, evaluation of adhesive force, curing quality and color consistency is more detailed, spraying abnormity is classified, multiple detection means act synergistically, interference such as environment illumination and material reflectivity is reduced, and the detection accuracy of spraying quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optical detection, and particularly relates to a method for detecting the spraying quality of the surface of a glass bottle. Background Art

[0002] The technical field of optical detection includes detection methods for the surface, internal structure, and material properties of objects, mainly relying on physical phenomena such as the propagation, reflection, scattering, interference, diffraction, and absorption of light for analysis. This technical field is widely used in industrial production, medical diagnosis, materials science, etc., for non-contact detection and high-precision measurement. In industrial quality inspection, optical detection technology is often used for identifying surface defects, thickness measurement, color analysis, and coating uniformity detection. This field mainly includes methods such as laser interferometry detection, spectral analysis, polarized light detection, fluorescence imaging, and machine vision detection. Each method achieves high-precision quality control based on specific optical characteristics. Among them, spectral analysis mainly uses the absorption or scattering characteristics of light to detect material composition, and machine vision detection combines image processing algorithms to analyze surface defects or spraying uniformity.

[0003] Among them, the method for detecting the spraying quality of the surface of a glass bottle refers to using optical detection technology to evaluate the quality of the spray coating on the surface of the glass bottle. This patent theme mainly focuses on detecting the uniformity, adhesion, thickness, and color consistency of the spray coating, and uses spectral analysis and image recognition technology to obtain detection data. The spectral analysis method judges the thickness and uniformity of the spray coating by measuring the reflection or transmission characteristics of the spray coating to light of a specific wavelength. The image recognition technology uses a high-resolution industrial camera to collect images of the surface of the glass bottle, and identifies defects in the spray coating, such as color difference, spots, or uneven spraying, through color space segmentation and texture analysis methods. In addition, polarized light detection is used to analyze the adhesion of the spray coating, and the curing quality of the coating is evaluated through changes in the polarization state. The entire detection process combines multiple optical means to ensure the stability and consistency of the spraying quality of the glass bottle.

[0004] Currently, during the quality inspection of glass bottle spraying, the spectral analysis method is relied on to measure the light absorption and reflection characteristics. However, the sensitivity to the subtle thickness changes on the surface is limited, and it is easy to overlook the minor deviations in the local spray coating. During the color detection process, the image recognition technology is vulnerable to environmental light, resulting in insufficient detection accuracy of color deviation. Especially on high-reflectivity materials, the risk of misjudgment is relatively high. For the identification of defects, the existing methods mainly rely on the texture analysis of the surface image, making it difficult to distinguish the particle defects and poor curing problems inside the spray coating, resulting in some hidden defects not being accurately detected. The evaluation of the adhesion of the spray coating does not fully consider the polarization characteristics of light and only relies on optical contrast analysis, making it difficult to quantify the uniformity of the curing state and affecting the overall judgment of the spraying quality. The lack of systematic analysis of the change in the transmittance at multiple angles leads to limitations in the judgment of the spraying thickness and color deviation, making it difficult to comprehensively identify the abnormal areas of the spray coating. The above deficiencies lead to great uncertainties in the spraying quality control, affecting the product consistency and the accuracy of subsequent process adjustment. Summary of the Invention

[0005] The object of the present invention is to solve the drawbacks existing in the prior art and to propose a method for detecting the spraying quality of the surface of a glass bottle.

[0006] To achieve the above object, the present invention adopts the following technical solution: A method for detecting the spraying quality of the surface of a glass bottle, comprising the following steps:

[0007] S1: At a specified wavelength, by adjusting the polarization angle to obtain the target incident light, irradiate the spray coating of the glass bottle, collect the transmitted spectral signal, calculate the parallel and perpendicular polarization transmittances and the ratio of the spray coating, and generate the polarization transmittance ratio.

[0008] S2: Based on the polarization transmittance ratio, obtain the vertical incident narrow-band laser scattering signal, calculate the coherent attenuation rate, set the normal region threshold to determine whether the attenuation rate exceeds the range, and generate a record of the local abnormal region identification of the spray coating.

[0009] S3: Combining the record of the local abnormal region identification of the spray coating, calculate the change rate of the differential angle transmittance, analyze the color deviation and the thickness abnormal region, and obtain the spray coating thickness distribution and color deviation data.

[0010] S4: Based on the record of the local abnormal region identification of the spray coating and the spray coating thickness distribution and color deviation data, determine the position and density of the surface defect area, analyze the thickness non-uniformity and color deviation, calculate the correlation, and generate the spray coating quality evaluation data.

[0011] S5: According to the spray coating quality evaluation data, distinguish the color deviation, thickness abnormality and defect type, correspondingly mark the over-limit category, calculate the deviation range and deviation ratio, analyze the thickness offset and uniformity, and generate the spray coating defect location classification data.

[0012] As a further solution of the present invention, the polarization transmittance includes parallel polarization transmittance, perpendicular polarization transmittance, and transmittance ratio. The identification record of the local abnormal area of the spray coating specifically includes the coordinates of the abnormal area, the area of the abnormal area, and the abnormal value of the coherent attenuation rate. The thickness distribution and color deviation data of the spray coating include the transmittance peak value, the change rate of the transmittance at the differential angle, the color deviation distribution, and the thickness abnormal area. The quality evaluation data of the spray coating specifically includes the position of the defect area, the density of the defect area, the analysis result of the thickness non-uniformity, the analysis result of the color deviation, and the influencing factors of the spraying quality. The defect location and classification data of the spray coating include the over-limit category of the color deviation, the thickness abnormal category, the defect type classification, the deviation range of the detection position, the deviation ratio, the thickness offset, and the analysis result of the thickness uniformity.

[0013] As a further solution of the present invention, the specific steps for obtaining the incident light of the target wavelength at the set polarization angle, irradiating the spray coating on the glass bottle, collecting the transmission spectrum signal, calculating the parallel and perpendicular polarization transmittances of the spray coating, and calculating the ratio of the two to generate the polarization transmittance are as follows:

[0014] S101: Obtain the incident light of the target wavelength at the set horizontal polarization angle and vertical polarization angle, irradiate the spray coating on the surface of the glass bottle, adjust the incident angle and receiving angle of the spectral detector, record the polarization transmission spectrum signal of the spray coating on the surface of the glass bottle, perform formatting processing on the spectral data, and group the spectral data according to the polarization direction to obtain the polarization transmission spectrum signal data;

[0015] S102: Based on the polarization transmission spectrum signal data, for the differential wavelength points, extract the light intensity values of the horizontal polarization component and the vertical polarization component, calculate the transmittance at multiple wavelength points, and perform a ratio calculation on the transmitted light intensity values in different polarization directions and the corresponding incident light intensity values to obtain the polarization direction transmittance data;

[0016] S103: Call the polarization direction transmittance data, calculate the ratio of the horizontal polarization component transmittance to the vertical polarization component transmittance for all wavelength points, sort the ratio data by wavelength points, and generate the polarization transmittance.

[0017] As a further solution of the present invention, the specific formula for calculating the transmittance at multiple wavelength points is:

[0018]

[0019] Calculate the transmittance T at multiple wavelength points λ , and perform a ratio calculation on the transmitted light intensity values in different polarization directions and the corresponding incident light intensity values to obtain the polarization direction transmittance data;

[0020] where T λrepresents the transmittance at the representative wavelength λ, I ⊥,λ represents the light intensity value of the vertically polarized component at the wavelength λ, I ||,λ represents the light intensity value of the horizontally polarized component at the wavelength λ represents the incident light intensity value at the wavelength λ3 represents the cumulative sum of the product of the vertically polarized and horizontally polarized light intensities between the wavelengths λ1 and λ2 represents the total sum of the incident light intensity values between the wavelengths λ3 and λ4

[0021] As a further solution of the present invention, based on the polarization transmittance ratio, the specific steps for obtaining the vertically incident narrow-band laser scattering signal, calculating the coherent attenuation rate, setting the normal region threshold to judge whether the attenuation rate exceeds the range, and generating the local abnormal region identification record of the spray coating are as follows

[0022] S201: Obtain the polarization transmittance ratio of the spray coating, detect the scattering signal generated after the narrow-band laser is vertically incident on the spray coating on the surface of the glass bottle, collect the coherent length data of the reflected scattered light recorded by the detector, calculate the coherent attenuation rate of the scattered light according to the coherent length data, and generate the coherent attenuation rate distribution record of the spray coating

[0023] S202: Based on the coherent attenuation rate distribution record of the spray coating, set the coherent attenuation rate threshold of the normal region of the spray coating, compare the coherent attenuation rate data of the detection position with the set threshold, judge whether the attenuation rate exceeds the threshold range, record the positions exceeding the threshold range, and classify and mark the regions higher and lower than the threshold to generate the abnormal attenuation rate region marking result of the spray coating

[0024] S203: Call the abnormal attenuation rate region marking result of the spray coating, screen out the actual positions of the weak regions, particle defect points, spray coating accumulation and over-spraying regions of the spray coating, combine the detection position coordinate information, identify the abnormal regions, and obtain the local abnormal region identification data of the spray coating

[0025] As a further solution of the present invention, the specific steps for calculating the differential angle transmittance change rate in combination with the local abnormal region identification record of the spray coating, analyzing the color deviation and thickness abnormal regions, and obtaining the thickness distribution and color deviation data of the spray coating are as follows

[0026] S301: According to the polarization transmittance ratio and the local abnormal region identification data of the spray coating, obtain the multi-angle light source transmittance signals during the rotation process, calculate the multi-angle transmittance curve, and record the spectral distribution in the corresponding wavelength range to obtain the multi-angle transmittance peak and spectral distribution data

[0027] S302: Calculate the gradient change of transmittance at adjacent angles based on the multi-angle transmittance peak and spectral distribution data, analyze the multi-angle change rate of transmittance during rotation, aggregate the transmittance gradients at all angles, and obtain the multi-angle transmittance gradient change information;

[0028] S303: Based on the multi-angle transmittance gradient change information, compare the multi-angle transmittance gradient with the overall trend, filter out the areas where the transmittance gradient change exceeds the benchmark threshold and mark them as color deviation areas, filter out the areas where the transmittance gradient change is lower than the benchmark threshold and mark them as abnormal areas of the spray coating thickness, and obtain the spray coating thickness distribution and color deviation data.

[0029] As a further solution of the present invention, the specific formula for calculating the multi-angle transmittance curve is:

[0030]

[0031] Obtain the multi-angle light source transmittance signals during rotation and record the spectral distribution within the corresponding wavelength range to obtain the multi-angle transmittance peak and spectral distribution data;

[0032] Among them, T θ represents the transmittance at different angles during rotation, represents the light source power corresponding to the wavelength λ i α i represents the absorption coefficient of the spray coating at the wavelength λ i d i represents the local thickness of the spray coating at the wavelength λ i Δd i represents the local thickness change of the spray coating at the wavelength λ i θ represents the rotation angle, cos(θ) represents the influence factor of the rotation angle on the transmittance, Δθ j represents the rotation error at the angle θ j B represents the number of measured angles, and n represents the number of measured wavelengths.

[0033] As a further solution of the present invention, based on the local abnormal area identification records of the spray coating and the spray coating thickness distribution and color deviation data, the specific steps for determining the position and density of the surface defect area, analyzing the thickness non-uniformity and color deviation, calculating the correlation, and generating the spray coating quality evaluation data are as follows:

[0034] S401: Obtain the local abnormal area identification data of the spray coating and the spray coating thickness and color deviation data, extract the coordinate information, area and morphological characteristics of the abnormal area, calculate the distribution mean, range and thickness gradient change value of the thickness, and combine the mean, maximum deviation value and deviation range of the color deviation to generate the spray coating abnormal area statistical value;

[0035] S402: Based on the statistical value of the abnormal area of the sprayed coating, calculate the distribution density of the coordinate information of the abnormal area. Use the regional area and the thickness gradient change value to classify the thickness non-uniformity, and calculate the proportion of the abnormal area under different thickness categories. Call the maximum deviation value and deviation range of the color deviation to classify the distribution of the color deviation in different thickness categories, and generate the defective distribution area of the sprayed coating;

[0036] S403: Call the defective distribution area of the sprayed coating. Analyze the correlation among the coordinate information of the abnormal area, the classification of the thickness non-uniformity, and the classification data of the color deviation, as well as the change trends of the thickness non-uniformity and the color deviation. Calculate the degree of influence on the overall quality of the sprayed coating, and generate the quality evaluation data of the sprayed coating.

[0037] As a further solution of the present invention, the specific steps for distinguishing color deviation, thickness abnormality, and defect type according to the quality evaluation data of the sprayed coating, corresponding to mark the overlimit category, calculate the deviation range and deviation ratio, and analyze the thickness offset and uniformity to generate the defect location classification data of the sprayed coating are as follows:

[0038] S501: According to the quality evaluation data of the sprayed coating, extract the color deviation value, the thickness value of the sprayed coating, and the defect characteristic value of the spraying area. Conduct deviation calculation on the data, screen the areas exceeding the average threshold, and correspondingly mark the overlimit category to generate the overlimit area classification marking data;

[0039] S502: Based on the overlimit area classification marking data, extract the overlimit area data according to color deviation, thickness abnormality, and defect type respectively. Match the detection position of the sprayed coating according to the overlimit category, calculate the deviation range and deviation ratio of the detection position, and generate the abnormal detection coordinate data of the sprayed coating;

[0040] S503: Call the abnormal detection coordinate data of the sprayed coating. Calculate the color offset data for the color deviation area, analyze the thickness offset and thickness uniformity for the thickness abnormal area of the sprayed coating, and generate the defect location classification data of the sprayed coating for the defect area.

[0041] As a further solution of the present invention, the specific formula for matching the detection position of the sprayed coating according to the overlimit category is:

[0042]

[0043] Calculate the deviation range D p of the detection position, and the specific formula for the deviation ratio R d of the detection position is:

[0044]

[0045] Calculate the detection position deviation ratio R d , match the detection position of the spray coating according to the overlimit category, calculate the detection position deviation range and deviation ratio, and generate the abnormal detection coordinate data of the spray coating;

[0046] Among them, D p represents the detection position deviation range, X i represents the abscissa of the i-th overlimit area, X c represents the abscissa of the matched detection position of the spray coating, Y j represents the ordinate of the j-th overlimit area, Y c represents the ordinate of the matched detection position of the spray coating, S represents the number of abscissa data points of the overlimit area, m represents the number of ordinate data points of the overlimit area, T k represents the thickness value at the k-th detection position, p represents the total number of thickness detection points, R d represents the detection position deviation ratio, L r represents the detection reference length.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0048] In the present invention, by irradiating the spray coating with light at a polarization angle, the polarization component of the transmitted light is obtained, so as to accurately analyze the thickness uniformity and internal structure, identify the weak areas, particle defects and overspray of the spray coating, improve the defect detection accuracy, collect multi-angle transmittance data and calculate the change rate, accurately locate the color deviation and thickness abnormality, and cross-analyze multiple optical parameters, so that the evaluation of adhesion, curing quality and color consistency is more refined, accurately classify the spraying abnormality, and the synergistic effect of multiple detection means reduces the interference of environmental light, material reflectivity, etc., and improves the detection accuracy of the spraying quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is the step flow diagram of the present invention;

[0050] Figure 2 is the step flow chart of S1 of the present invention;

[0051] Figure 3 is the step flow chart of S2 of the present invention;

[0052] Figure 4 is the step flow chart of S3 of the present invention;

[0053] Figure 5 is the step flow chart of S4 of the present invention;

[0054] Figure 6 is the step flow chart of S5 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0055] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0057] Please refer to Figure 1 , a method for detecting the spraying quality of the surface of a glass bottle, comprising the following steps:

[0058] S1: At a specified wavelength, obtain target incident light by adjusting the polarization angle, irradiate the sprayed coating on the surface of the glass bottle, collect the polarization-direction transmission spectrum signal recorded by the spectral detector, extract the transmission rates of the parallel polarization component and the perpendicular polarization component of the sprayed coating at the wavelength point, calculate the ratio of the two, and generate a polarization transmission ratio;

[0059] S2: Based on the polarization transmission ratio, obtain the scattering signal of narrow-band laser vertically incident on the sprayed coating on the surface of the glass bottle, collect the coherent length data of the reflected scattered light recorded by the detector, calculate the coherent attenuation rate of the scattered light at the detection position, set the coherent attenuation rate threshold for the normal area of the sprayed coating, and judge whether the attenuation rate exceeds the threshold range. If the attenuation rate is higher than the threshold, mark it as a weak area or a particle flaw point of the sprayed coating. If the attenuation rate is lower than the threshold, mark it as an area of piled-up or over-sprayed coating of the sprayed coating, and generate a record of the local abnormal area identification of the sprayed coating;

[0060] S3: According to the record of the local abnormal area identification of the sprayed coating, based on the glass bottle rotation detection process, obtain the transmittance peak data at multiple angles, calculate the transmittance change rate at multiple angles. If the transmittance change rate is higher than the overall trend, mark it as a color deviation area. If the transmittance change rate is lower than the overall trend, mark it as an area with abnormal thickness of the sprayed coating, and obtain the data of the thickness and color deviation of the sprayed coating;

[0061] S4: Use the records of local abnormal area identification of the spray coating and the data of the thickness and color deviation of the spray coating to determine the position and density of the surface defect area, analyze the non-uniformity of the thickness during the spraying process and capture the color deviation, calculate the correlation between the three, analyze the factors affecting the spraying quality, and generate the spray coating quality evaluation data;

[0062] S5: Based on the spray coating quality evaluation data, classify the deviation areas exceeding the set threshold, distinguish the color deviation, the thickness abnormality of the spray coating and the defect type, mark the over-limit category correspondingly, calculate the deviation range and deviation ratio of the detection position, analyze the thickness offset and thickness uniformity, and generate the spray coating defect location and classification data;

[0063] The polarization transmittance includes the parallel polarization transmittance, the vertical polarization transmittance, and the transmittance ratio. The record of the local abnormal area identification of the spray coating is specifically the abnormal area coordinates, the abnormal area area, and the abnormal value of the coherent attenuation rate. The spray coating thickness distribution and color deviation data include the transmittance peak value, the change rate of the transmittance at different polarization angles, the color deviation distribution, and the thickness abnormal area. The spray coating quality evaluation data is specifically the defect area position, the defect area density, the analysis result of the thickness non-uniformity, the analysis result of the color deviation, and the factors affecting the spraying quality. The spray coating defect location and classification data include the over-limit category of the color deviation, the thickness abnormality category, the defect type classification, the deviation range of the detection position, the deviation ratio, the thickness offset, and the analysis result of the thickness uniformity.

[0064] Please refer to Figure 2 , the specific steps of S1 are as follows:

[0065] S101: At a specified wavelength, obtain the target incident light by adjusting the polarization angle, irradiate the spray coating on the surface of the glass bottle, adjust the incident angle and receiving angle of the spectral detector, record the polarization transmission spectral signal of the spray coating on the surface of the glass bottle, perform formatting processing on the spectral data, and group the spectral data according to the polarization direction to obtain the polarization transmission spectral signal data;

[0066] Obtain the incident light of the target wavelength with the set horizontal polarization angle and vertical polarization angle. Generate a light beam with a specific polarization angle through the light source system. This light beam can be controlled by a polarizer or a liquid crystal tunable polarizer to ensure that the incident light has a strictly defined polarization direction and wavelength distribution. Irradiate the spray-coated layer on the surface of the glass bottle so that it interacts with the external coating of the glass bottle. According to the material of the glass surface and the thickness of the spray-coated layer, a part of the incident light is transmitted and the other part is reflected. By adjusting the incident angle and the receiving angle of the spectral detector, the detector can receive the optical signals of the horizontal polarization component and the vertical polarization component transmitted by the spray-coated layer respectively. To ensure the accuracy of the data, spectral data needs to be collected within multiple angular ranges. For example, within the range of the incident angle from 0° to 60°, a measurement is taken every 5°, and it is ensured that the receiving angle of the detector is adjusted synchronously to achieve the complete acquisition of the polarization transmission spectrum. After the spectral detector obtains the spectral data, format the data, including filtering out noise, normalizing the intensity values, etc., and group the data according to the polarization direction, and store the horizontal polarization transmission spectrum and the vertical polarization transmission spectrum data respectively, thereby forming the complete polarization transmission spectrum signal data.

[0067] S102: Based on the polarization transmission spectrum signal data, for different wavelength points, extract the light intensity values of the horizontal polarization component and the vertical polarization component, calculate the transmittance at multiple wavelength points, and perform a ratio calculation on the transmitted light intensity values in different polarization directions and the corresponding incident light intensity values to obtain the polarization direction transmittance data;

[0068] Based on the obtained polarization transmission spectrum signal data, for different wavelength points, extract the light intensity values of the horizontal polarization component and the vertical polarization component, and use a high-precision spectrometer to measure the transmitted light intensities of these components respectively. For example, for laser light sources with wavelengths of 532nm, 632.8nm, and 1064nm, the transmitted intensities Ih = 0.45, 0.62, 0.38 in the horizontal polarization direction and the transmitted intensities Iv = 0.30, 0.55, 0.28 in the vertical polarization direction are measured respectively. To calculate the transmittance at multiple wavelength points, it is necessary to compare with the incident light intensity I0. Set I0 to 1.00, then the transmittance calculation formula is T = I / I0, where I represents the transmitted light intensity. At 532nm, the horizontal polarization transmittance Th = 0.45 / 1.00 = 0.45, and the vertical polarization transmittance Tv = 0.30 / 1.00 = 0.30. To obtain the transmittance data by calculating the ratio of the transmitted light intensities in different polarization directions, compare the ratio of the horizontal and vertical polarization transmittances. Define R = Th / Tv, then at 532nm, R = 0.45 / 0.30 = 1.5. Similarly, calculate the ratios at different wavelengths, and then obtain the polarization transmittance data at different wavelength points to complete the basic calculation of spectral analysis.

[0069] S103: Based on the polarization transmission spectrum signal data, for different wavelength points, extract the light intensity values of the horizontal polarization component and the vertical polarization component, calculate the transmittance at multiple wavelength points, and calculate the ratio of the transmitted light intensity value in the different polarization directions to the corresponding incident light intensity value to obtain the polarization direction transmittance data;

[0070] The specific formula for calculating the transmittance at multiple wavelength points is:

[0071]

[0072] Calculate the transmittance T at multiple wavelength points λ , and calculate the ratio of the transmitted light intensity value in the different polarization directions to the corresponding incident light intensity value to obtain the polarization direction transmittance data;

[0073] where, T λ represents the transmittance at wavelength λ, I ⊥,λ represents the light intensity value of the vertical polarization component at wavelength λ, I ||,λ represents the light intensity value of the horizontal polarization component at wavelength λ, represents the incident light intensity value at wavelength λ3, represents the cumulative sum of the product of the vertical polarization and horizontal polarization light intensities from wavelength λ1 to λ2, represents the sum of the incident light intensity values from wavelength λ3 to λ4;

[0074] Parameter definition and data acquisition:

[0075] I ⊥,λ : The light intensity value of the vertical polarization component at wavelength λ. This is obtained by measuring the light at a specific wavelength under experimental conditions using a polarization spectrometer.

[0076] I ||,λ : The light intensity value of the horizontal polarization component at wavelength λ, also obtained by measuring with a polarization spectrometer.

[0077] I 0,λ : The light intensity value of the incident light at wavelength λ, obtained from the data provided by a standard light source or through a pre-calibrated spectrometer.

[0078] Specific numerical settings and calculation examples:

[0079] Assume that at a wavelength of 500 nm, I ⊥,500nm = 20 units, I ||,500nm = 30 units, I 0,500nm = 100 units.

[0080] Assume that we need to calculate the data in the wavelength range from 400 nm to 700 nm. Let λ1 = 400 nm, λ2 = 700 nm, λ3 = 400 nm, and λ4 = 700 nm.

[0081] Calculate the value of:

[0082] If I 0,λ has an average value of about 150 units in the range of 400 nm to 700 nm, and there are 301 data points in this interval, then units.

[0083] Calculate

[0084] Assume that in the range of 400 nm to 700 nm, the average value of the product of I ⊥,λ and I ||,λ is 600 units, and for the same 301 data points in this interval, then Thus units.

[0085] Calculate T λ :

[0086] Substitute the value of λ = 500 nm and calculate as:

[0087]

[0088] This result shows that at a wavelength of 500 nm, the transmittance T 500 of the polarization direction is 0.96%. This means that the transmittance at the measured wavelength is 0.96% of the incident light intensity value, and this value can be used for further analysis of the polarized light characteristics of the substance.

[0089] Please refer to Figure 3 , and the specific steps of S2 are:

[0090] S201: Obtain the polarization transmittance ratio, detect the scattering signal generated when the narrow-band laser is vertically incident on the spray coating on the glass bottle surface, collect the data of the coherence length of the reflected scattered light recorded by the detector, calculate the coherent attenuation rate of the scattered light according to the coherence length data, and generate a record of the coherent attenuation rate distribution of the spray coating;

[0091] To obtain the polarization transmittance ratio, it is necessary to use a polarization measurement device to perform multi-angle optical measurements on the spray coating on the glass bottle surface, record the transmittance parameters when the laser of a specific wavelength passes through the spray coating, and the transmittance calculation method is where I t represents the transmitted light intensity, I i represents the incident light intensity. The transmittance data measured at different angles need to be normalized to eliminate the influence of the light source power fluctuation in the experimental environment. The normalization formula is where T refrepresents the transmittance of the substrate without the spray coating. The average polarization transmittance of the spray coating is obtained through multiple sets of measurement data. Then, a narrow-band laser is vertically incident on the surface of the spray coating of the glass bottle, and the detector records the intensity distribution of the scattered signal. The scattered signal can be collected by a photomultiplier tube (PMT) or a photon counter, and the arrival time of the photons is recorded to form a time distribution curve. According to the change of the scattered signal, the coherence length of the reflected scattered light is calculated. The specific calculation method is where L c is the coherence length, c is the speed of light, n is the refractive index of the spray coating, and Δf is the spectral width of the light source. By collecting the coherence length data at different positions, the coherence attenuation rate of the scattered light is calculated. The calculation method of the attenuation rate is where I s represents the intensity of the scattered light, and x is the detection position. Using the calculation results of the attenuation rates at multiple detection points, a record of the coherence attenuation rate distribution of the spray coating is constructed.

[0092] S202: Based on the record of the coherence attenuation rate distribution of the spray coating, set the coherence attenuation rate threshold for the normal area of the spray coating. Compare the coherence attenuation rate data at the detection position with the set threshold to determine whether the attenuation rate exceeds the threshold range. Record the positions that exceed the threshold range, and classify and mark the areas above and below the threshold to generate the marking result of the abnormal attenuation rate area of the spray coating;

[0093] Based on the record of the coherence attenuation rate distribution of the spray coating, to set the coherence attenuation rate threshold for the normal area of the spray coating, it is necessary to select the data of the uniform area of the spray coating of the glass bottle as the reference, and calculate the average coherence attenuation rate R avg and the standard deviation σ R of each point in this area. The threshold is set to R th = R avg ±kσ R , where k is an empirical coefficient, and its usual value range is 2 ≤ k ≤ 3 to cover the data of most normal areas. Compare the coherence attenuation rate data at the detection position with the set threshold. If the attenuation rate R at a certain position exceeds R avg +kσ R , then there may be weak spots or particle defects in the spray coating in this area. If R is lower than R avg -kσ R , then there may be spray coating accumulation or overspray phenomenon in this area. The specific classification method is: if R > R th,upper then mark it as a weak area or particle defect area of the spray coating. If R < R th,lower then mark it as a spray coating accumulation or overspray area. After classification and marking, the data forms the distribution of the abnormal attenuation rate area of the spray coating, and the marking result of the abnormal attenuation rate area of the spray coating is obtained.

[0094] S203: Call the marked results of the abnormal attenuation rate regions of the sprayed coating, screen out the actual positions of the weak regions, particle defect points, coating accumulation and overspray regions of the sprayed coating, combine with the detection position coordinate information, identify the abnormal regions, and obtain the identification data of the local abnormal regions of the sprayed coating;

[0095] Call the marked results of the abnormal attenuation rate regions of the sprayed coating, screen out the actual positions of the weak regions, particle defect points, coating accumulation and overspray regions of the sprayed coating, perform position matching on all abnormal regions according to the spatial coordinate information in the detection data. The weak region of the sprayed coating can be defined as the region where the attenuation rate is greater than the normal range. The particle defect points usually show high attenuation rate points that protrude locally. By setting the standard deviation σ of the attenuation rate within the local window w w , if the attenuation rate of a certain point exceeds 3σ of the window mean w , then this point can be defined as a particle defect point. The coating accumulation region shows a low coherent attenuation rate region. If multiple points around the detection point all satisfy R < R th,lower , then it is defined as a coating accumulation region. After determining the classification of the abnormal regions by the above method, combine with the detection position coordinates to obtain the identification data of the local abnormal regions of the sprayed coating.

[0096] Please refer to Figure 4 , the specific steps of S3 are as follows:

[0097] S301: According to the polarization transmittance and the identification data of the local abnormal regions of the sprayed coating, obtain the multi-angle light source transmission signals during the rotation process, calculate the multi-angle transmittance curve, and record the spectral distribution in the corresponding wavelength range to obtain the multi-angle transmittance peak and spectral distribution data;

[0098] Calculate the multi-angle transmittance curve using the formula:

[0099]

[0100] Obtain the multi-angle light source transmission signals during the rotation process, and record the spectral distribution in the corresponding wavelength range to obtain the multi-angle transmittance peak and spectral distribution data;

[0101] Among them, T θ represents the transmittance at different angles during the rotation process, represents the light source power corresponding to the wavelength λ i , α i represents the absorption coefficient of the sprayed coating at the wavelength λ i , d i represents the local thickness of the sprayed coating at the wavelength λ i , Δd i represents the local thickness change of the sprayed coating at the wavelength λ iThe local thickness variation at a certain point, θ represents the rotation angle, cos(θ) represents the influence factor of the rotation angle on the transmittance, and Δθ j represents the angle θ j is the rotation error at a certain point, B represents the number of measured angles, and n represents the number of measured wavelengths;

[0102] Formula calculation and derivation:

[0103] Calculate the numerator part of the transmittance:

[0104] First, calculate the transmittance contribution at each wavelength:

[0105]

[0106] Taking the wavelength of 500nm as an example:

[0107]

[0108] The calculated result is:

[0109]

[0110] Calculate the denominator part of the transmittance:

[0111] Sum up the light source powers of all wavelengths. Assume that 5 wavelengths are measured, and the power of each wavelength is 1.5W / m 2 :

[0112]

[0113] Calculate the first part of the transmittance:

[0114] Substitute the above results:

[0115]

[0116] Calculate the normalized sum of squares of the thickness variation and the angular error:

[0117] For the thickness variation:

[0118]

[0119] For the angular error, assume that 3 angles are measured, and the error of each angle is 0.0087 radians:

[0120]

[0121] Calculate the normalization factor:

[0122] Add the above results and take the square root:

[0123]

[0124] Take the reciprocal:

[0125]

[0126] Final transmittance calculation:

[0127] Multiply all parts together:

[0128] T θ = 0.866 × 4.436 ≈ 3.844;

[0129] This result indicates the normalized transmittance of the spray coating at a 30° angle under the set measurement conditions.

[0130] S302: Based on the multi-angle transmittance peak and spectral distribution data, calculate the gradient change of the transmittance between adjacent angles, analyze the multi-angle change rate of the transmittance during rotation, aggregate the transmittance gradients of all angles, and obtain the multi-angle transmittance gradient change information;

[0131] After obtaining the multi-angle transmittance peak and spectral distribution data, it is necessary to calculate the gradient change of the transmittance between adjacent angles and analyze the change rate of the transmittance at different angles during rotation. First, define the transmittance gradient change, that is, calculate the change rate of the transmittance between adjacent angles. Specifically, when calculating, take every 5° as a step, calculate the difference in transmittance between adjacent angles, and divide by the angle increment to obtain the transmittance gradient under the change of a unit angle. The calculation of the transmittance gradient change requires traversing all angles and sorting out the overall gradient change trend. If the transmittance gradient change within a certain angle range is significantly higher than the average value of adjacent angles, there may be non-uniformity of the spray coating or abnormal coating thickness during the spraying process. When further analyzing, the standard deviation σ ΔT can be introduced to measure the overall fluctuation of the transmittance gradient change. By calculating the average value of the transmittance gradient changes of all angles and the standard deviation σ ΔT , the abnormal range of different gradient changes can be defined. For example, if the gradient change of a certain angle exceeds the average value , there may be abnormal changes in the spray coating thickness in this angle area, and if the gradient change of a certain area is lower than , the spray coating in this area may be too uniform and lack normal optical gradient characteristics. After the calculation is completed, sort out the transmittance gradient change information of all angles for subsequent analysis.

[0132] S303: Based on the multi-angle transmittance gradient change information, compare the multi-angle transmittance gradient with the overall trend, screen out the transmittance gradient changes that exceed the reference threshold, mark them as color deviation areas, screen out the transmittance gradient changes that are lower than the reference threshold, mark them as spray coating thickness abnormal areas, and obtain the spray coating thickness distribution and color deviation data;

[0133] According to the transmittance gradient change information, further screen the areas where the transmittance gradient change exceeds the reference threshold, and mark them as color deviation areas. At the same time, screen the areas where the transmittance gradient change is lower than the reference threshold, and mark them as abnormal spray coating thickness areas. Specifically, when operating, first, it is necessary to set the reference threshold ΔT of the gradient change thresh , and this threshold can be based on the average gradient change of all measurement points and the standard deviation σ ΔT for setting. For example, set If the transmittance gradient change value at a certain angle is greater than this threshold, it indicates that the transmittance change in this area is too fast, which may be due to the uneven color distribution of the spray coating. Therefore, mark this area as a color deviation area. On the other hand, set the reference threshold ΔT of the abnormal spray coating thickness low , usually ΔT low can be set as If the transmittance gradient change value at a certain angle is lower than this threshold, it indicates that the thickness of the spray coating in this area may be abnormal, such as being too thick or too thin. After the calculation is completed, visualize the detection results of color deviation and thickness abnormality to identify the abnormal areas at different angles, and finally obtain the spray coating thickness distribution and color deviation data.

[0134] Please refer to Figure 5 , and the specific steps of S4 are as follows:

[0135] S401: Obtain the identification data of the local abnormal areas of the spray coating and the data of the spray coating thickness and color deviation, extract the coordinate information, area, and morphological characteristics of the abnormal areas, calculate the distribution mean, range, and thickness gradient change value of the thickness, and combine the mean, maximum deviation value, and deviation range of the color deviation to generate the statistical value of the abnormal areas of the spray coating;

[0136] Obtain the identification data of the local abnormal areas of the spray coating and the data of the spray coating thickness and color deviation, extract the coordinate information, area, and morphological characteristics of the abnormal areas. Based on the coordinate information of the abnormal areas, extract the spray coating thickness data and conduct distribution statistics. Use the mean formula to calculate the thickness mean, where x i is the thickness data at the detection point, and n is the total number of detection points. Obtain the range of the spray coating thickness. Use range = x max - x min to calculate the difference between the maximum thickness and the minimum thickness, and then evaluate the distribution characteristics of the thickness. Combine the spray coating thickness data and calculate the change trend along the detection path. Use to calculate the thickness change rate between different detection points, where Δh is the thickness difference between adjacent detection points, and Δd is the detection point spacing. Obtain the spray coating thickness gradient change value, call the color deviation data, and use Calculate the mean color deviation, where c i is the color deviation value at each detection point, obtain the maximum deviation value and deviation range of the color deviation, combine the thickness data and the color deviation data, construct the characteristic data of the abnormal area of the sprayed coating, and finally obtain the statistical value of the abnormal area of the sprayed coating.

[0137] S402: Based on the statistical value of the abnormal area of the sprayed coating, calculate the distribution density of the coordinate information of the abnormal area, use the regional area and the thickness gradient change value to classify the thickness non-uniformity, and calculate the proportion of the abnormal area in different thickness categories. Call the maximum deviation value and deviation range of the color deviation to classify the distribution of the color deviation in different thickness categories, and generate the defective distribution area of the sprayed coating;

[0138] Based on the statistical value of the abnormal area of the sprayed coating, extract the coordinate information of the abnormal area, adopt the two-dimensional density calculation method, and use to calculate the distribution density, where N is the number of marked points in the abnormal area, A is the total area of the abnormal area, obtain the distribution density data of the abnormal area, call the thickness gradient change value of the sprayed coating, and classify the thickness non-uniformity by using the threshold judgment method. Set the thickness gradient threshold θ h , when the thickness gradient > θ h , mark this area as the thickness mutation area, otherwise mark it as the thickness uniform area, calculate the proportion of the abnormal area in different thickness categories, and use to calculate the proportion of each thickness category area in the overall detection area, where A c is the total area of a certain category of abnormal area, A t is the area of the overall detection area, call the maximum deviation value and deviation range of the color deviation to classify the distribution of the color deviation in different thickness categories, and set the color deviation threshold θ c , when the color deviation > θ c , mark it as the serious color deviation area, otherwise mark it as the slight color deviation area. Combine the thickness and color deviation classification results to obtain the defective distribution area of the sprayed coating.

[0139] S403: Call the defective distribution area of the sprayed coating, analyze the correlation between the coordinate information of the abnormal area, the classification of thickness non-uniformity and the color deviation classification data, the change trend of thickness non-uniformity and color deviation, calculate the impact degree on the overall quality of the sprayed coating, and generate the quality evaluation data of the sprayed coating;

[0140] Call the defective distribution area of the sprayed coating, analyze the correlation among the coordinate information of the abnormal area, the classification of thickness non-uniformity and the color deviation classification data, and use the Pearson correlation coefficient Calculate the linear correlation between the thickness non-uniformity and the color deviation, where X i is the thickness gradient data, and Y i is the color deviation data. and are their respective means. Obtain the correlation coefficient between the thickness and the color deviation, analyze the changing trends of the thickness non-uniformity and the color deviation, use the regression analysis method to fit the changing relationship between the two, calculate the fitting curve equation between the thickness change Δh and the color deviation Δc, and combine with the quality standard of the sprayed coating to set the quality impact threshold θ q . When ρ > θ q , it indicates that the thickness non-uniformity has a greater impact on the color deviation. Further calculate the influence degree of different defect regions on the overall quality of the sprayed coating. Use the influence ratio = % to calculate the influence proportion of the abnormal region in the overall spraying region, where A d is the total area of the region with defects, and A t is the area of the overall spraying region. Finally, obtain the quality evaluation data of the sprayed coating.

[0141] Please refer to Figure 6 , and the specific steps of S5 are as follows:

[0142] S501: According to the quality evaluation data of the sprayed coating, extract the color deviation value, the sprayed coating thickness value, and the defect characteristic value of the spraying region, perform deviation calculation on the data, screen the regions exceeding the average threshold, and correspondingly mark the over-limit category to generate over-limit region classification mark data;

[0143] According to the quality evaluation data of the sprayed coating, first extract the color deviation value, the sprayed coating thickness value, and the defect characteristic value of the spraying region. Among them, the color deviation value can extract the color difference information of the RGB channel through the image processing algorithm, and the calculation method can adopt the ΔE color difference formula, that is, ΔE = √[(L2 - L1) 2 +(a2 - a1) 2 +(b2 - b1) 2, where L, a, and b represent the brightness, red-green deviation value, and blue-yellow deviation value of the color space respectively. The thickness value of the spray coating can be obtained by an ultrasonic or laser thickness gauge. The defect characteristic value can be extracted based on parameters such as the texture characteristics of the surface structure and the irregularity of the edge contour identified by machine vision. Subsequently, data deviation calculations are performed on each parameter, and the calculation method is the deviation ratio relative to the average value or standard value. For example, the deviation rate R = (Vi - Vavg) / Vavg × 100%, where Vi is the single-point measurement value and Vavg is the regional average value. By setting a threshold Th to judge whether the deviation exceeds the standard range, if |R| > Th, then the area is determined as an over-limit area. The areas exceeding the threshold are screened and classified based on the deviation type. Color deviation can be classified according to the ΔE threshold. For example, ΔE < 2 is the normal range, 2 ≤ ΔE < 5 is a slight deviation, and ΔE ≥ 5 is a serious deviation. Thickness deviation can be determined based on the standard deviation σ of the thickness measurement data and the set deviation range Th. For example, |Tmeasurement - Tstandard| > Th. Defects are classified according to the defect size, depth, and density. Combining the measurement results, the areas exceeding the average threshold are classified and marked. For example, a three-color marking method is used (red represents serious deviation, yellow represents slight deviation, and green represents normal), and finally, over-limit area classification marking data is generated.

[0144] S502: Based on the over-limit area classification marking data, extract the over-limit area data according to color deviation, thickness abnormality, and defect type respectively. Match the spray coating detection positions according to the over-limit categories, calculate the deviation range and deviation ratio of the detection positions, and generate spray coating abnormal detection coordinate data;

[0145] The specific formula for matching the spray coating detection positions according to the over-limit categories is:

[0146]

[0147] Calculate the deviation range D of the detection position p , and the deviation ratio R of the detection position d The specific formula is:

[0148]

[0149] Calculate the deviation ratio R of the detection position d , match the spray coating detection positions according to the over-limit categories, calculate the deviation range and deviation ratio of the detection positions, and generate spray coating abnormal detection coordinate data;

[0150] Among them, D p represents the deviation range of the detection position, X i represents the abscissa of the i-th over-limit area, X c represents the abscissa of the matched spray coating detection position, Y j represents the ordinate of the j-th over-limit area, Yc represents the ordinate of the detected position of the matching spray coating layer, S represents the number of abscissa data points in the over-limit area, m represents the number of ordinate data points in the over-limit area, and T k represents the thickness value at the k-th detected position, p represents the total number of thickness detection points, and R d represents the detection position deviation ratio, L r represents the detection reference length,

[0151] The detection position deviation range D p Calculation:

[0152] Step 1: Calculate the average deviation of the abscissa and ordinate.

[0153] Average deviation of the abscissa:

[0154] Set the abscissa X of the over-limit area i and the abscissa X of the detected position of the matching spray coating layer c .

[0155] Calculate the deviation |X i -X c | between each over-limit area point and the detected position.

[0156] Sum up these deviations and divide by the number of data points n to obtain the average deviation of the abscissa.

[0157] Average deviation of the ordinate:

[0158] Similarly, set the ordinate Y of the over-limit area j and the ordinate Y of the detected position of the matching spray coating layer c .

[0159] Calculate the deviation |Y j -Y c | between each over-limit area point and the detected position.

[0160] Sum up these deviations and divide by the number of data points m to obtain the average deviation of the ordinate.

[0161] Step 2: Calculate the root mean square of the thickness values.

[0162] Set the thickness value T of the detected position k .

[0163] Calculate the square of each thickness value

[0164] Sum up these squared values, divide by the total number p of thickness detection points, and then take the square root to obtain the root mean square of the thickness values.

[0165] Step 3: Calculate the detection position deviation range Dp 。

[0166] Add the average deviations of the abscissa and ordinate to obtain the total average deviation.

[0167] Multiply the total average deviation by the root mean square of the thickness value to obtain the detection position deviation range D p 。

[0168] Substitute specific values for calculation:

[0169] Set parameters:

[0170] The number of abscissa data points S in the overlimit area = 5.

[0171] The number of ordinate data points m in the overlimit area = 5.

[0172] The total number of thickness detection points p at the detection position = 5.

[0173] The abscissa values X in the overlimit area i Are respectively: 100, 105, 98, 102, 101.

[0174] The abscissa X of the matching spray coating detection position c = 100.

[0175] The ordinate values Y in the overlimit area j Are respectively: 200, 198, 202, 199, 201. The ordinate Y of the matching spray coating detection position c = 200.

[0176] The thickness values T at the detection position k Are respectively: 50, 52, 51, 49, 50 microns.

[0177] Calculation process:

[0178] Average deviation of abscissa:

[0179]

[0180] Average deviation of ordinate:

[0181]

[0182] Total average deviation:

[0183]

[0184] Root mean square of thickness value:

[0185]

[0186] Detection position deviation range D p:

[0187] 1.6 × 50.41 ≈ 80.66 microns;

[0188] Calculation of the detection position deviation ratio R d of:

[0189] Step 1: Determine the detection reference length L r .

[0190] Assume the detection reference length L r = 500 microns.

[0191] Step 2: Calculate the detection position deviation ratio R d .

[0192] Use the formula:

[0193]

[0194] Substitute the values:

[0195]

[0196] Result analysis:

[0197] Detection position deviation range D p is approximately 80.66 microns.

[0198] This result represents the average deviation between the detection position and the detection position of the matching spray coating, taking into account the influence of the thickness value.

[0199] Detection position deviation ratio R d is approximately 16.13%.

[0200] This result represents the percentage of the detection position deviation range relative to the detection reference length, used to evaluate the deviation degree of the detection position.

[0201] S503: Call the spray coating anomaly detection coordinate data, for the color deviation area, calculate the color offset data, for the spray coating thickness anomaly area, analyze the thickness offset and thickness uniformity, and for the defect area, generate the spray coating defect location classification data;

[0202] Call the spray coating anomaly detection coordinate data, for the color deviation area, calculate the color offset data, use the ΔE color difference formula to calculate the color offset of different detection points, and further analyze the color offset direction, for example, calculate the change trend of the color components through the RGB channels. For the spray coating thickness anomaly area, analyze the thickness offset and thickness uniformity. The thickness offset can be calculated using the deviation ratio R = (T measured - T standard) / T standard × 100%, and the thickness uniformity can be calculated by the variance σ 2 = ∑(Ti - Tavg)2 Measured by / (N - 1), for the defective area, generate defect location classification data of the sprayed coating, which can be classified according to defect size, shape, depth and distribution density. For example, defects with a size d < 0.5mm are minor defects, 0.5mm ≤ d < 2mm are medium defects, and d ≥ 2mm are severe defects. The classification basis of defect size comes from the surface quality standard and functional requirements of the sprayed coating. For example, in automotive coating inspection, if the defect size d is less than 0.5mm, it is difficult to detect with the naked eye and has little impact on the overall appearance, so it can be determined as a minor defect; when 0.5mm ≤ d < 2mm, such defects are visible under certain lighting conditions and affect the local aesthetics, so they can be classified as medium defects; when d ≥ 2mm, the defects can significantly affect the appearance integrity and even the protective performance of the sprayed coating, so they are classified as severe defects. This classification basis can be further dynamically adjusted in combination with the coating thickness T, surface glossiness G, and visual visibility V. For example, if T is relatively thin (<50μm), even a 0.4mm defect may significantly affect the surface quality, so the threshold for minor defects can be appropriately reduced to d < 0.4mm; if G is relatively high (>85GU, gloss unit), the visibility of the defect increases, and at this time the upper limit of medium defects can be reduced to 1.5mm; in addition, if the defect density D exceeds a certain threshold (such as D > 0.01 per mm 2 ), then minor defects may accumulate into medium defects and need to be reclassified. Therefore, the setting of the defect size threshold needs to be dynamically adjusted in combination with the coating material characteristics, spraying process parameters and the final application environment to ensure the rationality of classification. The defect distribution density D can be calculated as D = (total number of defects / total inspection area), and finally form the defect classification data of the sprayed coating.

[0203] The above is only the preferred embodiment of the present invention, and it does not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for detecting the spraying quality of the surface of a glass bottle, characterized in that, It includes the following steps: S1: At a specified wavelength, obtain the target incident light by adjusting the polarization angle, irradiate the spray coating on the glass bottle, collect the transmission spectrum signal, calculate the parallel and perpendicular polarization transmittances and their ratio of the spray coating, and generate the polarization transmittance ratio. S2: Based on the polarization transmittance ratio, obtain the vertical incident narrowband laser scattering signal, calculate the coherent attenuation rate, set the normal region threshold to determine whether the attenuation rate exceeds the range, and generate the record of the local abnormal region identification of the spray coating. S3: Combine the record of the local abnormal region identification of the spray coating, calculate the change rate of the differential angle transmittance, analyze the color deviation and the thickness abnormal region, and obtain the thickness distribution and color deviation data of the spray coating. S4: Based on the record of the local abnormal region identification of the spray coating and the thickness distribution and color deviation data of the spray coating, determine the position and density of the surface defect area, analyze the thickness non-uniformity and color deviation, calculate the correlation, and generate the spray coating quality evaluation data. S5: According to the spray coating quality evaluation data, distinguish the color deviation, thickness abnormality and defect type, mark the over-limit category correspondingly, calculate the deviation range and deviation ratio, analyze the thickness offset and uniformity, and generate the spray coating defect location and classification data.

2. The surface spraying quality inspection method of the glass bottle according to claim 1, characterized in that The polarization transmittance ratio includes the parallel polarization transmittance, perpendicular polarization transmittance, and transmittance ratio. The record of the local abnormal region identification of the spray coating is specifically the abnormal region coordinates, abnormal region area, and abnormal value of the coherent attenuation rate. The thickness distribution and color deviation data of the spray coating include the transmittance peak, change rate of the differential angle transmittance, color deviation distribution, and thickness abnormal region. The spray coating quality evaluation data is specifically the defect area position, defect area density, thickness non-uniformity analysis result, color deviation analysis result, and factors affecting the spraying quality. The spray coating defect location and classification data include the over-limit category of color deviation, thickness abnormality category, defect type classification, detection position deviation range, deviation ratio, thickness offset, and thickness uniformity analysis result.

3. The method for detecting the spraying quality of the glass bottle surface according to claim 1, wherein At a specified wavelength, the specific steps to obtain the target incident light by adjusting the polarization angle, irradiate the spray coating on the glass bottle, collect the transmission spectrum signal, calculate the parallel and perpendicular polarization transmittances and their ratio of the spray coating, and generate the polarization transmittance ratio are as follows: S101: Obtain the incident light of the target wavelength with the set horizontal polarization angle and vertical polarization angle, irradiate the spray coating on the glass bottle surface, adjust the incident angle and receiving angle of the spectral detector, record the polarization transmission spectrum signal of the spray coating on the glass bottle surface, perform formatting processing on the spectral data, and group the spectral data according to the polarization direction to obtain the polarization transmission spectrum signal data. S102: Based on the polarization transmission spectrum signal data, for the differential wavelength points, extract the light intensity values of the horizontal polarization component and vertical polarization component, calculate the transmittance at multiple wavelength points, perform ratio calculation on the transmitted light intensity values in different polarization directions and the corresponding incident light intensity values, and obtain the polarization direction transmittance data. S103: Call the polarization direction transmittance data, calculate the ratio of the horizontal polarization component transmittance to the vertical polarization component transmittance for all wavelength points, sort the ratio data by wavelength points, and generate the polarization transmittance ratio.

4. The method for detecting the spraying quality of the glass bottle surface according to claim 3, characterized in that, The specific formula for calculating the transmittance at multiple wavelengths is as follows: Calculate the transmittance T at multiple wavelength points λ , calculate the ratio of the transmitted light intensity value with different polarization directions to the corresponding incident light intensity value to obtain the polarization direction transmittance data; Among them, T λ represents the transmittance at wavelength λ, I ⊥,λ represents the light intensity value of the vertically polarized component at wavelength λ, I ∥,λ represents the light intensity value of the horizontally polarized component at wavelength λ, represents the incident light intensity value at wavelength λ3, represents the cumulative sum of the product of the vertically polarized and horizontally polarized light intensities between wavelengths λ1 and λ2, represents the total sum of the incident light intensity values between wavelengths λ3 and λ4.

5. The method for detecting the spraying quality of the glass bottle surface according to claim 1, characterized in that Based on the polarization transmittance ratio, the specific steps for obtaining the vertically incident narrow-band laser scattering signal, calculating the coherent attenuation rate, setting the normal region threshold to determine whether the attenuation rate exceeds the range, and generating the identification record of the local abnormal region of the sprayed coating are as follows: S201: Obtain the polarization transmittance ratio of the sprayed coating, detect the scattering signal generated after the narrow-band laser is vertically incident on the surface of the glass bottle sprayed coating, collect the coherent length data of the reflected scattered light recorded by the detector, calculate the coherent attenuation rate of the scattered light according to the coherent length data, and generate the record of the coherent attenuation rate distribution of the sprayed coating; S202: Based on the record of the coherent attenuation rate distribution of the sprayed coating, set the coherent attenuation rate threshold for the normal region of the sprayed coating, compare the coherent attenuation rate data at the detection position with the set threshold, determine whether the attenuation rate exceeds the threshold range, record the positions that exceed the threshold range, and classify and mark the regions above and below the threshold to generate the marking result of the abnormal attenuation rate region of the sprayed coating; S203: Call the marking result of the abnormal attenuation rate region of the sprayed coating, screen out the actual positions of the weak regions, particle defect points, sprayed coating accumulation, and over-sprayed regions of the sprayed coating, combine the coordinate information of the detection position, identify the abnormal regions, and obtain the identification data of the local abnormal region of the sprayed coating.

6. The method for detecting the spraying quality of the glass bottle surface according to claim 1, characterized in that Combined with the identification record of the local abnormal region of the sprayed coating, the specific steps for calculating the change rate of the differential angle transmittance, analyzing the color deviation and the thickness abnormal region, and obtaining the thickness distribution and color deviation data of the sprayed coating are as follows: S301: According to the polarization transmittance ratio and the identification data of the local abnormal region of the sprayed coating, obtain the multi-angle light source transmittance signal during the rotation process, calculate the multi-angle transmittance curve, and record the spectral distribution in the corresponding wavelength range to obtain the multi-angle transmittance peak and spectral distribution data; S302: Based on the multi-angle transmittance peak and spectral distribution data, calculate the gradient change of the transmittance between adjacent angles, analyze the multi-angle change rate of the transmittance during the rotation process, and aggregate the transmittance gradients of all angles to obtain the multi-angle transmittance gradient change information; S303: Based on the multi-angle transmittance gradient change information, compare the multi-angle transmittance gradient with the overall trend, screen out the transmittance gradient changes that exceed the reference threshold and mark them as color deviation regions, screen out the transmittance gradient changes that are lower than the reference threshold and mark them as the thickness abnormal regions of the sprayed coating to obtain the thickness distribution and color deviation data of the sprayed coating.

7. The method for detecting the spraying quality of the glass bottle surface according to claim 6, wherein, The specific formula for calculating the multi-angle transmittance curve is as follows: Obtain the multi-angle light source transmittance signal during the rotation process, and record the spectral distribution in the corresponding wavelength range to obtain the multi-angle transmittance peak and spectral distribution data; Among them, T θ represents the transmittance at different angles during the rotation process, represents the wavelength λ i corresponding to the light source power, α i represents the absorption coefficient of the sprayed coating at the wavelength λ i at that point, d i represents the local thickness of the sprayed coating at the wavelength λ i at that point, Δd i represents the change in the local thickness of the sprayed coating at the wavelength λ i at that point, θ represents the rotation angle, cos(θ) represents the influence factor of the rotation angle on the transmittance, Δθ j represents the rotation error at the angle θ j at that point, B represents the number of measured angles, and n represents the number of measured wavelengths.

8. The method for detecting the spraying quality of the glass bottle surface according to claim 1, wherein, Based on the identification record of the local abnormal region of the sprayed coating and the thickness distribution and color deviation data of the sprayed coating, determine the position and density of the surface defect region, analyze the thickness non-uniformity and color deviation, calculate the correlation, and generate the specific steps for the quality evaluation data of the sprayed coating are as follows: S401: Obtain the identification data of the local abnormal area of the sprayed coating and the data of the thickness and color deviation of the sprayed coating, extract the coordinate information, area and morphological characteristics of the abnormal area, calculate the distribution mean, range and thickness gradient change value of the thickness, and combine the mean, maximum deviation value and deviation range of the color deviation to generate the statistical value of the abnormal area of the sprayed coating; S402: Based on the statistical value of the abnormal area of the sprayed coating, calculate the distribution density of the coordinate information of the abnormal area, classify the thickness non-uniformity by using the area and thickness gradient change value, calculate the proportion of the abnormal area in different thickness categories, and call the maximum deviation value and deviation range of the color deviation to classify the distribution of the color deviation in different thickness categories to generate the defective distribution area of the sprayed coating; S403: Call the defective distribution area of the sprayed coating, analyze the correlation between the coordinate information, thickness non-uniformity classification and color deviation classification data of the abnormal area, the change trend of the thickness non-uniformity and the color deviation, calculate the influence degree on the overall quality of the sprayed coating, and generate the quality evaluation data of the sprayed coating.

9. The method for detecting the spraying quality of the glass bottle surface according to claim 1, wherein, The specific steps for generating the defective location classification data of the sprayed coating by distinguishing the color deviation, thickness abnormality and defect type according to the quality evaluation data of the sprayed coating, corresponding marking the overlimit category, calculating the deviation range and deviation ratio, and analyzing the thickness offset and uniformity are as follows. S501: According to the quality evaluation data of the sprayed coating, extract the color deviation value, sprayed coating thickness value and defect characteristic value of the spraying area, perform deviation calculation on the data, screen the areas exceeding the average threshold, and correspondingly mark the overlimit category to generate the overlimit area classification marking data; S502: Based on the overlimit area classification marking data, extract the overlimit area data according to the color deviation, thickness abnormality and defect type respectively, match the detection position of the sprayed coating according to the overlimit category, calculate the deviation range and deviation ratio of the detection position, and generate the abnormal detection coordinate data of the sprayed coating; S503: Call the abnormal detection coordinate data of the sprayed coating, calculate the color offset data for the color deviation area, analyze the thickness offset and thickness uniformity for the thickness abnormal area of the sprayed coating, and generate the defective location classification data of the sprayed coating for the defect area.

10. The method for detecting the spraying quality of the glass bottle surface according to claim 9, wherein, The specific formula for matching the detection position of the sprayed coating according to the overlimit category is: Calculate the detection position deviation range D p , and the detection position deviation ratio R d The specific formula is as follows: Calculate the detection position deviation ratio R d , match the detection position of the sprayed coating according to the overlimit category, calculate the deviation range and deviation ratio of the detection position, and generate abnormal detection coordinate data of the sprayed coating; Among them, D p represents the detection position deviation range, X i represents the abscissa of the i-th overrun area, X c represents the abscissa of the detection position of the matched spray coating, Y j represents the ordinate of the j-th overrun area, Y c represents the ordinate of the detection position of the matched spray coating, S represents the number of data points of the abscissa of the overrun area, m represents the number of data points of the ordinate of the overrun area, T k represents the thickness value at the k-th detection position, p represents the total number of thickness detection points, R d represents the detection position deviation ratio, L r represents the detection reference length.

Images