Epoxy material defect repairing device, method and equipment based on infrared focusing heating

Abstract

The embodiment of the invention discloses an epoxy material defect repairing device and method based on infrared focusing heating and a medium. The device comprises an image collector, a defect locator, a console, a focusing controller and a focusing device, and the image collector is used for collecting epoxy material image data; the defect locator is used for detecting the state information of the epoxy material and acquiring the information of the epoxy material according to the image data of the epoxy material; the console is used for acquiring epoxy material defect data according to the epoxy material information, and matching optimal repair data according to the current epoxy material defect data; the focusing controller is used for outputting a repairing signal for repairing the defective epoxy material by the focusing device according to the optimal repairing data; and the focusing device is used for generating infrared radiation according to the repair signal and focusing the infrared radiation to the defective epoxy material so as to perform defect repair on the defective epoxy material. And infrared radiation is generated through the focusing device and is focused on the defective epoxy material, so that accurate repair of the defect is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of epoxy material defect repairing, and in particular to an epoxy material defect repairing device, method and equipment based on infrared focused heating. Background Art

[0002] As a type of covalently cross-linked polymer material, epoxy material has excellent physical, mechanical and electrical insulation properties and good adhesion properties. It has been widely used in defense and various sectors of the national economy. It is used as casting, impregnation, laminating materials, adhesives, coatings, etc., and has played a huge role in the fields of construction, machinery, and electronic packaging.

[0003] However, as a thermosetting polymer material, epoxy materials are susceptible to external impacts and microcracks due to their poor toughness. These microcracks are difficult to repair because they are deep inside the structure. If they are not repaired, they may develop into macro cracks, causing further damage and shortening the service life of the entire system. How to eliminate these cracks after they occur while maintaining their comprehensive performance is of great significance for expanding the application of epoxy materials and extending their service life. Traditional damage repair techniques (welding and patching) are limited to visible cracks and are not instant or autonomous. Researchers have proposed a solution: introducing a mobile phase into the epoxy polymer, flowing to the damaged site and filling the cracks, upgrading the material to a self-healing material. Self-healing can be defined as the ability of a material to recover from damage / cracks by itself. Intrinsic self-healing methods are widely used because they do not require the storage of external healing agents or catalysts in self-healing chemistry, can be repeatedly healed at the same damaged site of the coating, and are more competitive in the production and application of epoxy materials. The principle of the intrinsic self-healing method to repair epoxy materials is to introduce special bonds (reversible chemical bonds) so that the epoxy material has the ability to self-heal. The self-healing process is driven by the chemical bonds of the matrix. Therefore, the material is designed with the inherent potential to reorganize after damage in the presence of external triggers such as heat, light or chemicals.

[0004] In the existing technology, researchers usually choose external heating as the trigger factor for the chemical bond-driven self-repair process, and the traditional heating methods include: heat conduction between the epoxy material and the heated object in direct contact, and heat convection that requires a medium to transfer heat. However, these two methods require a long preheating time during repair, which will waste resources and is not in line with the concept of sustainable development; real-time monitoring of defect repair cannot be achieved during the repair process; and accurate repair of the surface and internal defective parts of the epoxy material cannot be achieved. Summary of the invention

[0005] Based on this, it is necessary to propose an epoxy material defect repair device, method and equipment based on infrared focused heating to address the above problems.

[0006] An epoxy material defect repair device based on infrared focused heating, the device comprising: a defect locator, an image collector, a console, a focus controller, a focus device,

[0007] The image collector is connected to the console and is used to collect epoxy material image data.

[0008] The defect locator is connected to the image collector and is used to detect the state information of the epoxy material and obtain the epoxy material information according to the epoxy material image data.

[0009] The console is connected to the focus controller and is used to obtain epoxy material defect data according to the epoxy material information, and match the optimal repair data with the current epoxy material defect data.

[0010] The focusing controller is connected to the focusing device and is used to output a repair signal for the focusing device to repair the defective epoxy material according to the optimal repair data.

[0011] The focusing device is installed above the defect locator, and is used for generating infrared radiation according to the repair signal, and focusing the infrared radiation to the defective epoxy material to perform defect repair on the defective epoxy material.

[0012] The focusing device specifically includes: an infrared light source, a convex lens, a grating, and a focusing lens.

[0013] The infrared light source is used to adjust the output laser parameters according to the repair signal to generate infrared radiation with thermal radiation effect.

[0014] The infrared light source is placed at the focal point of one end of the convex lens, so as to output the infrared radiation in the form of a parallel light beam.

[0015] The grating is coaxially opposite to the optical center of the convex lens and is used to make the parallel light beam perpendicular to the grating surface, thereby completing the grating control of the infrared radiation output wavelength and beam quality.

[0016] The focusing lens is connected to the grating, and is used for converging the infrared radiation regulated by the grating and irradiating the converged infrared radiation to the defective epoxy material, so as to repair the defective epoxy material.

[0017] The device further specifically comprises:

[0018] A stage, with the upper side of the stage facing the defect locator, is used for placing the epoxy material.

[0019] A method for repairing epoxy material defects based on infrared focused heating, the method comprising:

[0020] Collect epoxy material image data.

[0021] Detecting the state information of the epoxy material, and acquiring the epoxy material information according to the epoxy material image data.

[0022] Epoxy material defect data is acquired according to the epoxy material information, and optimal repair data is matched with the current epoxy material defect data.

[0023] A repair signal for repairing the epoxy material is output according to the optimal repair data.

[0024] Infrared radiation is generated according to the repair signal, and the infrared radiation is focused on the defective epoxy material to repair the defective epoxy material.

[0025] Wherein, after generating infrared radiation according to the repair signal and focusing the infrared radiation to the defective epoxy material to repair the defective epoxy material, the method further specifically includes:

[0026] The state information of the epoxy material is detected in real time to obtain the repair state of the epoxy material until the defects of the epoxy material are completely repaired.

[0027] Stop heating and allow the epoxy to cool before inspecting the repair.

[0028] The step of acquiring epoxy material defect data according to the epoxy material information and matching optimal repair data with the current epoxy material defect data specifically includes:

[0029] Epoxy material defect samples are input into the epoxy material database to form a training set. The epoxy material defect samples are stored in the epoxy material database after passing through the classification network, the detection network and the segmentation network, thereby completing the training of the epoxy material defect samples.

[0030] The trained epoxy material defect samples are stored in the epoxy material database.

[0031] The epoxy material information is used as a test set of the epoxy material database, and the epoxy material information is passed through the classification network to determine the epoxy material defect type.

[0032] The time domain and frequency domain characteristics of the epoxy material defect data in the epoxy material defect type are extracted to obtain defective epoxy material characteristic data.

[0033] The optimal repair data matching the defective epoxy material is determined according to the current characteristic data of the defective epoxy material.

[0034] The step of determining the optimal repair data matching the defective epoxy material according to the current characteristic data of the defective epoxy material specifically includes:

[0035] The current defective epoxy material characteristic data are stacked to form a high-dimensional tensor.

[0036] Determine two-dimensional data of defective epoxy material according to the high-dimensional tensor.

[0037] The window attention mechanism is used to extract the local features of the two-dimensional data of the defective epoxy material.

[0038] The local features of the defective epoxy material two-dimensional data are passed through the detection network to obtain epoxy material defect results.

[0039] The epoxy material defect result is used to correct the defective area on the surface of the epoxy material through the segmentation network, and the optimal repair data matching the defective epoxy material is determined.

[0040] The step of generating infrared radiation according to the repair signal and focusing the infrared radiation onto the defective epoxy material to repair the defective epoxy material specifically includes:

[0041] The outgoing laser parameters are adjusted according to the repair signal to generate infrared radiation with thermal radiation effect.

[0042] The infrared radiation is output as a parallel beam.

[0043] The infrared radiation output wavelength and beam quality are grating-controlled.

[0044] The infrared radiation regulated by the grating is converged and irradiated to the defective epoxy material to repair the defective epoxy material.

[0045] The step of converging the infrared radiation regulated by the grating and irradiating the converged infrared radiation to the epoxy material to repair defects of the epoxy material specifically includes:

[0046] The infrared radiation after grating adjustment is converged, and the converged light is irradiated to the epoxy material.

[0047] When the infrared wavelength of the infrared radiation after grating adjustment is consistent with the absorption wavelength of the heated epoxy material, the temperature of the epoxy material increases and the defects of the epoxy material are repaired.

[0048] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the method described above.

[0049] The embodiments of the present invention have the following beneficial effects:

[0050] The present invention accurately collects image data of epoxy materials through an image collector, and the defect locator uses image processing and analysis algorithms to detect defect status information in epoxy materials in real time, and obtains epoxy material information based on epoxy material image data. Furthermore, the console quickly obtains epoxy material defect data based on epoxy material information, and finds optimal repair data through a matching algorithm. Furthermore, the focusing controller outputs a repair signal based on the optimal repair data, accurately controls the operation of the focusing device, and ensures that the infrared radiation can be accurately focused on the defective epoxy material, thereby improving the repair effect. In addition, the intelligent processing of the focusing controller also reduces errors in human operation and improves the overall performance of the system. Finally, infrared radiation is generated by the focusing device and focused on the defective epoxy material, thereby achieving accurate repair of defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] in:

[0053] Figure 1 A schematic structural diagram of an embodiment of an epoxy material defect repairing device based on infrared focused heating provided by the present invention;

[0054] Figure 2 A schematic structural diagram of another embodiment of an epoxy material defect repairing device based on infrared focused heating provided by the present invention;

[0055] Figure 3 A schematic structural diagram of an embodiment of a focusing device provided by the present invention;

[0056] Figure 4 A schematic flow chart of an embodiment of an epoxy material defect repair method based on infrared focused heating provided by the present invention;

[0057] Figure 5 A schematic flow chart of another embodiment of a method for repairing epoxy material defects based on infrared focused heating provided by the present invention;

[0058] Figure 6 A schematic flow chart of another embodiment of a method for repairing epoxy material defects based on infrared focused heating provided by the present invention;

[0059] Figure 7 A schematic structural diagram of an embodiment of the device provided by the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] like Figure 1 As shown, Figure 1 The schematic diagram of the structure of an embodiment of an epoxy material defect repair device based on infrared focused heating provided by the present invention. An epoxy material 10 defect repair device based on infrared focused heating, the device comprises: a defect locator 2, an image collector 1, a console 3, a focus controller 4, a focus device 5,

[0062] The image collector 1 is connected to the console 3 and is used to collect epoxy material image data.

[0063] Exemplarily, the image collector 1 is a USB image collector 1, which is an interface card for connecting an industrial camera and an industrial control system, and provides data transmission and processing functions for a machine vision system. The image collector 1 is connected to the console 3, so that the control system of the console 3 can read the defective epoxy material image data from the camera through the bus of the image acquisition card, and perform the next step of processing and application.

[0064] The defect locator 2 is connected to the image collector 1 and is used to detect the state information of the epoxy material 10 and obtain the epoxy material information according to the epoxy material image data.

[0065] Exemplarily, the defect locator 2 is a laser confocal defect locator 2, which uses laser as a light source and adopts a conjugate focusing principle and device. The defect locator 2 is connected to the image collector 1, and uses the epoxy material image data collected by the image collector 1 to process, observe, analyze and output the epoxy material image data to obtain information of the epoxy material 10. The defect locator 2 can be used to perform tomography and imaging of the sample (epoxy material 10), and non-destructive observation and analysis of the three-dimensional spatial structure of the sample.

[0066] The control console 3 is connected to the focus controller 4, and is used to obtain epoxy material defect data according to epoxy material information, and match the optimal repair data with the current epoxy material defect data.

[0067] Exemplarily, the console 3, as the "brain" of the entire device, is preferably a computer with logical judgment ability, fast operation speed, high calculation accuracy, strong storage function, and high degree of automation. The console 3 is connected to the focus controller 4, and based on the deep learning supervision method, the epoxy material defect data is obtained according to the epoxy material information, and the optimal repair data is matched by the current epoxy material defect data.

[0068] The focusing controller 4 is connected to the focusing device 5 and is used to output a repair signal for the focusing device 5 to repair the defective epoxy material 10 according to the optimal repair data.

[0069] Exemplarily, the focus controller 4 is connected to the focus device 5. As an intermediate unit connecting the console 3 and the focus device 5, the focus controller 4 can convert the optimal repair data from the console 3 into a repair signal for the focus device 5 to repair the defective epoxy material 10.

[0070] The focusing device 5 is installed above the defect locator 2 , and is used to generate infrared radiation according to the repair signal, and focus the infrared radiation to the defective epoxy material 10 to repair the defective epoxy material 10 .

[0071] Exemplarily, the focusing device 5 is installed above the defect locator 2, adjusts the output laser parameters according to the repair signal, generates infrared radiation with a thermal radiation effect, outputs the infrared radiation in a parallel light beam, controls the output wavelength and beam quality of the infrared radiation by the grating 53, converges the infrared radiation after being controlled by the grating 53 and irradiates the converged infrared radiation to the epoxy material 10, so as to repair the defects of the epoxy material 10.

[0072] It can be seen from the above description that the present invention accurately collects image data of epoxy materials through the image collector, and the defect locator uses image processing and analysis algorithms to detect defect status information in epoxy materials in real time, and obtains epoxy material information based on epoxy material image data. Furthermore, the console quickly obtains epoxy material defect data based on epoxy material information, and finds the optimal repair data through a matching algorithm. Furthermore, the focusing controller outputs a repair signal based on the optimal repair data, accurately controls the operation of the focusing device, and ensures that the infrared radiation can be accurately focused on the defective epoxy material, thereby improving the repair effect. In addition, the intelligent processing of the focusing controller also reduces errors in human operation and improves the overall performance of the system. Finally, infrared radiation is generated by the focusing device and focused on the defective epoxy material, thereby achieving accurate repair of defects.

[0073] like Figure 2 As shown, Figure 2The schematic diagram of another embodiment of the epoxy material defect repairing device based on infrared focused heating provided by the present invention further comprises: a stage 7, the stage 7 is directly opposite to the defect locator 2, and is used to place the epoxy material 10.

[0074] For example, the stage 7 is directly above the defect locator 2, and the stage 7 provides a stable support surface for the epoxy material 10 to ensure that it does not move or slide during the inspection process. The epoxy material to be inspected is placed on the stage, adjusted to a suitable inspection position, and further, the defect locator 2 is started for inspection.

[0075] like Figure 3 As shown, Figure 3 The focusing device 5 specifically comprises: an infrared light source 51, a convex lens 52, a grating 53, and a focusing lens 54.

[0076] The infrared light source 51 is used to adjust the output laser parameters according to the repair signal to generate infrared radiation with thermal radiation effect.

[0077] Exemplarily, the infrared light source 51 is generally divided into four types: thermal radiation infrared light source, gas discharge infrared light source, laser infrared light source, and array matrix infrared light source. Preferably, the laser infrared light source has the advantages of good directionality, high beam quality, high electro-optical conversion efficiency, and long life. By using the infrared light source 51, the outgoing laser parameters are adjusted according to the repair signal to generate infrared radiation with thermal radiation effect.

[0078] An infrared light source 51 is placed at the focal point of one end of the convex lens 52 for outputting infrared radiation in the form of a parallel beam.

[0079] Exemplarily, an infrared light source 51 is placed at the focal point of one end of the convex lens 52, and the infrared radiation emitted by the infrared light source 51 is a parallel light beam, utilizing the principle that the convex lens 52 emits parallel light from the incident light at the focal point.

[0080] The grating 53 is coaxially opposite to the optical center of the convex lens 52 and is used to make the parallel light beam perpendicular to the surface of the grating 53, thereby completing the grating 53 control of the infrared radiation output wavelength and beam quality.

[0081] Exemplarily, the grating 53 is coaxially opposite to the optical center of the convex lens 52, and the parallel light emitted from the convex lens 52 is perpendicular to the surface of the grating 53. The grating 53 can achieve the regulation of the infrared radiation output wavelength and the beam quality by selecting specific grating 53 parameters. According to the shape of the periodic structure, the grating 53 can be divided into two categories: ruled grating 53 and holographic grating 53. Preferably, the holographic grating 53 has a higher diffraction efficiency.

[0082] The focusing lens 54 is connected to the grating 53 and is used to focus the infrared radiation regulated by the grating 53 and irradiate the focused infrared radiation to the epoxy material 10 to repair defects of the epoxy material 10 .

[0083] Exemplarily, the focusing lens 54 is coaxially opposite to the optical center of the grating 53, and the focusing lens 54 focuses the infrared light regulated by the grating 53, and the focused light is irradiated on the epoxy material 10 to heat the defective part of the epoxy material 10. The focusing lens 54 is preferably a convex lens 52.

[0084] From the above description, it can be seen that the present invention generates infrared radiation through a focusing device and focuses it on the defective epoxy material, thereby achieving accurate repair of defects. The penetrability and heating effect of infrared radiation can effectively improve the defect state of the epoxy material and improve the overall performance of the material. At the same time, the accuracy and stability of the focusing device also ensure the reliability and efficiency of the repair process.

[0085] like Figure 4 As shown, Figure 4 A schematic diagram of a process flow of an embodiment of an epoxy material defect repair method based on infrared focused heating provided by the present invention. A method for repairing epoxy material defects based on infrared focused heating, the method comprising:

[0086] S101: Collecting epoxy material image data.

[0087] For example, referring to Figure 2 , read the defective epoxy material image data from the camera through the bus of the image acquisition card 1.

[0088] S102: Detecting the state information of the epoxy material, and obtaining the epoxy material information according to the epoxy material image data.

[0089] Exemplarily, the defect locator 2 detects the state information of the epoxy material 10, and the epoxy material image data acquired by the image acquirer 1 is used to process, observe, analyze and output the epoxy material image data to acquire the epoxy material information.

[0090] S103: Obtain epoxy material defect data according to the epoxy material information, and match the optimal repair data with the current epoxy material defect data.

[0091] Exemplarily, epoxy material defect samples are input into an epoxy material database to form a training set, and the epoxy material defect samples are stored in the epoxy material database after passing through a classification network, a detection network, and a segmentation network, thereby completing the training of the epoxy material defect samples; the trained epoxy material defect samples are stored in the epoxy material database; the epoxy material information is used as a test set of the epoxy material database, and the epoxy material information is passed through a classification network to determine the epoxy material defect type; the time domain and frequency domain characteristics of the epoxy material defect data in the epoxy material defect type are extracted to obtain defective epoxy material feature data; and the optimal repair data matching the defective epoxy material is determined based on the current defective epoxy material feature data.

[0092] S104: Outputting a repair signal for repairing the epoxy material according to the optimal repair data.

[0093] Exemplarily, based on the deep learning supervision method, the defect data of the epoxy material 10 is obtained according to the information of the epoxy material 10, and the optimal repair data is matched by the current defect data of the epoxy material 10. According to the optimal repair data, a repair signal such as the repair trajectory of the focusing device 5, the wavelength of the infrared light source laser, the angle of the laser, and the power of the laser is output.

[0094] S105: Generate infrared radiation according to the repair signal, and focus the infrared radiation to the defective epoxy material to repair the defective epoxy material.

[0095] Exemplarily, the output laser parameters are adjusted according to the repair signal to generate infrared radiation with a thermal radiation effect; the infrared radiation is output as a parallel beam; the output wavelength and beam quality of the infrared radiation are grating-controlled; the grating-controlled infrared radiation is converged and the converged infrared radiation is irradiated on a defective epoxy material to repair the defective epoxy material.

[0096] From the above description, it can be seen that the present invention uses image processing and analysis algorithms to detect defect status information in epoxy materials in real time, and obtains epoxy material information based on epoxy material image data. Further, epoxy material defect data is quickly obtained based on epoxy material information, and the optimal repair data is found through a matching algorithm. Further, a repair signal is output based on the optimal repair data, and the operation of the focusing device is accurately controlled to ensure that the infrared radiation can be accurately focused on the defective epoxy material, thereby improving the repair effect. Finally, the infrared radiation is focused on the defective epoxy material, achieving accurate repair of the defect.

[0097] like Figure 5 As shown, Figure 5 A schematic diagram of a process flow of an embodiment of an epoxy material defect repair method based on infrared focused heating provided by the present invention. A method for repairing epoxy material defects based on infrared focused heating, the method comprising:

[0098] S201: Collecting epoxy material image data.

[0099] S202: Detecting status information of the epoxy material, and acquiring epoxy material information according to the epoxy material image data.

[0100] It should be noted that steps S201-S202 are Figure 4 This has been discussed in detail in the implementation scenario shown and will not be repeated here.

[0101] S203: Inputting epoxy material defect samples into the epoxy material database to form a training set. The epoxy material defect samples are stored in the epoxy material database after passing through the classification network, the detection network, and the segmentation network, thereby completing the training of the epoxy material defect samples.

[0102] For example, a large number of epoxy material defect samples are input into the console epoxy material database to form a training set; the training set (D train ):

[0103]

[0104] Among them, X i is the epoxy material defect sample, Y i is the corresponding defect label, and N is the number of samples.

[0105] Furthermore, the input epoxy material defect samples are stored in the epoxy material database of the console after passing through the classification network, the detection network, and the segmentation network, completing the training of the epoxy material defect training set; the training set is input into the classification, detection, and segmentation networks through the following formula:

[0106] F train =Train(D tratin ,Siamese Network,Detection Network,SegmentationNetwork);

[0107] Among them, F train is the epoxy material defect sample after training, Train() is the training operation, D train is the training set, Siamese Network is the classification network, Detection Network is the detection network, and Segmentation Network is the segmentation network.

[0108] S204: The trained epoxy material defect samples are stored in the epoxy material database.

[0109] For example, the trained model is stored in the console database:

[0110] D database ←F train ;

[0111] Among them, D database For the console database, F train These are the epoxy material defect samples after training.

[0112] S205: The epoxy material information is used as a test set of the epoxy material database, and the epoxy material information is classified through a classification network to determine the epoxy material defect type.

[0113] Exemplarily, the epoxy material data after entering the console data collector is a test set of the console epoxy material database;

[0114] Epoxy Material Data (X test ) as the test set:

[0115] D test ={X test}∈D database ;

[0116] Among them, D test is the test set, X test is the epoxy material data, D database For the console database.

[0117] Further, the current epoxy material information data enters the classification network constructed by the Siamese network to determine whether the epoxy material contains defects and obtain the type of defects;

[0118] Whether there are defects is determined by the following formula:

[0119] E W (X,X test )=∥G W (X)-G W (X test )∥;

[0120] Among them, X is the information data of epoxy material without defects, Xtest is the current information data of epoxy material; G W (X) is a parameterized function.

[0121] When E W (X,X test )>0, indicating that the epoxy material contains defect information;

[0122] When E W (X,X test )=0, indicating that the epoxy material does not contain defect information.

[0123] The defect type (Y pred ):

[0124] Y pred =Siamese Network(E W (X,X test ));

[0125] Among them, Y pred is the defect type, Siamese Network is the classification network, E W (X,X test ) is the epoxy material defect data.

[0126] S206: Extracting time domain and frequency domain features of epoxy material defect data in the epoxy material defect type, and obtaining defective epoxy material feature data.

[0127] Exemplarily, the fast Fourier transform FFT and variational mode decomposition VMD are combined to extract the time domain and frequency domain characteristics of the epoxy material defect data and obtain the defective epoxy material characteristic data.

[0128] S207: stacking the current defective epoxy material feature data to form a high-dimensional tensor.

[0129] Exemplarily, the current defective epoxy material feature data is stacked to form a high-dimensional tensor:

[0130]

[0131] Among them, x n is the characteristic data of defective epoxy material of the nth sample, X stacked is a high-dimensional tensor.

[0132] S208: Determine two-dimensional data of defective epoxy material according to the high-dimensional tensor.

[0133] For example, a high-dimensional tensor is input to the SWinTransformer model. The input (X input ) is determined by the following formula:

[0134] X input =X stacked ∈R H×W×C ;

[0135] Among them, H is the height of the two-dimensional data of the defective epoxy material, W is the width of the two-dimensional data of the defective epoxy material, and C is the number of channels of the two-dimensional data of the defective epoxy material.

[0136] Furthermore, the window attention mechanism is used to extract the defective epoxy material 2D data.

[0137] The window attention mechanism in SWinTransformer can be expressed as:

[0138]

[0139] Among them, Z i,j is the two-dimensional data of defective epoxy materials, Q, K, V are query, key and value matrices respectively, W i,j is the area within the window, d k The dimension of the key.

[0140] S209: Extract local features of defective epoxy material 2D data using window attention mechanism.

[0141] For example, after multiple layers of window attention mechanism, combined with convolutional layers, the local features F of the two-dimensional data of defective epoxy materials are extracted:

[0142]

[0143] in, is the feature extraction function, and Conv is the convolution operation.

[0144] S210: Local features of the defective epoxy material two-dimensional data are detected through a detection network to obtain epoxy material defect results.

[0145] For example, the specific epoxy material defect result P outputted is defect Determined according to the following formula:

[0146] P defect =DetectionNetwork(F,Y pred );

[0147] Among them, Detection Network is the detection network, Y pred is the defect type, which is the output of step S205.

[0148] S211: The epoxy material defect result corrects the defect area on the surface of the epoxy material through the segmentation network, and determines the optimal repair data matching the defective epoxy material.

[0149] For example, the epoxy material information data in the epoxy material defect result is segmented by the segmentation network to correct the defect area from the background to obtain the optimal repair data S defect , including epoxy material defect location, category, attributes and other information of defects.

[0150] S defect =SegmentationNetwork(X test ,P pred );

[0151] Among them, X test For the current epoxy material information data, P pred Correction data for correcting defective epoxy materials.

[0152] S212: Outputting a repair signal for repairing the defective epoxy material according to the optimal repair data.

[0153] It should be noted that step S212 Figure 4 This has been discussed in detail in the implementation scenario shown and will not be repeated here.

[0154] like Figure 6 As shown, Figure 6 A schematic diagram of a process flow of an embodiment of an epoxy material defect repair method based on infrared focused heating provided by the present invention. A method for repairing epoxy material defects based on infrared focused heating, the method comprising:

[0155] S301: adjusting the outgoing laser parameters according to the repair signal to generate infrared radiation with thermal radiation effect.

[0156] For example, referring to Figure 1 , according to the repair signal such as the wavelength of the laser emitted by the infrared light source 51, the angle of the laser emitted, the intensity of the laser emitted, etc., the parameters of the laser emitted are adjusted to generate infrared radiation with a thermal radiation effect.

[0157] S302: Outputting infrared radiation in a parallel light beam.

[0158] Exemplarily, the infrared radiation with thermal radiation effect emitted by the infrared light source 51 is incident from the focus of one end of the convex lens 52, and the incident light beam passes through the convex lens 52 and is output from the other end as a parallel light beam.

[0159] S303: Perform grating control on the infrared radiation output wavelength and beam quality.

[0160] Exemplarily, the parallel light beam emitted from the convex lens 52 is perpendicular to the surface of the grating 53 , and the grating 53 is used to control the infrared radiation output wavelength and the light beam quality.

[0161] S304: Converging the infrared radiation regulated by the grating and irradiating the converged infrared radiation to the defective epoxy material to repair the defective epoxy material.

[0162] Exemplarily, the infrared radiation with thermal radiation effect regulated by the grating 53 is converged by the focusing lens 54, and the converged light is irradiated on the defect of the defective epoxy material 10 by utilizing the excellent deep penetration of infrared rays; when the wavelength of the emitted infrared rays is consistent with the absorption wavelength of the heated defective epoxy material 10, the heated epoxy material 10 is continuously irradiated with infrared rays; after the molecules and atoms inside the epoxy material 10 absorb the radiation energy of the infrared wavelength, the molecules and atoms inside the epoxy material 10 "resonate" at this time - strong vibration and rotation are generated, which not only produces a transition of the energy level from the ground state to the excited state, but also enhances the amplitude of various motions centered on the equilibrium position, increases the dipole moment (the product of the center distance of the positive and negative charges and the charge carried by the charge center), and increases the internal energy of the particle; the macroscopic reflection of the intensified motion of the microstructure particles is the increase in the temperature of the epoxy material 10; because the epoxy material 10 has the ability to self-repair under photothermal conditions, as the focused laser signal continues to provide photothermal energy, the defects of the epoxy material 10 are gradually repaired.

[0163] S305: Detect the status information of the epoxy material in real time and obtain the repair status of the epoxy material until the epoxy material is completely repaired.

[0164] Illustratively, as the defects of the epoxy material 10 are repaired, the focusing controller 4 corrects the parameters of the laser signal in real time according to the defect status. For example, the parameters output by the focusing controller 4 before the defect repair produce a stronger photothermal laser signal for the infrared light source 51. As the repair progresses, the defects of the epoxy material 10 are gradually repaired, and the parameters output by the focusing controller 4 cause the photothermal signal generated by the infrared light source 51 to gradually become a weaker photothermal laser signal until all the defects of the epoxy material 10 are repaired.

[0165] S306: Stop heating and wait for the epoxy material to cool down before checking the repair effect.

[0166] like Figure 7 As shown, Figure 7 The structure diagram of an embodiment of the medium provided by the present invention is shown in FIG. The medium 20 stores at least one computer program 21, which is executed by a processor to implement the following Figure 4 , Figure 5 and Figure 6 In one embodiment, the medium 20 may be a storage chip, a hard disk, a mobile hard disk, a USB flash drive, an optical disk, or other readable and writable storage tools, or a server, etc.

[0167] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0168] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0169] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device, and non-volatile computer storage medium will not be repeated here.

[0170] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0171] For the convenience of description, the above device is described by being divided into various units according to their functions and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware. It should be understood by those skilled in the art that this specification embodiment can be provided as a method, system, or computer program product. Therefore, this specification embodiment can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification embodiment can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] This specification is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0175] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0176] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0177] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0178] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0179] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0180] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0181] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. An epoxy material defect repair device based on infrared focused heating, characterized in that: The device comprises: an image collector, a defect locator, a control console, a focusing controller, and a focusing device. The image collector is connected to the console and is used to collect epoxy material image data; The defect locator is connected to the image collector and is used to detect the state information of the epoxy material and obtain the epoxy material information according to the epoxy material image data; The console is connected to the focus controller and is used to obtain epoxy material defect data according to the epoxy material information, and match the optimal repair data with the current epoxy material defect data; The focusing controller is connected to the focusing device and is used to output a repair signal for the focusing device to repair the defective epoxy material according to the optimal repair data; The focusing device is installed above the defect locator, and is used for generating infrared radiation according to the repair signal, and focusing the infrared radiation to the defective epoxy material to perform defect repair on the defective epoxy material.

2. The epoxy material defect repairing device based on infrared focused heating according to claim 1 is characterized in that: The focusing device specifically includes: an infrared light source, a convex lens, a grating, and a focusing lens. The infrared light source is used to adjust the output laser parameters according to the repair signal to generate infrared radiation with thermal radiation effect; The infrared light source is placed at the focal point of one end of the convex lens, and is used to output the infrared radiation in a parallel light beam; The grating is coaxially opposite to the optical center of the convex lens, and is used to make the parallel light beam perpendicular to the grating surface, so as to complete the grating control of the infrared radiation output wavelength and beam quality; The focusing lens is connected to the grating, and is used for converging the infrared radiation regulated by the grating and irradiating the converged infrared radiation to the defective epoxy material, so as to repair the defective epoxy material.

3. The epoxy material defect repairing device based on infrared focused heating according to claim 2 is characterized in that: The device further specifically comprises: A stage, with the upper side of the stage facing the defect locator, is used for placing the epoxy material.

4. A method for repairing epoxy material defects based on infrared focused heating, characterized in that: The method comprises: Collect epoxy material image data; Detecting status information of the epoxy material, and acquiring epoxy material information according to the epoxy material image data; Acquire epoxy material defect data according to the epoxy material information, and match optimal repair data with the current epoxy material defect data; Outputting a repair signal for repairing the epoxy material according to the optimal repair data; Infrared radiation is generated according to the repair signal, and the infrared radiation is focused onto the defective epoxy material to repair the defective epoxy material.

5. The method for repairing epoxy material defects based on infrared focused heating according to claim 4, characterized in that: After generating infrared radiation according to the repair signal and focusing the infrared radiation to the defective epoxy material to repair the defective epoxy material, the method further specifically includes: Detecting the status information of the epoxy material in real time and obtaining the repair status of the epoxy material until the defects of the epoxy material are completely repaired; Stop heating and allow the epoxy to cool before inspecting the repair.

6. The method for repairing epoxy material defects based on infrared focused heating according to claim 4, characterized in that: The step of acquiring epoxy material defect data according to the epoxy material information and matching optimal repair data with the current epoxy material defect data specifically includes: Inputting epoxy material defect samples into the epoxy material database to form a training set, the epoxy material defect samples are stored in the epoxy material database after passing through the classification network, the detection network, and the segmentation network, and the training of the epoxy material defect samples is completed; The trained epoxy material defect samples are stored in the epoxy material database; The epoxy material information is used as a test set of the epoxy material database, and the epoxy material information is passed through the classification network to determine the epoxy material defect type; Extracting time domain and frequency domain characteristics of epoxy material defect data in the epoxy material defect type to obtain defective epoxy material feature data; The optimal repair data matching the defective epoxy material is determined according to the current characteristic data of the defective epoxy material.

7. The method for repairing epoxy material defects based on infrared focused heating according to claim 6, characterized in that: The determining of the optimal repair data matching the defective epoxy material according to the current characteristic data of the defective epoxy material specifically includes: Stacking the current defective epoxy material feature data to form a high-dimensional tensor; Determine two-dimensional data of defective epoxy material according to the high-dimensional tensor; Using a window attention mechanism to extract local features of the two-dimensional data of the defective epoxy material; The local features of the defective epoxy material two-dimensional data are passed through the detection network to obtain epoxy material defect results; The epoxy material defect result is used to correct the defective area on the surface of the epoxy material through the segmentation network, and the optimal repair data matching the defective epoxy material is determined.

8. The method for repairing epoxy material defects based on infrared focused heating according to claim 7, characterized in that: The step of generating infrared radiation according to the repair signal and focusing the infrared radiation onto the defective epoxy material to repair the defective epoxy material specifically includes: adjusting the outgoing laser parameters according to the repair signal to generate infrared radiation with thermal radiation effect; Outputting the infrared radiation in a parallel beam; Performing grating control on the infrared radiation output wavelength and beam quality; The infrared radiation regulated by the grating is converged and irradiated to the defective epoxy material to repair the defective epoxy material.

9. The method for repairing epoxy material defects based on infrared focused heating according to claim 8, characterized in that: The infrared radiation regulated by the focusing grating is irradiated to the epoxy material to repair defects of the epoxy material, specifically including: Converging the infrared radiation after grating control, and irradiating the converged light onto the epoxy material; When the infrared wavelength of the infrared radiation after grating adjustment is consistent with the absorption wavelength of the heated epoxy material, the temperature of the epoxy material increases and the defects of the epoxy material are repaired.

10. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 4 to 9.

Images