A method and system for detecting the quality of three-proof coating of a PCB board

Abstract

The present invention discloses a method and system for detecting the quality of three-proof coating of PCB board, the method comprising: obtaining the visible light reflection image and the scattering spectrum data of the near infrared band of the PCB surface; performing spatial domain filtering on the visible light reflection image to extract the pixels of the interface area, and calculating the coating thickness gradient distribution based on the Mie scattering characteristics in the scattering spectrum data, and fusing to generate the edge gradient distribution map; according to the gradient amplitude change rate in the edge gradient distribution map, using an adaptive dynamic threshold algorithm to segment the effective coverage area of the coating layer, and extracting the curvature extreme point density and boundary fractal dimension parameters at the segmentation boundary. The present invention solves the three major technical barriers of "difficult to capture microscopic defects, unmeasurable interface performance, and delayed failure risk display" in traditional detection, and realizes the dual-dimensional accurate diagnosis of the coating structure density and interface reliability.

Description

Technical Field

[0001] This application relates to the technical field of PCB board detection, and particularly to a method and system for detecting the quality of three-proof coating on a PCB board. Background Art

[0002] With the development of miniaturization and high-density integration of electronic devices, the quality of the three-proof paint coating on a printed circuit board (PCB) directly affects the long-term reliability of the product in harsh environments such as high humidity and salt spray.

[0003] The existing Chinese patent with the publication number CN117994243B relates to the technical field of PCB board detection, specifically a method for detecting the coating quality of a PCB board. It segments the collected PCB image to obtain a three-proof paint coverage area map; performs edge filtering to obtain an image containing bubble edge information; extracts bubble features to obtain a set of bubble feature maps; calculates to obtain a bubble result set; classifies the bubble result set to obtain conclusions and suggestions. This method for detecting the coating quality of a PCB board, by segmenting the collected PCB image to obtain a three-proof paint coverage area map, then performing edge filtering, extracting bubble features, calculating the bubble size, etc., to obtain the bubble situation of the PCB board, and classifying the bubble result set to obtain conclusions and suggestions, realizes the detection of coating bubbles on the PCB board, and solves the problem that the appearance of bubbles or blisters on the PCB affects the flatness and insulation performance of the coating.

[0004] However, in the process of implementing the relevant technical solutions, it is found that there are at least the following technical problems:

[0005] The above technology mainly relies on visible light imaging technology. It extracts the coating area through gray threshold segmentation and combines edge filtering to detect macroscopic bubbles. Although such methods are used in rapid detection on the production line, the detection system based on two-dimensional image morphology analysis can only identify macroscopic bubbles with a diameter of more than 50μm, and lacks the ability to detect micron-sized pores (<20μm) inside the coating and weak interface bonding areas. And such micro-defects are the potential causes of failures such as dielectric breakdown and ion migration; in addition, the existing technology cannot quantitatively evaluate the interface bonding strength between the coating layer and the PCB substrate, resulting in the inability to warn of interface peeling failures caused by thermal stress cycling or mechanical vibration. Such hidden defects often appear after the equipment has been in service for several months, resulting in high after-sales maintenance costs. Summary of the Invention

[0006] To solve the above problems, an embodiment of the present invention provides a method for detecting the quality of three-proof coating on a PCB board, and the method includes:

[0007] Obtain the visible light reflection image on the surface of the PCB and the scattering spectral data in the near-infrared band;

[0008] Perform spatial domain filtering on the visible light reflection image to extract interface region pixels. At the same time, calculate the thickness gradient distribution of the coating layer based on the Mie scattering characteristics in the scattering spectral data, and fuse and generate an edge gradient distribution map;

[0009] According to the rate of change of the gradient amplitude in the edge gradient distribution map, use an adaptive dynamic threshold algorithm to segment the effective coverage area of the coating layer, and extract the density of curvature extreme points and the boundary fractal dimension parameter at the segmentation boundary;

[0010] Input the density of curvature extreme points and the boundary fractal dimension parameter into a pre-trained coating curing morphology prediction model, and output the predicted value of the interface bonding strength of the coating layer and the coordinates of the potential peeling risk area through coupling thermodynamic simulation data;

[0011] Scan the surface of the coating layer with an array dielectric coupling sensor, measure the impedance phase response of each scanning point at different excitation frequencies, and calculate the microscopic porosity distribution map according to the slope of the phase offset changing with frequency;

[0012] Perform spatio-temporal registration on the predicted value of the interface bonding strength, the coordinates of the potential peeling risk area, and the microscopic porosity distribution map, and generate a comprehensive evaluation matrix of the coating layer quality through a multi-source data decision fusion algorithm, and output a defect location report and a quality grade classification result.

[0013] Further, the spatial domain filtering method includes:

[0014] Use a non-uniform illumination compensation algorithm to perform illumination equalization on the visible light reflection image. The algorithm calculates the pixel compensation coefficient by establishing a local illumination distribution model, where the compensation coefficient is dynamically adjusted according to the surface roughness characteristics in the near-infrared band scattering spectral data.

[0015] Further, the method for generating the edge gradient distribution map includes:

[0016] Superimpose the gradient phase information of the visible light reflection image and the Mie scattering phase delay of the near-infrared scattering spectrum, and eliminate the interference of the substrate material texture on the coating boundary recognition through phase gradient consistency verification.

[0017] Further, the adaptive dynamic threshold algorithm includes:

[0018] Establish a probability density function according to the statistical distribution of the rate of change of the gradient amplitude, use variational mode decomposition technology to separate the threshold response characteristics of the coating body and the boundary transition region, and dynamically determine the segmentation threshold interval.

[0019] Further, the training method of the coating curing morphology prediction model includes:

[0020] A finite element simulation model of heat-humidity-force multi-physics field coupling is constructed, and a training set of interface stress distribution under different curing conditions is generated by introducing the time-varying viscoelastic constitutive equation of the coating material. The training set includes the mapping relationship between temperature gradient, moisture penetration depth and interface peeling stress.

[0021] Furthermore, the analysis method of the impedance phase response includes:

[0022] An equivalent circuit model of the microscopic pores in the coating layer was established, and the phase shift at different frequencies was fitted by the Cole-Cole distribution function to extract the pore connectivity index and the equivalent dielectric relaxation time parameters.

[0023] Furthermore, the implementation method of spatiotemporal registration includes:

[0024] A three-dimensional registration coordinate system is established based on the spatial topological structure of the coating surface. The mechanical confidence of the predicted value of the interface bonding strength and the electrical sensitivity of the micro-porosity distribution are weightedly fused to generate a quality evaluation weight matrix with physical interpretability.

[0025] Furthermore, a method for detecting the quality of the conformal coating of a PCB board further includes:

[0026] A multi-frequency eddy current sensing unit is integrated into the array dielectric coupling sensor, and the coating dielectric phase response and substrate eddy current skin effect signals are synchronously collected through frequency division multiplexing technology;

[0027] Based on the inverse square relationship between the skin depth of eddy current signals and the frequency, a frequency domain blind source separation model is constructed to decouple the cross-coupled noise components caused by metal substrate defects from the dielectric phase response.

[0028] The frequency domain characteristics of high-frequency eddy currents, which are sensitive to the pore closure of the coating surface, and low-frequency eddy currents, which characterize the continuity of the base metal, are used to reconstruct the microscopic porosity distribution map after removing the base artifacts.

[0029] A PCB board conformal coating quality inspection system, the system comprising:

[0030] Dual-mode acquisition module, which acquires the visible light reflection image and the scattering spectrum data in the near-infrared band of the PCB surface;

[0031] A gradient map generation module, which performs spatial domain filtering on the visible light reflection image to extract interface area pixels, and calculates the coating thickness gradient distribution based on the Mie scattering characteristics in the scattering spectrum data, and fuses them to generate an edge gradient distribution map;

[0032] The dynamic threshold segmentation module segments the effective coverage area of the coating layer according to the gradient amplitude change rate in the edge gradient distribution map, and adopts an adaptive dynamic threshold algorithm to extract the curvature extreme point density and boundary fractal dimension parameters at the segmentation boundary;

[0033] The interface strength prediction module inputs the curvature extreme point density and boundary fractal dimension parameters into a pre-trained coating curing morphology prediction model, and outputs the predicted value of the coating interface bonding strength and the coordinates of the potential peeling risk area through coupling thermodynamic simulation data;

[0034] The dielectric pore analysis module scans the surface of the coating layer through an array of dielectric coupling sensors, measures the impedance phase response of each scanning point at different excitation frequencies, and calculates the microscopic porosity distribution map according to the slope of the phase offset change with frequency;

[0035] The result output module performs spatio-temporal registration on the predicted value of the interface bonding strength, the coordinates of the potential peeling risk area, and the microscopic porosity distribution map, generates a comprehensive evaluation matrix of the coating quality through a multi-source data decision fusion algorithm, and outputs a defect location report and a quality grade classification result.

[0036] The technical effects and advantages of a three-proof coating quality detection method and system for PCB boards provided by the present invention:

[0037] The present invention constructs a multi-modal sensing and dielectric-mechanical coupling analysis system, overcomes the three major technical barriers of "difficult to capture microscopic defects, impossible to measure interface performance, and late manifestation of failure risks" in traditional detection, and realizes the two-dimensional accurate diagnosis of the coating layer structure compactness and interface reliability. The present invention jointly models the polarization phase topology mapping of near-infrared Mie scattering and the Cole-Cole distribution of dielectric relaxation spectra to establish a three-dimensional dielectric anisotropy characterization of the internal microstructure of the coating, breaks through the shielding effect of the optical diffraction limit on microscopic defects, realizes the non-destructive visualization of the nano-scale heterogeneous interface in the coating-substrate transition region, and accurately locks the preferential path of ion migration; constructs an adhesion work dynamic evolution model of the coating-substrate interface based on the thermodynamic potential function, integrates the acoustic surface wave dispersion characteristics and the entropy change correlation of the dielectric relaxation time spectrum, reveals the energy threshold for the initiation and propagation of interface cracks in thermal stress cycles, and realizes the identification of the subcritical state of interface peeling through the phase change characteristics of acoustic-electric dual-mode signals; adopts a curvature manifold learning algorithm to deconstruct the surface fluctuation mode of the coating, and distinguishes real defects from substrate features through the phase gradient consistency verification of topological invariants, eliminating the optical aliasing effect caused by copper foil roughness, and improving the recognition specificity of microcracks and pores. Description of the Drawings

[0038] Figure 1Flowchart of a three-proof coating quality detection method for a PCB board in Embodiment 1;

[0039] Figure 2 Flowchart of a three-proof coating quality detection method for a PCB board in Embodiment 2;

[0040] Figure 3 Schematic connection diagram of a three-proof coating quality detection system for a PCB board in Embodiment 3. Specific implementation manners

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] Embodiment 1: Please refer to Figure 1 As shown, the embodiment of the present invention provides a three-proof coating quality detection method for a PCB board, and the method includes:

[0043] Obtain the visible light reflection image on the surface of the PCB and the scattering spectrum data in the near-infrared band.

[0044] Perform spatial domain filtering processing on the visible light reflection image to extract the interface area pixels. At the same time, calculate the coating thickness gradient distribution based on the Mie scattering characteristics in the scattering spectrum data, and fuse to generate an edge gradient distribution map.

[0045] According to the gradient amplitude change rate in the edge gradient distribution map, use the adaptive dynamic threshold algorithm to segment the effective coverage area of the coating layer, and extract the curvature extreme point density and boundary fractal dimension parameters at the segmentation boundary.

[0046] Input the curvature extreme point density and boundary fractal dimension parameters into the pre-trained coating curing morphology prediction model, and output the predicted value of the coating interface bonding strength and the coordinates of the potential peeling risk area through coupling thermodynamic simulation data.

[0047] Scan the surface of the coating layer through an array dielectric coupling sensor, measure the impedance phase response of each scan point at different excitation frequencies, and calculate the microscopic porosity distribution map according to the slope of the phase offset change with frequency.

[0048] Perform spatio-temporal registration on the predicted value of the interface bonding strength, the coordinates of the potential peeling risk area, and the microscopic porosity distribution map, and generate a comprehensive evaluation matrix of the coating layer quality through a multi-source data decision fusion algorithm, and output a defect location report and a quality grade classification result.

[0049] Use a CCD or CMOS sensor camera to obtain visible light reflection images, while the scattered spectral data in the near-infrared band can be obtained using a near-infrared spectrometer.

[0050] The spatial domain filtering processing method includes:

[0051] Use a non-uniform illumination compensation algorithm to equalize the illumination of the visible light reflection image. The algorithm calculates the pixel compensation coefficient by establishing a local illumination distribution model, where the compensation coefficient is dynamically adjusted according to the surface roughness characteristics in the near-infrared band scattered spectral data.

[0052] The specific method includes:

[0053] Divide the visible light reflection image into multiple local regions. In each region, establish a two-dimensional Gaussian distribution model based on the pixel brightness statistical value, fit the illumination attenuation trend of the region, and generate the initial illumination compensation coefficient. However, due to the difference in the surface roughness of the PCB substrate, it will affect the distribution of the specular component of the visible light reflection. It is difficult to accurately distinguish the real coating boundary from the illumination artifacts directly based on the statistical model of the visible light image. Therefore, combine the surface roughness characteristics extracted from the scattered spectral data in the near-infrared band to dynamically correct the compensation coefficient. The correction method includes:

[0054] When the Mie scattering phase delay of the near-infrared scattered spectrum increases, it indicates that the surface roughness of the current region is relatively high. At this time, enhance the spatial smoothing constraint weight of the compensation coefficient to suppress the brightness mutation caused by the microstructure scattering in the high-roughness region; conversely, when the surface roughness is relatively low, give priority to retaining the high-frequency texture details to improve the recognition rate of the coating boundary.

[0055] The compensation coefficient after dynamic adjustment acts on the visible light reflection image, eliminating the influence of non-uniform illumination while retaining the real interface characteristics of the coating and the substrate, providing a more robust preprocessing result for the subsequent generation of the edge gradient distribution map.

[0056] The method for generating the edge gradient distribution map includes:

[0057] Superimpose the gradient phase information of the visible light reflection image and the Mie scattering phase delay of the near-infrared scattered spectrum, and eliminate the interference of the substrate material texture on the coating boundary recognition through the phase gradient consistency verification.

[0058] In the process of generating the edge gradient distribution map, first, the gradient field of the visible light reflection image is calculated, and the phase direction angle information of each pixel point is extracted to characterize the edge trend of the coating; simultaneously, the Mie scattering phase delay in the near-infrared scattering spectrum data is analyzed. The Mie scattering phase delay reflects the refractive index difference between the coating material and the substrate at the sub-wavelength scale. After spatially registering the two phase characteristics, a composite phase map is generated using the dual-channel phase superposition algorithm. The logical basis of the dual-channel phase superposition algorithm includes: the visible light gradient phase information is used to identify the macroscopic edge trend, and its phase angle change rate is positively correlated with the coating thickness mutation region; the near-infrared Mie scattering phase delay enhances the phase jump characteristics at the coating-substrate interface by detecting the optical field interference effect at the dielectric interface.

[0059] When the substrate material has periodic textures (such as fiberglass woven structures), its visible light gradient phase will show regular fluctuations, but the corresponding Mie scattering phase delay remains stable because the substrate surface is not covered with a coating. Using this characteristic, phase gradient consistency discrimination conditions are set, including:

[0060] If the phase angle change rate of a certain area exceeds the preset threshold (such as ±15°), while the change amplitude of the Mie scattering phase delay is lower than the critical value (such as <5°), then this area is determined to be substrate texture interference and is attenuated in the composite phase map; when the fluctuation trends of the two phase characteristics are strongly correlated in space, it is confirmed as the real coating boundary and the phase superposition result is retained.

[0061] The composite phase map after being corrected by the phase gradient consistency discrimination is normalized and mapped to obtain the edge gradient distribution map.

[0062] The phase gradient consistency discrimination significantly suppresses the interference of the substrate material microstructure on the coating boundary recognition; for example, the pseudo-edges caused by the substrate texture may produce a phase angle mutation of 30° - 45° in the visible light phase map, but since the Mie scattering phase delay of the uncoated area only fluctuates by 2° - 3°, it will be effectively filtered out in the consistency verification stage.

[0063] The adaptive dynamic threshold algorithm includes:

[0064] A probability density function is established based on the statistical distribution of the gradient amplitude change rate, and the variational mode decomposition technique is used to separate the threshold response characteristics of the coating body and the boundary transition region, dynamically determining the segmentation threshold interval.

[0065] The adaptive dynamic threshold algorithm specifically includes:

[0066] By statistically analyzing the rate of change of the gradient magnitude of all pixel points in the spectrum, it can be found that its probability density function exhibits a bimodal distribution characteristic. The main peak corresponds to the low-gradient fluctuation in the coating body region, and the secondary peak represents the high-gradient transition in the boundary transition region. However, in actual detection, the two peaks often partially overlap due to the gradual change of the coating thickness or the interference of substrate residues, resulting in difficulty in accurately segmenting with a single threshold. Therefore, the variational mode decomposition technique is introduced to decompose the original gradient signal into multiple modal components, including the first modal component, the second modal component, and the residual component.

[0067] The first modal component captures the low-frequency slow-varying characteristics of the coating body region, and its amplitude envelope is related to the material uniformity.

[0068] The second modal component extracts the intermediate-frequency oscillation characteristics of the boundary transition region, reflecting the interface mutation between the coating layer and the substrate.

[0069] The residual component includes high-frequency interference introduced by noise and substrate micro-defects.

[0070] Calculate the energy proportion of each modal component to determine whether the current analysis region is near an effective boundary.

[0071] Taking the initial bimodal center value as a constraint condition, the KL divergence minimization criterion is used to adjust the bandwidth of the modal components, so that the decomposed modal components can accurately separate the coating body and boundary characteristics in the time-frequency domain.

[0072] According to the processed modal components above, reconstruct the threshold response curve to dynamically determine the segmentation threshold interval. Exemplarily:

[0073] When it is detected that there is a gradual change in thickness in a certain local area (manifested as a continuous increase in the amplitude of the second modal component), the algorithm adjusts the lower threshold from 0.35 of the standard value to 0.28 to expand the boundary capture range; conversely, for the high-uniformity coating area (the energy proportion of the first mode > 70%), the upper threshold is tightened to suppress the generation of pseudo-boundaries.

[0074] The training method of the coating curing morphology prediction model includes:

[0075] Construct a finite element simulation model of multi-physical field coupling (heat-moisture-force), and by introducing the time-varying viscoelastic constitutive equation of the coating material, generate a training set of interface stress distributions under different curing conditions. The training set includes the mapping relationship between the temperature gradient, the humidity penetration depth, and the interface peeling stress.

[0076] In the training stage of the coating curing morphology prediction model, construct a finite element simulation framework for heat-moisture-force coupling. The construction method of the finite element simulation framework includes:

[0077] Thermal field modeling: Characterize the evolution of the temperature gradient inside the coating during the curing process through the unsteady heat conduction equation, considering the non-linear effects of factors such as heating rate and environmental heat dissipation on the temperature distribution.

[0078] Moisture field modeling: Simulate the moisture penetration process using Fick's diffusion law, and introduce a dynamic change model of the coating porosity to reflect the time-varying characteristics of the moisture absorption performance during the curing stage.

[0079] Mechanical modeling: Combine the time-varying viscoelastic constitutive equation, express the elastic modulus and relaxation time parameters of the coating as functions of the degree of cure and temperature-humidity conditions, and accurately depict the stress relaxation behavior during the transformation of the material from liquid to solid state.

[0080] By jointly solving the above models, generate a dataset of interfacial stress distributions covering different process conditions;

[0081] Exemplary:

[0082] Set a non-uniform distribution of the temperature gradient from 25°C to 80°C in the simulation, the moisture penetration depth varies in layers within the range of 0.1 mm to 0.5 mm, and output the component data of the corresponding peeling stress in the normal and tangential directions of the interface. This component data forms a structured training set through parametric sampling, where each data includes an input vector (extreme value of temperature gradient, characteristic length of moisture penetration, and curing time) and an output vector (amplitude of the maximum peeling stress and critical peeling angle).

[0083] To solve the problem of model generalization caused by the uncertainty of coating material parameters in actual detection, a material property perturbation mechanism is introduced in the simulation stage. The material property perturbation mechanism includes:

[0084] Apply a random fluctuation of ±15% to the key parameters such as activation energy and free volume fraction in the viscoelastic constitutive equation to generate virtual samples with statistical diversity.

[0085] During the training process, use a bidirectional long short-term memory network to capture the temporal correlation of multi-physical field parameters, and design an attention mechanism to strengthen the cross-scale correlation feature extraction of moisture penetration and stress accumulation. The trained coating curing morphology prediction model can, according to the temperature and humidity distribution data obtained from on-line detection (such as infrared thermal imaging and near-infrared humidity sensing results), predict the spatial distribution trend of the interfacial peeling stress in real time.

[0086] The analysis method of impedance phase response includes:

[0087] Establish an equivalent circuit model of the microscopic pores of the coating layer, fit the phase offset at different frequencies through the Cole-Cole distribution function, and extract the pore connectivity index and equivalent dielectric relaxation time parameters.

[0088] Specific analysis methods include:

[0089] First, a hierarchical equivalent circuit model is constructed based on the microscopic morphological characteristics after coating curing. The hierarchical equivalent circuit model includes a surface conduction path, a bulk dielectric layer, and an interfacial transport channel.

[0090] Surface conduction path: A resistance network formed by conductive carbonized products at the pore edges, whose resistance value is negatively correlated with the pore opening ratio.

[0091] Bulk dielectric layer: The uncured coating body is equivalent to a parallel combination of resistor-capacitor units, and the capacitance component reflects the polarization characteristics of the matrix material.

[0092] Interfacial transport channel: The ion migration path at the coating-substrate interface is modeled as a series of constant phase angle elements, which characterizes non-ideal charge transport behavior.

[0093] Phase shift data in the range of 10 Hz to 1 MHz are obtained through broadband impedance spectroscopy measurement. The Cole-Cole distribution function is used for non-linear fitting of the frequency response curve. By introducing the relaxation time distribution parameter, the Cole-Cole distribution function can simultaneously characterize the multi-scale relaxation effects of the pore structure, including:

[0094] High frequency band (>100 kHz): Corresponding to the dipole orientation polarization of nanoscale isolated pores, the equivalent dielectric relaxation time is obtained by fitting. When its value is less than 1 μs, it indicates good pore closure.

[0095] Medium frequency band (1 kHz - 100 kHz): Reflecting the ion diffusion relaxation of micron-scale connected pores, the closer the extracted pore connectivity index α is to 1, the higher the pore network penetration.

[0096] Low frequency band (<1 kHz): Correlating with the interfacial polarization effect of macroscopic interface defects, which is used to correct the boundary conditions of the equivalent circuit model.

[0097] Exemplary:

[0098] When analyzing a polyester coating sample, the fitting results show that the equivalent dielectric relaxation time = 0.85 μs and α = 0.76, indicating that although there are some sub-micron pores in the coating (the equivalent dielectric relaxation time is short), the connectivity index is lower than the qualified threshold of 0.8, and a quality warning needs to be triggered. This result can be cross-validated with the interfacial stress prediction result. When α < 0.8, the probability that the peak value of the interfacial peeling stress exceeds the critical value of the material adhesion strength is increased to 92%.

[0099] The implementation methods of spatio-temporal registration include:

[0100] Based on the spatial topological structure of the coating surface, a three-dimensional registration coordinate system is established, and the mechanical confidence of the predicted interface bonding strength value and the electrical sensitivity of the microscopic porosity distribution are weighted and fused to generate a physically interpretable quality evaluation weight matrix.

[0101] The specific implementation methods include:

[0102] Based on the curvature distribution of the coating surface (obtained by analyzing the density of curvature extreme points), a non-uniformly meshed three-dimensional registration coordinate system is established, where the spatial resolution of each grid node is aligned with the pixel scale of multi-spectral imaging to achieve physical data association, including:

[0103] Project the predicted interface bonding strength distribution data onto the three-dimensional coordinate system, and based on the spatial correlation analysis of the stress gradient, calculate the mechanical confidence parameters at each node to reflect the probability distribution of the interface peeling risk.

[0104] Normalize the pore connectivity index and the dielectric relaxation time parameter, and combine the spatial topological relationship of the conductive channels in the equivalent circuit model to generate a distribution heat map representing the electrical response sensitivity of microscopic defects.

[0105] Design a two-parameter adaptive weight function, where the mechanical confidence weight increases non-linearly with the increase in the standard deviation of the predicted interface bonding strength value, and the electrical sensitivity weight is positively correlated with the local gradient magnitude of the porosity distribution. For example, in the region where the curvature of the coating edge changes suddenly (curvature radius < 0.3 mm), the mechanical weight is increased to 0.7 to give priority to responding to the interface peeling risk; while in the uniform region at the center of the coating (porosity > 5%), the electrical weight is increased to 0.6 to strengthen the detection of microscopic defects.

[0106] Through Gaussian process regression, optimize the spatial continuity of the electrical sensitivity weight and the mechanical confidence weight to generate a physically interpretable quality evaluation weight matrix. Each unit value of the quality evaluation weight matrix represents the comprehensive quality coefficient of the corresponding spatial position. When the comprehensive quality coefficient is lower than 0.4 (example threshold), a hierarchical warning is triggered. The hierarchical warning criteria include:

[0107] When the comprehensive quality coefficient is in the range of 0.3 - 0.4, it indicates the need for fine-tuning of local process parameters.

[0108] When the comprehensive quality coefficient is less than 0.3, it is determined as a high-risk area of structural failure, and adaptive detection needs to be initiated for re-inspection.

[0109] The multi-source data decision fusion algorithm includes:

[0110] Construct a D-S confidence assignment framework using the theory of evidential reasoning, transform the boundary integrity score into a basic probability assignment function, and perform uncertainty reasoning in combination with the prior distribution function of the interface bonding force level to output the confidence interval evaluation result of defect location.

[0111] The multi-source data decision fusion algorithm specifically includes:

[0112] Establish an identification framework for coating quality evaluation, define three basic propositions of "interface bonding failure", "pore densification defect", and "composite damage", and realize decision-making reasoning through the following steps:

[0113] Map the boundary integrity score (curvature extreme point density and gradient direction consistency parameter) to the initial belief assignment.

[0114] When the high-density curvature region (>15 points / mm²) and the direction dispersion degree >60°, assign a basic probability of 0.6 to the proposition of "interface bonding failure".

[0115] Low pore connectivity index (α<0.7) accompanied by short dielectric relaxation time , assign a belief of 0.55 to the proposition of "pore densification defect".

[0116] The remaining uncertain part is retained as the global conflict factor for conflict resolution during subsequent evidence synthesis.

[0117] Combine the interface bonding force level distribution to establish a prior probability correction model based on the Beta function; for example, when the standard deviation of the adhesion strength of the batch material exceeds 0.8 MPa, increase the prior weight of the proposition of "composite damage" to 0.3 to reflect the influence of the inherent performance fluctuation of the material on the defect mode.

[0118] For areas with high conflict (global conflict factor K>0.4), trigger the adaptive weighted correction mechanism, and the adaptive weighted correction mechanism includes:

[0119] Introduce the spatial confidence parameter in the quality evaluation weight matrix to perform local weighted average processing on the conflicting evidence.

[0120] Finally, output a three-dimensional confidence interval heat map, where each voxel contains a confidence distribution in the interval [0.2, 0.85]. When the confidence of "interface bonding failure" exceeds 0.7 and the spatially continuous area >4 mm², it is determined as a high-risk defect cluster.

[0121] Example 2: As Figure 2As shown, this embodiment further improves the design on the basis of embodiment 1. The difference is that in actual operation, it is found that in embodiment 1, only the dielectric coupling sensor is relied on to detect the porosity, but the electromagnetic field distortion caused by the inherent defects of the metal substrate (such as microcracks and grain boundary segregation) is not considered, resulting in the aliasing of the pore signal and the substrate artifact. Based on this, a PCB board three-proof coating quality detection method also includes:

[0122] A multi-frequency eddy current sensing unit is integrated in the array dielectric coupling sensor, and the coating dielectric phase response and substrate eddy current skin effect signals are synchronously collected through frequency division multiplexing technology.

[0123] A frequency domain blind source separation model is constructed based on the inverse square relationship between the skin depth of eddy current signals and the frequency, and the cross-coupling noise components caused by metal substrate defects are decoupled from the dielectric phase response.

[0124] The frequency domain characteristics of high-frequency eddy currents, which are sensitive to the pore closure of the coating surface, and low-frequency eddy currents, which characterize the continuity of the base metal, are used to reconstruct the microscopic porosity distribution map after removing the base artifacts.

[0125] Furthermore, the multi-frequency eddy current sensing unit includes a dielectric sensor and an eddy current sensing unit; the dielectric sensor measures the phase shift response of the dielectric constant of the coating layer by applying a high-frequency alternating electric field (typical excitation frequency is 1MHz-10MHz), while the eddy current sensing unit adopts a wide-band scanning mode (typical coverage range is 50kHz-5MHz) to obtain the skin effect signal of the base metal through the principle of electromagnetic induction; the two types of sensors adopt a coplanar electrode design to ensure the temporal and spatial synchronization of the dielectric-eddy current signals and avoid the registration error introduced by the scanning position offset.

[0126] Furthermore, by extracting the impedance mutation characteristics reflecting the grain boundary cracks or oxide layers of the substrate metal from the low-frequency eddy current signal (such as below 100kHz), the artifact noise template of the substrate defect is reconstructed; at the same time, the high sensitivity of the high-frequency eddy current signal (such as above 1MHz) to the near-surface pore closure of the coating is utilized to establish the frequency domain orthogonality criterion of the pore-substrate signal; the cross-coupling components related to the substrate artifacts are separated from the mixed dielectric phase spectrum through the independent component analysis (ICA) algorithm to achieve dynamic noise suppression of the real pore response of the coating.

[0127] Furthermore, the porosity distribution reconstruction is optimized according to the physical property differences of the multi-frequency eddy current signals. The reconstruction method includes:

[0128] Due to the relatively shallow skin depth, high-frequency eddy currents mainly capture the closed state of micron-sized pores on the coating surface, and the signal amplitude is negatively correlated with the pore gas filling rate; low-frequency eddy currents penetrate the coating and reach the substrate, excluding the interference of substrate cracks on the coating structure evaluation through metal continuity detection; the denoised dielectric phase slope and the high-frequency eddy current amplitude are weighted and fused to generate a microscopic porosity distribution map resistant to substrate interference, forming a spatial correlation mapping with the interface bonding strength, and jointly input into a multi-source decision fusion engine for comprehensive quality evaluation.

[0129] Embodiment 3: As Figure 3 shown, based on the same inventive concept as a method for detecting the quality of three-proof coating of a PCB board in the foregoing embodiments, the present application provides a system for detecting the quality of three-proof coating of a PCB board. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes:

[0130] A dual-modal acquisition module, which acquires the visible light reflection image and the scattered spectrum data in the near-infrared band on the surface of the PCB.

[0131] A gradient map generation module, which performs spatial domain filtering on the visible light reflection image to extract the interface area pixels, and at the same time calculates the coating thickness gradient distribution based on the Mie scattering characteristics in the scattered spectrum data, and fuses them to generate an edge gradient distribution map.

[0132] A dynamic threshold segmentation module, which divides the effective coverage area of the coating layer according to the gradient amplitude change rate in the edge gradient distribution map, and adopts an adaptive dynamic threshold algorithm to extract the curvature extreme point density and the boundary fractal dimension parameters at the segmentation boundary.

[0133] An interface strength prediction module, which inputs the curvature extreme point density and the boundary fractal dimension parameters into a pre-trained coating curing morphology prediction model, and outputs the predicted value of the coating interface bonding strength and the coordinates of the potential peeling risk area through coupling thermodynamic simulation data.

[0134] A dielectric pore analysis module, which scans the surface of the coating layer through an array of dielectric coupling sensors, measures the impedance phase response of each scanning point at different excitation frequencies, and calculates the microscopic porosity distribution map according to the slope of the phase offset change with frequency.

[0135] A result output module, which performs spatio-temporal registration on the predicted value of the interface bonding strength, the coordinates of the potential peeling risk area and the microscopic porosity distribution map, generates a comprehensive evaluation matrix of the coating layer quality through a multi-source data decision fusion algorithm, and outputs a defect location report and a quality grade classification result.

[0136] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

[0137] The above are only the preferred specific embodiments of the embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application, according to the technical solution and its concept of the present application, makes equivalent substitutions or changes, and should be covered within the protection scope of the present application.

Claims

1. A method for detecting the quality of three-proof coating on a PCB board, characterized in that, Including: Obtain the visible light reflection image of the PCB surface and the scattering spectral data in the near-infrared band; Perform spatial domain filtering processing on the visible light reflection image to extract the pixel of the interface region. At the same time, calculate the thickness gradient distribution of the coating layer based on the Mie scattering characteristics in the scattering spectral data, and fuse to generate an edge gradient distribution map; According to the rate of change of the gradient amplitude in the edge gradient distribution map, use the adaptive dynamic threshold algorithm to segment the effective coverage area of the coating layer, and extract the density of the curvature extreme points and the boundary fractal dimension parameters at the segmentation boundary; Input the density of the curvature extreme points and the boundary fractal dimension parameters into the pre-trained coating curing morphology prediction model, and output the predicted value of the interface bonding strength of the coating layer and the coordinates of the potential peeling risk area through coupling thermodynamic simulation data; Scan the surface of the coating layer through an array dielectric coupling sensor, measure the impedance phase response of each scan point at different excitation frequencies, and calculate the microscopic porosity distribution map according to the slope of the phase offset change with frequency; Perform spatio-temporal registration on the predicted value of the interface bonding strength, the coordinates of the potential peeling risk area, and the microscopic porosity distribution map, and generate a comprehensive quality evaluation matrix of the coating layer through a multi-source data decision fusion algorithm, and output a defect location report and a quality grade classification result.

2. The quality inspection method for the three-proof coating of a PCB board according to claim 1, wherein The spatial domain filtering processing method includes: Use the non-uniform illumination compensation algorithm to perform illumination equalization processing on the visible light reflection image. The algorithm calculates the pixel compensation coefficient by establishing a local illumination distribution model, and the compensation coefficient is dynamically adjusted according to the surface roughness characteristics in the near-infrared band scattering spectral data.

3. A method for detecting the quality of three-proof coating of a PCB board according to claim 1, characterized in that, The method for generating the edge gradient distribution map includes: Superimpose the gradient phase information of the visible light reflection image and the Mie scattering phase delay of the near-infrared scattering spectrum, and eliminate the interference of the substrate material texture on the coating boundary recognition through phase gradient consistency verification.

4. A method for detecting the quality of three-proof coating of a PCB board according to claim 1, characterized in that, The adaptive dynamic threshold algorithm includes: Establish a probability density function according to the statistical distribution of the rate of change of the gradient amplitude, use the variational mode decomposition technology to separate the threshold response characteristics of the coating body and the boundary transition region, and dynamically determine the segmentation threshold interval.

5. A method for detecting the quality of three-proof coating of a PCB board according to claim 1, characterized in that, The training method of the coating curing morphology prediction model includes: Construct a finite element simulation model of the multi-physical field coupling of heat, humidity and force. By introducing the time-varying viscoelastic constitutive equation of the coating material, generate a training set of the interface stress distribution under different curing conditions. The training set includes the mapping relationship between the temperature gradient, the humidity penetration depth and the interface peeling stress.

6. A method for detecting the quality of three-proof coating of a PCB board according to claim 1, characterized in that, The analysis method of the impedance phase response includes: Establish an equivalent circuit model of the microscopic pores of the coating layer, fit the phase offset at different frequencies through the Cole-Cole distribution function, and extract the pore connectivity index and the equivalent dielectric relaxation time parameter.

7. A PCB board three-conformal coating quality detection method according to claim 1, characterized in that: The implementation method of spatio-temporal registration includes: Establish a three-dimensional registration coordinate system based on the spatial topology structure of the coating layer surface, and perform weighted fusion on the mechanical confidence of the predicted value of the interface bonding strength and the electrical sensitivity of the microscopic porosity distribution to generate a quality evaluation weight matrix with physical interpretability.

8. A method for detecting the quality of three-proof coating of a PCB board according to claim 1, characterized in that, Also including: Integrate a multi-frequency eddy current sensing unit in the array dielectric coupling sensor, and synchronously collect the dielectric phase response of the coating layer and the eddy current skin effect signal of the substrate through frequency division multiplexing technology; A frequency-domain blind source separation model is constructed based on the inverse square relationship between the skin depth of eddy current signals and the square of the frequency, and the cross-coupling noise component caused by metal substrate defects is decoupled from the dielectric phase response; Using the frequency-domain characteristics that high-frequency eddy currents are sensitive to the closure degree of pores on the coating surface and low-frequency eddy currents characterize the continuity of the substrate metal, a microscopic porosity distribution map with substrate artifacts removed is reconstructed.

9. A three-proof coating quality detection system for a PCB board, characterized in that, The system includes: A dual-modal acquisition module that acquires the visible light reflection image and the scattering spectral data in the near-infrared band on the surface of the PCB; A gradient map generation module that performs spatial domain filtering on the visible light reflection image to extract interface region pixels, and at the same time calculates the coating thickness gradient distribution based on the Mie scattering characteristics in the scattering spectral data, and fuses to generate an edge gradient distribution map; A dynamic threshold segmentation module that, according to the gradient amplitude change rate in the edge gradient distribution map, uses an adaptive dynamic threshold algorithm to segment the effective coverage area of the coating, and extracts the density of curvature extreme points and the boundary fractal dimension parameters at the segmentation boundary; An interface strength prediction module that inputs the density of curvature extreme points and the boundary fractal dimension parameters into a pre-trained coating curing morphology prediction model, and outputs the predicted value of the coating interface bonding strength and the coordinates of the potential peeling risk area through coupling thermodynamic simulation data; A dielectric pore analysis module that scans the surface of the coating through an array of dielectric coupling sensors, measures the impedance phase response of each scan point at different excitation frequencies, and calculates the microscopic porosity distribution map according to the slope of the phase shift amount changing with frequency; A result output module that spatially and temporally registers the predicted value of the interface bonding strength, the coordinates of the potential peeling risk area, and the microscopic porosity distribution map, generates a comprehensive evaluation matrix of the coating quality through a multi-source data decision fusion algorithm, and outputs a defect location report and a quality grade classification result.

Images