Circuit board back drilling hole STUB detection method and detection system

Abstract

The invention discloses a circuit board back drilling STUB detection method and system, and the method comprises the following steps: obtaining a cross section image set generated by scanning a to-be-detected circuit board through employing an electronic computer tomography technology, and the cross section image set comprises a plurality of cross section images which are sequentially arranged according to the height of a cross section; analyzing the cross section images in the image set in sequence, determining the position of the end of the remaining Stub, and recording the position as a first position; determining the position of a layer which is electrically connected with the residual Stub and is closest to the end of the residual Stub, and recording the position as a second position; and calculating the distance between the first position and the second position to determine whether the back drilling hole Stub is qualified or not. The position relation between the Stub in the back drilling hole and the signal layer is accurately detected through the tomography technology and the artificial intelligence technology, an expensive camera is not needed, and a finished circuit board does not need to be damaged.

Description

Technical Field

[0001] The present invention relates to the field of circuit device detection, and in particular to a circuit board back-drilled STUB detection method and a detection system. Background Art

[0002] After the through-hole metallization operation is performed on the circuit board, the stubs in the through-holes will introduce parasitic capacitance and inductance, causing signal reflection and crosstalk, affecting signal integrity.

[0003] The back drilling process is a technology used to optimize signal integrity in the manufacture of multi-layer PCBs (printed circuit boards). The core principle is to remove the unused part of the through hole (i.e., the stub) from the back of the PCB by precisely controlling the drilling depth to reduce the parasitic effects of the through hole, reduce reflections, crosstalk and delays in signal transmission, and significantly reduce discontinuities in signal transmission. The remaining part after removing the stub is usually called a Stub.

[0004] The purpose of retaining the Stub is to realize the electrical connection of the first several layers on the front side of the circuit board, usually to realize the electrical connection between the layers on the surface of the circuit board and the signal layers inside the circuit board.

[0005] The back drilling depth needs to be strictly controlled. If the remaining stub length does not meet the requirements, the performance of the circuit board will be seriously affected.

[0006] Since the through-holes are relatively small and the thickness of the circuit board is not large, optical inspection requires not only expensive cameras but also low precision. Current optical inspection or manual inspection is to determine whether the remaining stub is connected to the signal layer and disconnected from the power layer / ground layer, but cannot make a more detailed inspection of its specific location.

[0007] Another method of stub detection is to destroy the finished product, that is, to cut the first product produced by the equipment to detect whether the remaining stub in the back-drilled hole meets the requirements. If it does not meet the requirements, the equipment needs to be debugged until the first product is qualified before subsequent production can be carried out. This method not only causes damage to the test product, but also seriously affects efficiency. In addition, it cannot eliminate the risk of the product failing again due to errors caused by long-term operation of the equipment.

[0008] The disclosure of the above background technology content is only used to assist in understanding the concept and technical solution of the present application. It does not necessarily belong to the prior art of the present application, nor does it necessarily provide technical guidance. In the absence of clear evidence that the above content has been disclosed before the filing date of the present application, the above background technology should not be used to evaluate the novelty and creativity of the present application. Summary of the invention

[0009] The object of the present invention is to provide a method for accurately detecting the positional relationship between a stub and a signal layer in a back-drilled hole by using a tomography technique.

[0010] To achieve the above object, the technical solution adopted by the present invention is as follows: A method for detecting stubs in back-drilled holes of a circuit board is provided, wherein the remaining stubs in the holes after back-drilling are detected. The detection method comprises the following steps: Acquire a cross-sectional image set generated by scanning the circuit board to be inspected using electronic computer tomography technology, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Using a pre-built first AI model, sequentially analyzing the cross-sectional images in the image set, determining the location of the end of the remaining Stub, which is recorded as a first location; Using the pre-built second AI model, determine the position of a layer electrically connected to the remaining Stub and closest to the end of the remaining Stub, and record it as a second position; The distance between the first position and the second position is calculated to determine whether the back-drilled hole Stub is qualified.

[0011] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the circuit board back drilling stub detection method provided by the embodiment of the present invention also includes: Inputting the cross-sectional images of the cross-sectional image set into the first AI model in sequence; The first AI model determines a cross-sectional image corresponding to the first position; The first AI model is trained in the following way: Obtaining a sample image: scanning the sample circuit board using a computer tomography technique and generating a cross-sectional image set, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Manual labeling: labeling the cross-sectional images that reflect the end features of the remaining stub with the first type of labels; Repeatedly obtain sample images and manually label them to form a learning sample set; Divide the learning sample set into a training set and a validation set; Input the learning samples of the training set into the basic model for iterative training; The model after iterative training is verified using the learning samples of the verification set. If the verification fails, the iterative training continues; if the verification passes, the first AI model is obtained.

[0012] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the first AI model estimates the probability of each input cross-sectional image having the end features of the remaining Stub; The first AI model determines the cross-sectional image corresponding to the first position in the following manner: If the probability value of the first image being estimated to have the end feature of the remaining stub is less than a preset first probability threshold, and the probability value of the second image adjacent to the first image being estimated to have the end feature of the remaining stub reaches the first probability threshold, the cross-sectional image corresponding to the first position is determined based on the first image or the second image.

[0013] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the first AI model determines the cross-sectional image corresponding to the first position in any of the following ways: Method 1 is to select an image as the cross-sectional image corresponding to the first position from a plurality of continuous cross-sectional images with the second image as the first image and excluding the first image; The second method is to select an image as the cross-sectional image corresponding to the first position from a plurality of continuous cross-sectional images, with the first image being the first image and excluding the second image; Method three is to preset a second probability threshold value, which is greater than or equal to the first probability threshold value; the first AI model determines a third image that satisfies the following conditions: the probability value of the third image having the end feature of the remaining stub is estimated to reach the second probability threshold value; among a plurality of continuous cross-sectional images with the third image as the first one, select an image as the cross-sectional image corresponding to the first position; Method 4 is to calculate the difference between two adjacent cross-sectional images in a first group of continuous cross-sectional images with the second image as the first image and excluding the first image, and if the difference is greater than a preset difference threshold, calculate the difference between two adjacent cross-sectional images in the next group; repeat the above steps until the difference between the kth and k+1th cross-sectional images after the second image is found to be less than or equal to the preset difference threshold, where k is a positive integer; and use the [k / 2]th cross-sectional image after the second image as the cross-sectional image corresponding to the first position, wherein [ ] is an operation symbol for rounding, rounding up, or rounding down.

[0014] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the setting value of the first probability threshold is determined by the following method: Inputting the test image set into the first AI model that has completed training, and obtaining a probability value for each cross-sectional image in the test image set to be estimated to have an end feature of the remaining Stub; Manually determine the target cross-sectional image corresponding to the position of the end of the remaining Stub in the test image set; Determining the probability values ​​of the adjacent images on both sides of the target cross-sectional image being estimated; A reference value of the first probability threshold is determined within an interval range of probability values ​​estimated for the adjacent images on both sides.

[0015] Further, according to any one of the above-mentioned technical solutions or a combination of multiple technical solutions, multiple test image sets are used to obtain corresponding reference values ​​of multiple first probability thresholds; After denoising the reference values ​​of the multiple first probability thresholds, an average value is calculated to serve as the first probability threshold.

[0016] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the circuit board back drilling stub detection method provided by the embodiment of the present invention also includes: inputting the cross-sectional images of the cross-sectional image set into the second AI model in sequence; The second AI model determines a cross-sectional image corresponding to the second position; The second AI model is trained in the following way: Obtaining a sample image: scanning the sample circuit board using a computer tomography technique and generating a cross-sectional image set, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Manual labeling: annotate the cross-sectional images that reflect the characteristics of the layers closest to the stub end and connected to it with the second type of labels; Repeatedly obtain sample images and manually label them to form a learning sample set; Divide the learning sample set into a training set and a validation set; Input the learning samples of the training set into the basic model for iterative training; The model after iterative training is verified using the learning samples of the verification set. If the verification fails, the iterative training continues; if the verification passes, the second AI model is obtained.

[0017] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the second AI model estimates the probability of each input cross-sectional image having a layer feature that is closest to and connected to the Stub end, and the layer feature includes a line morphology feature connected to the Stub; The second AI model determines the cross-sectional image corresponding to the second position in the following manner: For a set of cross-sectional images whose cross-sectional sorting direction is from the back side to the front side of the circuit board, sequential identification is performed, if the probability value of the fourth image having the layer feature estimated for the first time is less than a preset third probability threshold, and the probability value of the fifth image adjacent to the fourth image estimated to have the layer feature reaches the preset third probability threshold, then the cross-sectional image corresponding to the second position is determined according to the fourth image or the fifth image; A set of cross-sectional images with a cross-sectional sorting direction from the front side to the back side of the circuit board are identified in sequence. If the probability value of the fourth image estimated for the last time to have the layer feature is less than a preset third probability threshold, and the probability value of the fifth image adjacent to it estimated to have the layer feature reaches the third probability threshold, the cross-sectional image corresponding to the second position is determined based on the fourth image or the fifth image.

[0018] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the second AI model determines the cross-sectional image corresponding to the second position in any of the following ways: The first method is to select an image from a plurality of continuous cross-sectional images, the fifth image being the first image and excluding the fourth image, as the cross-sectional image corresponding to the second position; The second method is to preset a fourth probability threshold value, which is greater than the third probability threshold value; the second AI model determines a sixth image that satisfies the following conditions: the probability value of the sixth image having the layer feature is estimated to reach the fourth probability threshold value; and from a plurality of continuous cross-sectional images with the sixth image as the first image, select an image as the cross-sectional image corresponding to the second position; Method three is to determine, among a plurality of continuous cross-sectional images with the fifth image as the first one and excluding the fourth image, a seventh image and an eighth image that meet the following conditions and are adjacent: when the second AI model estimates for the first time that the probability value of the eighth image having the layer feature is less than the third probability threshold and the probability value of the seventh image having the layer feature reaches the third probability threshold, then determine the center image between the fifth image and the seventh image as the cross-sectional image corresponding to the second position; Method 4 is to calculate the difference in probability values ​​of two adjacent cross-sectional images of the first group being estimated to have the layer feature among a plurality of continuous cross-sectional images with the fifth image as the first image and excluding the fourth image, and if the difference is less than a preset difference threshold, calculate the difference in probability values ​​of two adjacent cross-sectional images of the next group being estimated to have the layer feature; repeat the above steps until the corresponding probability value difference between the p-th and p+1-th cross-sectional images after the fifth image is found to be greater than or equal to the difference threshold, where p is a positive integer; and use the [p / 2]-th cross-sectional image after the fifth image as the cross-sectional image corresponding to the second position, wherein [ ] is an operation symbol for rounding, rounding up, or rounding down; Method five is to determine, among a plurality of continuous cross-sectional images with the fifth image as the first one and excluding the fourth image, a ninth image that satisfies the following conditions for the first time: the probability value of the ninth image being estimated to have the layer feature is greater than both the corresponding probability values ​​of the previous image and the next image; and to use the ninth image as the cross-sectional image corresponding to the second position.

[0019] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the setting value of the third probability threshold is determined by the following method: Inputting the test image set into the trained second AI model to obtain a probability value of each cross-sectional image in the test image set being estimated to have the layer feature; Manually determine a target cross-sectional image corresponding to a location of a layer electrically connected to the remaining Stub in the test image set; Determining the probability values ​​of the adjacent images on both sides of the target cross-sectional image being estimated; A reference value of the third probability threshold is determined within an interval range of the probability values ​​estimated for the adjacent images on both sides.

[0020] Further, according to any one of the above-mentioned technical solutions or a combination of multiple technical solutions, multiple test image sets are used to obtain corresponding reference values ​​of multiple third probability thresholds; After denoising the reference values ​​of the plurality of third probability thresholds, an average value is calculated to serve as the third probability threshold.

[0021] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, the distance between the first position and the second position is calculated by the following method: Determine the arrangement sequence numbers of the cross-sectional image corresponding to the first position and the cross-sectional image corresponding to the second position in the cross-sectional image set respectively; Calculate the difference between the first position and the second position; Determine a scanning step distance according to the working parameters of the electronic computer tomography, wherein the scanning step distance is the distance between two consecutive scans of the same object; The distance between the first position and the second position is determined by calculating the product of the scanning step distance and the sequence number difference.

[0022] Further, based on any one of the above-mentioned technical solutions or a combination of multiple technical solutions, whether the back-drilled stub is qualified is determined by the following method: Set the stub qualified length range [L min ,L max ], where L min L is the lower limit of the stub qualified length range. max The upper limit of the qualified length range of the stub. Define the distance between the first position and the second position as l 0, if L min ≤ l 0≤L max , the back-drilled stub is determined to be qualified, otherwise the back-drilled stub is determined to be unqualified.

[0023] According to another aspect of the present invention, there is provided a circuit board back-drilling STUB detection system, comprising an electronic computer tomography device and a processor, wherein the electronic computer tomography device is configured to scan a circuit board to be detected and generate a cross-sectional image set; The processor is configured to execute the steps of the detection method described above.

[0024] Further, based on any one of the technical solutions or a combination of multiple technical solutions mentioned above, the electronic computer tomography device includes one or more light pipes and flat panel detectors corresponding to the light pipes one by one.

[0025] The beneficial effects brought by the technical solution provided by the present invention are as follows: a. Using tomography technology instead of optical imaging, it is possible to obtain a set of cross-sectional images and accurately detect the positional relationship between the stub and the signal layer in the back-drilled hole; b. Accurately locate the cross-sectional image where the stub end and the signal layer are located in the cross-sectional image set obtained by tomography, and convert it into the actual height difference between the stub end and the signal layer as the basis for detection; c. Ability to conduct inspections during the circuit board production process, reduce the defective rate of finished circuit boards, and reduce the difficulty of maintenance; d. Based on the intelligent algorithm, it can accurately identify the center position of the inclined surface at the end of the stub as the first position, and accurately identify the center position of the signal layer as the second position, especially in the stub detection of precision circuit boards, giving full play to the advantages of high precision measurement accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 A flow chart of a circuit board back drilling STUB detection method provided for an exemplary embodiment of the present invention; Figure 2 A schematic diagram of a scanning process of an electronic computer tomography device of a circuit board back-drilling STUB detection system provided by an exemplary embodiment of the present invention; Figure 3 A partial cross-sectional schematic diagram of a circuit board after secondary back drilling is provided for an exemplary embodiment of the present invention; Figure 4 A conventional back drilling process flow chart is provided for an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0030] The implementation process of the back drilling process is as follows: Figure 4 As shown: Step 1: Initial through-hole processing: First, complete the through-hole processing that runs through the entire thickness of the PCB.

[0031] Step 2: Metallize (copper coat) the through holes.

[0032] Step 3: Secondary back drilling: Use a larger diameter drill bit (usually 0.15~0.2mm larger than the original through-hole diameter) to drill from the back side of the PCB to remove the copper barrel stub to a specified depth.

[0033] Step 4: Remove burrs from the drilled holes and optionally fill them with resin to improve mechanical stability.

[0034] Step 5: Grind the board to remove excess material (overflowing resin) from the upper and lower surfaces of the circuit board.

[0035] Among them, the drilling depth of the secondary back drilling in step 3 needs to be strictly controlled. If the copper tube stub is removed too little, it will cause serious reflection, crosstalk and delay in signal transmission; if the copper tube stub is removed too much, it will also cause the connection stability of the two layers closest to the front of the circuit board. Multi-layer circuit boards are precision devices, and the layers are relatively compact, which increases the difficulty of verifying that the back drilling depth is consistent with the design requirements.

[0036] The cross section of the back-drilled hole of the circuit board obtained after step 3 is as follows Figure 3 As shown, after removing the copper tube stub of the specified depth, the remaining Stub 300 is left. Figure 3 As can be seen in the figure, the end of Stub300 in the hole is inclined due to the influence of the larger diameter drill bit used in the secondary back drilling.

[0037] The present invention aims to use tomography technology to accurately detect the positional relationship between the Stub 300 and the signal layer 400 in the back-drilled hole. In one embodiment of the present invention, a circuit board back-drilled hole Stub detection method is provided to detect the remaining Stub in the hole after back drilling, such as Figure 1 As shown, the detection method comprises the following steps: S1: obtaining a cross-sectional image set generated by scanning a circuit board to be inspected using electronic computer tomography technology, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; The computer tomography (CT) device includes a light tube and a flat panel detector corresponding to the light tube. Figure 2 , the number of light pipes and flat panel detectors are four and they correspond one to one. According to the dotted arrows, the first light pipe 110, the second light pipe 120, the third light pipe 130, and the fourth light pipe 140 distributed on a circle work in sequence, that is, they illuminate the same circuit board to be inspected in sequence. Correspondingly, the first flat panel detector 210, the second flat panel detector 220, the third flat panel detector 230, and the fourth flat panel detector 240 cooperate with the corresponding light pipes in sequence to achieve imaging. Another method is to set only one light pipe and one flat panel detector, and then move them to multiple positions in sequence to illuminate and image the circuit board to be inspected at different angles. Regardless of the method, the illumination distance of the light pipes at different positions is roughly equal, and the illumination angle is roughly the same as the angle between the plane where the circuit board is located.

[0038] CT imaging obtains an image set. In this embodiment, it is assumed that the back of the circuit board to be inspected faces the scanning device, so the cross-sectional image set is Figure 3 As an example, a collection of cross sections is sorted from bottom to top. The following is an example for explanation. It should be understood that without paying any creative labor, Figure 3 The set of cross sections ordered from top to bottom in the figure can also be used as a cross-sectional image set to implement the technical solution of the present invention, and the corresponding technical solution distinguished by this also falls within the scope of protection claimed by the present invention.

[0039] S2: Using the pre-built first AI model, sequentially analyze the cross-sectional images in the image set to determine the location of the end of the remaining Stub, which is recorded as the first location; taking a round drill bit as an example, the Stub feature is a circular ring in the cross section. Figure 3 For example, in the cross-sectional image set from bottom to top, there is no Stub feature in the previous cross-sectional image. Affected by the larger diameter drill bit used in the secondary back drilling, the end of Stub300 in the hole is inclined until it reaches the end position, and the Stub feature appears.

[0040] Specifically, the first position is located by using a pre-built first AI model: the cross-sectional images of the cross-sectional image set are sequentially input into the first AI model, and the first AI model estimates the probability of each input cross-sectional image having the end feature of the remaining stub; the first AI model determines the cross-sectional image corresponding to the first position by the following method: If the probability value of the first image being estimated to have the end feature of the remaining stub is less than a preset first probability threshold, and the probability value of the second image adjacent to the first image being estimated to have the end feature of the remaining stub reaches the first probability threshold, the cross-sectional image corresponding to the first position is determined based on the first image or the second image.

[0041] It can be determined that, according to the different settings of the first probability threshold, the first image and the second image can represent Figure 3 The boundary between the lower end of Stub 300 and the non-Stub area (i.e., the lowest height position of the lower end inclined surface) can also be characterized. Figure 3 The interface at any point on the lower inclined surface of Stub300 identified in Figure 3 The interface at the highest height position of the lower end inclined surface of Stub 300 is marked.

[0042] In different embodiments, the position corresponding to the first image recognized to have the Stub feature (ie, the second image) may be used as the first position, or Figure 3 As shown, a position slightly above the second image is used as the first position 310 .

[0043] Specifically, the first AI model is trained in the following ways: Obtaining a sample image: scanning the sample circuit board using a computer tomography technique and generating a cross-sectional image set, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Manual labeling: labeling the cross-sectional images that reflect the end features of the remaining stub with the first type of labels; Repeatedly obtain sample images and manually label them to form a learning sample set; Divide the learning sample set into a training set and a validation set; Input the learning samples of the training set into the basic model for iterative training. The training process is that the first AI model analyzes the end features of the remaining Stub for each cross-sectional image in each sample, and estimates the probability that each cross-sectional image is the cross-sectional image corresponding to the first position. The expected goal of the training is to estimate that the cross-sectional image with the highest probability is the cross-sectional image in this sample marked with the first type of label. If the requirements for model accuracy are lowered, the expected goal of the training can also be lowered to estimate that the cross-sectional image with the highest probability and the cross-sectional image marked with the first type of label are within a preset adjacent range, for example, the interval between the two in the cross-sectional image set of the sample does not exceed 3 image sets; The model after iterative training is verified using the learning samples of the verification set. If the verification fails, the iterative training continues; if the verification passes, the first AI model is obtained.

[0044] In a specific embodiment, the manual annotation of the first type of label can be carried out in the following manner: display each cross-sectional image in the sample in the form of an image, and observe with the naked eye the cross-sectional image with the weakest feature from none to something of the end feature of the remaining stub, assuming that the image sequence number of the corresponding image set is 100; as the end feature of the remaining stub becomes clearer and clearer, until a cross-sectional image with a stable clarity of the end feature of the remaining stub is observed, assuming that the image sequence number of the corresponding image set is 190; when the image sequence numbers of the image set are consecutive integers, the first type of label is annotated on the cross-sectional image with the image sequence number of 145.

[0045] The setting of the first probability threshold may affect the accuracy of the estimation result of the first AI model. In one embodiment, the setting value of the first probability threshold is determined by: Inputting the test image set into the first AI model that has completed training, and obtaining a probability value for each cross-sectional image in the test image set to be estimated to have an end feature of the remaining Stub; Manually determine the target cross-sectional image corresponding to the position of the end of the remaining Stub in the test image set; Determining the probability values ​​of the adjacent images on both sides of the target cross-sectional image being estimated; A reference value of the first probability threshold is determined within an interval range of probability values ​​estimated for the adjacent images on both sides.

[0046] In a further embodiment, multiple test image sets can be input into the first AI model in batches to obtain corresponding reference values ​​of multiple first probability thresholds; after denoising the reference values ​​of the multiple first probability thresholds, the average value is calculated as the first probability threshold.

[0047] S3: using the pre-built second AI model, determine the position of a layer electrically connected to the remaining Stub and closest to the end of the remaining Stub, recorded as a second position; For example, the subsequent cross-sectional images are compared in the direction from the first image to the second image to find the adjacent fourth image and fifth image that meet the following conditions: the layer feature is not recognized in the fourth image, the layer feature is recognized in the fifth image, and the layer feature includes the line morphology feature connected to the stub; The layer feature is shown in the cross-sectional image as a metal strip intersecting with a circular ring representing the stub feature, and the second position 320 to be found is Figure 3 The height position of the first layer connected to the Stub from bottom to top.

[0048] Specifically, the second position is located by a pre-built second AI model: the second AI model estimates the probability of each input cross-sectional image having a layer feature that is closest to and connected to the Stub end, wherein the layer feature includes a line morphology feature connected to the Stub; the second AI model determines the cross-sectional image corresponding to the second position by the following method: For a set of cross-sectional images whose cross-sectional sorting direction is from the back side to the front side of the circuit board, sequential identification is performed, if the probability value of the fourth image having the layer feature estimated for the first time is less than a preset third probability threshold, and the probability value of the fifth image adjacent to the fourth image estimated to have the layer feature reaches the preset third probability threshold, then the cross-sectional image corresponding to the second position is determined according to the fourth image or the fifth image; A set of cross-sectional images with a cross-sectional sorting direction from the front side to the back side of the circuit board are identified in sequence. If the probability value of the fourth image estimated for the last time to have the layer feature is less than a preset third probability threshold, and the probability value of the fifth image adjacent to it estimated to have the layer feature reaches the third probability threshold, the cross-sectional image corresponding to the second position is determined based on the fourth image or the fifth image.

[0049] It can be determined that the fourth image and the fifth image are Figure 3 The boundary between the lower surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0050] In different embodiments, the position corresponding to the first image (ie, the fifth image) recognized to have the layer feature may be used as the second position, or Figure 3 As shown, a position slightly above the fifth image is used as the second position 320 .

[0051] The second AI model is trained in the following way: Obtaining a sample image: scanning the sample circuit board using a computer tomography technique and generating a cross-sectional image set, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Manual labeling: annotate the cross-sectional images that reflect the characteristics of the layers closest to the stub end and connected to it with the second type of labels; Repeatedly obtain sample images and manually label them to form a learning sample set; Divide the learning sample set into a training set and a validation set; Input the learning samples of the training set into the basic model for iterative training. The training process is that the second AI model analyzes the layer features that are electrically connected to the remaining Stub and closest to the end of the remaining Stub for each cross-sectional image in each sample, and estimates the probability that each cross-sectional image is a cross-sectional image corresponding to the second position. The expected goal of the training is to estimate that the cross-sectional image with the highest probability is the cross-sectional image in this sample marked with the second type of label. If the requirements for model accuracy are lowered, the expected goal of the training can also be lowered to estimate that the cross-sectional image with the highest probability and the cross-sectional image marked with the second type of label are within a preset adjacent range, for example, the interval between the two in the cross-sectional image set of the sample does not exceed 3 image sets; The model after iterative training is verified using the learning samples of the verification set. If the verification fails, the iterative training continues; if the verification passes, the second AI model is obtained.

[0052] In a specific embodiment, the manual annotation of the second type of label can be carried out in the following manner: display each cross-sectional image in the sample in the form of an image, observe with the naked eye a cross-sectional image in which the layer feature electrically connected to the remaining Stub and closest to the end of the remaining Stub has the weakest feature from nothing to something, and assume that the image sequence number of the corresponding image set is 1000; as the layer feature becomes clearer and clearer, until a cross-sectional image in which the layer feature reaches a stable clarity is observed, and assume that the image sequence number of the corresponding image set is 1150; when the image sequence numbers of the image set are consecutive integers, the second type of label is annotated on the cross-sectional image with the image sequence number of 1075.

[0053] The setting of the third probability threshold may affect the accuracy of the estimation result of the second AI model. In one embodiment, the setting value of the third probability threshold is determined by: Inputting the test image set into the trained second AI model to obtain a probability value of each cross-sectional image in the test image set being estimated to have the layer feature; Manually determine a target cross-sectional image corresponding to a location of a layer electrically connected to the remaining Stub in the test image set; Determining the probability values ​​of the adjacent images on both sides of the target cross-sectional image being estimated; A reference value of the third probability threshold is determined within an interval range of the probability values ​​estimated for the adjacent images on both sides.

[0054] In a further embodiment, multiple test image sets can be input into the second AI model in batches to obtain corresponding reference values ​​of multiple third probability thresholds; after denoising the reference values ​​of the multiple third probability thresholds, the average value is calculated as the third probability threshold.

[0055] S4: Calculate the distance between the first position and the second position to determine whether the back-drilled hole Stub is qualified.

[0056] Specifically, determine the arrangement serial numbers of the cross-sectional image corresponding to the first position and the cross-sectional image corresponding to the second position in the cross-sectional image set respectively; calculate the difference in serial numbers corresponding to the first position and the second position; determine the scanning step distance according to the working parameters of the electronic computed tomography scanning, and the scanning step distance is the distance between the cross-sections of the same object scanned twice before and after; determine the distance between the first position and the second position by calculating the product of the scanning step distance and the serial number difference.

[0057] like Figure 3 As shown, the height distance between the first position 310 and the second position 320 is l 0, set the Stub qualified length range [L min ,L max ], where L min L is the lower limit of the stub qualified length range. max The upper limit of the stub qualified length range; if L min ≤ l 0≤L max , the back-drilled stub is determined to be qualified, otherwise the back-drilled stub is determined to be unqualified.

[0058] The following is a detailed description of an embodiment of an AI model determining cross-sectional images corresponding to the first position and the second position: First embodiment: According to the probability estimation result of the first AI model, the first image and the second image are located. In this embodiment, the first probability threshold is set so that the first image and the second image represent Figure 3 The boundary between the lower end of the Stub 300 and the non-Stub area (ie, the lowest height position of the lower end inclined surface) is shown in FIG.

[0059] Among the continuous multiple cross-sectional images with the second image as the first one and excluding the first image, one image is selected as the cross-sectional image corresponding to the first position, for example, the second image is directly used as the cross-sectional image corresponding to the first position, or the fifth image is counted upward from the second image as the cross-sectional image corresponding to the first position. The specific one to be selected can be determined by referring to the Stub structure of the circuit board, such as the length of the inclined surface of the lower end of the Stub formed by the drill bit used for back drilling. The longer the length, the farther the cross-sectional image from the second image is selected.

[0060] Second embodiment: According to the probability estimation result of the first AI model, the first image and the second image are located. In this embodiment, the first probability threshold is set so that the first image and the second image represent Figure 3 The interface at the highest height position of the lower end inclined surface of Stub 300 or the interface at any position on the inclined surface.

[0061] Among the continuous multiple cross-sectional images with the first image as the first one and excluding the second image, an image is selected as the cross-sectional image corresponding to the first position, for example, the first image is directly used as the cross-sectional image corresponding to the first position, or the first image is used as the starting point to count downward, for example, the fifth image is used as the cross-sectional image corresponding to the first position. The specific image to be selected can be determined with reference to the Stub structure of the circuit board, such as the length of the inclined surface of the lower end of the Stub formed by the drill bit used for back drilling. The longer the length, the farther the cross-sectional image from the first image is selected.

[0062] Third embodiment: According to the probability estimation result of the first AI model, the first image and the second image are located. In this embodiment, the first probability threshold is set so that the first image and the second image represent Figure 3 The boundary between the lower end of the Stub 300 and the non-Stub area (ie, the lowest height position of the lower end inclined surface) is shown in FIG.

[0063] A second probability threshold is preset, which is greater than or equal to the first probability threshold, so that the first image and the second image represent Figure 3 The first AI model determines a third image that satisfies the following conditions: the probability value of the third image having the end feature of the remaining Stub is estimated to reach the second probability threshold; among multiple consecutive cross-sectional images with the third image as the first one, an image is selected as the cross-sectional image corresponding to the first position, and the third image is preferably selected as the cross-sectional image corresponding to the first position.

[0064] Fourth embodiment: According to the probability estimation result of the first AI model, the first image and the second image are located. In this embodiment, the first probability threshold is set so that the first image and the second image represent Figure 3 The boundary between the lower end of the Stub 300 and the non-Stub area (ie, the lowest height position of the lower end inclined surface) is shown in FIG.

[0065] In a plurality of continuous cross-sectional images with the second image as the first image and excluding the first image, the difference between two adjacent cross-sectional images of the first group is calculated. If the difference is greater than a preset difference threshold, the difference between two adjacent cross-sectional images of the next group is calculated. The above steps are repeated until the difference between the k-th and k+1-th cross-sectional images after the second image is found to be less than or equal to the preset difference threshold, where k is a positive integer. The [k / 2]-th cross-sectional image after the second image is used as the cross-sectional image corresponding to the first position, where [ ] is an operation symbol for rounding, rounding up, or rounding down.

[0066] See also Figure 3 , the lower end of Stub300 is in an eight-shaped shape, so the corresponding cross-sectional images of the lower end all have circular rings, and the size of the circular rings decreases from large to small in the multiple cross-sectional images from bottom to top. This embodiment uses this to locate the highest position of the inclined surface by calculating the difference between two adjacent cross-sectional images. Then the [k / 2]th cross-sectional image after the second image is used as the cross-sectional image at the center of the inclined surface, that is, Figure 3 A first position 310 is shown.

[0067] Fifth embodiment: According to the probability estimation result of the second AI model, the fourth image and the fifth image are located. In this embodiment, the third probability threshold is set so that the fourth image and the fifth image represent Figure 3 The boundary between the lower surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0068] Among the continuous multiple cross-sectional images with the fifth image as the first one and excluding the fourth image, an image is selected as the cross-sectional image corresponding to the second position. For example, the fifth image is directly used as the cross-sectional image corresponding to the second position, or the fifth image is used as the cross-sectional image corresponding to the second position by counting upward from the fifth image. The specific image to be selected can be determined by referring to the layer structure of the circuit board. For example, the thicker the signal layer, the farther the cross-sectional image from the fifth image is selected.

[0069] Sixth embodiment: According to the probability estimation result of the second AI model, the fourth image and the fifth image are located. In this embodiment, the third probability threshold is set so that the fourth image and the fifth image represent Figure 3 The boundary between the lower surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0070] The signal layer 400 has a certain thickness. From the lower surface of the signal layer upward, the image of the layer gradually becomes clear from blurred. Accordingly, a fourth probability threshold is preset, which is greater than the third probability threshold; the second AI model determines a sixth image that satisfies the following conditions: the probability value of the sixth image having the layer characteristics is estimated to reach the fourth probability threshold; among multiple consecutive cross-sectional images with the sixth image as the first one, an image is selected as the cross-sectional image corresponding to the second position. Specifically, the sixth image can be directly used as the cross-sectional image corresponding to the second position.

[0071] Seventh embodiment: According to the probability estimation result of the second AI model, the fourth image and the fifth image are located. In this embodiment, the third probability threshold is set so that the fourth image and the fifth image represent Figure 3 The boundary between the lower surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0072] The signal layer 400 has a certain thickness. Among the continuous multiple cross-sectional images with the fifth image as the first image and excluding the fourth image, the seventh image and the eighth image that meet the following conditions and are adjacent are determined to represent Figure 3 The boundary between the upper surface of the signal layer 400 and the non-signal layer is as follows: When the second AI model estimates for the first time that the probability value of the eighth image having the layer feature is less than the third probability threshold and the probability value of the seventh image having the layer feature reaches the third probability threshold, the center image between the fifth image and the seventh image is determined as the cross-sectional image corresponding to the second position.

[0073] Eighth embodiment: According to the probability estimation result of the second AI model, the fourth image and the fifth image are located. In this embodiment, the third probability threshold is set so that the fourth image and the fifth image represent Figure 3 The boundary between the lower surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0074] The signal layer 400 has a certain thickness. The idea of ​​this embodiment is to determine the characteristic of the signal layer 400 in a plurality of continuous cross-sectional images with the fifth image as the first image and excluding the fourth image. Figure 3 A cross-sectional image of the boundary between the upper surface of the signal layer 400 and the non-signal layer as indicated in FIG. 4 : Calculate the difference in probability values ​​of two adjacent cross-sectional images of the first group being estimated to have the layer feature; if the difference is less than a preset difference threshold, calculate the difference in probability values ​​of two adjacent cross-sectional images of the next group being estimated to have the layer feature; repeat the above steps until the corresponding probability value difference between the p-th and p+1-th cross-sectional images after the fifth image is found to be greater than or equal to the difference threshold, where p is a positive integer; and use the [p / 2]th cross-sectional image after the fifth image as the centered image of the upper and lower surfaces of the signal layer 400, as the cross-sectional image corresponding to the second position, wherein [ ] is an operation symbol for rounding, rounding up, or rounding down.

[0075] Ninth embodiment: According to the probability estimation result of the second AI model, the fourth image and the fifth image are located. In this embodiment, the third probability threshold is set so that the fourth image and the fifth image represent Figure 3 The boundary between the lower surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0076] The signal layer 400 has a certain thickness. The image of the layer is a process from blurry to clear and then blurry again. The idea of ​​this embodiment is to locate this clear high point: Among a plurality of continuous cross-sectional images with the fifth image as the first one and excluding the fourth image, a ninth image that first satisfies the following conditions is determined: the probability value of the ninth image estimated to have the layer feature is greater than both the corresponding probability values ​​of the previous image and the next image; and the ninth image is used as the cross-sectional image corresponding to the second position.

[0077] Other embodiments: Any one of the first to fourth embodiments may be combined with any one of the fifth to ninth embodiments.

[0078] Compared with the first embodiment in which the second image is used as the cross-sectional image corresponding to the first position and the second embodiment in which the first image is used as the cross-sectional image corresponding to the first position, the third embodiment in which the centered third image is determined as the cross-sectional image corresponding to the first position and the fourth embodiment in which the feature of the tapered circular ring on the cross-section is used to more accurately determine the center position of the inclined surface at the end of Stub300 as the first position; on the other hand, compared with the fifth embodiment in which the fifth image is used as the cross-sectional image corresponding to the second position, the seventh embodiment, the eighth embodiment and the ninth embodiment can more accurately determine the center position of the signal layer 400 as the second position.

[0079] The above embodiment of more accurately determining the center position of the inclined surface at the end of Stub 300 as the first position and more accurately determining the center position of the signal layer 400 as the second position can better meet the detection requirements of high-precision circuit boards: the overall thickness of precision circuit boards is relatively thin. With the development of technology, the spacing between layers is at the micron level. Precision technology can achieve a layer spacing of about 100 microns, while the thickness of the circuit board layer itself is usually 20 to 35 microns, and the thickness of the inclined surface at the end of the Stub caused by the drilling process is usually 10 to 20 microns. The preferred embodiment of the present invention takes the thickness of the layer itself and the inclined height of the Stub end into considerations that affect the detection accuracy, optimizes the algorithm in detail, and performs Stub detection based on identifying the center position of the inclined surface at the end of the Stub and the center position of the signal layer. This is particularly important for improving the Stub detection accuracy of precision circuit boards.

[0080] Without creative work, the technical solution of the new embodiment obtained by adjusting the first embodiment to the ninth embodiment also falls within the scope of protection claimed by the present invention. For example, the solution for determining the fourth image and the fifth image is adjusted to: For a set of cross-sectional images whose cross-sectional sorting direction is from the back side to the front side of the circuit board, sequential identification is performed. If the probability value of the fourth image having the layer feature estimated for the second time is less than the preset third probability threshold, and the probability value of the fifth image adjacent to it estimated to have the layer feature reaches the preset third probability threshold, then the fourth image and the fifth image represent Figure 3 The boundary between the upper surface of the signal layer 400 and the non-signal layer as indicated in ; For a set of cross-sectional images whose cross-sectional sorting direction is from the front side to the back side of the circuit board, sequential identification is performed. If the probability value of the fourth image having the layer feature estimated for the second time is less than a preset third probability threshold, and the probability value of the fifth image adjacent to it being estimated to have the layer feature reaches the third probability threshold, then the fourth image and the fifth image represent Figure 3 The boundary between the upper surface of the signal layer 400 and the non-signal layer is shown in FIG.

[0081] In one embodiment of the present invention, a circuit board back-drilled STUB detection system is provided, comprising an electronic computer tomography device and a processor, wherein the electronic computer tomography device is configured to scan the circuit board to be inspected and generate a set of cross-sectional images; the electronic computer tomography device comprises one or more light pipes and a flat-panel detector corresponding to the light pipes.

[0082] The processor is configured with an AI model for determining the cross-sectional images corresponding to the first position and the second position, respectively. The specific training method of the AI ​​model will not be described in detail. The processor determines the arrangement sequence numbers of the cross-sectional image corresponding to the first position and the cross-sectional image corresponding to the second position in the cross-sectional image set, and determines the sequence number difference between the two; Determine a scanning step distance according to the working parameters of the electronic computer tomography, wherein the scanning step distance is the distance between two consecutive scans of the same object; The distance between the first position and the second position is determined by calculating the product of the scanning step distance and the sequence number difference, and the distance is compared with a set qualified range to determine whether the back-drilled hole Stub is qualified.

[0083] For circuit boards that pass the inspection, you can proceed to the subsequent resin filling process. For circuit boards that fail the inspection, you can choose to repair them and then re-inspect them or directly discard them to reduce the defective rate of finished products.

[0084] The circuit board back-drilled hole STUB detection system provided in this embodiment and the circuit board back-drilled hole STUB detection method provided in the above embodiment belong to the same inventive concept. The entire content of the circuit board back-drilled hole STUB detection method embodiment is incorporated into the circuit board back-drilled hole STUB detection system embodiment by reference and will not be repeated here.

[0085] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0086] The above is only a specific implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A circuit board back-drilling stub detection method, characterized in that: The remaining stub in the hole after back drilling is detected, and the detection method includes the following steps: Acquire a cross-sectional image set generated by scanning the circuit board to be inspected using electronic computer tomography technology, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Using a pre-built first AI model, sequentially analyzing the cross-sectional images in the image set, determining the location of the end of the remaining Stub, which is recorded as a first location; Using the pre-built second AI model, determine the position of a layer electrically connected to the remaining Stub and closest to the end of the remaining Stub, and record it as a second position; The distance between the first position and the second position is calculated to determine whether the back-drilled hole Stub is qualified.

2. The circuit board back drilling stub detection method according to claim 1, characterized in that: Also includes: Inputting the cross-sectional images of the cross-sectional image set into the first AI model in sequence; The first AI model determines a cross-sectional image corresponding to the first position; The first AI model is trained in the following way: Obtaining a sample image: scanning the sample circuit board using a computer tomography technique and generating a cross-sectional image set, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Manual labeling: labeling the cross-sectional images that reflect the end features of the remaining stub with the first type of labels; Repeatedly obtain sample images and manually label them to form a learning sample set; Divide the learning sample set into a training set and a validation set; Input the learning samples of the training set into the basic model for iterative training; The model after iterative training is verified using the learning samples of the verification set. If the verification fails, the iterative training continues; if the verification passes, the first AI model is obtained.

3. The circuit board back drilling stub detection method according to claim 2, characterized in that: The first AI model estimates the probability of each input cross-sectional image having the end features of the remaining Stub; The first AI model determines the cross-sectional image corresponding to the first position in the following manner: If the probability value of the first image being estimated to have the end feature of the remaining stub is less than a preset first probability threshold, and the probability value of the second image adjacent to the first image being estimated to have the end feature of the remaining stub reaches the first probability threshold, the cross-sectional image corresponding to the first position is determined based on the first image or the second image.

4. The circuit board back drilling stub detection method according to claim 3, characterized in that: The first AI model determines the cross-sectional image corresponding to the first position in any of the following ways: Method 1 is to select an image as the cross-sectional image corresponding to the first position from a plurality of continuous cross-sectional images with the second image as the first image and excluding the first image; The second method is to select an image as the cross-sectional image corresponding to the first position from a plurality of continuous cross-sectional images, with the first image being the first image and excluding the second image; Method three is to preset a second probability threshold value, which is greater than or equal to the first probability threshold value; the first AI model determines a third image that satisfies the following conditions: the probability value of the third image having the end feature of the remaining stub is estimated to reach the second probability threshold value; among a plurality of continuous cross-sectional images with the third image as the first one, select an image as the cross-sectional image corresponding to the first position; Method 4 is to calculate the difference between two adjacent cross-sectional images of a first group among a plurality of continuous cross-sectional images with the second image as the first image and excluding the first image, and if the difference is greater than a preset difference threshold, calculate the difference between two adjacent cross-sectional images of a next group; Repeat the above steps until the difference between the kth and k+1th cross-sectional images after the second image is found to be less than or equal to a preset difference threshold, where k is a positive integer; and use the [k / 2]th cross-sectional image after the second image as the cross-sectional image corresponding to the first position, wherein [ ] is an operation symbol for rounding, rounding up, or rounding down.

5. The circuit board back drilling stub detection method according to claim 3, characterized in that: The setting value of the first probability threshold is determined by: Inputting the test image set into the first AI model that has completed training, and obtaining a probability value for each cross-sectional image in the test image set to be estimated to have an end feature of the remaining Stub; Manually determine the target cross-sectional image corresponding to the position of the end of the remaining Stub in the test image set; Determining the probability values ​​of the adjacent images on both sides of the target cross-sectional image being estimated; A reference value of the first probability threshold is determined within an interval range of probability values ​​estimated for the adjacent images on both sides.

6. The circuit board back drilling stub detection method according to claim 5, characterized in that: Using a plurality of test image sets respectively, obtaining a plurality of corresponding reference values ​​of first probability thresholds; After denoising the reference values ​​of the multiple first probability thresholds, an average value is calculated to serve as the first probability threshold.

7. The circuit board back drilling stub detection method according to claim 1, characterized in that: Also includes: inputting the cross-sectional images of the cross-sectional image set into the second AI model in sequence; The second AI model determines a cross-sectional image corresponding to the second position; The second AI model is trained in the following way: Obtaining a sample image: scanning the sample circuit board using a computer tomography technique and generating a cross-sectional image set, wherein the cross-sectional image set includes a plurality of cross-sectional images arranged in order of heights of the cross-sections; Manual labeling: annotate the cross-sectional images that reflect the characteristics of the layers closest to the stub end and connected to it with the second type of labels; Repeatedly obtain sample images and manually label them to form a learning sample set; Divide the learning sample set into a training set and a validation set; Input the learning samples of the training set into the basic model for iterative training; The model after iterative training is verified using the learning samples of the verification set. If the verification fails, the iterative training continues; if the verification passes, the second AI model is obtained.

8. The circuit board back drilling stub detection method according to claim 7, characterized in that: The second AI model estimates the probability of each input cross-sectional image having a layer feature that is closest to and connected to the Stub end, wherein the layer feature includes a line morphology feature connected to the Stub; The second AI model determines the cross-sectional image corresponding to the second position in the following manner: For a set of cross-sectional images whose cross-sectional sorting direction is from the back side to the front side of the circuit board, sequential identification is performed, if the probability value of the fourth image having the layer feature estimated for the first time is less than a preset third probability threshold, and the probability value of the fifth image adjacent to the fourth image estimated to have the layer feature reaches the preset third probability threshold, then the cross-sectional image corresponding to the second position is determined according to the fourth image or the fifth image; A set of cross-sectional images with a cross-sectional sorting direction from the front side to the back side of the circuit board are identified in sequence. If the probability value of the fourth image estimated for the last time to have the layer feature is less than a preset third probability threshold, and the probability value of the fifth image adjacent to it estimated to have the layer feature reaches the third probability threshold, the cross-sectional image corresponding to the second position is determined based on the fourth image or the fifth image.

9. The circuit board back drilling stub detection method according to claim 8, characterized in that: The second AI model determines the cross-sectional image corresponding to the second position in any of the following ways: The first method is to select an image from a plurality of continuous cross-sectional images, the fifth image being the first image and excluding the fourth image, as the cross-sectional image corresponding to the second position; The second method is to preset a fourth probability threshold value, which is greater than the third probability threshold value; the second AI model determines a sixth image that satisfies the following conditions: the probability value of the sixth image having the layer feature is estimated to reach the fourth probability threshold value; and from a plurality of continuous cross-sectional images with the sixth image as the first image, select an image as the cross-sectional image corresponding to the second position; Method three is to determine, among a plurality of continuous cross-sectional images with the fifth image as the first one and excluding the fourth image, a seventh image and an eighth image that meet the following conditions and are adjacent: when the second AI model estimates for the first time that the probability value of the eighth image having the layer feature is less than the third probability threshold and the probability value of the seventh image having the layer feature reaches the third probability threshold, then determine the center image between the fifth image and the seventh image as the cross-sectional image corresponding to the second position; The fourth method is to calculate the difference of the probability values ​​of two adjacent cross-sectional images in a first group being estimated to have the layer feature among a plurality of continuous cross-sectional images with the fifth image as the first image and excluding the fourth image, and if the difference is less than a preset difference threshold, calculate the difference of the probability values ​​of two adjacent cross-sectional images in a next group being estimated to have the layer feature; Repeat the above steps until the probability difference between the p-th and p+1-th cross-sectional images after the fifth image is found to be greater than or equal to the difference threshold, where p is a positive integer; and use the [p / 2]-th cross-sectional image after the fifth image as the cross-sectional image corresponding to the second position, where [ ] is an operation symbol for rounding, rounding up, or rounding down; Method five is to determine, among a plurality of continuous cross-sectional images with the fifth image as the first one and excluding the fourth image, a ninth image that satisfies the following conditions for the first time: the probability value of the ninth image being estimated to have the layer feature is greater than both the corresponding probability values ​​of the previous image and the next image; and to use the ninth image as the cross-sectional image corresponding to the second position.

10. The circuit board back drilling stub detection method according to claim 8, characterized in that: The setting value of the third probability threshold is determined by: Inputting the test image set into the trained second AI model to obtain a probability value of each cross-sectional image in the test image set being estimated to have the layer feature; Manually determine a target cross-sectional image corresponding to a location of a layer electrically connected to the remaining Stub in the test image set; Determining the probability values ​​of the adjacent images on both sides of the target cross-sectional image being estimated; A reference value of the third probability threshold is determined within an interval range of the probability values ​​estimated for the adjacent images on both sides.

11. The circuit board back drilling stub detection method according to claim 10, characterized in that: Using a plurality of test image sets respectively, obtaining a plurality of corresponding reference values ​​of third probability thresholds; After denoising the reference values ​​of the plurality of third probability thresholds, an average value is calculated to serve as the third probability threshold.

12. The circuit board back-drilling stub detection method according to any one of claims 1 to 11, characterized in that: The distance between the first position and the second position is calculated by: Determine the arrangement sequence numbers of the cross-sectional image corresponding to the first position and the cross-sectional image corresponding to the second position in the cross-sectional image set respectively; Calculate the difference between the first position and the second position; Determine a scanning step distance according to the working parameters of the electronic computer tomography, wherein the scanning step distance is the distance between two consecutive scans of the same object; The distance between the first position and the second position is determined by calculating the product of the scanning step distance and the sequence number difference.

13. The circuit board back drilling stub detection method according to claim 12, characterized in that: Determine whether the back-drilled stub is qualified by the following methods: Set the stub qualified length range [L min ,L max ], where L min L is the lower limit of the stub qualified length range. max The upper limit of the qualified length range of the stub. Define the distance between the first position and the second position as l 0, if L min ≤ l 0≤L max , the back-drilled stub is determined to be qualified, otherwise the back-drilled stub is determined to be unqualified.

14. A circuit board back drilling STUB detection system, characterized in that: It includes a computer tomography device and a processor, wherein the computer tomography device is configured to scan a circuit board to be inspected and generate a set of cross-sectional images; The processor is configured to perform the steps of the detection method according to any one of claims 1 to 13.

15. The circuit board back drilling STUB detection system according to claim 14, characterized in that: The electronic computer tomography device includes one or more light pipes and flat panel detectors corresponding to the light pipes.

Images