CN112756768A - Welding quality evaluation method and system based on ultrasonic image feature fusion - Google Patents
Welding quality evaluation method and system based on ultrasonic image feature fusion Download PDFInfo
- Publication number
- CN112756768A CN112756768A CN202011506451.4A CN202011506451A CN112756768A CN 112756768 A CN112756768 A CN 112756768A CN 202011506451 A CN202011506451 A CN 202011506451A CN 112756768 A CN112756768 A CN 112756768A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- welding
- image
- defect
- welding quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K20/00—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating
- B23K20/12—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating the heat being generated by friction; Friction welding
- B23K20/122—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating the heat being generated by friction; Friction welding using a non-consumable tool, e.g. friction stir welding
- B23K20/1245—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating the heat being generated by friction; Friction welding using a non-consumable tool, e.g. friction stir welding characterised by the apparatus
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K20/00—Non-electric welding by applying impact or other pressure, with or without the application of heat, e.g. cladding or plating
- B23K20/26—Auxiliary equipment
Abstract
The invention provides a welding quality evaluation method and system based on ultrasonic image feature fusion, which relate to the technical field of welding quality detection, can obtain three-dimensional information of internal defects of a welding joint through B-scan and C-scan images of ultrasonic detection, and realize comprehensive characterization of welding quality by fusing a plurality of defect characteristic quantities through information entropy, and have comprehensive and high accuracy of evaluation information; the method comprises the following steps: s1, carrying out ultrasonic detection on the backfilling type friction stir spot welding joint, and collecting a B-scanning image and a C-scanning image of a welding area; s2, analyzing and processing the obtained B-scanning image and C-scanning image, extracting effective information in the images and defect characteristics in the welding spot, and forming three-dimensional information representation of the welding quality; and S3, endowing different weight coefficients to the characteristic quantity in the three-dimensional information representation by using the information entropy, and then fusing the different weight coefficients into a comprehensive index serving as an evaluation result. The technical scheme provided by the invention is suitable for the welding quality evaluation process.
Description
Technical Field
The invention relates to the technical field of welding quality detection, in particular to a welding quality evaluation method and system based on ultrasonic image feature fusion.
Background
The backfill type friction stir spot welding is a novel welding technology. The welding process has no keyhole after welding, high joint strength and high quality, so that the welding process is widely applied to welding of common light metals such as aluminum alloy, magnesium alloy and the like in the fields of aerospace, automobiles, shipbuilding and the like. However, in the welding process, improper selection of welding parameters can cause defects such as insufficient backfill, hook defects, holes and the like in the joint, and the defects are easy to expand into cracks, so that the mechanical property of the product is reduced. Therefore, detection of welding defects and evaluation of welding quality are very important.
The traditional welding quality detection method comprises a metallographic method, a tensile shear test, a microhardness method and the like, but the methods are destructive detection methods, so that the application range is limited to a certain extent. In recent years, there has been increasing interest in characterizing weld quality using non-destructive inspection techniques. In nondestructive testing, ultrasonic testing is widely applied to testing and evaluation of welding quality due to the advantages of high sensitivity, high testing speed, capability of realizing three-dimensional characterization of the interior of a material and the like.
Scholars at home and abroad do a lot of work on ultrasonic characterization of welding quality. On one hand, aiming at the ultrasonic A-scan waveform signal, the amplitude and the attenuation coefficient in the waveform are extracted to represent the nugget diameter, the weld width and the like. However, structural noise inside the material affects the ultrasonic signal, so a scholars converts a time domain signal into a frequency domain for analysis, and quantitatively evaluates the quality of welding through characteristics such as a main frequency value and spectral energy. On the other hand, for the ultrasonic C-scan image, a learner adopts a bilinear interpolation algorithm to improve the resolution of the welding seam C-scan image, and can effectively extract information such as the size and the shape of the welding seam; in addition, researches show that the width of a weld joint in an ultrasonic C-scan image and the tensile shear strength have the same trend, and the ultrasonic C-scan can effectively represent the welding quality.
Related patents for ultrasonic detection of welding quality at home and abroad are basically discussion on detection equipment and methods. For example, chinese patent document CN106124624A discloses an automatic detection device and method for spot welding quality of thin plate, which processes the detected waveform to obtain the horizontal and vertical coordinates of each echo, calculates the number of wave peaks, nugget diameter, attenuation coefficient, indentation depth and pore diameter, and determines the type of spot welding quality according to the calculation result. The method mainly analyzes the A-scan waveform, and the larger the scanning range is, the more the A-scan waveforms are obtained, thereby bringing about the problems of large data size of analysis, low analysis efficiency and the like. More importantly, the A-scan waveform is a one-dimensional signal, and the distribution characteristics of the welding defects in a three-dimensional space are difficult to fully characterize, so that the evaluation capability of the technology on the welding quality is limited.
Therefore, it is necessary to research a welding quality evaluation method and system based on 3D ultrasound image feature fusion to address the deficiencies of the prior art and to solve or alleviate one or more of the above problems.
Disclosure of Invention
In view of the above, the invention provides a welding quality evaluation method and system based on ultrasonic image feature fusion, which can obtain three-dimensional information of internal defects of a welding joint through B-scan and C-scan images of ultrasonic detection, and realize comprehensive characterization of welding quality by fusing a plurality of defect feature quantities through information entropy, and have comprehensive and high accuracy of evaluation information.
In one aspect, the invention provides a welding quality evaluation method based on ultrasonic image feature fusion, and the method comprises the following steps:
s1, carrying out ultrasonic detection on the backfill type friction stir spot welding joint, and acquiring an ultrasonic B-scan image and an ultrasonic C-scan image of a welding area;
s2, analyzing and processing the obtained ultrasonic B-scanning image and ultrasonic C-scanning image, extracting effective information in the images and defect characteristics in the welding spot, and forming three-dimensional information representation of welding quality;
and S3, endowing different weight coefficients to the characteristic quantity in the three-dimensional information representation by using the information entropy, and then fusing the characteristic quantity into a comprehensive index to serve as an evaluation result of the backfill type friction stir spot welding.
As with the above-described aspects and any possible implementation, there is further provided an implementation in which the defect feature inside the solder joint includes: the ring width, the maximum defect area, the average defect area in the ultrasonic C-scan image, and the weld defect depth in the ultrasonic B-scan image.
The above-described aspects and any possible implementation further provide an implementation, and the backfilled friction stir spot welding joint is ultrasonically detected by using a high-frequency ultrasonic microscope in step S1.
In accordance with the above-described aspect and any possible implementation manner, an implementation manner is further provided, in which the data normalization is performed on the feature matrix of the three-dimensional information representation before performing step S3.
In accordance with the foregoing aspect and any one of the possible implementations, there is further provided an implementation that the high-frequency ultrasonic microscope is a pulse reflection type ultrasonic microscope, and the coupling mode is a water immersion type.
The above aspects and any possible implementation manner further provide an implementation manner, wherein before ultrasonic detection, detection parameters are selected; the detection parameters include: probe type, probe frequency, depth of focus, scan range, step accuracy, gain size, time valve, and imaging resolution.
In the above aspect and any possible implementation manner, step S1 further provides that the spot welding test samples at a plurality of medium rotation speeds are subjected to ultrasonic detection, and ultrasonic C-scan images and ultrasonic B-scan images at different rotation speeds are obtained.
As for the above-mentioned aspect and any possible implementation manner, there is further provided an implementation manner, and the specific step of step S2 includes:
s2.1, carrying out binarization processing on the obtained ultrasonic B-scanning image and ultrasonic C-scanning image to obtain a binarized image;
and S2.2, determining defect characteristic data shown by each image according to the process characteristics of the binary image and the detection sample, and obtaining a characteristic vector of the detection sample.
As for the above-mentioned aspect and any possible implementation manner, there is further provided an implementation manner, and the specific step of step S3 includes:
s3.1, converting the eigenvector obtained in the step S2.2 into a defect characteristic matrix;
s3.2, normalizing the defect feature matrix and calculating the contribution degree of each feature;
s3.3, calculating the information entropy of each feature according to the contribution degree; calculating a weight coefficient of each feature according to the information entropy;
and S3.4, fusing all the characteristic quantities into a comprehensive index according to the weight coefficient, and taking the comprehensive index as an evaluation result of the backfill type friction stir spot welding.
In another aspect, the present invention provides a welding quality evaluation system based on ultrasonic image feature fusion, including:
the ultrasonic detection module is used for carrying out ultrasonic detection on the backfilling type friction stir spot welding joint and acquiring an ultrasonic B-scanning image and an ultrasonic C-scanning image of a welding area;
the image processing module is used for analyzing and processing the ultrasonic B-scanning image and the ultrasonic C-scanning image and extracting effective information in the images and defect characteristics in the welding spot;
the three-dimensional representation module is used for forming three-dimensional information representation of welding quality according to the data of the welding joints extracted by the image processing module;
and the evaluation module is used for endowing different weight coefficients to the characteristic quantity in the three-dimensional information representation by using the information entropy, and then fusing the different weight coefficients into a comprehensive index to serve as an evaluation result of the backfill type friction stir spot welding.
Compared with the prior art, the invention can obtain the following technical effects: according to the method, the space distribution state of the internal defects of the backfill type friction stir spot welding joint can be obtained by extracting the key characteristic information of the ultrasonic C-scanning image and the ultrasonic B-scanning image, a plurality of defect characteristic quantities are fused by an information entropy method, and then the comprehensive characterization of the welding quality is realized.
Of course, it is not necessary for any one product in which the invention is practiced to achieve all of the above-described technical effects simultaneously.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a welding quality evaluation method based on 3D ultrasonic image feature fusion according to an embodiment of the present invention;
FIG. 2 is a diagram of the geometry of an object under examination provided by an embodiment of the present invention;
FIG. 3 is an ultrasonic C-scan image provided by one embodiment of the present invention;
FIG. 4 is an ultrasound B-scan image provided by one embodiment of the present invention;
FIG. 5 is a graph of the three-dimensional composite feature, shear strength, as a function of rotational speed provided by one embodiment of the present invention.
Detailed Description
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
In order to overcome the defects of the prior art, the invention provides a welding quality evaluation method based on ultrasonic image feature fusion, and the comprehensive characterization of the welding quality is realized. The content comprises the following steps: firstly, carrying out ultrasonic detection on a backfill type friction stir spot welding joint by using a high-frequency ultrasonic microscope, selecting proper detection parameters, and acquiring an ultrasonic B-scanning image and an ultrasonic C-scanning image of a welding area; then, analyzing and processing the obtained ultrasonic B-scanning image and the C-scanning image, and extracting effective information in the images and defect characteristics inside a welding spot, wherein the effective information and the defect characteristics comprise the annular width, the maximum defect area, the average defect area and the defect depth in the B-scanning image in the C-scanning image, so that three-dimensional information representation of the welding quality is formed; on the basis, different weight coefficients are given to the extracted three-dimensional characteristic quantities by using the information entropy, and the characteristic quantities are fused into a comprehensive index for carrying out comprehensive evaluation on the backfill type friction stir spot welding. According to the method, the space distribution state of the internal defects of the backfill type friction stir spot welding joint can be obtained by extracting the key characteristic information of the ultrasonic C-scanning image and the ultrasonic B-scanning image, a plurality of defect characteristic quantities are fused by an information entropy method, and then the comprehensive characterization of the welding quality is realized.
The evaluation method specifically comprises the following steps:
step 1: detecting the backfill type friction stir spot welding joint by using a high-frequency ultrasonic microscope, selecting optimal detection parameters, and acquiring ultrasonic B-scan images and C-scan images of a welding area;
the high-frequency ultrasonic microscope is a pulse reflection type ultrasonic microscope, and the coupling mode is a water immersion type. The detection parameters include: probe type, probe frequency, focusing depth, scanning range, stepping precision, gain size, time valve, imaging resolution and the like; and adjusting the detection parameters of the ultrasonic microscope for multiple times, and acquiring an ultrasonic C-scan image and an ultrasonic B-scan image with the best imaging effect.
The specific steps of step 1 include:
step 1.1: observing the characteristics of the shape, the size, the process and the like of the pattern to be detected, selecting a proper ultrasonic probe, focusing the ultrasonic probe on the root position of a welding spot by adjusting the height of the probe, and determining the scanning area according to the size of the sample;
step 1.2: adjusting the stepping precision, the gain size and the time gate for multiple times, observing the imaging effect, selecting the optimal detection parameter combination, finely scanning the sample, and collecting a C-scan image of a welding area;
step 1.3: marking a line in the diameter direction of the welding area in the C-scan image to form a B-scan section, performing B-scan on the sample, and adjusting a proper time valve to generate an ultrasonic B-scan image;
step 1.4: and (3) carrying out the ultrasonic detection operation from the step 1.1 to the step 1.3 on the spot welding samples with 5 rotating speeds to obtain C-scanning images and B-scanning images of the welding area at different rotating speeds.
Step 2: processing and analyzing the ultrasonic image obtained in the step 1, and extracting characteristic quantity of the welding spot defect in the image, namely: the annular width, the maximum defect area and the average defect area in the ultrasonic C-scanning image and the welding defect depth in the ultrasonic B-scanning image;
the ultrasonic image processing is specifically to perform binarization processing on an image gray scale map, and is performed based on the following formula:
in the formula: f (x, y) is an original image gray matrix, T is a binarization threshold value, and g (x, y) is an image gray matrix after binarization;
solder joint defect characteristics include: the extracted characteristics such as the annular width, the maximum defect area, the average defect area and the like in the ultrasonic C-scan image are ultrasonic characteristics parallel to the welding surface, and the extracted defect depth in the ultrasonic B-scan image is ultrasonic characteristics vertical to the welding surface, so that three-dimensional information representation of the internal defect of the welding joint is formed.
The specific steps of step 2 include:
step 2.1: carrying out binarization processing on the ultrasonic B-scan image and the ultrasonic C-scan image of the welding area obtained in the step 1.4;
step 2.2: analyzing the binary images obtained in the step 2.1, and determining the defect characteristics shown by each image, namely the ring width, the maximum defect area, the average defect area and the defect depth, by combining the process characteristics of the detection sample;
step 2.3: analyzing and processing the ultrasonic B-scan and C-scan of each sample, extracting the characteristic quantity in the step 2.2, and establishing a characteristic vector corresponding to the sample: xi＝[xWidth of ring,xMaximum defect area,xMean area of defect,xDepth of defect]TAnd i represents a sample number to be measured.
And step 3: after the characteristic matrix is subjected to data normalization, different weight coefficients are given to the extracted three-dimensional characteristic quantities by using the information entropy, and a plurality of characteristic quantities are fused into a comprehensive index for carrying out comprehensive evaluation on the backfill type friction stir spot welding;
the specific steps of step 3 include:
step 3.1: converting the feature vectors extracted in the step 2.3 into a defect feature matrix Xm×nI.e. by
Wherein m represents the number of samples to be measured, n represents the number of characteristic quantities of a single sample, and XijAnd (4) representing the j ultrasonic characteristic quantity of the i sample.
Step 3.2: and (3) carrying out normalization processing on the defect feature matrix obtained in the step (3.1), wherein the formula is as follows:
using normalized defect feature matrix
Calculating the contribution degree of the ith sample to the jth feature, wherein the formula is as follows:
step 3.3: according to the contribution p obtained in step 3.2ijAnd calculating the information entropy of each feature, wherein the calculation formula is as follows:
using information entropy EjCalculating the weight coefficient of each feature, wherein the calculation formula is as follows:
thereby obtaining a defect characteristic weight coefficient matrix W ═ W1,W2,...,Wn]Wherein W isjIs greater than 0 and
step 3.4: using the weight coefficient W obtained in step 3.3jFusing n characteristic quantities into a new characteristic index:
wherein the content of the first and second substances,
for the normalized defect feature matrix, WTIs a transposed matrix of the feature weight matrix,
is an index indicating the size of the defect, and the larger the index is, the poorer the welding quality is, so that it is available
Comprehensively characterizing the welding quality.
Example 1:
a welding quality evaluation method based on 3D ultrasonic image feature fusion is disclosed, as shown in FIG. 1, the method comprises the following steps: firstly, carrying out ultrasonic detection on a backfill type friction stir spot welding joint by using a high-frequency ultrasonic microscope, and acquiring an ultrasonic B-scan image and an ultrasonic C-scan image of a welding area; then, analyzing and processing the obtained ultrasonic B-scanning image and the C-scanning image, and extracting effective information in the images and defect characteristics inside a welding spot, wherein the effective information and the defect characteristics comprise the annular width, the maximum defect area, the average defect area and the defect depth in the B-scanning image in the C-scanning image, so that three-dimensional information representation of the welding quality is formed; on the basis, different weight coefficients are given to the extracted three-dimensional characteristic quantities by using the information entropy, and the characteristic quantities are fused into a comprehensive index for carrying out comprehensive evaluation on the backfill type friction stir spot welding. The method mainly comprises the following steps:
s1) detecting the backfill type friction stir spot welding joint by using a high-frequency ultrasonic microscope, selecting the optimal detection parameters, and acquiring an ultrasonic B-scan image and an ultrasonic C-scan image of a welding area;
s2) processing and analyzing the ultrasonic image obtained in S1), and extracting the characteristic quantity of the welding spot defect in the image, namely: the annular width, the maximum defect area and the average defect area in the ultrasonic C-scanning image and the welding defect depth in the ultrasonic B-scanning image;
s3), after data normalization is carried out on the characteristic matrix, different weight coefficients are given to the extracted three-dimensional characteristic quantities by utilizing the information entropy, and a plurality of characteristic quantities are fused into a comprehensive index for carrying out comprehensive evaluation on the backfill type friction stir spot welding.
The high-frequency ultrasonic microscope of S1) is a pulse reflection type ultrasonic microscope, and the coupling mode is a water immersion type;
the detection parameters comprise: probe type, probe frequency, focusing depth, scanning range, stepping precision, gain size, time valve, imaging resolution and the like; and adjusting the detection parameters of the ultrasonic microscope for multiple times, and acquiring an ultrasonic C-scan image and an ultrasonic B-scan image with the best imaging effect.
The ultrasonic detection in the step S1) comprises the following specific steps:
s1.1) observing the characteristics of the shape, size, process and the like of a pattern to be detected, selecting a proper ultrasonic probe, focusing the ultrasonic probe on the root position of a welding spot by adjusting the height of the probe, and determining the scanning area;
the tested sample is formed by welding two 2524Al-Cu-Mg alloy plates through backfill type friction stir spot welding, the size of a substrate is 150mm multiplied by 50mm multiplied by 2mm, the outer diameter of a spot welding stirring sleeve is 9mm, the depth of a downward prick is 2.6mm, the rotating speeds are 2200rpm, 2400rpm, 2600rpm, 2800rpm and 3000rpm respectively, and the welded sample to be tested is shown in figure 2.
The thickness of the welded area of the sample was 4mm, the depth of the stabbing 2.6mm, and the frequency of the probe was chosen to be 50MHz, in combination with the maximum depth of focus of the probe in the material. Adjusting the Z-axis position of the probe according to the A-scan waveform to focus the probe on the root of the welding spot, adjusting the X, Y-axis position of the probe to be positioned in the center of a welding area, and setting the C-scan area to be 10mm multiplied by 10mm due to the outer diameter of the stirring sleeve being 9 mm;
s1.2) adjusting the stepping precision, the gain size and the time gate for multiple times, observing the imaging effect, selecting the optimal detection parameter combination, finely scanning the sample, and collecting a C-scan image of a welding area;
respectively selecting the stepping precision to be 80um, 40um and 20um, adjusting the gain to meet the requirement that the maximum amplitude of the defect is 85%, 80% and 75% of the range, carrying out C-scan imaging on a welding area, observing the imaging effect under different parameter settings, selecting the parameter combination with the best imaging effect, carrying out fine scanning on a sample, and acquiring an ultrasonic C-scan image of the sample;
s1.3) scribing in the diameter direction of a welding area in the C-scan image to be used as a B-scan section, B-scanning the sample, and adjusting a proper time valve to generate an ultrasonic B-scan image;
the selection of a time valve needs to be paid attention to during B-scan imaging, and the valve range should include interface waves and welding defect echoes, so that the smooth extraction of defect characteristic quantities can be ensured;
s1.4) carrying out the ultrasonic detection operations from S1.1) to S1.3) on the spot welding samples with 5 rotating speeds to obtain C-scan images and B-scan images of welding areas at different rotating speeds, as shown in FIGS. 3 and 4.
The S2) comprises the following specific steps:
s2.1) carrying out binarization processing on the ultrasonic B-scan image and the ultrasonic C-scan image of the welding area obtained in the S1.4), and carrying out binarization processing based on the following formula:
in the formula: f (x, y) is an original image gray matrix, T is a binarization threshold value, and g (x, y) is an image gray matrix after binarization;
and (3) introducing the ultrasonic C-scan image and the ultrasonic B-scan image into MATLAB, converting the images into a gray value matrix f (x, y), when the stepping precision is 20um, the resolution of the C-scan image is 500 multiplied by 500, the size of the gray value matrix is also 500 multiplied by 500, and selecting a proper threshold value according to the gray value histogram to carry out binarization processing T to obtain a gray value matrix g (x, y) of the binary image of the welding defect.
S2.2) analyzing the binary image obtained in the S2.1), and determining defect characteristics shown by each image, namely ring width, maximum defect area, average defect area and defect depth, by combining the process characteristics of a detection sample;
the image characteristics are analyzed to find that the defects in the C scanning image are distributed in a ring shape and represent the area without welding, the larger the area is, the worse the welding quality is, and according to the defect characteristics, several characteristics capable of representing the welding quality can be determined: annular width, maximum defect area, average defect area.
The annular width may be determined by the following equation:
w＝Rs-R
where Rs is the outer diameter of the cannula, R is the minimum radius tangent to the defect in the C-scan image, and is concentric with Rs, as shown in FIG. 3;
the average defect area may reflect the overall level of defects, i.e., the larger the average defect area, the worse the weld quality. When the maximum defect area is larger, stress concentration is more likely to occur, and the welding quality is poorer. The number of defects (N) and the area of each defect (S) can be determined by mathematical statistics using a 4-domain algorithmi) Thereby determining the maximum defect area (S)max) And average defect area
Smax＝max(Si)
The defect depth feature amount h is reflected in the B-scan image, and appears as a distance between the defect reflection echo and the sample surface wave, as shown in fig. 4. Meanwhile, the defect depth h can be calculated through the A scanning waveform, and the calculation formula is as follows:
wherein, t1Indicating the time of reception of the interfacial wave, t2Representing the defect wave reception time, c representing the speed of sound in the material;
s2.3) analyzing the ultrasonic B-scan and C-scan of each sample, extracting the characteristic quantity of S2.2), and establishing a characteristic vector of each sample: xi＝[xWidth of ring,xMaximum defect area,xMean area of defect,xDepth of defect]TAnd i represents a sample number to be measured.
The S3) concrete steps are:
s3.1) combining the feature vectors extracted in S2.3) into a defect feature matrix Xm×n；
The number of welding samples to be detected is 5, and 4 ultrasonic characteristic quantities can be extracted from each welding sample in xijThe j ultrasonic characteristic quantity of the i-th welding sample is shown, and the characteristic matrix X consisting of all the welding samples5×4Can be expressed as:
s3.2) carrying out normalization processing on the defect characteristic matrix obtained in the S3.1), wherein the formula is as follows:
using normalized defect feature matrix
Calculating the contribution degree of the ith sample to the jth feature, wherein the formula is as follows:
s3.3) contribution p from S3.2)ijAnd calculating the information entropy of each feature, wherein the calculation formula is as follows:
using information entropy EjCalculating the weight coefficient of each feature, wherein the calculation formula is as follows:
thereby obtaining a defect characteristic weight coefficient matrix W ═[W1,W2,W3,W4]Wherein W isjIs greater than 0 and
s3.4) weight coefficient W obtained by using S3.3)jFusing n characteristic quantities into a new characteristic index:
wherein the content of the first and second substances,
for the normalized defect feature matrix, WTIs a transposed matrix of the feature weight matrix,
is an index indicating the size of the defect, and the larger the index is, the poorer the welding quality is, so that it is available
Comprehensively characterizing the welding quality.
Ultrasonic detection is carried out on samples obtained by backfilling type friction stir welding at different rotating speeds, ultrasonic B-scan images and C-scan images of a welding area are obtained, defect information in the images is extracted, the defect characteristics are fused into a comprehensive index by an information entropy method, the result is matched with the shearing strength, and the effectiveness of the method is verified as shown in fig. 5. As can be seen from fig. 5, as the rotational speed increases, the 3DF decreases first, then increases, then decreases, consistent with the change in shear strength; the welding quality was the worst when the rotation speed was 2400rpm, and the welding quality was the best when the rotation speed was 2800 rpm.
The invention has the advantages that:
1. the invention can simultaneously obtain an ultrasonic C-scan image and an ultrasonic B-scan image at the backfill type friction stir spot welding joint by utilizing a high-frequency ultrasonic microscopic detection technology, extracts different key characteristic quantities from the ultrasonic images, and can realize accurate representation of three-dimensional space information of the internal defects of the welding joint.
2. According to the invention, different weight coefficients are given to different ultrasonic characteristic quantities by an information entropy method, and a plurality of characteristic quantities become a comprehensive index by utilizing the weight coefficients, so that the quality of welding quality can be quantitatively represented, and the problems of incompleteness, inaccuracy and the like existing when a certain characteristic quantity is used for representing the quality of a welding seam independently in the traditional method can be effectively solved.
The welding quality evaluation method and system based on ultrasonic image feature fusion provided by the embodiment of the application are described in detail above. The above description of the embodiments is only for the purpose of helping to understand the method of the present application and its core ideas; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
As used in the specification and claims, certain terms are used to refer to particular components. As one skilled in the art will appreciate, manufacturers may refer to a component by different names. This specification and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. "substantially" means within an acceptable error range, and a person skilled in the art can solve the technical problem within a certain error range to substantially achieve the technical effect. The description which follows is a preferred embodiment of the present application, but is made for the purpose of illustrating the general principles of the application and not for the purpose of limiting the scope of the application. The protection scope of the present application shall be subject to the definitions of the appended claims.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The foregoing description shows and describes several preferred embodiments of the present application, but as aforementioned, it is to be understood that the application is not limited to the forms disclosed herein, but is not to be construed as excluding other embodiments and is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the application as described herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the application, which is to be protected by the claims appended hereto.
Claims (10)
1. A welding quality evaluation method based on ultrasonic image feature fusion is characterized by comprising the following steps:
s1, carrying out ultrasonic detection on the backfill type friction stir spot welding joint, and acquiring an ultrasonic B-scan image and an ultrasonic C-scan image of a welding area;
s2, analyzing and processing the obtained ultrasonic B-scanning image and ultrasonic C-scanning image, extracting effective information in the images and defect characteristics in the welding spot, and forming three-dimensional information representation of welding quality;
and S3, endowing different weight coefficients to the characteristic quantity in the three-dimensional information representation by using the information entropy, and then fusing the characteristic quantity into a comprehensive index to serve as an evaluation result of the backfill type friction stir spot welding.
2. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 1, wherein the defect features inside the welding spot comprise: the ring width, the maximum defect area, the average defect area in the ultrasonic C-scan image, and the weld defect depth in the ultrasonic B-scan image.
3. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 1, wherein in step S1, the backfilled friction stir spot welding joint is ultrasonically detected by using a high-frequency ultrasonic microscope.
4. The method for evaluating the welding quality based on the ultrasonic image feature fusion of claim 1, wherein the data normalization is performed on the feature matrix of the three-dimensional information representation before the step S3 is performed.
5. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 3, wherein the high-frequency ultrasonic microscope is a pulse reflection type ultrasonic microscope, and the coupling mode is a water immersion type.
6. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 3, wherein detection parameters are selected before ultrasonic detection; the detection parameters include: probe type, probe frequency, depth of focus, scan range, step accuracy, gain size, time valve, and imaging resolution.
7. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 1, wherein step S1 is implemented by performing ultrasonic inspection on a plurality of spot welding samples at a medium rotation speed, so as to obtain ultrasonic C-scan images and ultrasonic B-scan images at different rotation speeds.
8. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 1, wherein the specific steps of step S2 include:
s2.1, carrying out binarization processing on the obtained ultrasonic B-scanning image and ultrasonic C-scanning image to obtain a binarized image;
and S2.2, determining defect characteristic data shown by each image according to the process characteristics of the binary image and the detection sample, and obtaining a characteristic vector of the detection sample.
9. The ultrasonic image feature fusion-based welding quality evaluation method according to claim 8, wherein the specific steps of step S3 include:
s3.1, converting the eigenvector obtained in the step S2.2 into a defect characteristic matrix;
s3.2, normalizing the defect feature matrix and calculating the contribution degree of each feature;
s3.3, calculating the information entropy of each feature according to the contribution degree; calculating a weight coefficient of each feature according to the information entropy;
and S3.4, fusing all the characteristic quantities into a comprehensive index according to the weight coefficient, and taking the comprehensive index as an evaluation result of the backfill type friction stir spot welding.
10. A welding quality evaluation system based on 3D ultrasonic image feature fusion is characterized in that the system comprises:
the ultrasonic detection module is used for carrying out ultrasonic detection on the backfilling type friction stir spot welding joint and acquiring an ultrasonic B-scanning image and an ultrasonic C-scanning image of a welding area;
the image processing module is used for analyzing and processing the ultrasonic B-scanning image and the ultrasonic C-scanning image and extracting effective information in the images and defect characteristics in the welding spot;
the three-dimensional representation module is used for forming three-dimensional information representation of welding quality according to the data of the welding joints extracted by the image processing module;
and the evaluation module is used for endowing different weight coefficients to the characteristic quantity in the three-dimensional information representation by using the information entropy, and then fusing the different weight coefficients into a comprehensive index to serve as an evaluation result of the backfill type friction stir spot welding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011506451.4A CN112756768B (en) | 2020-12-18 | 2020-12-18 | Welding quality evaluation method and system based on ultrasonic image feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011506451.4A CN112756768B (en) | 2020-12-18 | 2020-12-18 | Welding quality evaluation method and system based on ultrasonic image feature fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112756768A true CN112756768A (en) | 2021-05-07 |
| CN112756768B CN112756768B (en) | 2021-12-14 |
Family
ID=75694335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011506451.4A Active CN112756768B (en) | 2020-12-18 | 2020-12-18 | Welding quality evaluation method and system based on ultrasonic image feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112756768B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469388A (en) * | 2021-09-06 | 2021-10-01 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN113588786A (en) * | 2021-07-21 | 2021-11-02 | 国能新朔铁路有限责任公司 | Steel rail flaw detection system, display method and device and computer equipment |
| CN114693562A (en) * | 2022-04-15 | 2022-07-01 | 黄淮学院 | Image enhancement method based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050132809A1 (en) * | 2002-02-06 | 2005-06-23 | Applied Metrics, Inc. | Methods for ultrasonic inspection of spot and seam resistance welds in metallic sheets and a spot weld examination probe system (SWEPS) |
| CN104267102A (en) * | 2014-10-27 | 2015-01-07 | 哈尔滨工业大学 | Method for detecting welding seam of friction stir welding through ultrasonic phased array |
| CN107576729A (en) * | 2017-09-15 | 2018-01-12 | 南京中车浦镇城轨车辆有限责任公司 | Weld defect detection and quick extraction system and method based on ultrasonic phase array |
| CN108414623A (en) * | 2018-02-09 | 2018-08-17 | 中车青岛四方机车车辆股份有限公司 | A kind of resistance spot welding quality evaluation method based on ultrasonic scanning imaging |
| US10161910B2 (en) * | 2016-01-11 | 2018-12-25 | General Electric Company | Methods of non-destructive testing and ultrasonic inspection of composite materials |
| CN111007148A (en) * | 2018-10-08 | 2020-04-14 | 中国科学院声学研究所 | Spot welding ultrasonic quality evaluation method |
| CN111351851A (en) * | 2018-12-20 | 2020-06-30 | 核动力运行研究所 | Ultrasonic signal reciprocating dislocation intelligent identification and signal calibration method |
-
2020
- 2020-12-18 CN CN202011506451.4A patent/CN112756768B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050132809A1 (en) * | 2002-02-06 | 2005-06-23 | Applied Metrics, Inc. | Methods for ultrasonic inspection of spot and seam resistance welds in metallic sheets and a spot weld examination probe system (SWEPS) |
| CN104267102A (en) * | 2014-10-27 | 2015-01-07 | 哈尔滨工业大学 | Method for detecting welding seam of friction stir welding through ultrasonic phased array |
| US10161910B2 (en) * | 2016-01-11 | 2018-12-25 | General Electric Company | Methods of non-destructive testing and ultrasonic inspection of composite materials |
| CN107576729A (en) * | 2017-09-15 | 2018-01-12 | 南京中车浦镇城轨车辆有限责任公司 | Weld defect detection and quick extraction system and method based on ultrasonic phase array |
| CN108414623A (en) * | 2018-02-09 | 2018-08-17 | 中车青岛四方机车车辆股份有限公司 | A kind of resistance spot welding quality evaluation method based on ultrasonic scanning imaging |
| CN111007148A (en) * | 2018-10-08 | 2020-04-14 | 中国科学院声学研究所 | Spot welding ultrasonic quality evaluation method |
| CN111351851A (en) * | 2018-12-20 | 2020-06-30 | 核动力运行研究所 | Ultrasonic signal reciprocating dislocation intelligent identification and signal calibration method |
Non-Patent Citations (1)
| Title |
|---|
| 刘经纬等: "《"互联网+"人工智能技术实现》", 30 June 2019, 首都经济贸易大学出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113588786A (en) * | 2021-07-21 | 2021-11-02 | 国能新朔铁路有限责任公司 | Steel rail flaw detection system, display method and device and computer equipment |
| CN113469388A (en) * | 2021-09-06 | 2021-10-01 | 江苏中车数字科技有限公司 | Maintenance system and method for rail transit vehicle |
| CN114693562A (en) * | 2022-04-15 | 2022-07-01 | 黄淮学院 | Image enhancement method based on artificial intelligence |
| CN114693562B (en) * | 2022-04-15 | 2022-11-25 | 黄淮学院 | Image enhancement method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112756768B (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112756768B (en) | Welding quality evaluation method and system based on ultrasonic image feature fusion | |
| Felice et al. | Sizing of flaws using ultrasonic bulk wave testing: A review | |
| JP4910769B2 (en) | Pipe quality control method and manufacturing method | |
| Thornton et al. | Progress in NDT of resistance spot welding of aluminium using ultrasonic C-scan | |
| Komura et al. | Crack detection and sizing technique by ultrasonic and electromagnetic methods | |
| US7503218B2 (en) | Methods and system for ultrasound inspection | |
| US20030234239A1 (en) | Method and system for assessing quality of spot welds | |
| CN105021142B (en) | The measuring method and equipment therefor of a kind of laser lap weld width | |
| CN112098526B (en) | Near-surface defect feature extraction method for additive product based on laser ultrasonic technology | |
| Sen et al. | Ultrasonic thickness measurement for aluminum alloy irregular surface parts based on spectral analysis | |
| CN104634876A (en) | Method for detecting inclusions in metal material by virtue of ultrasonic scanning microscope | |
| CN112525996B (en) | Ultrasonic imaging detection method for isotropic pyrolytic graphite | |
| CN101832973A (en) | Ultrasonic testing process of marine steel-welding joint phased array | |
| CN112666265A (en) | Method for making water immersion ultrasonic nondestructive testing process for laser additive connection area | |
| Jacques et al. | Ultrasonic backscatter sizing using phased array–developments in tip diffraction flaw sizing | |
| Liu et al. | Ultrasonic C-scan detection for stainless steel spot welding based on wavelet package analysis | |
| Liu et al. | Ultrasonic C-scan detection for stainless steel spot welds based on signal analysis in frequency domain | |
| JP4364031B2 (en) | Ultrasonic flaw detection image processing apparatus and processing method thereof | |
| Reverdy et al. | Inspection of spot welds using an ultrasonic phased array | |
| Reverdy et al. | Inspection of Spot Welds Using a Portable Ultrasonic Phased‐Array System | |
| CN114324598B (en) | High-quality imaging method and system for ultrasonic detection of bolts | |
| Fortunko et al. | Evaluation of pipeline girth welds using low-frequency horizontally polarized waves | |
| Zahran et al. | Automatic classification of defects in time-of-flight diffraction data | |
| Le Nevé et al. | High Temperature Hydrogen Attack: New NDE Advanced Capabilities—Development and Feedback | |
| Kustroń et al. | A high frequency ultrasonic imaging of welded joints |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |