Multi-layer PCB quality detection method and system

Abstract

The invention relates to the technical field of image data processing, in particular to a multi-layer PCB quality detection method and system, and the method comprises the steps: determining a standard X-ray detection graph of the same model as a target multi-layer PCB and a spatial structure component therein, and calculating an initial standard X attenuation coefficient of the spatial structure component; further calculating a comprehensive average multilayer attenuation coefficient of the target multilayer PCB in the target local scanning area, further determining a target penetration path when the target local scanning area is irradiated by the initial preset X-ray intensity, and further calculating the ray shielding intensity of the target local scanning area; and determining the adaptive ray intensity of the target local scanning area, and re-scanning the target local scanning area to determine the quality of the PCB. The X-ray intensity is adjusted for re-scanning, so that each local scanning area on the multi-layer PCB is displayed as complete as possible, and the quality detection precision of the multi-layer PCB is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a method and system for detecting the quality of a multi-layer PCB circuit board. Background Art

[0002] Multilayer PCBs are composed of alternating conductive layers (copper foil) and insulating layers (prepreg) pressed together under high temperature and high pressure to create a complex circuit board. They primarily include seven PCB structural components: inner layers, outer layers, through-holes, blind vias, buried vias, core, and prepreg. The inner layers refer to the middle conductive layers used for signal routing and power / ground planes; the outer layers refer to the top and bottom layers, used for component placement and soldering; through-holes are holes that penetrate all layers; blind vias connect only the outer layer to a portion of the inner layer; buried vias connect only the inner layers, not through the outer layers; the core refers to the rigid substrate that provides mechanical strength; and the prepreg is the adhesive layer that cures during lamination to bond the layers together. The high-temperature, high-pressure pressing process of these PCB structural components into a complex circuit board can lead to incomplete electrical connections between layers, resulting in open circuits or short circuits. Therefore, multilayer PCBs require quality inspection.

[0003] To prevent damage to multi-layer PCB circuit boards during the quality inspection process, the existing technology usually uses X-rays with a fixed intensity to irradiate multi-layer PCB circuit boards of the same model, continuously scans the local scanning area until the scan is completed, generates a detection image based on the attenuation of the X-rays during the scanning process, and performs quality inspection on the detection image; however, in the actual process, when X-rays are vertically irradiated on the outer layer of the multi-layer PCB circuit board, the PCB spatial structural components facing downward from various areas of the outer surface form different arrangements and combinations, and the circuit board components after each arrangement and combination have different abilities to weaken the X-rays as a whole. When the traditional method uses X-rays with a fixed intensity to scan, the local scanning area on the multi-layer PCB circuit board may not be fully displayed, thereby interfering with the quality inspection accuracy of the multi-layer PCB circuit board. Summary of the Invention

[0004] In order to solve the technical problem that the quality inspection accuracy of multi-layer PCB circuit boards is low when scanning with X-rays of fixed intensity, the purpose of the present invention is to provide a multi-layer PCB circuit board quality inspection method and system. The technical solutions adopted are as follows:

[0005] The present invention provides a method for detecting the quality of a multi-layer PCB circuit board, the method comprising:

[0006] Determine the standard X-ray inspection image of the same model and normal quality as the target multi-layer PCB circuit board and the PCB spatial structural components therein, and calculate the initial standard X-ray attenuation coefficients of different PCB spatial structural components;

[0007] Based on the initial standard X attenuation coefficient, calculate the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components inside the target multi-layer PCB circuit board in the same longitudinal space;

[0008] Determining the target penetration path within the target local scanning area when the initially predetermined X-ray intensity is irradiated based on the comprehensive average multi-layer attenuation coefficient, and calculating the ray shielding intensity of the target local scanning area based on the target penetration path;

[0009] The adaptive ray intensity of the target local scanning area is determined using the ray blocking intensity, and the target local scanning area is rescanned using the adaptive ray intensity to determine the quality of the PCB circuit board.

[0010] Furthermore, the calculation of the initial standard X attenuation coefficients of different PCB spatial structural components includes:

[0011] Based on the standard X-ray inspection diagram, determine the target local scanning area formed by the superposition of different layers of PCB spatial structural components in the same longitudinal space inside the target multi-layer PCB circuit board;

[0012] Determine the PCB spatial structure component sequence and grayscale value mean of the target local scanning area, and calculate the initial standard X attenuation coefficient of the target type of PCB spatial structure component using the PCB spatial structure component sequence and grayscale value mean;

[0013] The PCB spatial structure component sequence is formed by arranging the PCB spatial structure components in each scanning area in a layer sequence.

[0014] Furthermore, the method of calculating the initial standard X attenuation coefficient of the target type of PCB spatial structural component by using the PCB spatial structural component sequence and the gray value mean includes:

[0015] Establish an equation between the PCB spatial structure component sequence and the grayscale value mean, and calculate the target grayscale value of the target type of PCB spatial structure component;

[0016] The target grayscale value mean is converted into the intensity of the penetrated ray, and the initial standard X-ray attenuation coefficient of the target type of PCB spatial structure component is calculated based on the Beer-Lambert law.

[0017] Furthermore, the calculation of the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components within the target multi-layer PCB circuit board in the same longitudinal space based on the initial standard X attenuation coefficient includes:

[0018] Determine the component thickness of the PCB spatial structure component and the overall thickness of the target local scanning area, as well as the number of components of the PCB spatial structure component in the target local scanning area;

[0019] Using the initial standard X attenuation coefficient, component thickness, overall thickness, and number of components, the comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated.

[0020] Furthermore, the initial standard X attenuation coefficient, component thickness, overall thickness, and number of components are used to calculate the comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area, including:

[0021] The length of the low-interference path in the target local scanning area is calculated using the component thickness and the overall thickness. The low-interference path represents the path where the prepreg is located.

[0022] Using the initial standard X attenuation coefficient, component thickness, and component quantity, the average type attenuation coefficient of the PCB spatial structure components is calculated;

[0023] The comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated using the low-interference path length, overall thickness and average type attenuation coefficient.

[0024] Furthermore, the step of determining the target penetration path when the target local scanning area is irradiated with the initially predetermined X-ray intensity based on the comprehensive average multi-layer attenuation coefficient includes:

[0025] Determining a region to be adjusted in the local scanning intensity in the target local scanning region according to the comprehensive average multi-layer attenuation coefficient;

[0026] Starting from the first layer of the area where the local scanning intensity is to be adjusted, iteratively accumulate the average type attenuation coefficients of the PCB spatial structural components in the area where the local scanning intensity is to be adjusted, and calculate the layer grayscale mean of the target number of layers;

[0027] Determine the grayscale difference between the target layer's grayscale mean and the measured grayscale mean, and use the layer number corresponding to the minimum grayscale difference as the attenuation stop layer;

[0028] The first layer to the attenuation stop layer of the area to be adjusted for the local scanning intensity is determined as the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is used to irradiate the target local scanning area.

[0029] Furthermore, determining the area to be adjusted in the local scanning intensity in the target local scanning area according to the comprehensive average multi-layer attenuation coefficient includes:

[0030] According to the initial predetermined X-ray intensity corresponding to the standard X-ray detection map, the target local scanning area is irradiated to obtain the corresponding actual grayscale mean value;

[0031] According to the initially predetermined X-ray intensity and the comprehensive average multi-layer attenuation coefficient, the theoretical grayscale mean of the target local scanning area is calculated based on the Beer-Lambert law;

[0032] The mean difference value is obtained by subtracting the theoretical mean grayscale value from the actual mean grayscale value, and the local scanning area with the mean difference value greater than or equal to the preset difference threshold is used as the local scanning intensity adjustment area.

[0033] Furthermore, the calculation of the ray shielding intensity of the target local scanning area based on the target penetration path includes:

[0034] determining the number of remaining layers of the area to be adjusted for the local scanning intensity after the attenuation stop layer;

[0035] The residual type attenuation coefficients of the PCB spatial structure components in the remaining number of layers are calculated using the average type attenuation coefficients of the PCB spatial structure components in the remaining number of layers;

[0036] The ray shielding intensity of the area where the local scanning intensity is to be adjusted is calculated using the number of types of PCB spatial structural components in the remaining layers and the residual type attenuation coefficients.

[0037] Furthermore, the method of rescanning the target local scanning area using the adaptive ray intensity to determine the quality of the PCB circuit board includes:

[0038] Use adaptive ray intensity to rescan the target local scanning area to obtain a new multi-layer PCB circuit board ray inspection map;

[0039] Based on the new multi-layer PCB circuit board radiographic inspection map, DBSCAN clustering is performed on the PCB spatial structure components in each layer to obtain component superposition clusters after longitudinal superposition;

[0040] Determine the reference theoretical grayscale mean and the actual detection grayscale mean of the target local scanning area occupied by the component superposition cluster clusters, and use the difference between the reference theoretical grayscale mean and the actual detection grayscale mean to determine whether the target local scanning area is a quality defect area to determine the quality of the PCB circuit board.

[0041] The present invention provides a multi-layer PCB circuit board quality inspection system for implementing any of the above multi-layer PCB circuit board quality inspection methods; the system comprises:

[0042] The ray attenuation analysis module is used to determine a standard X-ray inspection image of normal quality of the same model as the target multi-layer PCB circuit board and the PCB spatial structural components therein, and calculate the initial standard X-ray attenuation coefficients of different PCB spatial structural components; based on the initial standard X-ray attenuation coefficients, calculate the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components in the same longitudinal space within the target multi-layer PCB circuit board;

[0043] A ray penetration test module is used to determine the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is irradiated according to the comprehensive average multi-layer attenuation coefficient, and calculate the ray shielding intensity of the target local scanning area based on the target penetration path;

[0044] The ray intensity adjustment module is used to determine the adaptive ray intensity of the target local scanning area using the ray blocking intensity, and rescan the target local scanning area using the adaptive ray intensity to determine the quality of the PCB circuit board.

[0045] The present invention has the following beneficial effects:

[0046] The present invention obtains the attenuation coefficients of various PCB spatial structural components contained in multiple layers within a multi-layer PCB circuit board to be inspected, referring to existing standard radiographic inspection diagrams that have been verified for quality inspection. Based on the attenuation coefficients, the present invention analyzes the superposition of paths that hinder X-ray penetration by various components within each layer of the multi-layer PCB circuit board in the same longitudinal space. The present invention further analyzes the degree to which X-rays at an initial intensity are blocked when scanning the surface of the multi-layer PCB circuit board. Ultimately, the ray blocking intensity is determined, and the X-ray intensity is adjusted based on this intensity to re-scan. Quality inspection of the multi-layer PCB circuit board is performed based on the characteristics of the multi-layer component superposition, so that the local scan area on the multi-layer PCB circuit board is displayed as completely as possible, thereby improving the quality inspection accuracy of the multi-layer PCB circuit board. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flowchart of a method for inspecting the quality of a multi-layer PCB circuit board provided by one embodiment of the present invention;

[0049] Figure 2 A detailed flow chart of step S1 in a multi-layer PCB circuit board quality inspection method provided by one embodiment of the present invention;

[0050] Figure 3 A detailed flow chart of step S2 in a multi-layer PCB circuit board quality inspection method provided by one embodiment of the present invention;

[0051] Figure 4 A detailed flow chart of step S3 in a multi-layer PCB circuit board quality inspection method provided by one embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of the hardware operating environment of a multi-layer PCB circuit board quality inspection device according to an embodiment of the present invention;

[0053] Figure 6 This is a schematic diagram of the framework structure of a multi-layer PCB circuit board quality inspection system according to an embodiment of the present invention;

[0054] Figure 7 A schematic diagram of a multi-layer PCB circuit board radiographic inspection method provided by an embodiment of the present invention;

[0055] Figure 8 A schematic diagram of a sequence of PCB spatial structural components involved in a multi-layer PCB circuit board quality inspection method provided by an embodiment of the present invention;

[0056] Figure 9 A schematic diagram of component overlay clustering involved in a multi-layer PCB circuit board quality inspection method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a multi-layer PCB quality inspection method according to the present invention, including its specific implementation, structure, features, and effectiveness. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0058] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0059] The following describes in detail a method for detecting the quality of a multi-layer PCB circuit board provided by the present invention with reference to the accompanying drawings.

[0060] Example 1:

[0061] For the multi-layer PCB circuit board quality inspection method provided by the present invention, please refer to Figure 1 , which shows a flow chart of the steps of a multi-layer PCB circuit board quality inspection method provided by an embodiment of the present invention.

[0062] The method comprises:

[0063] Step S1, determining a standard X-ray inspection image of a target multi-layer PCB circuit board of the same model and normal quality and the PCB spatial structural components therein, and calculating the initial standard X-ray attenuation coefficients of different PCB spatial structural components;

[0064] In this embodiment, the model of the target multi-layer PCB circuit board to be inspected is selected, and then the X-ray inspection image of the multi-layer PCB circuit board of the same model is extracted from the X-ray digital inspection image backup library, such as Figure 7 As shown, Figure 7 A schematic diagram of a multi-layer PCB circuit board radiographic inspection method provided in an embodiment of the present invention. The multi-layer PCB circuit radiographic inspection image is a known qualified inspection image, i.e., a standard X-ray inspection image of normal quality.

[0065] The PCB spatial design drawings of each layer of the same model multi-layer PCB circuit in the database are exported, and the PCB spatial structural components of each layer of the multi-layer PCB circuit board are identified by semantic segmentation using a trained neural network to obtain several PCB spatial structural components (such as through holes, blind holes, buried holes, etc.) of each layer of the PCB circuit board. The neural network is set to the HRNet model, and the loss function is set to the cross-entropy loss function. In addition, the same model mentioned in this embodiment refers to the same type of PCB spatial structural components included.

[0066] Specifically, in one embodiment, please refer to Figure 2 , the step S1 comprises:

[0067] Step S11, based on the standard X-ray detection image, determining a target local scanning area formed by superimposing different layers of PCB spatial structural components in the same longitudinal space inside the target multi-layer PCB circuit board;

[0068] Based on the standard X-ray inspection image, the top layer of the target multi-layer PCB circuit board is used as the starting layer. The trained neural network is used to divide the PCB circuit board into local scanning areas from the top layer to the bottom layer in the same longitudinal space to obtain multiple target local scanning areas.

[0069] Combine the PCB spatial structure components at the corresponding positions on each layer of the PCB circuit board from each local scan area to obtain a sequence of PCB spatial structure components for each local scan area. The neural network is set to the YOLOv3 model, and the loss function is set to the mean square error function.

[0070] Step S12, determining the PCB spatial structural component sequence and grayscale value mean of the target local scanning area, and calculating the initial standard X attenuation coefficient of the target type of PCB spatial structural component using the PCB spatial structural component sequence and grayscale value mean;

[0071] Among them, the PCB spatial structure component sequence is formed by arranging the PCB spatial structure components in each layer of the scanning area in layer order. To facilitate understanding of the PCB spatial structure component sequence, please refer to Figure 8 , Figure 8 A schematic diagram of a PCB spatial structural component sequence involved in a multi-layer PCB circuit board quality inspection method provided in an embodiment of the present invention, where L1 = {a, 1, b, 1} represents a PCB spatial structural component sequence in the first local scanning area, which contains four layers; L4 = {c, c, c, c} represents a PCB spatial structural component sequence in the fourth local scanning area, which contains four layers; wherein a represents a blind hole, 1 represents no hole, b represents a buried hole, and c represents a through hole.

[0072] The step S12 specifically includes:

[0073] Establish an equation between the PCB spatial structure component sequence and the grayscale value mean, and calculate the target grayscale value of the target type of PCB spatial structure component;

[0074] The target grayscale value mean is converted into the intensity of the penetrated ray, and the initial standard X-ray attenuation coefficient of the target type of PCB spatial structure component is calculated based on the Beer-Lambert law.

[0075] In this embodiment, a numerical relationship is established between the sequence of PCB spatial structural components in each target local scanning area and the mean grayscale value of the corresponding scanning area in the multi-layer PCB circuit board radiographic inspection image, as shown in the following Table 1:

[0076]

[0077] Table 1

[0078] Based on the numerical relationship, the Beer-Lambert law and the grayscale value conversion formula are constructed to construct the corresponding equations (such as ), and then determine the target grayscale value for each type of PCB spatial structural component, and then calculate the initial standard X attenuation coefficient γ for each type of PCB spatial structural component. The various target types of PCB spatial structural components here refer to inner layers, outer layers, through holes, blind vias, buried vias, core boards, prepregs, etc.

[0079] Among them, the conversion relationship between the gray value G and the intensity of the ray after penetration I (gray value conversion formula) is:

[0080] G = k × I + G0 (linear model);

[0081] G = k × lnI + G0 (logarithmic model, relatively more commonly used);

[0082] k: gain factor (determined by the sensitivity of the detector);

[0083] G0: Background noise offset.

[0084] Among them, the attenuation formula of the Beer-Lambert law is as follows:

[0085] I=I0×e -μ·t

[0086] I0: incident ray intensity (before penetrating the object, in this scheme, it refers to the initial predetermined X-ray intensity);

[0087] I: intensity of the rays after penetration;

[0088] μ: linear attenuation coefficient (related to material density and atomic number);

[0089] t: penetration path length (object thickness).

[0090] After converting the target grayscale value mean into the intensity of the penetrating ray, the initial standard X attenuation coefficient (corresponding to the linear attenuation coefficient μ) of each target type of PCB spatial structural component is calculated based on the above-mentioned Beer-Lambert law. Here, the initial standard X attenuation coefficient is referred to as γ.

[0091] During the calculation process, the same PCB spatial structure component may be affected by the actual application scenario, and multiple different values may be calculated. The average of all corresponding values can be taken as the initial standard X attenuation coefficient γ of the corresponding type of PCB spatial structure component. (γ is always a negative number)

[0092] Step S2, calculating the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components within the target multi-layer PCB circuit board in the same longitudinal space based on the initial standard X attenuation coefficient;

[0093] The initial standard X-ray attenuation coefficient γ calculated in the above process is roughly calculated by matching the grayscale detection image with the component combination. In fact, the attenuation coefficient will be affected by the combined influence of the multi-layer PCB circuit board, X-rays and the actual environment, resulting in detailed differences.

[0094] The penetration effect of X-rays is affected by material properties (such as atomic number and density), as well as their geometric area and structure (thickness and stacking). Multilayer PCBs are subject to scenario constraints, and the material properties, geometric area, and thickness of the same PCB spatial structural components are identical. Therefore, X-rays of the same intensity will have the same penetration effect when passing through a penetration path containing the same type and number of PCB spatial structural components (such as a->1->1->b->a and a->b->1->1->a). In summary, the primary factors affecting the X-ray penetration path are the number and thickness of different PCB spatial structural components.

[0095] After the PCB spatial structural components on each PCB layer inside the multi-layer PCB circuit board are arranged, the prepreg between the layers acts as an adhesive layer and is pressed together under high temperature and high pressure to form a flat multi-layer PCB circuit board. The PCB spatial structural components on each PCB layer are not arranged in exactly the same position. During the pressing process, the prepreg will fill the extra gaps between the layers. However, because the prepreg's attenuation effect on X-rays is basically negligible in actual scenarios, the thickness of the corresponding PCB spatial structural components in each local scanning area will also have a significant impact on the X-ray penetration effect due to the different corresponding penetration paths.

[0096] Specifically, in one embodiment, please refer to Figure 3 , the step S2 comprises:

[0097] Step S21, determining the component thickness of the PCB spatial structural component, the overall thickness of the target local scanning area, and the number of components of the PCB spatial structural component in the target local scanning area;

[0098] Step S22 , using the initial standard X attenuation coefficient, component thickness, overall thickness, and number of components, calculate the comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area.

[0099] Wherein, the step S22 specifically includes:

[0100] The length of the low-interference path in the target local scanning area is calculated using the component thickness and the overall thickness. The low-interference path represents the path where the prepreg is located.

[0101] Using the initial standard X attenuation coefficient, component thickness, and component quantity, the average type attenuation coefficient of the PCB spatial structure components is calculated;

[0102] The comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated using the low-interference path length, overall thickness and average type attenuation coefficient.

[0103] Count the component thickness h of each PCB spatial structure component.

[0104] Count the overall thickness H of each target local scanning area.

[0105] The greater the difference between the overall thickness of a single local scanning area and the theoretical thickness formed by the sequence of its PCB spatial structural components, the longer the penetration path provided by the prepreg in the corresponding local scanning area. This means that there is more space to support low-loss X-rays when they penetrate the corresponding local scanning area. Based on h and H, calculate the low-interference path length L of each local scanning area:

[0106]

[0107] Where I represents the total number of PCB spatial structure components contained in the PCB spatial structure component sequence of each local scanning area; i represents the serial number of each PCB spatial structure component in each local scanning area.

[0108] The component thickness h of each PCB spatial structure component in the PCB spatial structure component sequence of a single local scanning area is sorted in descending order, and the component quantity N of each PCB spatial structure component in the local scanning area is counted.

[0109] Based on h and N, the total attenuation path L1 = h × N of each type of PCB spatial structural component in each local scanning area is calculated.

[0110] In a single local scanning area, if the penetration path provided by a single type of PCB spatial structural component is longer, the initial standard X-ray attenuation coefficient is smaller, indicating that when X-rays irradiate the local scanning area, the PCB spatial structural component of the corresponding type acts as the main component to absorb X-rays: Based on the initial standard X-ray attenuation coefficient γ, the number of components N, and the total type attenuation path L1, the average type attenuation coefficient γ1 of each PCB spatial structural component in each local scanning area is calculated:

[0111]

[0112] Among them, n represents the serial number of each PCB spatial structure component in the local scanning area, γ nIndicates the initial standard X attenuation coefficient of each PCB spatial structural component in its corresponding local scanning area.

[0113] If the penetration path provided by the overall PCB spatial structural components in a single local scanning area accounts for a larger proportion, the overall attenuation coefficient is smaller, indicating that the range of possible variation of the initial standard X attenuation coefficient γ in a single local scanning area is larger: Based on the low-interference path length L, the overall thickness H, and the average type attenuation coefficient γ1, calculate the comprehensive average multi-layer attenuation coefficient γ2 in each local scanning area:

[0114]

[0115] At this point, the comprehensive average multi-layer attenuation coefficient in each local scanning area is obtained.

[0116] Step S3, determining the target penetration path inside the target local scanning area when the initially predetermined X-ray intensity is irradiated based on the comprehensive average multi-layer attenuation coefficient, and calculating the ray shielding intensity of the target local scanning area based on the target penetration path;

[0117] For a local scanning area containing the same type and number of PCB spatial structural components (for example, the sequence of PCB spatial structural components is {1, b, b, 1, 1, a}, {a, 1, b, 1, b, 1}), although the overall attenuation of X-rays is basically the same and the final radiographic imaging effect is basically the same, their different arrangements and combinations result in different attenuation intensities on each layer within the corresponding penetration path. If the X-rays are completely attenuated midway, the traditional method can only obtain the local image effect corresponding to the multi-layer PCB circuit board that has not penetrated, but cannot locate at which layer the X-rays stop attenuating, and thus cannot determine the corresponding target penetration path, and cannot reasonably adjust the intensity based on the remaining unpenetrated PCB spatial structural components to obtain a detection image with accurate information expression.

[0118] Specifically, in one embodiment, please refer to Figure 4 , the step S3 comprises:

[0119] Step S31, determining the area to be adjusted for the local scanning intensity in the target local scanning area according to the comprehensive average multi-layer attenuation coefficient;

[0120] The step S31 specifically includes:

[0121] According to the initial predetermined X-ray intensity corresponding to the standard X-ray detection map, the target local scanning area is irradiated to obtain the corresponding actual grayscale mean value;

[0122] According to the initially predetermined X-ray intensity and the comprehensive average multi-layer attenuation coefficient, the theoretical grayscale mean of the target local scanning area is calculated based on the Beer-Lambert law;

[0123] The mean difference value is obtained by subtracting the theoretical mean grayscale value from the actual mean grayscale value, and the local scanning area with the mean difference value greater than or equal to the preset difference threshold is used as the local scanning intensity adjustment area.

[0124] In this embodiment, the X-ray intensity is set to the same value as the X-ray intensity of the multi-layer PCB circuit board X-ray detection image, that is, it is set to the initial predetermined X-ray intensity corresponding to the standard X-ray detection image, and each local scanning area on the PCB circuit board to be inspected is irradiated in turn to obtain the actual grayscale mean value of each local scanning area.

[0125] According to the set X-ray intensity and the comprehensive average multi-layer attenuation coefficient in each local scanning area, the theoretical grayscale mean value of each local scanning area is calculated based on the Beer-Lambert law mentioned above.

[0126] The local scanning area where the theoretical grayscale mean is less than the actual grayscale mean by 20 (the preset gap threshold can be adjusted according to actual conditions), that is, the local scanning area corresponding to the mean gap value is greater than or equal to the preset gap threshold, is set as the local scanning intensity adjustment area.

[0127] The acquired local scanning intensity is to be adjusted in an area that may be an area with quality defects or an area with insufficient X-ray intensity. Since increasing the ray intensity will not significantly affect the image display effect of the area with quality defects, an analysis of the X-ray intensity adjustment is first performed to further screen out areas that may have quality defects.

[0128] Step S32, starting from the first layer of the area to be adjusted for the local scanning intensity, iteratively accumulates the average type attenuation coefficients of the PCB spatial structural components in the area to be adjusted for the local scanning intensity, and calculates the layer grayscale mean of the target number of layers;

[0129] Step S33, determining the grayscale difference between the target layer's grayscale mean and the measured grayscale mean, and taking the layer number corresponding to the minimum grayscale difference as the attenuation stop layer;

[0130] Step S34 , determining the first layer to the attenuation stop layer in the area to be adjusted for the local scanning intensity as the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is used to irradiate the target local scanning area.

[0131] In this embodiment, the following description is made by taking any c-th local scanning intensity adjustment area as an example:

[0132] Starting from the first layer, the average attenuation coefficient γ1 of each type of PCB spatial structural component is iteratively accumulated. The layer-level grayscale mean corresponding to the target layer is calculated (similarly according to the Beer-Lambert law). The layer with the minimum grayscale difference between the layer-level grayscale mean and the measured grayscale mean is set as the attenuation stop layer. (If there are multiple minimum values, the layer with the first minimum value is set as the attenuation stop layer.) Once the attenuation stop layer is determined, the target penetration path is determined.

[0133] In one embodiment, the calculating of the ray shielding intensity of the target local scanning area based on the target penetration path specifically includes:

[0134] determining the number of remaining layers of the area to be adjusted for the local scanning intensity after the attenuation stop layer;

[0135] The residual type attenuation coefficients of the PCB spatial structure components in the remaining number of layers are calculated using the average type attenuation coefficients of the PCB spatial structure components in the remaining number of layers;

[0136] The ray shielding intensity of the area where the local scanning intensity is to be adjusted is calculated using the number of types of PCB spatial structural components in the remaining layers and the residual type attenuation coefficients.

[0137] Count the number of remaining layers M after the attenuation stop layer, and refer to the above process of calculating the average type attenuation coefficient γ1 to calculate the residual type attenuation coefficient γ3 of each PCB spatial structure component under the remaining number of layers M:

[0138]

[0139] Among them, M1 represents the number of layers of each PCB spatial structure component included in the remaining number of layers M, and the corresponding m1 represents the serial number of each PCB spatial structure component included in the remaining number of layers M; γ m1 It represents the initial standard X attenuation coefficient of each PCB spatial structure component in the remaining number of layers M, h m1 Indicates the component thickness of each PCB spatial structure component in the remaining number of layers M.

[0140] If the number of layers not penetrated by X-rays after the attenuation stop layer is large, and the number and types of corresponding unirradiated PCB spatial structural components are large, it means that the number of layers and components not penetrated by X-rays and blocked in the corresponding local scanning intensity adjustment area is large, reflecting that the initial intensity of X-rays is weaker and more enhancement processing is needed: According to the residual attenuation coefficient γ3 of each PCB spatial structural component under the remaining number of layers M, calculate the ray blocking intensity D of the cth local scanning intensity adjustment area c :

[0141]

[0142] Where N1 c represents the number of types of PCB spatial structural components existing in the remaining number of layers M in the c-th local scanning intensity to be adjusted area, n1 represents the corresponding PCB spatial structural component type serial number, and c refers to the c-th local scanning intensity to be adjusted area; represents the residual type attenuation coefficient of each PCB spatial structural component in the cth local scanning intensity adjustment area; M c Indicates the number of layers remaining after the attenuation termination layer in the cth local scan intensity adjustment area; M1 c Indicates the number of layers remaining after the attenuation termination layer in the cth local scan intensity adjustment area, including the number of layers of each PCB spatial structure component; Indicates the number of layers of any PCB spatial structural component type that does not exist in the c-th local scanning intensity adjustment area.

[0143] At this point, the ray blocking intensity of each local scanning intensity adjustment area is obtained.

[0144] Step S4: determining the adaptive ray intensity of the target local scanning area using the ray shielding intensity, and rescanning the target local scanning area using the adaptive ray intensity to determine the quality of the PCB circuit board.

[0145] The method of rescanning the target local scanning area using the adaptive ray intensity to determine the quality of the PCB circuit board specifically includes:

[0146] Use adaptive ray intensity to rescan the target local scanning area to obtain a new multi-layer PCB circuit board ray inspection map;

[0147] Based on the new multi-layer PCB circuit board radiographic inspection map, DBSCAN clustering is performed on the PCB spatial structure components in each layer to obtain component superposition clusters after longitudinal superposition;

[0148] Determine the reference theoretical grayscale mean and the actual detection grayscale mean of the target local scanning area occupied by the component superposition cluster clusters, and use the difference between the reference theoretical grayscale mean and the actual detection grayscale mean to determine whether the target local scanning area is a quality defect area to determine the quality of the PCB circuit board.

[0149] In this embodiment, similarly based on the Beer-Lambert law, the ray shielding intensity of each local scanning intensity adjustment area is substituted as the linear attenuation coefficient to calculate the adaptive ray intensity of each local scanning intensity adjustment area.

[0150] Start the X-ray device to rescan each local scanning area on the surface of the multi-layer PCB circuit board to be inspected. When scanning the corresponding local scanning intensity adjustment area, adjust the X-ray intensity to the corresponding adaptive ray intensity before scanning; when scanning the area outside the local scanning intensity adjustment area, adjust the X-ray intensity to the initial intensity before scanning; after scanning all local scanning areas, download the new multi-layer PCB circuit board X-ray inspection map.

[0151] Based on the new multi-layer PCB circuit board radiographic inspection diagram, please refer to Figure 9 , Figure 9 A schematic diagram of component stacking clusters involved in a multi-layer PCB quality inspection method provided by an embodiment of the present invention. DBSCAN clustering (density-based clustering algorithm) is performed on the PCB spatial structural components within each layer of the multi-layer PCB to obtain multiple component clusters for each layer. These multiple component clusters for each layer are then stacked vertically to obtain a stacked component cluster.

[0152] The attenuation coefficient of the local scanning area occupied by the component superposition cluster is calculated, and based on the Beer-Lambert law and the conversion calculation formula between grayscale and ray intensity mentioned above, the comparative theoretical grayscale mean of each local scanning area occupied by the component superposition cluster is calculated.

[0153] The actual detection grayscale mean of each local scanning area occupied by the statistical component superposition cluster clusters; the local scanning area where the difference between the actual detection grayscale mean and the corresponding control theoretical grayscale mean (i.e., the actual detection grayscale mean minus the control theoretical grayscale mean) is greater than 25 (preset value, which can be adjusted according to actual conditions) is set as a quality defect area.

[0154] If there are quality defect areas on the multi-layer PCB circuit board, the multi-layer PCB circuit board is deemed to be unqualified; conversely, if there are no quality defect areas on the multi-layer PCB circuit board, the multi-layer PCB circuit board is deemed to be qualified.

[0155] The present invention obtains the attenuation coefficients of various PCB spatial structural components contained in multiple layers within a multi-layer PCB circuit board to be inspected, referring to existing standard radiographic inspection diagrams that have been verified for quality inspection. Based on the attenuation coefficients, the present invention analyzes the superposition of paths that hinder X-ray penetration by various components within each layer of the multi-layer PCB circuit board in the same longitudinal space. The present invention further analyzes the degree to which X-rays at an initial intensity are blocked when scanning the surface of the multi-layer PCB circuit board. Ultimately, the ray blocking intensity is determined, and the X-ray intensity is adjusted based on this intensity to re-scan. Quality inspection of the multi-layer PCB circuit board is performed based on the characteristics of the multi-layer component superposition, so that the local scan area on the multi-layer PCB circuit board is displayed as completely as possible, thereby improving the quality inspection accuracy of the multi-layer PCB circuit board.

[0156] Example 2:

[0157] The embodiment of the present invention further provides a multi-layer PCB circuit board quality inspection device. The multi-layer PCB circuit board quality inspection device can be a data calculation and processing device such as a computer, a server, or a combination of multiple devices.

[0158] like Figure 5 As shown, Figure 5 It is a structural diagram of the hardware operating environment of the multi-layer PCB circuit board quality inspection equipment involved in the embodiment of the present invention.

[0159] like Figure 5 As shown, the multi-layer PCB circuit board quality inspection device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display (Display), an input unit such as a control panel, and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005, which is a computer storage medium, may include a multi-layer PCB circuit board quality inspection program.

[0160] Those skilled in the art will understand that Figure 5 The hardware structure shown in the figure does not constitute a limitation of the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0161] Continue to refer to Figure 5 , Figure 5 The memory 1005 as a computer-readable storage medium may include an operating system, a user interface module, a network communication module, and a multi-layer PCB circuit board quality detection program.

[0162] exist Figure 5 In the embodiment, the network communication module is mainly used to connect to the server and can communicate data with the server; and the processor 1001 can call the multi-layer PCB circuit board quality detection program stored in the memory 1005 and execute the steps in the above embodiments.

[0163] The hardware structure of the multi-layer PCB circuit board quality inspection device described above is used to implement various embodiments of the multi-layer PCB circuit board quality inspection method of the present invention.

[0164] In addition, the present invention also provides a multi-layer PCB circuit board quality detection system, please refer to Figure 6 , the multi-layer PCB circuit board quality inspection system includes:

[0165] The ray attenuation analysis module A10 is used to determine a standard X-ray inspection image of normal quality of the same model as the target multi-layer PCB circuit board and the PCB spatial structural components therein, and calculate the initial standard X-ray attenuation coefficients of different PCB spatial structural components; based on the initial standard X-ray attenuation coefficients, calculate the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components within the target multi-layer PCB circuit board in the same longitudinal space;

[0166] The radiation penetration test module A20 is used to determine the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is irradiated according to the comprehensive average multi-layer attenuation coefficient, and calculate the radiation shielding intensity of the target local scanning area based on the target penetration path;

[0167] The ray intensity adjustment module A30 is used to determine the adaptive ray intensity of the target local scanning area using the ray blocking intensity, and rescan the target local scanning area using the adaptive ray intensity to determine the quality of the PCB circuit board.

[0168] Furthermore, the ray attenuation analysis module A10 is further configured to:

[0169] Based on the standard X-ray inspection diagram, determine the target local scanning area formed by the superposition of different layers of PCB spatial structural components in the same longitudinal space inside the target multi-layer PCB circuit board;

[0170] Determine the PCB spatial structure component sequence and grayscale value mean of the target local scanning area, and calculate the initial standard X attenuation coefficient of the target type of PCB spatial structure component using the PCB spatial structure component sequence and grayscale value mean;

[0171] The PCB spatial structure component sequence is formed by arranging the PCB spatial structure components in each scanning area in a layer sequence.

[0172] Furthermore, the ray attenuation analysis module A10 is further configured to:

[0173] Establish an equation between the PCB spatial structure component sequence and the grayscale value mean, and calculate the target grayscale value of the target type of PCB spatial structure component;

[0174] The target grayscale value mean is converted into the intensity of the penetrated ray, and the initial standard X-ray attenuation coefficient of the target type of PCB spatial structure component is calculated based on the Beer-Lambert law.

[0175] Furthermore, the ray attenuation analysis module A10 is further configured to:

[0176] Determine the component thickness of the PCB spatial structure component and the overall thickness of the target local scanning area, as well as the number of components of the PCB spatial structure component in the target local scanning area;

[0177] Using the initial standard X attenuation coefficient, component thickness, overall thickness, and number of components, the comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated.

[0178] Furthermore, the ray attenuation analysis module A10 is further configured to:

[0179] The length of the low-interference path in the target local scanning area is calculated using the component thickness and the overall thickness. The low-interference path represents the path where the prepreg is located.

[0180] Using the initial standard X attenuation coefficient, component thickness, and component quantity, the average type attenuation coefficient of the PCB spatial structure components is calculated;

[0181] The comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated using the low-interference path length, overall thickness and average type attenuation coefficient.

[0182] Furthermore, the ray penetration test module A20 is further used to:

[0183] Determining a region to be adjusted in the local scanning intensity in the target local scanning region according to the comprehensive average multi-layer attenuation coefficient;

[0184] Starting from the first layer of the area where the local scanning intensity is to be adjusted, iteratively accumulate the average type attenuation coefficients of the PCB spatial structural components in the area where the local scanning intensity is to be adjusted, and calculate the layer grayscale mean of the target number of layers;

[0185] Determine the grayscale difference between the target layer's grayscale mean and the measured grayscale mean, and use the layer number corresponding to the minimum grayscale difference as the attenuation stop layer;

[0186] The first layer to the attenuation stop layer of the area to be adjusted for the local scanning intensity is determined as the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is used to irradiate the target local scanning area.

[0187] Furthermore, the ray penetration test module A20 is further used to:

[0188] According to the initial predetermined X-ray intensity corresponding to the standard X-ray detection map, the target local scanning area is irradiated to obtain the corresponding actual grayscale mean value;

[0189] According to the initially predetermined X-ray intensity and the comprehensive average multi-layer attenuation coefficient, the theoretical grayscale mean of the target local scanning area is calculated based on the Beer-Lambert law;

[0190] The mean difference value is obtained by subtracting the theoretical mean grayscale value from the actual mean grayscale value, and the local scanning area with the mean difference value greater than or equal to the preset difference threshold is used as the local scanning intensity adjustment area.

[0191] Furthermore, the ray penetration test module A20 is further used to:

[0192] determining the number of remaining layers of the area to be adjusted for the local scanning intensity after the attenuation stop layer;

[0193] The residual type attenuation coefficients of the PCB spatial structure components in the remaining number of layers are calculated using the average type attenuation coefficients of the PCB spatial structure components in the remaining number of layers;

[0194] The ray shielding intensity of the area where the local scanning intensity is to be adjusted is calculated using the number of types of PCB spatial structural components in the remaining layers and the residual type attenuation coefficients.

[0195] Furthermore, the ray intensity adjustment module A30 is further configured to:

[0196] Use adaptive ray intensity to rescan the target local scanning area to obtain a new multi-layer PCB circuit board ray inspection map;

[0197] Based on the new multi-layer PCB circuit board radiographic inspection map, DBSCAN clustering is performed on the PCB spatial structure components in each layer to obtain component superposition clusters after longitudinal superposition;

[0198] Determine the reference theoretical grayscale mean and the actual detection grayscale mean of the target local scanning area occupied by the component superposition cluster clusters, and use the difference between the reference theoretical grayscale mean and the actual detection grayscale mean to determine whether the target local scanning area is a quality defect area to determine the quality of the PCB circuit board.

[0199] The specific implementation of the multi-layer PCB circuit board quality inspection system of the present invention is basically the same as the various embodiments of the multi-layer PCB circuit board quality inspection method described above, and will not be repeated here.

[0200] The present invention also provides a computer-readable storage medium having a multi-layer PCB quality inspection program stored thereon, wherein when the multi-layer PCB quality inspection program is executed by a processor, the steps of the multi-layer PCB quality inspection method described above are implemented.

[0201] Among them, the method implemented when the multi-layer PCB circuit board quality inspection program is executed can refer to the various embodiments of the multi-layer PCB circuit board quality inspection method of the present invention, and will not be repeated here.

[0202] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0203] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from the reference embodiment.

[0204] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0205] The above description is only a preferred embodiment of the present invention and does not limit the scope of protection of the present invention. All equivalent structural / method transformations made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or direct / indirect application in reference to related technical fields are included in the scope of protection of the present invention.

Claims

1. A multi-layer PCB circuit board quality inspection method, characterized in that: The method comprises: Determine the standard X-ray inspection image of the same model and normal quality as the target multi-layer PCB circuit board and the PCB spatial structural components therein, and calculate the initial standard X-ray attenuation coefficients of different PCB spatial structural components; Based on the initial standard X attenuation coefficient, calculate the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components inside the target multi-layer PCB circuit board in the same longitudinal space; Determining the target penetration path within the target local scanning area when the initially predetermined X-ray intensity is irradiated based on the comprehensive average multi-layer attenuation coefficient, and calculating the ray shielding intensity of the target local scanning area based on the target penetration path; The adaptive ray intensity of the target local scanning area is determined using the ray blocking intensity, and the target local scanning area is rescanned using the adaptive ray intensity to determine the quality of the PCB circuit board.

2. The multi-layer PCB circuit board quality inspection method according to claim 1, characterized in that: The calculation of the initial standard X attenuation coefficients of different PCB spatial structural components includes: Based on the standard X-ray inspection diagram, determine the target local scanning area formed by the superposition of different layers of PCB spatial structural components in the same longitudinal space inside the target multi-layer PCB circuit board; Determine the PCB spatial structure component sequence and grayscale value mean of the target local scanning area, and calculate the initial standard X attenuation coefficient of the target type of PCB spatial structure component using the PCB spatial structure component sequence and grayscale value mean; The PCB spatial structure component sequence is formed by arranging the PCB spatial structure components in each scanning area in a layer sequence.

3. The multi-layer PCB circuit board quality inspection method according to claim 2, characterized in that: The method of calculating the initial standard X attenuation coefficient of the target type of PCB spatial structural component by using the PCB spatial structural component sequence and the gray value mean includes: Establish an equation between the PCB spatial structure component sequence and the grayscale value mean, and calculate the target grayscale value of the target type of PCB spatial structure component; The target grayscale value mean is converted into the intensity of the penetrated ray, and the initial standard X-ray attenuation coefficient of the target type of PCB spatial structure component is calculated based on the Beer-Lambert law.

4. The multi-layer PCB circuit board quality inspection method according to claim 1, characterized in that: The calculation of the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components within the target multi-layer PCB circuit board in the same longitudinal space based on the initial standard X attenuation coefficient includes: Determine the component thickness of the PCB spatial structure component and the overall thickness of the target local scanning area, as well as the number of components of the PCB spatial structure component in the target local scanning area; Using the initial standard X attenuation coefficient, component thickness, overall thickness, and number of components, the comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated.

5. The multi-layer PCB circuit board quality inspection method according to claim 4, characterized in that: The initial standard X attenuation coefficient, component thickness, overall thickness, and number of components are used to calculate the comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area, including: The length of the low-interference path in the target local scanning area is calculated using the component thickness and the overall thickness. The low-interference path represents the path where the prepreg is located. Using the initial standard X attenuation coefficient, component thickness, and component quantity, the average type attenuation coefficient of the PCB spatial structure components is calculated; The comprehensive average multi-layer attenuation coefficient of the target multi-layer PCB circuit board in the target local scanning area is calculated using the low-interference path length, overall thickness and average type attenuation coefficient.

6. The multi-layer PCB circuit board quality inspection method according to claim 1, characterized in that: The step of determining the target penetration path inside the target local scanning area when the initially predetermined X-ray intensity is irradiated according to the comprehensive average multi-layer attenuation coefficient includes: Determining a region to be adjusted in the local scanning intensity in the target local scanning region according to the comprehensive average multi-layer attenuation coefficient; Starting from the first layer of the area where the local scanning intensity is to be adjusted, iteratively accumulate the average type attenuation coefficients of the PCB spatial structural components in the area where the local scanning intensity is to be adjusted, and calculate the layer grayscale mean of the target number of layers; Determine the grayscale difference between the target layer's grayscale mean and the measured grayscale mean, and use the layer number corresponding to the minimum grayscale difference as the attenuation stop layer; The first layer to the attenuation stop layer of the area to be adjusted for the local scanning intensity is determined as the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is used to irradiate the target local scanning area.

7. The multi-layer PCB circuit board quality inspection method according to claim 6, characterized in that: The step of determining the area to be adjusted in the local scanning intensity in the target local scanning area according to the comprehensive average multi-layer attenuation coefficient includes: According to the initial predetermined X-ray intensity corresponding to the standard X-ray detection map, the target local scanning area is irradiated to obtain the corresponding actual grayscale mean value; According to the initially predetermined X-ray intensity and the comprehensive average multi-layer attenuation coefficient, the theoretical grayscale mean of the target local scanning area is calculated based on the Beer-Lambert law; The mean difference value is obtained by subtracting the theoretical mean grayscale value from the actual mean grayscale value, and the local scanning area with the mean difference value greater than or equal to the preset difference threshold is used as the local scanning intensity adjustment area.

8. The multi-layer PCB circuit board quality inspection method according to claim 6, characterized in that: The calculating of the ray shielding intensity of the target local scanning area based on the target penetration path includes: determining the number of remaining layers of the area to be adjusted for the local scanning intensity after the attenuation stop layer; The residual type attenuation coefficients of the PCB spatial structure components in the remaining number of layers are calculated using the average type attenuation coefficients of the PCB spatial structure components in the remaining number of layers; The ray shielding intensity of the area where the local scanning intensity is to be adjusted is calculated using the number of types of PCB spatial structural components in the remaining layers and the residual type attenuation coefficients.

9. The multi-layer PCB circuit board quality inspection method according to claim 1, characterized in that: The method of rescanning the target local scanning area using adaptive ray intensity to determine the quality of the PCB circuit board includes: Use adaptive ray intensity to rescan the target local scanning area to obtain a new multi-layer PCB circuit board ray inspection map; Based on the new multi-layer PCB circuit board radiographic inspection map, DBSCAN clustering is performed on the PCB spatial structure components in each layer to obtain component superposition clusters after longitudinal superposition; Determine the reference theoretical grayscale mean and the actual detection grayscale mean of the target local scanning area occupied by the component superposition cluster clusters, and use the difference between the reference theoretical grayscale mean and the actual detection grayscale mean to determine whether the target local scanning area is a quality defect area to determine the quality of the PCB circuit board.

10. A multi-layer PCB circuit board quality inspection system, characterized in that: The system is used to implement the multi-layer PCB circuit board quality detection method according to any one of claims 1 to 9; the system comprises: The ray attenuation analysis module is used to determine a standard X-ray inspection image of normal quality of the same model as the target multi-layer PCB circuit board and the PCB spatial structural components therein, and calculate the initial standard X-ray attenuation coefficients of different PCB spatial structural components; based on the initial standard X-ray attenuation coefficients, calculate the comprehensive average multi-layer attenuation coefficient of the target local scanning area formed by the superposition of different layers of PCB spatial structural components in the same longitudinal space within the target multi-layer PCB circuit board; A ray penetration test module is used to determine the target penetration path inside the target local scanning area when the initial predetermined X-ray intensity is irradiated according to the comprehensive average multi-layer attenuation coefficient, and calculate the ray shielding intensity of the target local scanning area based on the target penetration path; The ray intensity adjustment module is used to determine the adaptive ray intensity of the target local scanning area using the ray blocking intensity, and rescan the target local scanning area using the adaptive ray intensity to determine the quality of the PCB circuit board.

Images