A method, apparatus and system for testing the quality of adhesive backing

Abstract

This invention provides a method, apparatus, and system for detecting the quality of adhesive backing, relating to the field of adhesive backing quality detection technology. The method includes: obtaining an ultrasonic feature vector QA; obtaining a similarity list λ; traversing λ, if λ... i >ρ i If the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions, then the overall adhesive backing area to be tested, TE, is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. The areas containing adhesive backing in TE are extracted to obtain a list of sub-adhesive backing images A corresponding to TE. A is then... j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j According to H j This invention determines whether the overall quality of the adhesive backing area of ​​the component to be tested meets the preset qualification conditions. It can improve the accuracy of testing, reduce computing power consumption, and improve the efficiency of testing adhesive backing quality.

Description

Technical Field

[0001] This invention relates to the field of adhesive quality testing technology, and in particular to an adhesive quality testing method, apparatus and system. Background Technology

[0002] In the field of electronic products, adhesive backing is commonly used to fix components such as screens and batteries. The presence of problems with the adhesive backing, such as bubbles, breaks, or unevenness, directly affects the overall quality of electronic products. For example, bubbles reduce the effective contact area between the adhesive backing and the substrate, decreasing local adhesion and potentially causing components to loosen. Breakage in the adhesive backing directly disrupts the overall stress balance, especially under vibration and impact, where the break point easily becomes a stress concentration point, leading to component detachment. Currently, adhesive backing inspection is typically performed through image processing, analyzing images of the adhesive backing to determine if problems exist. However, this inspection method requires very high computing power and has low efficiency. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0004] According to a first aspect of this application, a method for detecting the quality of adhesive backing is provided, the method comprising the following steps:

[0005] S100, in response to the component to be tested reaching the preset position, acquire the ultrasonic feature vector QA corresponding to the overall adhesive backing area of ​​the component to be tested; wherein, QA is obtained through a preset phased array ultrasonic probe;

[0006] S200, obtain the similarity between QA and each preset qualified ultrasonic feature vector to obtain a similarity list λ = (λ1, λ2, ..., λ3). i , …, λ n ), i=1, 2,...,n; where, λ i Let QA be the similarity between QA and the i-th qualified ultrasonic feature vector, and n be the number of qualified ultrasonic feature vectors.

[0007] S300, iterate through λ, if λ i >ρ i If the condition is met, the overall adhesive backing area of ​​the component under test is determined to meet the preset qualification criteria; otherwise, an overall adhesive backing image TE corresponding to the overall adhesive backing area is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. i The similarity threshold corresponding to the i-th qualified ultrasonic feature vector;

[0008] S400, extract the areas containing adhesive in TE to obtain a list of sub-adhesive images to be detected, A = (A1, A2, ..., A...). j Am ), j = 1, 2, ..., m; where A j Let m be the j-th sub-adhesive image to be detected, and m be the number of sub-adhesive images to be detected.

[0009] S500, A j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j A j The corresponding sub-ultrasound feature vector is obtained through A j The ultrasonic signal is obtained by collecting the corresponding ultrasonic probe;

[0010] S600, according to H j To determine whether the quality of the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions.

[0011] According to another aspect of this application, a backing adhesive quality testing device is also provided, the device comprising:

[0012] The ultrasonic feature vector acquisition module is used to acquire the ultrasonic feature vector QA corresponding to the overall adhesive backing area of ​​the component under test in response to the component under test reaching the preset position; wherein, QA is obtained through a preset phased array ultrasonic probe.

[0013] The similarity determination module is used to obtain the similarity between QA and each preset qualified ultrasonic feature vector to obtain a similarity list λ = (λ1, λ2, ..., λ3). i , …, λ n ), i=1, 2,...,n; where, λ i Let QA be the similarity between QA and the i-th qualified ultrasonic feature vector, and n be the number of qualified ultrasonic feature vectors.

[0014] The pass / fail judgment module is used to iterate through λ, and if λ... i >ρ i If the condition is met, the overall adhesive backing area of ​​the component under test is determined to meet the preset qualification criteria; otherwise, an overall adhesive backing image TE corresponding to the overall adhesive backing area is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. i The similarity threshold corresponding to the i-th qualified ultrasonic feature vector;

[0015] The sub-adhesive image extraction module is used to extract the areas containing adhesive in the TE to obtain a list of sub-adhesive images A = (A1, A2, ..., A...). j A m ), j = 1, 2, ..., m; where A jLet m be the j-th sub-adhesive image to be detected, and m be the number of sub-adhesive images to be detected.

[0016] The feature vector concatenation module is used to concatenate A... j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j A j The corresponding sub-ultrasound feature vector is obtained through A j The ultrasonic signal is obtained by collecting the corresponding ultrasonic probe;

[0017] The quality judgment module is used to determine the quality based on H. j To determine whether the quality of the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions.

[0018] According to another aspect of this application, a backing adhesive quality inspection system is also provided, including the aforementioned backing adhesive quality inspection device.

[0019] The present invention has at least the following beneficial effects:

[0020] The adhesive quality inspection method of this invention introduces ultrasonic feature vectors for initial screening, enabling rapid determination of most qualified products during the feature matching stage, while only initiating the image analysis process for suspected defective samples. This hierarchical processing mechanism effectively reduces the frequency of image processing module calls, allowing system computing resources to focus on key problem areas, significantly reducing the overall computational load compared to traditional solutions, making it particularly suitable for high-speed inspection scenarios on production lines.

[0021] Furthermore, a multi-dimensional defect detection system has been constructed. Existing technologies are limited by two-dimensional image features, making it difficult to identify deep structural defects. This invention, through the collaborative analysis of ultrasonic feature vectors and image features, can not only capture surface morphological anomalies but also detect hidden defects such as bubbles and delamination within the adhesive layer through ultrasonic signal attenuation characteristics. In particular, when using hybrid feature vectors for local area analysis, it can simultaneously evaluate multi-dimensional quality indicators such as adhesive layer thickness uniformity and bonding interface integrity, greatly improving the defect detection rate. While improving detection accuracy, it also reduces computational power consumption and increases detection efficiency. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1A flowchart of the adhesive quality testing method provided in an embodiment of the present invention. Detailed Implementation

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] It should be noted that, based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Furthermore, this device and / or practice the method can be implemented using other structures and / or functionalities besides one or more of the aspects set forth herein.

[0026] The following will refer to Figure 1 The flowchart shown illustrates a method for testing the quality of adhesive backing, introducing one such method.

[0027] The method for testing the quality of the adhesive backing may include the following steps:

[0028] S100, in response to the component to be tested reaching a preset position, acquire the ultrasonic feature vector QA corresponding to the overall adhesive backing area of ​​the component to be tested; wherein, QA is obtained through a preset phased array ultrasonic probe.

[0029] In this embodiment, the component to be tested can be a mobile phone casing with several adhesive backings. When the component to be tested reaches a preset position, an ultrasonic signal is emitted through a preset phased array ultrasonic probe and the ultrasonic signal returned from the entire adhesive backing area is received. The received ultrasonic signal is encoded and its features are extracted to obtain QA. The phased array ultrasonic probe includes several ultrasonic probes, and the ultrasonic signal collected by each ultrasonic probe can be encoded and its features extracted to obtain a sub-ultrasonic feature vector corresponding to each ultrasonic probe. Then, each sub-ultrasonic feature vector is concatenated to obtain QA.

[0030] Phased array ultrasonic waves can emit sound waves from multiple angles, penetrate the adhesive layer, and receive reflected signals. The signal characteristics (such as amplitude, phase, and propagation time) reflect the internal structure of the adhesive (whether there are defects such as bubbles or fractures). The phased array ultrasonic probe can achieve non-contact and rapid acquisition of the physical properties of the overall adhesive, which is suitable for real-time detection in automated production lines.

[0031] S200, obtain the similarity between QA and each preset qualified ultrasonic feature vector to obtain a similarity list λ = (λ1, λ2, ..., λ3). i , …, λ n ), i=1, 2,...,n; where, λ i Let be the similarity between QA and the i-th qualified ultrasonic feature vector, and n be the number of qualified ultrasonic feature vectors.

[0032] In this embodiment, cosine similarity, Euclidean distance, etc., can be used to measure the degree of matching between the feature to be detected and the qualified feature. A benchmark is established by using historical qualified data to quickly screen out obviously qualified or unqualified components.

[0033] Furthermore, the preset qualified ultrasonic feature vector can be obtained through the following steps:

[0034] S210, cluster the historical qualified ultrasonic feature vectors corresponding to several historical qualified parts that are the same as the part to be tested, to obtain a cluster list B = (B1, B2, ..., B...). i B n );B i Let i be the i-th cluster obtained by clustering; the pose of any historically qualified component relative to the phased array ultrasonic probe during testing may be the same as or different from the pose of the component to be tested relative to the phased array ultrasonic probe during testing.

[0035] In this embodiment, when detecting the adhesive backing area of ​​each historical component within a historical time period, the historical qualified ultrasonic feature vector corresponding to the detected qualified historical component can be obtained. It can be understood that when the historical qualified components reach the preset position, their poses are not necessarily the same, and there will be a deviation in pose. When there are enough historical components, the poses of the component to be detected when it reaches the preset position can be covered. The historical qualified ultrasonic feature vectors contained in each cluster can be understood as the ultrasonic feature vectors corresponding to historical qualified components with similar poses.

[0036] S220, B i The center vector is determined as the i-th qualified ultrasonic feature vector.

[0037] In this embodiment, B i The center vector is B i The average vector of all historical qualified ultrasonic feature vectors; by clustering, the normal fluctuations of qualified products (such as detection differences under different poses) are included, avoiding the rigidity of a single fixed standard and improving detection robustness.

[0038] S300, iterate through λ, if λ i >ρ iIf the condition is met, the overall adhesive backing area of ​​the component under test is determined to meet the preset qualification criteria; otherwise, an overall adhesive backing image TE corresponding to the overall adhesive backing area is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. i Let be the similarity threshold corresponding to the i-th qualified ultrasonic feature vector.

[0039] In this embodiment, if any λ i >ρ i This indicates QA and B i If the historical qualified ultrasonic feature vectors in the data are relatively similar, then the overall adhesive backing area of ​​the component to be tested is determined to be qualified; otherwise, an overall adhesive backing image TE is generated based on the ultrasonic signal. It should be noted that the similarity between the historical qualified ultrasonic feature vectors in each cluster is different. Therefore, each cluster corresponds to a similarity threshold to improve the accuracy of the judgment.

[0040] First, qualified parts are quickly filtered out using feature vectors to reduce the computational load of subsequent image processing; for suspected unqualified parts, further detailed analysis is performed using images.

[0041] Furthermore, ρ i It can be obtained through the following steps:

[0042] S310, obtain B i Each historical qualified ultrasonic feature vector in B i The similarity between the center vectors of B is used to obtain B. i The corresponding similarity list η i =(η i，1 η i，2, , ..., η i，j , ..., η i，f(i) ), j = 1, 2, ..., f(i); where η i，j For B i The j-th historical qualified ultrasonic eigenvector in B i The similarity between the center vectors of B, f(i) is the similarity between them. i The number of qualified ultrasonic feature vectors in the history.

[0043] S320, η i The minimum similarity in is determined as ρ i .

[0044] In this embodiment, the similarity threshold represents the minimum similarity of qualified features within a cluster, ensuring that the detection standard covers all qualified cases and reducing misjudgments (i.e., "qualified features must at least reach the similarity of the worst qualified sample within the cluster").

[0045] S400, extract the areas containing adhesive in TE to obtain a list of sub-adhesive images to be detected, A = (A1, A2, ..., A...). j A m ), j = 1, 2, ..., m; where A j Let be the j-th sub-image to be detected, and m be the number of sub-images to be detected.

[0046] In this embodiment, it can be understood that TE is an image of the overall adhesive backing area of ​​the component to be inspected. The overall adhesive backing area will contain areas without adhesive backing and areas with adhesive backing. A preset image segmentation algorithm (such as threshold segmentation, edge detection) can be used to locate the adhesive backing area and obtain the sub-adhesive backing image list A corresponding to TE, which is convenient for subsequent local defect detection.

[0047] S500, A j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j A j The corresponding sub-ultrasound feature vector is obtained through A j The ultrasonic signal is obtained by the corresponding ultrasonic probe.

[0048] In this embodiment, for each sub-image, the corresponding sub-ultrasound feature vector (from a neighboring probe) and sub-image feature vector are obtained and concatenated into a hybrid feature vector; multimodal data (ultrasound physical features + image visual features) are fused to improve the comprehensiveness of defect identification.

[0049] Furthermore, step S500 may include the following steps:

[0050] S510, obtain and A j The ultrasonic signal PA is acquired by the ultrasonic probe TU, which is the horizontal distance from the center point of the center point.

[0051] In this embodiment, the phased array ultrasonic probes are arranged in a matrix above a preset position. The coverage area of ​​each ultrasonic probe is limited, and is related to A. j The ultrasonic signal acquired by the ultrasonic probe TU, which is horizontally closest to the center point of the center point, can cover A. j Since the corresponding area is relatively large, the probe TU, which is horizontally closest to the center point of the sub-image, is selected because its signal is more accurate (closer distance means less noise). The ultrasonic signal PA acquired by the TU is used to extract A. j The basis for the corresponding sub-ultrasonic feature vector.

[0052] S520, perform feature extraction on PA to obtain A. jThe corresponding sub-ultrasound feature vector PB = (PB1, PB2, ..., PB2) r , ..., PB s ), r = 1, 2, ..., s; where PB r For A j The r-th element in the corresponding sub-ultrasound feature vector, s is A j The number of elements in the corresponding sub-ultrasonic feature vector.

[0053] In this embodiment, the ultrasonic signal corresponding to each ultrasonic probe has been feature extracted in S100 and can be used directly in S520.

[0054] S530, obtain A j The corresponding sub-image feature vector PC = (PC1, PC2, ..., PC3) x , ..., PC y x = 1, 2, ..., y; where PC x For A j The x-th element in the corresponding sub-image feature vector, y is A j The number of elements in the corresponding sub-image feature vector.

[0055] In this embodiment, those skilled in the art can use existing image feature extraction methods according to actual needs to obtain A. j The corresponding sub-image feature vector PC will not be elaborated here.

[0056] S540 splices PB and PC to obtain H. j = (PB, PC).

[0057] In this embodiment, ultrasonic features (reflecting internal structure) and image features (intuitively displaying the location of defects) are combined to avoid the limitations of a single mode (such as pure ultrasonic waves may miss surface unevenness, and pure images may miss internal bubbles).

[0058] Furthermore, TU may be located at a distance from A. j The center point is too far horizontally, so the corresponding ultrasonic signal may not completely cover A. j For the corresponding adhesive-backed area, if it is still stitched together with image features with equal weight, it may lead to an incorrect final judgment result; therefore, after step S530, the method further includes the following steps:

[0059] S550, obtain TU and A j Horizontal distance L from the center point TU and A j The maximum distance L between the boundary and the center point max .

[0060] S551, according to L TU and L max Determine the weight ω1 corresponding to the sub-ultrasound feature vector and the weight ω2 corresponding to the sub-image feature vector; where ω1 = 1 / 2 - (L TU / L max )×ψ; ψ is a preset coefficient, ψ<0.5; ω1+ω2=1.

[0061] S552, based on ω1 and ω2, perform weighted concatenation of PB and PC to obtain H. j = (ω1×PB, ω2×PC).

[0062] In this embodiment, the closer the distance (L) TU The smaller the value, the higher the weight of the ultrasonic feature; conversely, the higher the weight of the image feature. The weights are dynamically adjusted according to the detection location to avoid interference from the results caused by signal distortion from long-distance probes, thus achieving adaptive optimization of feature fusion. The weighted stitching strategy dynamically adjusts the weights according to the physical distance to optimize the feature fusion effect, which is especially suitable for complex detection scenarios (such as curved adhesive surfaces and multi-probe arrays).

[0063] S600, according to H j To determine whether the quality of the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions.

[0064] H is analyzed using a pre-set model. j This allows us to determine whether there are defects in each sub-region, thereby determining the overall quality of the adhesive backing.

[0065] Furthermore, step S600 may include the following steps:

[0066] S610, Input QA into the preset initial quality defect classification model to obtain the confidence list μ = (μ1, μ2, ..., μ... a , ..., μ b ), a=1, 2,...,b; among them, μ a The confidence level of the overall adhesive-backed area for quality defects of type a, where b is the preset number of quality defect types; μ c >μ c+1 c = 1, 2, ..., b-1.

[0067] In this embodiment, the confidence ranking of the overall quality defect types is first output using an initial quality defect classification model; the initial quality defect classification model can be a machine learning or deep learning model (such as CNN, random forest), and the training data is historical defect samples.

[0068] Furthermore, quality defects include: bubble defects, fracture defects, and unevenness defects.

[0069] S620, Obtain each preset single quality defect detection model to obtain a single quality defect detection model list E = (E1, E2, ..., E... a , ..., E b ); where E a This is a pre-defined single quality defect detection model for detecting the a-th type of quality defect.

[0070] In this embodiment, each preset single quality defect detection model targets one type of quality defect, and the order of the single quality defect detection models in E is the same as the order of the confidence levels in μ.

[0071] S630, obtain the preset value N=1.

[0072] S640, H j Enter to E N H j The confidence level V of the corresponding adhesive area having the Nth type of quality defect j，N .

[0073] S650, if V j，N If the value is greater than ε, then the quality of the overall adhesive backing area of ​​the component under test does not meet the preset acceptance criteria; otherwise, H is determined to be... j If the corresponding adhesive area does not have the Nth type of quality defect, proceed to S660; ε is the preset confidence threshold.

[0074] In this embodiment, when H j During the test, first H j The input is fed into the single quality defect detection model corresponding to the most likely quality defect. If the confidence level of the corresponding type of quality defect output by the single quality defect detection model is greater than the preset confidence level threshold, it can be directly determined that there is a quality problem in the overall adhesive area without the need for subsequent detection, thereby improving detection efficiency.

[0075] S660, if N < b, then obtain N = N + 1 and proceed to S640; otherwise, exit the current processing.

[0076] S670, if H j If no quality defect of any type is found in the corresponding adhesive backing area, then the overall quality of the adhesive backing area of ​​the component under test is determined to meet the preset qualification conditions.

[0077] In this embodiment, layered detection improves efficiency (first overall coarse screening, then local fine inspection); special models are designed for different types of quality defects to improve detection accuracy (e.g., bubbles appear as low reflection in ultrasonic images, and fractures appear as signal interruption, so the model can be trained specifically).

[0078] The method of this embodiment has at least the following beneficial effects:

[0079] 1. Multimodal fusion improves detection accuracy

[0080] Combining ultrasonic features (reflecting internal structure) with image features (intuitively displaying defect locations) avoids the limitations of single-modality testing (e.g., pure ultrasonic waves may miss surface unevenness, and pure images may miss internal air bubbles); the weighted stitching strategy dynamically adjusts weights based on physical distance to optimize feature fusion, making it particularly suitable for complex detection scenarios (e.g., curved adhesive backing, multi-probe arrays).

[0081] 2. Data-driven adaptive standards

[0082] By clustering historical qualified data to generate dynamic benchmarks (qualification feature vectors and thresholds), we can adapt to normal fluctuations in the production process (such as slight equipment deviations and material batch differences) and reduce the false judgment rate. The threshold is based on the minimum similarity within the cluster to ensure that "the qualified standard is not lower than the worst qualified sample in history" and improve the rationality of the testing standard.

[0083] 3. Layered detection improves efficiency.

[0084] First, qualified parts (S200-S300) are quickly screened using the overall feature vector. Only suspected unqualified parts are subjected to complex image segmentation and sub-region detection, which greatly reduces the amount of computation and is suitable for high-speed production lines. Staged defect classification (initial model coarse classification + single defect model fine inspection) avoids the inefficiency of uniformly processing all defect types and improves the detection speed.

[0085] 4. Targeted defect detection capability

[0086] It clearly covers typical defects such as bubbles, fractures, and unevenness. It uses the penetrating power of phased array ultrasound to detect internal defects (such as bubbles) and image analysis to detect surface defects (such as unevenness), achieving full coverage of all types of defects. The probe distance weighting strategy ensures the detection accuracy of local defects (such as edge fractures) and avoids missed detections due to signal attenuation.

[0087] 5. Automation and industrial adaptability

[0088] Non-contact detection, preset location triggering, and automatic model judgment make it fully compatible with automated production lines and support real-time online detection. Its reliance on historical data (clustering, model training) enables it to self-optimize, continuously improving detection performance as production data accumulates.

[0089] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0090] Embodiments of the present invention also provide a backing adhesive quality testing device, the device comprising:

[0091] The ultrasonic feature vector acquisition module is used to acquire the ultrasonic feature vector QA corresponding to the overall adhesive backing area of ​​the component under test when the component under test reaches the preset position; wherein, QA is obtained through a preset phased array ultrasonic probe.

[0092] The similarity determination module is used to obtain the similarity between QA and each preset qualified ultrasonic feature vector to obtain a similarity list λ = (λ1, λ2, ..., λ3). i , …, λ n ), i=1, 2,...,n; where, λ i Let be the similarity between QA and the i-th qualified ultrasonic feature vector, and n be the number of qualified ultrasonic feature vectors.

[0093] The pass / fail judgment module is used to iterate through λ, and if λ... i >ρ i If the condition is met, the overall adhesive backing area of ​​the component under test is determined to meet the preset qualification criteria; otherwise, an overall adhesive backing image TE corresponding to the overall adhesive backing area is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. i Let be the similarity threshold corresponding to the i-th qualified ultrasonic feature vector.

[0094] The sub-adhesive image extraction module is used to extract the areas containing adhesive in the TE to obtain a list of sub-adhesive images A = (A1, A2, ..., A...). j A m ), j = 1, 2, ..., m; where A j Let be the j-th sub-image to be detected, and m be the number of sub-images to be detected.

[0095] The feature vector concatenation module is used to concatenate A... j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j A j The corresponding sub-ultrasound feature vector is obtained through A jThe ultrasonic signal is obtained by the corresponding ultrasonic probe.

[0096] The quality judgment module is used to determine the quality based on H. j To determine whether the quality of the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions.

[0097] Embodiments of the present invention also provide a backing adhesive quality inspection system, including the backing adhesive quality inspection device as described in the above embodiments.

[0098] Embodiments of the present invention also provide an electronic device, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0099] The electronic device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.

[0100] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and a bus connecting different system components (including memory and processor).

[0101] The memory stores program code that can be executed by the processor, causing the processor to perform the steps in the various embodiments described in this specification.

[0102] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0103] The memory may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0104] A bus can represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus structures.

[0105] The electronic device can also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be performed via input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0106] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0107] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0108] While specific embodiments of the invention have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention.

Claims

1. A method for detecting the quality of adhesive backing, characterized in that, The method comprises the following steps: S100, in response to the component to be tested reaching the preset position, acquire the ultrasonic feature vector QA corresponding to the overall adhesive backing area of ​​the component to be tested; wherein, QA is obtained through a preset phased array ultrasonic probe; S200, obtain the similarity between QA and each preset qualified ultrasonic feature vector to obtain a similarity list λ = (λ1, λ2, ..., λ3). i , …, λ n ), i=1, 2,...,n; where, λ i Let QA be the similarity between QA and the i-th qualified ultrasonic feature vector, and n be the number of qualified ultrasonic feature vectors. S300, iterate through λ, if λ i >ρ i If the condition is met, the overall adhesive backing area of ​​the component under test is determined to meet the preset qualification criteria; otherwise, an overall adhesive backing image TE corresponding to the overall adhesive backing area is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. i The similarity threshold corresponding to the i-th qualified ultrasonic feature vector; S400, extract the areas containing adhesive in TE to obtain a list of sub-adhesive images to be detected, A = (A1, A2, ..., A...). j A m ), j = 1, 2, ..., m; where A j Let m be the j-th sub-adhesive image to be detected, and m be the number of sub-adhesive images to be detected. S500, A j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j A j The corresponding sub-ultrasound feature vector is obtained through A j The ultrasonic signal is obtained by collecting the corresponding ultrasonic probe; S600, according to H j To determine whether the quality of the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions.

2. The method for detecting the quality of adhesive backing according to claim 1, characterized in that, The preset qualified ultrasonic feature vector is obtained through the following steps: S210, cluster the historical qualified ultrasonic feature vectors corresponding to several historical qualified parts that are the same as the part to be tested, to obtain a cluster list B = (B1, B2, ..., B...). i B n ); B i The i-th cluster obtained by clustering; the pose of any historical qualified component relative to the phased array ultrasonic probe during testing may be the same as or different from the pose of the component to be tested relative to the phased array ultrasonic probe during testing. S220, B i The center vector is determined as the i-th qualified ultrasonic feature vector.

3. The method for detecting the quality of adhesive backing according to claim 2, characterized in that, ρ i It is obtained through the following steps: S310, obtain B i Each historical qualified ultrasonic feature vector in B i The similarity between the center vectors of B is used to obtain B. i The corresponding similarity list η i =(η i，1 η i，2, , ..., η i，j , ..., η i，f(i) ), j = 1, 2, ..., f(i); where η i，j For B i The j-th historical qualified ultrasonic eigenvector in B i The similarity between the center vectors of B, f(i) is the similarity between them. i The number of historical qualified ultrasonic feature vectors; S320, η i The minimum similarity in is determined as ρ i .

4. The method for detecting the quality of adhesive backing according to claim 1, characterized in that, Step S500 includes the following steps: S510, obtain and A j The ultrasonic signal PA acquired by the ultrasonic probe TU, which is the closest ultrasonic probe to the center point horizontally; S520, perform feature extraction on PA to obtain A. j The corresponding sub-ultrasound feature vector PB = (PB1, PB2, ..., PB2) r , ..., PB s ), r = 1, 2, ..., s; where PB r For A j The r-th element in the corresponding sub-ultrasound feature vector, s is A j The number of elements in the corresponding sub-ultrasonic feature vector; S530, obtain A j The corresponding sub-image feature vector PC = (PC1, PC2, ..., PC3) x , ..., PC y x = 1, 2, ..., y; where PC x For A j The x-th element in the corresponding sub-image feature vector, y is A j The number of elements in the corresponding sub-image feature vector; S540 splices PB and PC to obtain H. j = (PB, PC).

5. The method for detecting the quality of adhesive backing according to claim 4, characterized in that, Following step S530, the method further includes the following steps: S550, obtain TU and A j Horizontal distance L from the center point TU and A j The maximum distance L between the boundary and the center point max ; S551, according to L TU and L max Determine the weight ω1 corresponding to the sub-ultrasound feature vector and the weight ω2 corresponding to the sub-image feature vector; where ω1 = 1 / 2 - (L TU / L max )×ψ; ψ is a preset coefficient, ψ<0.5; ω1+ω2=1; S552, based on ω1 and ω2, perform weighted concatenation of PB and PC to obtain H. j = (ω1×PB, ω2×PC).

6. The method for detecting the quality of adhesive backing according to claim 1, characterized in that, Step S600 includes the following steps: S610, Input QA into the preset initial quality defect classification model to obtain the confidence list μ = (μ1, μ2, ..., μ... a , ..., μ b ), a=1, 2,...,b; among them, μ a The confidence level of the overall adhesive-backed area for quality defects of type a, where b is the preset number of quality defect types; μ c >μ c+1 c = 1, 2, ..., b-1; S620, Obtain each preset single quality defect detection model to obtain a single quality defect detection model list E = (E1, E2, ..., E... a , ..., E b ); where E a This is a pre-defined single quality defect detection model for detecting the a-th type of quality defect; S630, obtain the preset value N=1; S640, H j Enter to E N H j The confidence level V of the corresponding adhesive area having the Nth type of quality defect j，N ; S650, if V j，N If the value is greater than ε, then the quality of the overall adhesive backing area of ​​the component under test does not meet the preset acceptance criteria; otherwise, H is determined to be... j If the corresponding adhesive area does not have the Nth type of quality defect, proceed to S660; ε is the preset confidence threshold. S660, if N < b, then obtain N = N + 1 and proceed to S640; otherwise, exit the current processing. S670, if H j If no quality defect of any type is found in the corresponding adhesive backing area, then the overall quality of the adhesive backing area of ​​the component under test is determined to meet the preset qualification conditions.

7. The method for detecting the quality of adhesive backing according to claim 6, characterized in that, The quality defects include: bubble defects, fracture defects, and unevenness defects.

8. A backing adhesive quality testing device according to any one of claims 1-7, characterized in that, The device includes: The ultrasonic feature vector acquisition module is used to acquire the ultrasonic feature vector QA corresponding to the overall adhesive backing area of ​​the component under test in response to the component under test reaching the preset position; wherein, QA is obtained through a preset phased array ultrasonic probe. The similarity determination module is used to obtain the similarity between QA and each preset qualified ultrasonic feature vector to obtain a similarity list λ = (λ1, λ2, ..., λ3). i , …, λ n ), i=1, 2,...,n; where, λ i Let QA be the similarity between QA and the i-th qualified ultrasonic feature vector, and n be the number of qualified ultrasonic feature vectors. The pass / fail judgment module is used to iterate through λ, and if λ... i >ρ i If the condition is met, the overall adhesive backing area of ​​the component under test is determined to meet the preset qualification criteria; otherwise, an overall adhesive backing image TE corresponding to the overall adhesive backing area is generated based on the ultrasonic signal acquired by the phased array ultrasonic probe. i The similarity threshold corresponding to the i-th qualified ultrasonic feature vector; The sub-adhesive image extraction module is used to extract the areas containing adhesive in the TE to obtain a list of sub-adhesive images A = (A1, A2, ..., A...). j A m ), j = 1, 2, ..., m; where A j Let m be the j-th sub-adhesive image to be detected, and m be the number of sub-adhesive images to be detected. The feature vector concatenation module is used to concatenate A... j The corresponding sub-ultrasound feature vector is concatenated with the sub-image feature vector to obtain A. j The corresponding mixed feature vector H j A j The corresponding sub-ultrasound feature vector is obtained through A j The ultrasonic signal is obtained by collecting the corresponding ultrasonic probe; The quality judgment module is used to determine the quality based on H. j To determine whether the quality of the overall adhesive backing area of ​​the component to be tested meets the preset qualification conditions.

9. A backing adhesive quality inspection system, characterized in that, Includes the adhesive quality testing device as described in claim 8.

Images