Joint coating bonding ultrasonic detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a repaired mouth bonding ultrasonic detection method and device, electronic equipment and a storage medium. The method comprises the steps that a to-be-detected ultrasonic image of a repaired mouth bonding position is acquired through an ultrasonic detector; storing the ultrasonic image to be detected in a pre-configured database; acquiring a historical ultrasonic image from the database according to a detection requirement, and performing similarity calculation on the historical ultrasonic image and the ultrasonic image to be detected to obtain a calculation result; and selecting a target historical image from the historical ultrasonic images based on the calculation result, and obtaining a detection report based on the target historical image and the to-be-detected ultrasonic image. According to the invention, a modularization thought is adopted, functions of ultrasonic image detection, database management, user interaction and the like are processed separately, the automation degree and efficiency of detection are improved, personal errors are reduced, and the accuracy of detection is improved.

Description

Technical Field

[0001] The present application relates to the field of ultrasonic detection technology, and in particular to a method and device for ultrasonic detection of patch bonding, electronic equipment, and storage medium. Background Art

[0002] In the industrial field, the structural integrity and safety of key industries such as pipelines, aerospace and automobile manufacturing are of vital importance, and the inspection of the quality of patch bonding is a key link in ensuring these elements. Traditional inspection methods such as visual inspection and manual testing that have been relied on in history are not only time-consuming and labor-intensive, but their accuracy is greatly limited by the technical level of the operator. The advancement of science and technology has promoted the development of ultrasonic testing technology, which has gradually become the mainstream of the industry with its remarkable characteristics of high sensitivity and non-destructive testing.

[0003] However, traditional ultrasonic testing systems have many limitations, including complex operating procedures, cumbersome data processing, lack of real-time analysis capabilities and unfriendly user interfaces, as well as the inability to achieve high levels of automation and intelligence. Summary of the invention

[0004] In order to solve the above problems, the embodiments of the present application provide a method and device for ultrasonic detection of patch bonding, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] In the first aspect, in order to solve the above technical problems, the present application provides a method for ultrasonic detection of patch bonding, comprising:

[0006] Acquire the ultrasonic image to be tested at the patch bonding site by using an ultrasonic detector;

[0007] storing the ultrasonic image to be measured in a pre-configured database;

[0008] Acquire a historical ultrasonic image from the database according to the detection requirements, and perform similarity calculation on the historical ultrasonic image and the ultrasonic image to be detected to obtain a calculation result;

[0009] A target historical image is selected from the historical ultrasonic images based on the calculation result, and a detection report is obtained based on the target historical image and the ultrasonic image to be detected.

[0010] The beneficial effects are:

[0011] In the technical solution provided in the embodiments of the present application, an ultrasonic image to be tested at the patch bonding point is obtained by an ultrasonic detector, and the ultrasonic image to be tested is stored in a pre-configured database; then, historical ultrasonic images are obtained from the database according to the detection requirements, and the similarity between the historical ultrasonic images and the ultrasonic images to be tested is calculated to obtain the calculation results; based on the calculation results, the target historical images are selected from the historical ultrasonic images, and a detection report is obtained based on the target historical images and the ultrasonic images to be tested. In this way, the similarities and differences between the ultrasonic image to be tested and the historical ultrasonic images can be compared and analyzed, and targeted processing opinions can also be reflected in the detection report, which provides a judgment basis for the current detection of the ultrasonic image to be tested and improves the accuracy of ultrasonic detection. In addition, the solution provided by the application adopts a modular approach, which separates functions such as ultrasonic image detection, database management, and user interaction, improves the automation and efficiency of detection, reduces human errors, and improves the accuracy of detection.

[0012] In a second aspect, the present invention provides a patch bonding ultrasonic detection device, including an image acquisition module, a database module and an interaction module;

[0013] An image acquisition module is used to acquire an ultrasonic image to be tested at the patch bonding point through an ultrasonic detector;

[0014] A database module, used for storing the ultrasonic image to be measured in a pre-configured database;

[0015] An interactive module, used for acquiring historical ultrasonic images from the database according to detection requirements, performing similarity calculation on the historical ultrasonic images and the ultrasonic image to be detected, and obtaining a calculation result;

[0016] The interaction module is further used to select a target historical image from the historical ultrasonic images based on the calculation result, and obtain a detection report based on the target historical image and the ultrasonic image to be detected.

[0017] In a third aspect, the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the ultrasonic detection method for patch bonding as described above.

[0018] In a fourth aspect, the present application further provides a computer-readable storage medium having computer-readable instructions stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer executes the patch bonding ultrasonic detection method as described above.

[0019] In a fifth aspect, the present application further provides a computer program product or a computer program, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the patch bonding ultrasonic detection method provided in the above-mentioned various optional embodiments.

[0020] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0022] Figure 1 is a flow chart of a patch bonding ultrasonic detection method shown in an exemplary embodiment of the present application;

[0023] Figure 2 is a schematic diagram of a process for obtaining an ultrasonic image to be measured in an exemplary embodiment of the present application;

[0024] Figure 3 is a schematic diagram of a flow chart of adjusting detection parameters of an ultrasonic detector based on an adjustment method matching a signal state in an exemplary embodiment of the present application;

[0025] Figure 4 is a block diagram of a patch bonding ultrasonic detection device shown in an exemplary embodiment of the present application;

[0026] Figure 5 is a schematic diagram of a patch bonding ultrasonic detection device shown in another exemplary embodiment of the present application;

[0027] Figure 6 It is a structural diagram of a computer system suitable for implementing an electronic device of an embodiment of the present application. DETAILED DESCRIPTION

[0028] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0031] The term "multiple" as used in this application refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0032] In order to solve the various limitations of traditional ultrasonic detection systems and the problem that they cannot achieve high automation and intelligence, the embodiments of the present application propose a patch bonding ultrasonic detection method and device, electronic equipment, and computer-readable storage medium, which mainly involve patch bonding ultrasonic detection technology included in ultrasonic detection technology. These embodiments will be described in detail below.

[0033] First see Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for ultrasonic testing of patch bonding according to an exemplary embodiment of the present application. Figure 1 As shown, in an exemplary embodiment, the patch bonding ultrasonic detection method may include steps S101 to S104, which are described in detail as follows:

[0034] Step S101, obtaining an ultrasonic image of the patch bonding point to be tested by using an ultrasonic detector.

[0035] Step S102: storing the ultrasound image to be measured in a pre-configured database.

[0036] In this embodiment, after the ultrasonic image to be tested of the patch bonding site is obtained by an ultrasonic detector, the ultrasonic image to be tested is stored in a pre-configured database in order to facilitate the call of the ultrasonic image when using it and improve data processing efficiency.

[0037] Step S103, obtaining historical ultrasonic images from the database according to the detection requirements, performing similarity calculation on the historical ultrasonic images and the ultrasonic image to be detected, and obtaining a calculation result.

[0038] After the ultrasonic image to be tested is stored, a historical ultrasonic image matching the detection requirement is obtained from a database storing various ultrasonic images corresponding to historical moments according to the detection requirement, and then a similarity calculation is performed between the historical ultrasonic image and the ultrasonic image to be tested to obtain a calculation result. The calculation result represents the degree of similarity between the ultrasonic image to be tested and multiple historical ultrasonic images, which is conducive to analyzing the ultrasonic image to be tested based on the historical ultrasonic images.

[0039] Step S104, selecting a target historical image from the historical ultrasonic images based on the calculation result, and obtaining a detection report based on the target historical image and the ultrasonic image to be detected.

[0040] The calculation result represents the similarity between the corresponding historical ultrasonic image and the ultrasonic image to be tested. This embodiment selects the target historical image that meets the similarity requirement, and obtains a test report based on the target historical image and the ultrasonic image to be tested, so as to analyze the ultrasonic image to be tested through the test report and complete the ultrasonic detection of the patch joint.

[0041] As can be seen from the above, in the method provided in this embodiment, an ultrasonic image to be tested at the patch bonding point is obtained by an ultrasonic detector, and the ultrasonic image to be tested is stored in a pre-configured database; then, historical ultrasonic images are obtained from the database according to the detection requirements, and the similarity between the historical ultrasonic images and the ultrasonic images to be tested is calculated to obtain the calculation results; based on the calculation results, the target historical images are selected from the historical ultrasonic images, and a detection report is obtained based on the target historical images and the ultrasonic images to be tested. In this way, the similarities and differences between the ultrasonic image to be tested and the historical ultrasonic images can be compared and analyzed, and targeted processing opinions can also be reflected in the detection report, which provides a judgment basis for the current detection of the ultrasonic image to be tested and improves the accuracy of ultrasonic detection. In addition, the solution provided in the application adopts a modular approach, which separates functions such as ultrasonic image detection, database management, and user interaction, improves the automation and efficiency of detection, reduces human errors, and improves the accuracy of detection.

[0042] In an exemplary embodiment provided by the present application, a pre-configured feedback indicator threshold range is used to determine whether the initial ultrasonic image collected by the ultrasonic detector can be output as the ultrasonic image to be tested for ultrasonic testing of the patch bonding site. The specific steps may include:

[0043] An initial ultrasonic image of the patch bonding site is collected by an ultrasonic detector;

[0044] Comparing the feedback index corresponding to the initial ultrasound image with the feedback index threshold range to obtain a comparison result;

[0045] When the comparison result indicates that the initial ultrasonic image meets the acquisition condition corresponding to the feedback index threshold range, the initial ultrasonic image is output as the ultrasonic image to be tested.

[0046] In this embodiment, the feedback index corresponding to the initial ultrasonic image is compared with the feedback index threshold range to obtain a comparison result so as to perform quality detection on the initial ultrasonic image. When the comparison result indicates that the initial ultrasonic image meets the acquisition conditions corresponding to the feedback index threshold range, it means that the initial ultrasonic image meets the quality requirements, and the initial ultrasonic image is output as the ultrasonic image to be tested.

[0047] In another exemplary embodiment provided by the present application, when the comparison result indicates that the initial ultrasonic image meets the acquisition condition corresponding to the feedback index threshold range, the ultrasonic image to be tested is directly output, and conversely, the detection parameters of the ultrasonic detector are adjusted to obtain the ultrasonic image to be tested that meets the quality requirements. The specific steps may include:

[0048] When the comparison result indicates that the feedback index is within the feedback index threshold range, outputting the initial ultrasound image as the ultrasound image to be tested;

[0049] When the comparison result indicates that the feedback indicator is outside the feedback indicator threshold range, obtaining a signal state of the initial ultrasound image;

[0050] Adjusting the detection parameters of the ultrasonic detector based on an adjustment method matching the signal state, and recording the number of adjustments;

[0051] The adjusted ultrasonic detector is used to recapture the initial ultrasonic image until the feedback index of the initial ultrasonic image is within the feedback index threshold range, or the number of adjustments reaches the number threshold, and the corresponding initial ultrasonic image is output as the ultrasonic image to be tested.

[0052] like Figure 2 As shown, Figure 2It is a flow chart of obtaining an ultrasonic image to be tested in an exemplary embodiment of the present application. In this embodiment, the detection parameters of the ultrasonic detector are first set and feedback indicators, such as image signal-to-noise ratio, are defined, so as to configure the threshold range of the feedback indicator; then, an ultrasonic image is acquired according to the detection parameters, and the ultrasonic image quality is evaluated using the feedback indicator corresponding to the image, and compared with the set feedback indicator threshold range; if the feedback indicator is within the feedback indicator threshold range, the detected ultrasonic image obtained by using the initial parameters is analyzed, and if the feedback indicator is outside the feedback indicator threshold range, the detection parameters are adjusted and the ultrasonic image is acquired again.

[0053] In another exemplary embodiment, the signal status of the initial ultrasound image may be a signal with a wrong direction, a signal missing, or a signal with a weak direction but no obvious direction problem. Figure 3 , Figure 3 is a flow chart of adjusting the detection parameters of the ultrasonic detector based on an adjustment method matching the signal state in an exemplary embodiment of the present application, such as Figure 3 As shown, the detection parameters are adjusted as follows:

[0054] (1) If the signal direction is wrong or the signal is missing, adjust the probe angle of the ultrasonic detector.

[0055] The probe angle is dynamically adjusted according to the surface shape of the object being measured and the expected beam coverage area to adjust the incident angle of the probe. The specific formula for probe adjustment is expressed as:

[0056]

[0057] Where θ is the incident angle of the probe, v1 is the speed of sound in the first medium, and v2 is the speed of sound in the second medium.

[0058] (2) If the overall signal is weak but there is no obvious directional problem, adjust the probe pressure;

[0059] The probe pressure is adjusted according to the strength and stability of the signal. By adjusting the pressure of the probe on the object being measured, a clearer signal can be obtained. The specific formula for adjusting the probe pressure is:

[0060] F new =F current +ΔF

[0061] Where F is the new pressure setting, F current is the current pressure, ΔF is the pressure adjustment amount, and its value range is [0.1N, 0.5N].

[0062] (3) After the probe angle and probe pressure are adjusted, the signal-to-noise ratio is judged. If the signal-to-noise ratio does not reach the signal-to-noise ratio threshold, the signal gain is adjusted.

[0063] The signal gain is adjusted dynamically according to the strength of the received ultrasonic signal to ensure that the signal is neither too strong to be saturated nor too weak to lose information. The specific formula for signal gain adjustment is expressed as:

[0064] G new =G current ×(1+k×(SNR target -SNR current ))

[0065] Among them, G new is the new gain setting, G current is the current gain, SNR target is the target signal-to-noise ratio, SNR current is the target signal-to-noise ratio, k is a positive constant control factor, and its value range is [0.1, 0.3].

[0066] (4) When the probe angle, probe pressure, and signal gain are adjusted, a signal-to-noise ratio is determined. If the signal-to-noise ratio does not reach a signal-to-noise ratio threshold, the scanning speed is adjusted.

[0067] Depending on the size of the area being measured and the level of ultrasound image detail required, the scanning speed is adjusted to balance ultrasound image acquisition time and resolution.

[0068] v new =v current ×(1+d×(SNR target -SNR current ))

[0069] Among them, v new is the new scan speed, v current is the scanning speed, SNR target is the target signal-to-noise ratio, SNR current is the target signal-to-noise ratio, and d is a positive constant control factor with a value range of [0.05, 0.2].

[0070] The signal state of the collected initial ultrasonic image is repeatedly obtained, and the corresponding adjustment method is implemented until the feedback index of the initial ultrasonic image is within the feedback index threshold range, indicating that the image quality meets the standard, or the number of adjustments reaches the number threshold, then the adjustment is terminated, the adjusted detection parameters are output, and the ultrasonic detector is run using the adjusted detection parameters to obtain the ultrasonic image to be measured.

[0071] In this way, this embodiment adjusts the detection parameters of the ultrasonic detector by an adjustment method that matches the signal state of the initial ultrasonic image, so that when performing ultrasonic detection, the detection parameters of the ultrasonic detector can be adaptively adjusted according to real-time detection feedback of the ultrasonic detection, thereby improving the accuracy of ultrasonic detection of the patch joint.

[0072] In an exemplary embodiment provided by the present application, the ultrasound image to be tested is converted into a standardized form corresponding to the database and annotated with metadata before being stored, which facilitates storage management and ensures the efficiency of subsequent data calls. Therefore, the specific steps of storing the ultrasound image to be tested in the database may include:

[0073] Performing standardized conversion on the ultrasonic image to be tested to obtain a standard ultrasonic image that meets the format requirements corresponding to the pre-configured database;

[0074] Metadata annotation is performed on standard ultrasound images, and the annotated standard ultrasound images are stored in a database.

[0075] In this embodiment, the ultrasound image to be tested is converted into a standard format, and metadata is annotated for each ultrasound image, and then the converted ultrasound image and metadata are stored in a database, an index is established for the ultrasound image to be tested and the metadata in the database, and the database is backed up and data maintenance is performed regularly. The standard format includes "DICOM", "JPEG" or other industry-recognized ultrasound image formats. The use of ultrasound images in standard formats ensures the consistency and interoperability of ultrasound image data. Metadata strengthens the integrity of the data and ensures the accuracy of ultrasound image information. The creation of indexes improves the efficiency of data retrieval and realizes the consistency, interoperability and long-term archiving of ultrasound image data.

[0076] In addition, when storing and processing the ultrasonic image to be tested, the database also stores the basic data of the ultrasonic detector currently corresponding to the ultrasonic image to be tested, and establishes an index between the basic data and the ultrasonic image to be tested, where the basic data includes date and time, equipment name, operator, test location, parameter settings, test results, quality assessment, and repair measures. This enables orderly storage and rapid retrieval of data, which not only ensures the integrity and traceability of information, but also improves the efficiency and accuracy of data processing.

[0077] The database structure in this embodiment may include a basic information table, a formatted ultrasound image table, and an equipment information table. The basic information table is used to store all basic data related to the test, including equipment number, date and time, equipment name, operator, test location, parameter settings, test results, quality assessment, and repair measures. The formatted ultrasound image table is used to store ultrasound image data that has been standardized and converted; the equipment basic information table is used to store basic information and calibration status of the equipment in use, including the following fields: equipment number, equipment model, manufacturer, purchase date, and maintenance record.

[0078] In an exemplary embodiment provided by the present application, matching historical ultrasound images are selected based on the characteristics of the patch bonding specified by the detection requirements. The specific steps may include:

[0079] Determine the corresponding characteristic information of the patch bonding based on the detection requirements;

[0080] Based on the characteristic information, a historical ultrasound image matching the characteristic information is acquired from a database.

[0081] In this embodiment, the characteristic information of the patch bonding may include defect type, bonding material type, construction environment, etc., so as to obtain historical ultrasonic images matching the characteristic information from the database.

[0082] In an exemplary embodiment provided by the present application, after obtaining historical ultrasound images from a database according to detection requirements, it is also necessary to extract features of the ultrasound images to be tested, and obtain feature information to be tested for similarity calculation, and the specific steps may include:

[0083] Preprocessing the ultrasonic image to be tested, and performing deep feature extraction on the preprocessed ultrasonic image to be tested to obtain feature information to be tested;

[0084] The historical feature information of the historical ultrasonic image is obtained from the database, so as to calculate the similarity between the historical ultrasonic image and the ultrasonic image to be tested based on the feature information to be tested and the historical feature information.

[0085] In this embodiment, the preprocessing includes denoising and ultrasonic image enhancement. The ultrasonic image denoising adopts adaptive filtering technology to remove ultrasonic image noise, and the ultrasonic image enhancement adopts histogram equalization and local contrast enhancement technology to highlight the details of the ultrasonic image. Through the optimization strategy, the random noise and artifacts in the ultrasonic image are removed, the local features and overall contrast of the ultrasonic image to be measured are enhanced, thereby improving the clarity of the ultrasonic image to be measured.

[0086] After that, the feature extraction of ultrasound images is performed through the set ResNet-50 deep residual network model. This process uses convolutional layers, activation functions, pooling layers, batch normalization and dropout layers for feature extraction to learn complex features in ultrasound images and reduce overfitting. Through the deep extraction strategy, rich feature information to be tested is extracted from the ultrasound images to be tested, and the accuracy and robustness of the feature information to be tested are ensured through the powerful learning ability of the deep residual network, which provides strong data support for subsequent image analysis and improves accuracy and reliability. In addition, if the feature dimension of the output feature information to be tested is too high, the PCA principal component analysis dimensionality reduction technology can be used to reduce the dimension of the feature vector.

[0087] In the embodiments provided in the present application, the model training steps of the ResNet-50 deep residual network model for feature extraction may include:

[0088] (1) Data preparation: collect ultrasonic images of patch bonding of different types and qualities to improve the generalization ability of the model.

[0089] (2) ResNet-50 was selected as the pre-training model, and the structure of ResNet-50 was fine-tuned according to the characteristics of ultrasound images. The number of neurons in the final fully connected layer was adjusted according to the ultrasound image classification task, and the Softmax activation function of the output layer was adapted to meet the classification requirements.

[0090] (3) Divide the collected data set into training set, validation set and test set. Set the cross entropy loss function, use the Adam optimizer, and set the initial learning rate and batch size. Use the training set to train the model, and use the validation set to evaluate the model performance after each training cycle. Adjust the network parameters and learning rate according to the validation results until the model performance reaches the optimal level.

[0091] Specifically, samples were selected from the collected data set by random sampling technique, and the sampled data were divided into 70% training set, 15% validation set, and 15% test set ratios;

[0092] The cross entropy loss function is used, which is defined as:

[0093] L(x)=-∑p i log q i =-logq y , i=1...N

[0094] Among them, the classification task has N i categories, x is the sample, y is the true category, q is the predicted probability vector, each element of which represents the predicted probability that the sample belongs to each category, and p is the true probability distribution;

[0095] Select Adam optimizer for model training, set the initial learning rate to 0.001, and the batch size to 32;

[0096] When training a model using a training set, the back-propagation algorithm and optimizer should minimize the loss function. After each epoch, the performance of the model on the training set should be tested.

[0097] After the training cycle is over, the model performance is evaluated using the validation machine. If the performance of the model validation set begins to decline, an early stopping strategy is used to prevent overfitting.

[0098] According to the performance feedback of the validation set, the learning rate is adjusted using the decay strategy. According to the performance evaluation, the model is adjusted iteratively to select a model with the best performance on the validation set;

[0099] Use the test set to evaluate the final selected model and compare its performance on the training set and validation set to analyze whether the model is overfitting or underfitting. If there is no overfitting or underfitting, the final model is determined.

[0100] Then use the trained ResNet-50 model for feature extraction, and choose the output of the last pooling layer or the output of the last convolutional layer as the feature vector.

[0101] In this way, this embodiment improves the clarity of the ultrasonic image by preprocessing the ultrasonic image to be tested, and ensures the accuracy and robustness of the feature information through the powerful learning ability of the deep residual network, providing strong data support for subsequent ultrasonic image analysis, and also improving the accuracy and reliability of the entire ultrasonic detection system.

[0102] In an exemplary embodiment provided by the present application, the target historical image is selected by sorting the historical ultrasound images by similarity, and the specific steps may include:

[0103] The calculation results are sorted based on the numerical values ​​of the similarities represented by the calculation results to obtain a sorting result;

[0104] A preset number of historical ultrasound images are selected from the sorting results as target historical images.

[0105] In this embodiment, the similarity between the historical ultrasound image and the ultrasound image to be tested is calculated based on the feature information to be tested and the historical feature information. After the calculation results are obtained, the similarities represented by the calculation results are sorted from high to low. According to the sorting results, a preset number of historical ultrasound images with the highest similarity are selected as target historical images, for example, three target historical images.

[0106] Afterwards, a test report is obtained based on the ultrasonic head image to be tested and the target historical image. Specifically, basic information of the target historical image is extracted from the database: the basic information of the current ultrasonic image to be tested and the basic information of the target historical image are summarized to generate an analysis report.

[0107] In the embodiment provided in the present application, the calculation of similarity can be achieved by combining the calculation method of Euclidean distance and cosine similarity to create a combined distance measurement method, which takes into account the amplitude difference between feature vectors and the angle difference.

[0108] Let the two eigenvectors be and The combined distance is then defined as:

[0109]

[0110] In the formula, express and The Euclidean distance between express and The cosine similarity between them, α is a weight parameter with a value range of [0,1], which is used to balance the influence of Euclidean distance and cosine similarity.

[0111] In this way, the technical solution of this embodiment of the present application selects a preset number of target historical images from historical ultrasound images according to the numerical value of the similarity, and can effectively use the historical ultrasound images to provide a reference for the current ultrasound image to be tested, strengthen support for diagnostic decisions, and potentially improve the accuracy and efficiency of diagnosis.

[0112] Figure 4 FIG. 4 is a block diagram of an ultrasonic testing device 400 for patch bonding according to an exemplary embodiment of the present application. Figure 4 As shown, the device comprises:

[0113] An image acquisition module 401 is used to acquire an ultrasonic image of the patch bonding site through an ultrasonic detector;

[0114] The database module 402 is used to store the ultrasound image to be measured in a pre-configured database;

[0115] The interactive module 403 is used to obtain historical ultrasonic images from the database according to the detection requirements, and perform similarity calculation on the historical ultrasonic images and the ultrasonic images to be detected to obtain calculation results;

[0116] The interaction module 403 is further used to select a target historical image from the historical ultrasonic images based on the calculation result, and obtain a detection report based on the target historical image and the ultrasonic image to be detected.

[0117] The device applies the patch bonding ultrasonic detection method provided in the present application, and uses an ultrasonic detector to obtain the ultrasonic image to be tested at the patch bonding point through the image acquisition module 401, and stores the ultrasonic image to be tested in a pre-configured database through the database module 402; then the interactive module 403 obtains the historical ultrasonic image from the database according to the detection requirements, and calculates the similarity between the historical ultrasonic image and the ultrasonic image to be tested to obtain the calculation result; based on the calculation result, the target historical image is selected from the historical ultrasonic image, and a detection report is obtained based on the target historical image and the ultrasonic image to be tested. In this way, the similarities and differences between the ultrasonic image to be tested and the historical ultrasonic image can be compared and analyzed, and targeted processing opinions can also be reflected through the detection report, which provides a judgment basis for the current ultrasonic image to be tested and improves the accuracy of ultrasonic detection. In addition, the solution provided by the application adopts a modular approach, and separates functions such as ultrasonic image detection, database management, and user interaction, which improves the automation and efficiency of detection, reduces human errors, and improves the accuracy of detection.

[0118] See also Figure 5 , Figure 5 Schematic diagram of another exemplary embodiment of the present application showing an ultrasonic detection device for patch bonding. In this embodiment, the ultrasonic detection device for patch bonding includes an image acquisition module, a database module, a feature extraction module and an interaction module, which are used to implement the ultrasonic detection method for patch bonding provided in the present application.

[0119] The image acquisition module includes a device unit and a parameter adjustment unit. The device unit is configured with a parameter configuration strategy. The parameter configuration strategy includes calibrating the ultrasonic detector device and checking the cleanliness of the probe. After completing the calibration of the ultrasonic detector and the inspection of the probe, the detection parameters of the ultrasonic detector are configured for ultrasonic detection. The calibration of the ultrasonic detector includes calibrating the probe frequency, gain adjustment and focusing depth. The configured detection parameters include probe angle, probe pressure, signal gain and scanning speed. By calibrating the ultrasonic detector and configuring the ultrasonic parameters, accurate detection of the target can be achieved during ultrasonic detection, especially quality detection of the patch bonding point, reducing the loss of detection accuracy caused by equipment hardware.

[0120] The parameter adjustment unit is configured with an adaptive strategy, which includes real-time calling of the initial ultrasonic image, obtaining ultrasonic data, adjusting the detection parameters of the ultrasonic detector based on the ultrasonic data, so as to be able to adaptively adjust the detection parameters according to the real-time ultrasonic data, and collecting ultrasonic images under the adjusted detection parameters, wherein the detection parameters of the ultrasonic detector include detection angle, detection pressure, gain and scanning speed, and the detection parameters of the ultrasonic detector are adjusted by the adaptive strategy, so that when performing ultrasonic detection, the detection parameters of the ultrasonic detector can be adaptively adjusted according to the real-time detection feedback of the ultrasonic detection, thereby improving the ultrasonic detection accuracy of the target object. That is, in the patch bonding ultrasonic detection method provided by itself, the adaptive strategy is implemented, when the comparison result characterizes that the feedback index is outside the feedback index threshold range, the signal state of the initial ultrasonic image is obtained, and the detection parameters of the ultrasonic detector are adjusted based on the adjustment method matching the signal state.

[0121] The database module includes basic information unit, formatting unit and equipment information unit. The basic information unit is configured with data storage strategy, which includes storing basic data of ultrasonic detection, storing the ultrasonic images to be detected obtained by the image acquisition module, and establishing indexes. The basic data includes date and time, equipment name, operator, detection location, parameter setting, detection result, quality assessment, and repair measures. Through the configuration strategy of data storage, orderly storage and rapid retrieval of data are realized. This not only ensures the integrity and traceability of information, but also improves the efficiency and accuracy of data processing.

[0122] A standardized processing strategy is configured in the formatting unit. The standardized processing strategy includes converting the ultrasound images to be tested stored in the basic information unit into a standard format, annotating metadata for each converted ultrasound image to be tested, storing the converted ultrasound images and metadata in a database, establishing indexes for the ultrasound images to be tested and the metadata in the database, and regularly backing up the database and performing data maintenance. Through the standardized processing strategy, ultrasound images in a standard format are used to ensure the consistency and interoperability of ultrasound image data. Metadata enhances the integrity of the data and ensures the accuracy of ultrasound image information. The creation of indexes improves the efficiency of data retrieval and realizes the consistency, interoperability and long-term archiving of ultrasound image data.

[0123] The device information unit is configured with a device management strategy, which includes recording and managing the information of the test equipment. The device information includes the device name, model, manufacturer, purchase date, and maintenance record. Through the device management strategy, it can be ensured that the device information used for each test is accurately recorded and updated in a timely manner, thereby enhancing the transparency of equipment use and maintenance, and ensuring the reliability of testing activities and the traceability of equipment failures.

[0124] The feature extraction module includes a preprocessing unit, a feature extraction unit and an update storage unit. The preprocessing unit is configured with an optimization strategy. The optimization strategy includes performing ultrasonic image denoising and ultrasonic image enhancement processing on the ultrasonic images that have been stored in the database. The ultrasonic image denoising adopts adaptive filtering technology to remove ultrasonic image noise. The ultrasonic image enhancement adopts histogram equalization and local contrast enhancement technology to highlight the details of the ultrasonic image. Through the optimization strategy, random noise and artifacts in the ultrasonic image are removed, and the local features and overall contrast of the ultrasonic image are enhanced, thereby improving the clarity of the ultrasonic image.

[0125] The feature extraction unit is configured with a deep extraction strategy, which includes setting up a ResNet-50 deep residual network to perform feature extraction on ultrasound images. Through the deep extraction strategy, rich feature information is extracted from the ultrasound image, and the powerful learning ability of the deep residual network is used to ensure the accuracy and robustness of the feature information, which provides strong data support for subsequent ultrasound image analysis and improves the accuracy and reliability of the entire ultrasound detection system.

[0126] Updating the storage unit includes recording the updated results after feature extraction into the database. The updated results include ultrasonic image feature vectors, defect types, defect sizes, defect locations, equipment information, dates, and operators, ensuring that all detection data are systematically integrated and updated to facilitate subsequent query, analysis, and decision-making. Through a comprehensive data management and update mechanism, a solid foundation is provided for the long-term stability of ultrasonic testing and data-driven optimization.

[0127] The interactive module includes a data screening unit, a measurement unit and a report generation unit. The data screening unit is configured with a retrieval strategy. The retrieval strategy includes retrieving test data and results from the database according to the test requirements. The data and results include ultrasonic image feature vectors, defect types, defect sizes, defect locations, and corresponding test equipment information, test dates, and operators. Through the retrieval strategy, users can easily filter out records that meet specific standards, such as date ranges, equipment types, test personnel, etc., thereby achieving rapid access to and effective management of data. This personalized data retrieval mechanism provides convenient and accurate support for decision-making, ensuring the efficiency and relevance of information acquisition.

[0128] The measurement unit is configured with an evaluation strategy, which includes calculating the similarity between the ultrasound image to be tested and the screened target historical image, evaluating whether there are similar historical ultrasound images by calculating the similarity of the ultrasound image feature information, screening the target historical images in the database based on specific standards, retrieving the ultrasound image feature information of the target historical images, calculating the similarity between the feature information to be tested of the ultrasound image to be tested and the historical feature information of the target historical images, and providing historical ultrasound images with high similarity. Through the evaluation strategy, the target historical images can be effectively used to provide a reference for the current detection, strengthen the support for diagnostic decisions, and potentially improve the accuracy and efficiency of diagnosis.

[0129] It can be seen that the patch bonding ultrasonic detection device provided in this embodiment applies a patch bonding ultrasonic detection method provided in this application. The image acquisition module optimizes the clarity of the ultrasonic image by adopting an adaptive strategy, so that more accurate feature information can be extracted when extracting ultrasonic image features; the database module realizes the efficiency and accuracy of ultrasonic image data processing through data storage and standardized processing strategies, so that data can be quickly and accurately retrieved and saved when retrieving historical ultrasonic images and calculating similarities; the feature extraction module removes noise in the ultrasonic image through ultrasonic image preprocessing optimization and deep extraction strategies, enhances the contrast of the ultrasonic image, and extracts and processes accurate feature information of the ultrasonic image, so that the feature information is more reliable when calculating the similarity; the interactive module uses retrieval and evaluation strategies to personalize the selection of historical ultrasonic images from the database and then perform similarity evaluation, which provides a judgment basis for the current ultrasonic detection and improves the accuracy of ultrasonic detection.

[0130] It should be noted that the patch bonding ultrasonic detection device provided in the above embodiment and the patch bonding ultrasonic detection method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the patch bonding ultrasonic detection device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0131] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by one or more processors, the electronic device implements the ultrasonic detection method for patch bonding provided in the above-mentioned embodiments.

[0132] Figure 6 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 6The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0133] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603, such as executing the method in the above embodiment. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602 and RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0134] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0135] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 609, and / or installed from a removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0136] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0137] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0138] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0139] Another aspect of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned patch bonding ultrasonic detection method is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0140] Another aspect of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the patch bonding ultrasonic detection method provided in each of the above embodiments.

[0141] The above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions or improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for ultrasonic testing of patch bonding, characterized in that: The method comprises: Acquire the ultrasonic image to be tested at the patch bonding site by using an ultrasonic detector; storing the ultrasonic image to be measured in a pre-configured database; Acquire a historical ultrasonic image from the database according to the detection requirements, and perform similarity calculation on the historical ultrasonic image and the ultrasonic image to be detected to obtain a calculation result; A target historical image is selected from the historical ultrasonic images based on the calculation result, and a detection report is obtained based on the target historical image and the ultrasonic image to be detected.

2. The method according to claim 1, characterized in that The method of obtaining the ultrasonic image to be measured at the patch bonding location by using an ultrasonic detector includes: An initial ultrasonic image of the patch bonding site is collected by an ultrasonic detector; Comparing the feedback index corresponding to the initial ultrasound image with the feedback index threshold range to obtain a comparison result; When the comparison result indicates that the initial ultrasonic image meets the acquisition condition corresponding to the feedback index threshold range, the initial ultrasonic image is output as the ultrasonic image to be tested.

3. The method according to claim 2, characterized in that When the comparison result indicates that the initial ultrasonic image satisfies the acquisition condition corresponding to the feedback index threshold, outputting the initial ultrasonic image as the ultrasonic image to be tested includes: When the comparison result indicates that the feedback index is within the feedback index threshold range, outputting the initial ultrasonic image as the ultrasonic image to be tested; When the comparison result indicates that the feedback indicator is outside the feedback indicator threshold range, acquiring a signal state of the initial ultrasound image; Adjusting the detection parameters of the ultrasonic detector based on an adjustment method matching the signal state, and recording the number of adjustments; The adjusted ultrasonic detector is used to recapture the initial ultrasonic image until the feedback index of the initial ultrasonic image is within the feedback index threshold range, or the adjustment times reaches the times threshold, and the corresponding initial ultrasonic image is output as the ultrasonic image to be tested.

4. The method according to claim 1, characterized in that: The step of storing the ultrasonic image to be measured in a pre-configured database comprises: Performing a standardized conversion on the ultrasonic image to be measured to obtain a standard ultrasonic image that meets the format requirements corresponding to the pre-configured database; Metadata annotation is performed on the standard ultrasound image, and the annotated standard ultrasound image is stored in the database.

5. The method according to claim 1, characterized in that The acquiring of historical ultrasound images from the database according to the detection requirements includes: Determine the corresponding characteristic information of the patch bonding based on the detection requirements; A historical ultrasound image matching the characteristic information is acquired from the database based on the characteristic information.

6. The method according to claim 1, characterized in that After acquiring the historical ultrasound images from the database according to the detection requirements, the method further includes: Preprocessing the ultrasonic image to be tested, and performing deep feature extraction on the preprocessed ultrasonic image to be tested to obtain feature information to be tested; The historical feature information of the historical ultrasonic image is obtained from the database, so as to perform similarity calculation on the historical ultrasonic image and the ultrasonic image to be tested based on the feature information to be tested and the historical feature information.

7. The method according to claim 1, characterized in that Selecting a target historical image from the historical ultrasound images based on the calculation result includes: Sorting the calculation results based on the numerical values ​​of the similarities represented by the calculation results to obtain a sorting result; A preset number of historical ultrasound images are selected from the sorting results as target historical images.

8. A patch bonding ultrasonic detection device, characterized in that: include: An image acquisition module is used to acquire an ultrasonic image to be tested at the patch bonding point through an ultrasonic detector; A database module, used for storing the ultrasonic image to be measured in a pre-configured database; An interactive module, used for acquiring historical ultrasonic images from the database according to detection requirements, performing similarity calculation on the historical ultrasonic images and the ultrasonic image to be detected, and obtaining a calculation result; The interaction module is further used to select a target historical image from the historical ultrasonic images based on the calculation result, and obtain a detection report based on the target historical image and the ultrasonic image to be detected.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the patch bonding ultrasonic detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and when the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the patch bonding ultrasonic detection method according to any one of claims 1 to 7.

Images