A defect detection method and system based on capacitive imaging

Abstract

The present invention relates to the technical field of defect detection and analysis, and in particular to a defect detection method and system based on capacitive imaging. The present invention constructs a composite material attribute analysis model according to historical material attribute data, imports the material attribute data into the composite material attribute analysis model to analyze the material attributes of the composite material; constructs a composite material bonding layer analysis model according to historical bonding data, imports the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer; constructs a capacitive defect analysis model according to historical capacitive defect detection image data, imports the capacitive defect detection image data into the capacitive defect analysis model to analyze the composite material bonding layer defects; constructs a composite material defect risk prediction model to be detected, and predicts the defect risk of the composite material to be detected. The composite material production process can be optimized, the cost of capacitive imaging defect detection can be saved, and the efficiency of composite material defect detection can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of defect detection and analysis, and in particular to a defect detection method and system based on capacitive imaging. Background Art

[0002] Capacitive imaging technology is a non-destructive testing technology based on the capacitive edge effect coupled electric field. It uses a set of sensor array electrodes installed on the object to form a spatial sensitive field, and reflects the distribution change of the dielectric constant inside the object by measuring the capacitance change between different electrodes, thereby realizing the detection of internal defects or structural changes of the object.

[0003] Using capacitive imaging technology to detect defects in the bonding layer of composite materials is an efficient and non-contact detection method, which is particularly suitable for detecting tiny defects in the bonding layer, such as debonding, bubbles, cracks, etc. Defects inside the bonding layer of composite materials will lead to a decrease in the overall strength and stiffness of the composite material, so that the defects inside the bonding layer of the composite material become stress concentration areas. If subjected to external loads, it is more likely to cause damage to the composite material than other locations of other composite materials. Therefore, it is necessary to use capacitive imaging technology to detect defects in the produced composite materials to help manufacturers troubleshoot defective composite materials.

[0004] However, the existing capacitive imaging defect detection technology does not take into account the impact of the material properties of adhesives and composite materials on the formation of internal defects in the composite bonding layer. The existing technology only determines the location and size of defects through simple capacitive imaging, and cannot help producers optimize the composite production process in a targeted manner, nor can it improve the efficiency of defect detection in the composite production line.

[0005] In order to solve these problems, the present application designs a defect detection method and system based on capacitive imaging. Summary of the invention

[0006] In order to overcome the defects and shortcomings of the prior art, the present invention provides a defect detection method and system based on capacitive imaging, which analyzes the material properties of the composite material and the adhesive layer of the composite material; analyzes the defects of the adhesive layer of the composite material; constructs a defect risk prediction model for the composite material to be detected, and predicts the defect risk of the composite material to be detected. It can optimize the composite material production process, save the cost of capacitive imaging defect detection, and improve the efficiency of composite material defect detection.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a defect detection method based on capacitive imaging, comprising the following steps:

[0009] S1, obtaining material property data and bonding data of the composite material, and obtaining historical material property data and historical bonding data of the historical composite material; and obtaining capacitance defect detection image data of the composite material and historical capacitance defect detection image data of the historical composite material through a capacitance sensor;

[0010] S2. construct a composite material property analysis model based on historical material property data, and import the material property data into the composite material property analysis model to analyze the material properties of the composite material;

[0011] S3, constructing a composite material bonding layer analysis model based on historical bonding data, and importing the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer;

[0012] S4, constructing a capacitor defect analysis model based on historical capacitor defect detection image data, and importing the capacitor defect detection image data into the capacitor defect analysis model to analyze the defects of the composite material bonding layer;

[0013] S5. Construct a defect risk prediction model for the composite material to be tested based on the material property analysis results, the bonding layer analysis results and the capacitor defect analysis results, and predict the defect risk of the composite material to be tested.

[0014] In one implementation of the present invention, step S2 includes the following specific steps:

[0015] S21, obtaining material property data of the composite material and historical material property data of the historical composite material;

[0016] S22, substituting the material property data and the historical material property data into the material property difference coefficient calculation formula to calculate the material property difference coefficient of the composite material; the material property difference coefficient calculation formula is:

[0017] ;

[0018] Where cs is the material property difference coefficient of the composite material, c is the surface roughness of the composite material in the material property data, h is the surface curvature of the composite material in the material property data, and w represents the weight of the composite material in the material property data. represents the surface roughness of the i-th historical composite material of historical material attribute data, represents the surface radian of the i-th historical composite material of historical material attribute data, It represents the weight of the i-th historical composite material in the historical material attribute data, n represents the number of historical composite materials, and i is any one from 1 to n.

[0019] In one implementation of the present invention, step S3 includes the following specific steps:

[0020] S31, obtaining bonding data of the composite material and historical bonding data of the historical composite material;

[0021] S32, substituting the bonding data and the historical bonding data into a bonding difference coefficient calculation formula to calculate the bonding difference coefficient of the composite material bonding layer, wherein the bonding difference coefficient calculation formula is:

[0022] ;

[0023] Wherein zj represents the bonding difference coefficient of the bonding layer of the composite material, P represents the amount of adhesive used when bonding the composite material in the bonding data, s represents the area of ​​the bonding region of the composite material in the bonding data, T represents the curing temperature of the adhesive when bonding the composite material in the bonding data, t represents the curing time of the adhesive when bonding the composite material in the bonding data, represents the amount of adhesive used when bonding the i-th historical composite material in the historical bonding data, represents the area of ​​the i-th historical composite material bonding region in the historical bonding data, represents the curing temperature of the adhesive when bonding the i-th historical composite material in the historical bonding data, It represents the curing time of the adhesive when bonding the i-th historical composite material in the historical bonding data.

[0024] In one implementation of the present invention, step S4 includes the following specific steps:

[0025] S41, acquiring capacitance defect detection image data of composite materials and historical capacitance defect detection image data of historical composite materials;

[0026] S42, substituting the capacitor defect detection image data and the historical capacitor defect detection image data into a defect detection difference coefficient calculation formula to calculate the defect detection difference coefficient of the composite material bonding layer, the bonding layer defect detection difference coefficient calculation formula is:

[0027] ;

[0028] Where qx ​​represents the defect detection difference coefficient of the composite material bonding layer, q is the number of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, r is the number of pixels of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, and R is the total number of pixels in the composite material capacitor defect detection image. is the number of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the number of pixels of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the total number of pixels in the i-th historical composite material capacitor defect detection image, They represent the defect number influencing factor and defect area influencing factor respectively;

[0029] S43. Using the defect detection difference coefficient of the composite material bonding layer as the defect risk coefficient of the composite material bonding layer.

[0030] In one implementation of the present invention, step S5 includes the following specific steps:

[0031] S51, obtaining composite material defect sample data for training a composite material defect risk prediction model to be detected, wherein the composite material defect sample data includes material property difference coefficients of multiple composite materials and bonding difference coefficients of multiple composite material bonding layers and a defect risk coefficient obtained by calculation, dividing the composite material defect sample data for training the composite material defect risk prediction model to be detected into a defect sample training set and a defect sample test set, constructing a regression network model, using the material property difference coefficient and the bonding difference coefficient in the defect sample training set as inputs of the regression network model, using the defect risk coefficient in the defect sample training set as outputs of the regression network model, training the regression network model to obtain an initial regression network model; evaluating the model effect of the initial regression network model using an average error algorithm, and selecting a corresponding initial regression network model with a value greater than or equal to a preset evaluation value as the composite material defect risk prediction model to be detected;

[0032] S52, calculating the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested, inputting the calculated material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested into a defect risk prediction model for the composite material to be tested, and outputting the predicted defect risk coefficient of the bonding layer of the composite material to be tested.

[0033] In one implementation of the present invention, step S5 further includes the following specific steps:

[0034] S53, obtaining the predicted defect risk coefficient of the bonding layer of the composite material to be tested;

[0035] S54, presetting a defect risk threshold, and when the predicted defect risk coefficient of the bonding layer of the composite material to be inspected is less than or equal to the defect risk threshold, completing defect inspection of the composite material to be inspected;

[0036] S55. When the predicted defect risk coefficient of the bonding layer of the composite material to be tested is greater than the defect risk threshold, obtain the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested; preset the material property difference threshold and the bonding difference threshold, and when the material property difference coefficient of the composite material to be tested is greater than the material property difference threshold, issue an abnormal instruction to the producer that there is an abnormality in the surface treatment stage of the composite material, and reprocess the composite material; when the bonding difference coefficient of the bonding layer of the composite material to be tested is greater than the bonding difference threshold, issue an abnormal instruction to the producer that there is an abnormality in the bonding stage of the composite material, and reprocess the composite material.

[0037] In a second aspect, an embodiment of the present invention further provides a defect detection system based on capacitive imaging, comprising:

[0038] A data acquisition module is used to acquire material property data and bonding data of the composite material, and also to acquire historical material property data and historical bonding data of the historical composite material; and to acquire capacitance defect detection image data of the composite material and historical capacitance defect detection image data of the historical composite material through a capacitance sensor;

[0039] A composite material property analysis module is used to construct a composite material property analysis model based on historical material property data, and to import the material property data into the composite material property analysis model to analyze the material properties of the composite material;

[0040] A composite material bonding layer analysis module is used to construct a composite material bonding layer analysis model based on historical bonding data, and to import the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer;

[0041] A capacitance imaging defect analysis module is used to construct a capacitance defect analysis model based on historical capacitance defect detection image data, and import the capacitance defect detection image data into the capacitance defect analysis model to analyze the defects of the bonding layer of the composite material;

[0042] A defect risk prediction module is used to construct a defect risk prediction model for the composite material to be tested based on the material property analysis results, the bonding layer analysis results and the capacitance defect analysis results of the composite material, and to predict the defect risk of the composite material to be tested;

[0043] A control module is used to control the operation of the data acquisition module, the composite material property analysis module, the composite material bonding layer analysis module, the capacitive imaging defect analysis module and the defect risk prediction module.

[0044] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a defect detection method based on capacitive imaging by calling the computer program stored in the memory.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a defect detection method based on capacitive imaging.

[0046] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0047] The present invention constructs a composite material attribute analysis model according to historical material attribute data, imports the material attribute data into the composite material attribute analysis model to analyze the material attributes of the composite material; constructs a composite material bonding layer analysis model according to historical bonding data, imports the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer; constructs a capacitance defect analysis model according to historical capacitance defect detection image data, imports the capacitance defect detection image data into the capacitance defect analysis model to analyze the composite material bonding layer defects; constructs a composite material defect risk prediction model to be detected, and predicts the defect risk of the composite material to be detected. It can optimize the composite material production process, save the cost of capacitance imaging defect detection, and improve the efficiency of composite material defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0049] Figure 1 It is a schematic diagram of the overall process of a defect detection method based on capacitive imaging of the present invention;

[0050] Figure 2 It is a flow chart of the bonding process of composite materials in a defect detection method based on capacitive imaging of the present invention;

[0051] Figure 3 It is a structural schematic diagram of a defect detection system based on capacitive imaging of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0053] Example 1

[0054] like Figure 1 As shown, this embodiment provides a defect detection method based on capacitive imaging, which specifically includes the following steps:

[0055] S1, obtaining material property data and bonding data of the composite material, and obtaining historical material property data and historical bonding data of the historical composite material; and obtaining capacitance defect detection image data of the composite material and historical capacitance defect detection image data of the historical composite material through a capacitance sensor;

[0056] S2. construct a composite material property analysis model based on historical material property data, and import the material property data into the composite material property analysis model to analyze the material properties of the composite material;

[0057] In this embodiment, step S2 includes the following specific steps:

[0058] S21, obtaining material property data of the composite material and historical material property data of the historical composite material;

[0059] S22, substituting the material property data and the historical material property data into the material property difference coefficient calculation formula to calculate the material property difference coefficient of the composite material; the material property difference coefficient calculation formula is:

[0060] ;

[0061] Where cs is the material property difference coefficient of the composite material, c is the surface roughness of the composite material in the material property data, h is the surface curvature of the composite material in the material property data, and w represents the weight of the composite material in the material property data. represents the surface roughness of the i-th historical composite material of historical material attribute data, represents the surface radian of the i-th historical composite material of historical material attribute data, It represents the weight of the i-th historical composite material in the historical material attribute data, n represents the number of historical composite materials, and i is any one from 1 to n.

[0062] In this embodiment, the surface roughness of the composite material can increase the contact area between the adhesive and the adherend, forming more mechanical locking points, thereby improving the bonding strength. However, if the roughness is too large, the adhesive may not be able to fully fill the surface depressions, forming gaps, which will reduce the bonding strength, thereby causing defects in the composite bonding layer. When the surface curvature of the bonding area of ​​the composite material is large, it will also increase the difficulty of bonding the composite material, so that part of the bonding area of ​​the bonding layer is not covered with the adhesive, resulting in cavities in the bonding layer. Among them, the surface roughness of the composite material is measured by a high-precision roughness meter, and the surface curvature of the composite material is measured by an electronic digital display curvature measuring instrument.

[0063] S3, constructing a composite material bonding layer analysis model based on historical bonding data, and importing the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer;

[0064] In this embodiment, step S3 includes the following specific steps:

[0065] S31, obtaining bonding data of the composite material and historical bonding data of the historical composite material;

[0066] S32, substituting the bonding data and the historical bonding data into a bonding difference coefficient calculation formula to calculate the bonding difference coefficient of the composite material bonding layer, wherein the bonding difference coefficient calculation formula is:

[0067] ;

[0068] Wherein zj represents the bonding difference coefficient of the bonding layer of the composite material, P represents the amount of adhesive used when bonding the composite material in the bonding data, s represents the area of ​​the bonding region of the composite material in the bonding data, T represents the curing temperature of the adhesive when bonding the composite material in the bonding data, t represents the curing time of the adhesive when bonding the composite material in the bonding data, represents the amount of adhesive used when bonding the i-th historical composite material in the historical bonding data, represents the area of ​​the i-th historical composite material bonding region in the historical bonding data, represents the curing temperature of the adhesive when bonding the i-th historical composite material in the historical bonding data, It represents the curing time of the adhesive when bonding the i-th historical composite material in the historical bonding data.

[0069] S4, constructing a capacitor defect analysis model based on historical capacitor defect detection image data, and importing the capacitor defect detection image data into the capacitor defect analysis model to analyze the defects of the composite material bonding layer;

[0070] In this embodiment, the composite material adhesive includes but is not limited to: epoxy resin adhesive, polyurethane-based adhesive, acrylic-based adhesive; when bonding the composite material, the various parts of the composite material are firmly connected together by the adhesive to form an integral structure, which can enhance the interface strength between the composite materials and improve the mechanical properties of the overall structure. However, the adhesive may produce defects such as bubbles and pores during the curing process, and these defects may appear as changes in dielectric constants in capacitive imaging detection. Therefore, when performing defect detection on finished composite materials through capacitive imaging, it is necessary to consider the effect of the amount of adhesive and the area of ​​use on the defects.

[0071] In this embodiment, step S4 includes the following specific steps:

[0072] S41, acquiring capacitance defect detection image data of composite materials and historical capacitance defect detection image data of historical composite materials;

[0073] S42, substituting the capacitor defect detection image data and the historical capacitor defect detection image data into a defect detection difference coefficient calculation formula to calculate the defect detection difference coefficient of the composite material bonding layer, the bonding layer defect detection difference coefficient calculation formula is:

[0074] ;

[0075] Where qx ​​represents the defect detection difference coefficient of the composite material bonding layer, q is the number of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, r is the number of pixels of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, and R is the total number of pixels in the composite material capacitor defect detection image. is the number of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the number of pixels of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the total number of pixels in the i-th historical composite material capacitor defect detection image, They respectively represent the defect number influencing factor and the defect area influencing factor, which are set by those skilled in the art according to actual needs. The preferred way to set the influencing factor values ​​is: obtain 5000 sets of capacitance defect detection image data of composite materials and the corresponding historical capacitance defect detection image data of all historical composite materials, and obtain the defect detection results of the composite material bonding layer; and obtain the defect detection difference coefficient of the composite material bonding layer through the capacitance defect detection image data of the composite material and the corresponding historical capacitance defect detection image data of all historical composite materials, import the calculated defect detection difference coefficient of the composite material bonding layer and the defect detection results of the composite material bonding layer into the fitting software, and output the values ​​of the defect number influencing factor and the defect area influencing factor that meet the highest judgment accuracy;

[0076] S43. Using the defect detection difference coefficient of the composite material bonding layer as the defect risk coefficient of the composite material bonding layer.

[0077] S5. Construct a defect risk prediction model for the composite material to be tested based on the material property analysis results, the bonding layer analysis results and the capacitor defect analysis results, and predict the defect risk of the composite material to be tested.

[0078] In this embodiment, step S5 includes the following specific steps:

[0079] S51, obtaining composite material defect sample data for training a composite material defect risk prediction model to be detected, wherein the composite material defect sample data includes material property difference coefficients of multiple composite materials and bonding difference coefficients of multiple composite material bonding layers and a defect risk coefficient obtained by calculation, dividing the composite material defect sample data for training the composite material defect risk prediction model to be detected into a defect sample training set and a defect sample test set, constructing a regression network model, using the material property difference coefficient and the bonding difference coefficient in the defect sample training set as inputs of the regression network model, using the defect risk coefficient in the defect sample training set as outputs of the regression network model, training the regression network model to obtain an initial regression network model; evaluating the model effect of the initial regression network model using an average error algorithm, and selecting a corresponding initial regression network model with a value greater than or equal to a preset evaluation value as the composite material defect risk prediction model to be detected;

[0080] S52, calculating the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested, inputting the calculated material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested into a defect risk prediction model for the composite material to be tested, and outputting the predicted defect risk coefficient of the bonding layer of the composite material to be tested.

[0081] In this embodiment, step S5 further includes the following specific steps:

[0082] S53, obtaining the predicted defect risk coefficient of the bonding layer of the composite material to be tested;

[0083] S54, presetting a defect risk threshold, and when the predicted defect risk coefficient of the bonding layer of the composite material to be inspected is less than or equal to the defect risk threshold, completing defect inspection of the composite material to be inspected;

[0084] S55, such as Figure 2 As shown, when the predicted defect risk coefficient of the bonding layer of the composite material to be tested is greater than the defect risk threshold, the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested are obtained; the material property difference threshold and the bonding difference threshold are preset, and when the material property difference coefficient of the composite material to be tested is greater than the material property difference threshold, an abnormal instruction is issued to the producer in the surface treatment stage of the composite material, and the composite material is reprocessed; when the bonding difference coefficient of the bonding layer of the composite material to be tested is greater than the bonding difference threshold, an abnormal instruction is issued to the producer in the bonding stage of the composite material, and the composite material is reprocessed, wherein the defect risk threshold, the material property difference threshold and the bonding difference threshold are all set by technical personnel in this field according to specific circumstances and actual needs.

[0085] Example 2

[0086] like Figure 3 As shown, this embodiment provides a defect detection system based on capacitive imaging, including:

[0087] A data acquisition module is used to acquire material property data and bonding data of the composite material, and also to acquire historical material property data and historical bonding data of the historical composite material; and to acquire capacitance defect detection image data of the composite material and historical capacitance defect detection image data of the historical composite material through a capacitance sensor;

[0088] A composite material property analysis module is used to construct a composite material property analysis model based on historical material property data, and to import the material property data into the composite material property analysis model to analyze the material properties of the composite material;

[0089] A composite material bonding layer analysis module is used to construct a composite material bonding layer analysis model based on historical bonding data, and to import the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer;

[0090] A capacitance imaging defect analysis module is used to construct a capacitance defect analysis model based on historical capacitance defect detection image data, and import the capacitance defect detection image data into the capacitance defect analysis model to analyze the defects of the bonding layer of the composite material;

[0091] A defect risk prediction module is used to construct a defect risk prediction model for the composite material to be tested based on the material property analysis results, the bonding layer analysis results and the capacitance defect analysis results of the composite material, and to predict the defect risk of the composite material to be tested;

[0092] The control module is used to control the operation of the data acquisition module, the composite material property analysis module, the composite material bonding layer analysis module, the capacitance imaging defect analysis module and the defect risk prediction module.

[0093] In this embodiment, the composite material property analysis module is used to build a composite material property analysis model based on historical material property data, and import the material property data into the composite material property analysis model to analyze the material properties of the composite material; analyzing the material properties of the composite material includes the following specific steps:

[0094] Obtain material property data of composite materials and historical material property data of historical composite materials;

[0095] Substitute the material property data and the historical material property data into the material property difference coefficient calculation formula to calculate the material property difference coefficient of the composite material; the material property difference coefficient calculation formula is:

[0096] ;

[0097] Where cs is the material property difference coefficient of the composite material, c is the surface roughness of the composite material in the material property data, h is the surface curvature of the composite material in the material property data, and w represents the weight of the composite material in the material property data. represents the surface roughness of the i-th historical composite material of historical material attribute data, represents the surface radian of the i-th historical composite material of historical material attribute data, It represents the weight of the i-th historical composite material in the historical material attribute data, n represents the number of historical composite materials, and i is any one from 1 to n.

[0098] In this embodiment, the composite material bonding layer analysis module is used to construct a composite material bonding layer analysis model based on historical bonding data, and import the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer; analyzing the composite material bonding layer includes the following specific steps:

[0099] Obtain bonding data of composite materials and historical bonding data of historical composite materials;

[0100] The bonding data and historical bonding data are substituted into the bonding difference coefficient calculation formula to calculate the bonding difference coefficient of the composite material bonding layer. The bonding difference coefficient calculation formula is:

[0101] ;

[0102] Wherein zj represents the bonding difference coefficient of the bonding layer of the composite material, P represents the amount of adhesive used when bonding the composite material in the bonding data, s represents the area of ​​the bonding region of the composite material in the bonding data, T represents the curing temperature of the adhesive when bonding the composite material in the bonding data, t represents the curing time of the adhesive when bonding the composite material in the bonding data, represents the amount of adhesive used when bonding the i-th historical composite material in the historical bonding data, represents the area of ​​the i-th historical composite material bonding region in the historical bonding data, represents the curing temperature of the adhesive when bonding the i-th historical composite material in the historical bonding data, It represents the curing time of the adhesive when bonding the i-th historical composite material in the historical bonding data.

[0103] In this embodiment, the capacitance imaging defect analysis module is used to construct a capacitance defect analysis model based on historical capacitance defect detection images, and import the capacitance defect detection images into the capacitance defect analysis model to analyze the defects of the bonding layer of the composite material;

[0104] In this embodiment, analyzing defects in the bonding layer of the composite material includes the following specific steps:

[0105] Acquire capacitance defect detection image data of composite materials and historical capacitance defect detection image data of historical composite materials;

[0106] Substituting the capacitor defect detection image data and the historical capacitor defect detection image data into the defect detection difference coefficient calculation formula to calculate the defect detection difference coefficient of the composite material bonding layer, the bonding layer defect detection difference coefficient calculation formula is:

[0107] ;

[0108] Where qx ​​represents the defect detection difference coefficient of the composite material bonding layer, q is the number of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, r is the number of pixels of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, and R is the total number of pixels in the composite material capacitor defect detection image. is the number of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the number of pixels of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the total number of pixels in the i-th historical composite material capacitor defect detection image, They respectively represent the defect number influencing factor and the defect area influencing factor, which are set by those skilled in the art according to actual needs. The preferred way to set the influencing factor values ​​is: obtain 5000 sets of capacitance defect detection image data of composite materials and the corresponding historical capacitance defect detection image data of all historical composite materials, and obtain the defect detection results of the composite material bonding layer; and obtain the defect detection difference coefficient of the composite material bonding layer through the capacitance defect detection image data of the composite material and the corresponding historical capacitance defect detection image data of all historical composite materials, import the calculated defect detection difference coefficient of the composite material bonding layer and the defect detection results of the composite material bonding layer into the fitting software, and output the values ​​of the defect number influencing factor and the defect area influencing factor that meet the highest judgment accuracy;

[0109] The defect detection difference coefficient of the composite material bonding layer is used as the defect risk coefficient of the composite material bonding layer.

[0110] In this embodiment, the defect risk prediction module is used to construct a defect risk prediction model for the composite material to be detected based on the material property analysis results, the bonding layer analysis results and the capacitor defect analysis results of the composite material, and predict the defect risk of the composite material to be detected; predicting the defect risk of the composite material to be detected includes the following specific steps:

[0111] Obtain composite material defect sample data for training a composite material defect risk prediction model to be detected, wherein the composite material defect sample data includes material property difference coefficients of multiple composite materials and bonding difference coefficients of multiple composite material bonding layers obtained by calculation, and a defect risk coefficient; divide the composite material defect sample data for training the composite material defect risk prediction model to be detected into a defect sample training set and a defect sample test set; construct a regression network model; use the material property difference coefficient and the bonding difference coefficient in the defect sample training set as inputs of the regression network model; use the defect risk coefficient in the defect sample training set as outputs of the regression network model; train the regression network model to obtain an initial regression network model; evaluate the model effect of the initial regression network model using an average error algorithm, and select a corresponding initial regression network model with a value greater than or equal to a preset evaluation value as the composite material defect risk prediction model to be detected;

[0112] Calculate the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested, input the calculated material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested into the defect risk prediction model of the composite material to be tested, and output the predicted defect risk coefficient of the bonding layer of the composite material to be tested.

[0113] In this embodiment, predicting the defect risk of the composite material to be inspected further includes the following specific steps:

[0114] Obtaining the predicted defect risk coefficient of the bonding layer of the composite material to be tested;

[0115] A defect risk threshold is preset, and when the predicted defect risk coefficient of the bonding layer of the composite material to be inspected is less than or equal to the defect risk threshold, defect detection of the composite material to be inspected is completed;

[0116] like Figure 2 As shown, when the predicted defect risk coefficient of the bonding layer of the composite material to be tested is greater than the defect risk threshold, the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested are obtained; the material property difference threshold and the bonding difference threshold are preset, and when the material property difference coefficient of the composite material to be tested is greater than the material property difference threshold, an abnormal instruction is issued to the producer in the surface treatment stage of the composite material, and the composite material is reprocessed; when the bonding difference coefficient of the bonding layer of the composite material to be tested is greater than the bonding difference threshold, an abnormal instruction is issued to the producer in the bonding stage of the composite material, and the composite material is reprocessed, wherein the defect risk threshold, the material property difference threshold and the bonding difference threshold are all set by technical personnel in this field according to specific circumstances and actual needs.

[0117] The above-mentioned parameters in a defect detection system based on capacitive imaging of the present invention and the steps for each unit module to implement the corresponding functions can refer to the parameters and steps in the embodiment of a defect detection method based on capacitive imaging above, and will not be repeated here.

[0118] Example 3

[0119] An electronic device according to an embodiment of the present invention includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a defect detection method based on capacitive imaging by calling the computer program stored in the memory. It should be noted that all computer programs of a defect detection method based on capacitive imaging are implemented using C language, wherein the data acquisition module, the composite material property analysis module, the composite material bonding layer analysis module, the capacitive imaging defect analysis module, the defect risk prediction module and the control module are all controlled by a remote server.

[0120] Example 4

[0121] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0122] When the computer program runs on a computer device, the computer device is enabled to execute the above-mentioned defect detection method based on capacitance imaging.

[0123] Each embodiment of the present invention 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 IoT device and 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 embodiments.

[0124] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0125] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 generate 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.

[0127] 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.

[0128] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0129] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0130] 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 tape 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.

[0131] 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.

[0132] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A defect detection method based on capacitive imaging, characterized in that: The steps include: S1, obtaining material property data and bonding data of the composite material, and obtaining historical material property data and historical bonding data of the historical composite material; and obtaining capacitance defect detection image data of the composite material and historical capacitance defect detection image data of the historical composite material through a capacitance sensor; S2. construct a composite material property analysis model based on historical material property data, and import the material property data into the composite material property analysis model to analyze the material properties of the composite material; S3, constructing a composite material bonding layer analysis model based on historical bonding data, and importing the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer; S4, constructing a capacitor defect analysis model based on historical capacitor defect detection image data, and importing the capacitor defect detection image data into the capacitor defect analysis model to analyze the defects of the composite material bonding layer; S5. Construct a defect risk prediction model for the composite material to be tested based on the material property analysis results, the bonding layer analysis results, and the capacitor defect analysis results, and predict the defect risk of the composite material to be tested; The step S2 comprises the following specific steps: S21, obtaining material property data of the composite material and historical material property data of the historical composite material; S22, substituting the material property data and the historical material property data into the material property difference coefficient calculation formula to calculate the material property difference coefficient of the composite material; the material property difference coefficient calculation formula is: ； Where cs is the material property difference coefficient of the composite material, c is the surface roughness of the composite material in the material property data, h is the surface curvature of the composite material in the material property data, and w represents the weight of the composite material in the material property data. represents the surface roughness of the i-th historical composite material of historical material attribute data, represents the surface radian of the i-th historical composite material of historical material attribute data, represents the weight of the i-th historical composite material of the historical material attribute data, n represents the number of historical composite materials, and i is any one from 1 to n; The step S3 comprises the following specific steps: S31, obtaining bonding data of the composite material and historical bonding data of the historical composite material; S32, substituting the bonding data and the historical bonding data into a bonding difference coefficient calculation formula to calculate the bonding difference coefficient of the composite material bonding layer, wherein the bonding difference coefficient calculation formula is: ； Wherein zj represents the bonding difference coefficient of the bonding layer of the composite material, P represents the amount of adhesive used when bonding the composite material in the bonding data, s represents the area of ​​the bonding region of the composite material in the bonding data, T represents the curing temperature of the adhesive when bonding the composite material in the bonding data, t represents the curing time of the adhesive when bonding the composite material in the bonding data, represents the amount of adhesive used when bonding the i-th historical composite material in the historical bonding data, represents the area of ​​the i-th historical composite material bonding region in the historical bonding data, represents the curing temperature of the adhesive when bonding the i-th historical composite material in the historical bonding data, represents the curing time of the adhesive when bonding the i-th historical composite material in the historical bonding data; The step S4 comprises the following specific steps: S41, acquiring capacitance defect detection image data of composite materials and historical capacitance defect detection image data of historical composite materials; S42, substituting the capacitor defect detection image data and the historical capacitor defect detection image data into a defect detection difference coefficient calculation formula to calculate the defect detection difference coefficient of the composite material bonding layer, the bonding layer defect detection difference coefficient calculation formula is: ； Where qx ​​represents the defect detection difference coefficient of the composite material bonding layer, q is the number of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, r is the number of pixels of all defect areas extracted from the composite material capacitor defect detection image in the capacitor defect detection image data, and R is the total number of pixels in the composite material capacitor defect detection image. is the number of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the number of pixels of all defective areas extracted from the i-th historical composite material capacitor defect detection image in the historical capacitor defect detection image data, is the total number of pixels in the i-th historical composite material capacitor defect detection image, They represent the defect number influencing factor and defect area influencing factor respectively; S43, using the defect detection difference coefficient of the composite material bonding layer as a defect risk coefficient of the composite material bonding layer; The step S5 comprises the following specific steps: S51, obtaining composite material defect sample data for training a composite material defect risk prediction model to be detected, wherein the composite material defect sample data includes material property difference coefficients of multiple composite materials and bonding difference coefficients of multiple composite material bonding layers and a defect risk coefficient obtained by calculation, dividing the composite material defect sample data for training the composite material defect risk prediction model to be detected into a defect sample training set and a defect sample test set, constructing a regression network model, using the material property difference coefficient and the bonding difference coefficient in the defect sample training set as inputs of the regression network model, using the defect risk coefficient in the defect sample training set as outputs of the regression network model, training the regression network model to obtain an initial regression network model; evaluating the model effect of the initial regression network model using an average error algorithm, and selecting a corresponding initial regression network model with a value greater than or equal to a preset evaluation value as the composite material defect risk prediction model to be detected; S52, calculating the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested, inputting the calculated material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested into the defect risk prediction model of the composite material to be tested, and outputting the predicted defect risk coefficient of the bonding layer of the composite material to be tested; The step S5 also includes the following specific steps: S53, obtaining the predicted defect risk coefficient of the bonding layer of the composite material to be tested; S54, presetting a defect risk threshold, and when the predicted defect risk coefficient of the bonding layer of the composite material to be inspected is less than or equal to the defect risk threshold, completing defect inspection of the composite material to be inspected; S55. When the predicted defect risk coefficient of the bonding layer of the composite material to be tested is greater than the defect risk threshold, obtain the material property difference coefficient of the composite material to be tested and the bonding difference coefficient of the bonding layer of the composite material to be tested; preset the material property difference threshold and the bonding difference threshold, and when the material property difference coefficient of the composite material to be tested is greater than the material property difference threshold, issue an abnormal instruction to the producer that there is an abnormality in the surface treatment stage of the composite material, and reprocess the composite material; when the bonding difference coefficient of the bonding layer of the composite material to be tested is greater than the bonding difference threshold, issue an abnormal instruction to the producer that there is an abnormality in the bonding stage of the composite material, and reprocess the composite material.

2. A defect detection system based on capacitive imaging, which is implemented based on the defect detection method based on capacitive imaging according to claim 1, characterized in that: The system comprises: A data acquisition module is used to acquire material property data and bonding data of the composite material, and also to acquire historical material property data and historical bonding data of the historical composite material; and to acquire a capacitance defect detection image of the composite material and a historical capacitance defect detection image of the historical composite material through a capacitance sensor; A composite material property analysis module is used to construct a composite material property analysis model based on historical material property data, and to import the material property data into the composite material property analysis model to analyze the material properties of the composite material; A composite material bonding layer analysis module is used to construct a composite material bonding layer analysis model based on historical bonding data, and to import the bonding data into the composite material bonding layer analysis model to analyze the composite material bonding layer; Capacitive imaging defect analysis module, used to build a capacitor defect analysis model based on historical capacitor defect detection images, and import the capacitor defect detection images into the capacitor defect analysis model to analyze the defects of the composite material bonding layer; A defect risk prediction module is used to construct a defect risk prediction model for the composite material to be tested based on the material property analysis results, the bonding layer analysis results and the capacitance defect analysis results of the composite material, and to predict the defect risk of the composite material to be tested; A control module is used to control the operation of the data acquisition module, the composite material property analysis module, the composite material bonding layer analysis module, the capacitive imaging defect analysis module and the defect risk prediction module.

3. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the defect detection method based on capacitive imaging as described in claim 1 by calling the computer program stored in the memory.

4. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the defect detection method based on capacitance imaging as claimed in claim 1.

Images