CN116990229A - Defect detection method and system for copper plating layer surface of product - Google Patents
Defect detection method and system for copper plating layer surface of product Download PDFInfo
- Publication number
- CN116990229A CN116990229A CN202311247637.6A CN202311247637A CN116990229A CN 116990229 A CN116990229 A CN 116990229A CN 202311247637 A CN202311247637 A CN 202311247637A CN 116990229 A CN116990229 A CN 116990229A
- Authority
- CN
- China
- Prior art keywords
- defect
- copper
- judging
- array
- positions
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 367
- 238000001514 detection method Methods 0.000 title claims abstract description 98
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 title claims abstract description 39
- 229910052802 copper Inorganic materials 0.000 title claims abstract description 39
- 239000010949 copper Substances 0.000 title claims abstract description 39
- 238000007747 plating Methods 0.000 title claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 150
- 238000003466 welding Methods 0.000 claims abstract description 80
- 230000008859 change Effects 0.000 claims abstract description 78
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000003491 array Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 37
- 239000013598 vector Substances 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 7
- 239000000523 sample Substances 0.000 description 16
- 238000005070 sampling Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N19/00—Investigating materials by mechanical methods
- G01N19/08—Detecting presence of flaws or irregularities
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application discloses a defect detection method and a defect detection system for the surface of a copper plating layer of a product, belonging to the field of defect detection, wherein the method comprises the following steps: feeding copper-plated welding wires to be tested to the wire feeding direction, and fitting to obtain a wire feeding resistance change curve; calculating the change angle of the comprehensive curve, and acquiring defect scale information; setting a surface defect detection operator according to the defect scale information; constructing an electrical test result array at a plurality of positions on the surface of the copper-plated welding wire, dividing the electrical test result array by adopting a detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions; collecting images of a plurality of defect positions and carrying out gray processing to obtain a defect point set; and generating a defect detection result of the surface of the copper-plated welding wire based on the defect point set. The application solves the technical problem of low detection accuracy of the surface defects of the copper-plated welding wire in the prior art, and achieves the technical effect of improving the detection accuracy of the surface defects of the copper-plated welding wire.
Description
Technical Field
The application relates to the field of defect detection, in particular to a method and a system for detecting defects on the surface of a copper plating layer of a product.
Background
Copper-plated welding wires are widely used in the manufacture and connection of electronic products, and whether defects exist on the surface of a copper-plated layer directly affects the performance of the welding wires. At present, the method for detecting the surface defects of the copper-plated welding wire mainly adopts a means for detecting the surface morphology, such as a scanning electron microscope method, an optical method and the like. However, these methods can only perform partial scanning of the copper plating surface, and it is difficult to accurately judge the position and severity of the defect, resulting in a low detection accuracy.
Disclosure of Invention
The application provides a method and a system for detecting defects on the surface of a copper plating layer of a product, and aims to solve the technical problem that the detection accuracy of the defects on the surface of a copper plating welding wire in the prior art is low.
In view of the above problems, the present application provides a method and a system for detecting defects on the surface of a copper plating layer of a product.
In a first aspect of the present disclosure, a method for detecting defects on a copper plating layer surface of a product is provided, the method comprising: adopting a resistance testing component, feeding copper-plated welding wires to be tested, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve; calculating and obtaining a comprehensive curve change angle of a wire feeding resistance change curve, and analyzing and obtaining defect scale information of the copper-plated welding wire according to the comprehensive curve change angle; setting a detection operator for detecting the surface defects according to the defect scale information; based on the defect testing component, performing electrical testing at a plurality of positions on the surface of the copper-plated welding wire, constructing an electrical testing result array, dividing the electrical testing result array by adopting a detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule; based on the defect analysis part, acquiring images of a plurality of defect positions, carrying out graying treatment, and identifying the plurality of graying images to obtain a defect point set; and generating a defect detection result of the surface of the copper-plated welding wire based on the defect point set.
In another aspect of the present disclosure, a defect inspection system for a copper-clad surface of a product is provided, the system comprising: the resistance change curve module is used for feeding the copper-plated welding wire to be tested to the wire by adopting a resistance test component, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve; the defect scale information module is used for calculating and acquiring the comprehensive curve change angle of the wire feeding resistance change curve and analyzing and acquiring the defect scale information of the copper-plated welding wire according to the comprehensive curve change angle; the defect detection operator module is used for setting a detection operator for detecting surface defects according to the defect scale information; the surface electrical testing module is used for carrying out electrical testing on a plurality of positions on the surface of the copper-plated welding wire based on the defect testing component, constructing an electrical testing result array, dividing the electrical testing result array by adopting a detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule; the defect point collection module is used for collecting images of a plurality of defect positions based on the defect analysis component, carrying out graying treatment, and identifying the plurality of graying images to obtain a defect point collection; and the defect detection result module is used for generating a defect detection result of the surface of the copper-plated welding wire based on the defect point set.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the resistance testing component is adopted to carry out wire feeding resistance testing on the copper-plated welding wire so as to obtain a wire feeding resistance change curve, and defect scale information of the copper-plated welding wire is obtained through analysis, so that a basis is provided for setting of a follow-up detection operator; setting a detection operator for detecting surface defects according to the obtained defect scale information so as to ensure detection accuracy; adopting an electrical test component, setting a plurality of test points on the copper plating surface, obtaining a test result and constructing a result array so as to accurately locate a defect area; dividing an electrical test result by using a detection operator to obtain a local array of defects so as to accurately judge the positions of the defects; processing and identifying the image of the defect local array to obtain a defect point set so as to accurately obtain defect form information; according to the technical scheme of generating the accurate detection result of the copper plating surface defects by the defect point set, the technical problem that the detection accuracy of the copper plating welding wire surface defects is low in the prior art is solved, and the technical effect of improving the detection accuracy of the copper plating welding wire surface defects is achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting defects on a copper plating layer of a product according to an embodiment of the application;
FIG. 2 is a schematic flow chart of obtaining a defect point set in a defect detection method for a copper plating layer surface of a product according to an embodiment of the present application;
FIG. 3 is a schematic diagram showing a system for detecting defects on a copper plating layer of a product according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a resistance change curve module 11, a defect scale information module 12, a defect detection operator module 13, a surface electrical test module 14, a defect point collection module 15 and a defect detection result module 16.
Detailed Description
The technical scheme provided by the application has the following overall thought:
the embodiment of the application provides a method and a system for detecting defects on the surface of a copper plating layer of a product, which improve the accuracy and the effect of detecting the defects on the surface of the copper plating layer through the organic combination of resistance test analysis, electrical test and defect image processing. Firstly, carrying out comprehensive wire feeding resistance analysis on the copper-plated welding wire by adopting a resistance test means, and judging the size of the defect by fitting a curve. Then, according to the obtained defect scale information, a detection operator for detecting the surface defects is set. And then, constructing a test result array of the copper plating surface by utilizing an electrical test, dividing the array by adopting a detection operator, and accurately positioning a defect area. Finally, the image of the defect area is processed and identified to generate an accurate detection result of the copper plating surface defect, so that the detection effect of the copper plating welding wire surface defect is obviously improved, the technical effect of accurately detecting the copper plating surface defect is achieved, and the technical problem that the copper plating surface defect detection result is inaccurate in the prior art is solved.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for detecting defects on a copper plating surface of a product, which is applied to a device for detecting defects on a copper plating surface of a product, the device including a resistance test part, a defect test part, and a defect analysis part.
The embodiment of the application discloses a defect detection method for a copper plating layer surface of a product, which is applied to a defect detection device for the copper plating layer surface of the product, wherein the defect detection device comprises a resistance test component, a defect test component and a defect analysis component. According to the method, the accurate detection of the surface defects of the copper plating layer of the product is realized through the cooperation of the resistance test component, the defect test component and the defect analysis component. The resistance testing component is used for testing wire feeding resistance of the copper-plated welding wire to be detected, and when the surface of the copper-plated layer has defects, the wire feeding resistance can be changed; the defect test component is used for performing electrical tests, such as current tests and the like, at a plurality of positions on the surface of the copper-plated welding wire so as to judge a defect local array and a defect position; the defect analysis component collects image information at the defect position, and determines a defect point set through image processing, so that an accurate copper plating surface defect detection result is generated.
The defect detection method comprises the following steps:
adopting a resistance testing component, feeding copper-plated welding wires to be tested, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve;
in the embodiment of the application, the resistance testing component is adopted to feed the copper-plated welding wire to be detected, so that the copper-plated welding wire passes through the resistance testing component at a certain speed, and the resistance testing component tests the passing resistance of the copper-plated welding wire in the wire feeding process, so as to obtain the wire feeding resistance. The wire feeding resistance refers to the resistance of the copper-plated welding wire in the wire feeding process. Through continuous testing, a set of time series of wire feed resistances, i.e., wire feed resistance series, is obtained. And then, performing curve fitting on the obtained wire feeding resistance sequence by adopting a least square method and other data fitting algorithms so as to obtain a continuous change curve of the wire feeding resistance along with time, namely a wire feeding resistance change curve, so that the real continuous change condition of the wire feeding resistance of the copper-plated welding wire can be reflected, and a basis is provided for subsequent defect scale analysis.
Calculating and obtaining a comprehensive curve change angle of a wire feeding resistance change curve, and analyzing and obtaining defect scale information of the copper-plated welding wire according to the comprehensive curve change angle;
further, the method specifically comprises the following steps:
acquiring a time interval for testing wire feeding resistance;
determining a plurality of calculation points in the wire feeding resistance change curve according to the time interval;
calculating the included angles of tangent lines of the wire feeding resistance change curves at a plurality of groups of two adjacent calculation points to obtain a curve change angle set;
and calculating the average value of the defect change angle set to obtain the comprehensive curve change angle.
Further, the method further comprises the following steps:
the method comprises the steps of calling historical detection data of a plurality of copper-plated welding wires, processing to obtain a sample comprehensive defect change angle record, and setting to obtain a sample defect scale information record according to defect areas of the plurality of copper-plated welding wires;
constructing a defect scale analysis path based on the sample comprehensive defect change angle record and the sample defect scale information record;
and inputting the defect scale analysis path according to the change angle of the comprehensive curve for analysis, and obtaining the defect scale information.
In a preferred embodiment, the set sampling frequency, i.e. the number of resistance sampling tests per second, is first obtained by the resistance testing means, and then the inverse of this sampling frequency is taken as a time interval, e.g. the sampling frequency is 50Hz, i.e. 50 tests per second, and the time interval is 0.02 seconds. And secondly, analyzing a time starting point and a time ending point of the wire feeding resistance change curve to obtain a total time range of the whole wire feeding process, dividing the total duration of the whole wire feeding process by taking a time interval as a step length to obtain a plurality of time points in the wire feeding resistance change curve, wherein the points on the wire feeding resistance change curve corresponding to the time points are a plurality of calculation points. And taking out two adjacent calculation points on the wire feeding resistance change curve pair by pair, for each pair of adjacent calculation points, firstly solving the first derivative of the curve at the two points to obtain the slope of the tangent line, and then obtaining the included angle of the tangent line at the two adjacent points according to the slope of the two tangent lines. And then, recording the calculated included angle into a curve change angle set. And circularly processing all adjacent calculation point pairs to obtain a curve change angle set containing tangential angles at all adjacent calculation points on the wire feeding resistance change curve. And traversing the curve change angle set, accumulating all angle values, calculating to obtain an angle value sum, and dividing the calculated angle value sum by the number of angles in the change angle set to obtain the comprehensive curve change angle.
Next, historical inspection data for a plurality of copper plated wire is retrieved from the database, the inspection data including wire feed resistance profiles for the respective wire. And processing the historical data, extracting the comprehensive change angle of each curve, and forming a sample comprehensive defect change angle record. Meanwhile, according to the actual defect area of each welding wire obtained during history detection, corresponding sample defect scale information records are set. And then, taking the obtained sample comprehensive defect change angle record and sample defect scale information record as sample data, adopting a machine learning algorithm to construct a defect scale analysis path, for example, adopting a supervised learning method, and adopting a sample data training model to construct a mapping relation between the comprehensive change angle and the defect scale, wherein the more the wire feeding resistance is changed more severely, the larger the defect scale is, so that angle-to-scale prediction is realized. And then, inputting the comprehensive change angle corresponding to the wire feeding resistance change curve of the copper-plated welding wire to be detected into a trained defect scale analysis path, and outputting a corresponding defect scale prediction result as defect scale information according to the mapping relation obtained by training by the path so as to improve the detection efficiency and the detection accuracy.
Setting a detection operator for detecting the surface defects according to the defect scale information;
in the embodiment of the application, a detection operator for carrying out subsequent surface defect detection is set according to the obtained defect scale information of the copper-plated welding wire. The detection operator is used for dividing an electrical test result when the copper-plated welding wire is subjected to electrical test, and the detection operator is used for influencing the efficiency of the electrical test and the accuracy of the detection result. Specifically, when the defect size is small, a detection operator with a small size, for example, a matrix operator with a size of 2×2 is set; and when the defect size is larger, a larger detection operator, such as a 3×3 matrix operator or larger matrix operator, is arranged, so that the size of the detection window is matched with the defect size, and the detection efficiency is improved.
Based on the defect testing component, performing electrical testing at a plurality of positions on the surface of the copper-plated welding wire, constructing an electrical testing result array, dividing the electrical testing result array by adopting the detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule;
further, the method also comprises the following steps:
performing electrical tests on a plurality of positions on the surface of the copper-plated welding wire to obtain a plurality of electrical test results, and constructing an electrical test result array, wherein each electrical test result comprises current;
dividing an electrical test result array according to the detection operator to obtain a plurality of local arrays;
judging whether the maximum value and the minimum value of the electrical test result in each local array are larger than an electrical test difference threshold value according to a first judging rule, if so, judging the local array as a defective local array, and if not, calculating to obtain an electrical test result mean value in the local array;
judging whether the average value of the electrical test results is larger than or equal to an electrical test average value threshold value, if so, judging the electrical test results to be a normal local array, and if not, judging the electrical test results to be a special defect local array, wherein all positions in the special defect local array are defect positions;
a plurality of defect local arrays are statistically obtained.
Judging whether the electrical test result of the edge position in the defect local array is smaller than the electrical test result of the central position after tolerance compensation according to a second judging rule based on the plurality of defect local arrays, if so, marking as 1, and if not, marking as 0, so as to obtain a plurality of judging vectors;
if the judgment vector is 0, the position marked as 1 is taken as a defect position, and if the judgment vector is not 0, the central position is taken as a defect position;
and counting to obtain a plurality of defect positions.
In a preferred embodiment, first, sampling intervals are set on the surface of the copper-plated wire, and a plurality of sampling detection positions are determined. Secondly, through the defect test part, a plurality of probes are arranged around the surface of the copper-plated welding wire at each preset detection position, so that the copper-plated welding wire can be detected around the surface at one position. And electrifying the copper-plated welding wire, and acquiring an electrical detection result of each sampling detection position by using a probe, wherein the electrical detection result comprises a current value of the sampling detection position, so that a plurality of electrical test results are obtained. The current test results are then consolidated into an array to construct an array of electrical test results. Then, the preset detection operator is used as the window size of the electrical test result array, for example, windows of 2×2 and 3×3, according to the window size, the window is gradually slid in the vertical and horizontal directions of the array from the upper left corner on the electrical test result array, and when the window slides to a position, the electrical results in the window are taken out as a local array. And repeatedly sliding until the window scans the whole electrical test result array to obtain a plurality of local arrays.
Then, in each local array, finding the electrical test result with the largest current value as the maximum current value, and simultaneously finding the electrical test result with the smallest current value as the minimum current value, subtracting the minimum current value from the maximum current value, and calculating the current difference value in the local array. And then, reading an electrical test difference value threshold value preset according to the requirements of the copper-plated welding wire product, comparing the current difference value of the local array with the threshold value, and judging the local array as a defect local array according to a first judging rule if the current difference value of the local array is larger than the electrical test difference value threshold value.
If the current difference is not greater than the electrical test difference threshold, whether defects exist or not cannot be directly judged, and at the moment, the average value of all current values in the local array is calculated to obtain the average value of electrical test results in the local array. And then, reading a preset current average value judgment threshold value, and comparing the current average value of the local array with the current average value judgment threshold value. If the average value of the electrical test results of the local array is greater than or equal to the current average value judgment threshold value, judging that the local array is a normal local array. If the average value of the electrical test results is smaller than the current average value judgment threshold value, judging that the local array is a special defect local array. In a special defect local array, all locations within it are defect locations.
Traversing all the local arrays, judging the local arrays according to the first judging rule, and counting all the defect local arrays to obtain a plurality of defect local arrays.
And then, finding the current value of the central position of any defect local array, and performing tolerance compensation to obtain an electrical test result of the central position after the tolerance compensation. Meanwhile, sequentially taking out the edge positions of the array, respectively judging whether the current value of the array is smaller than the compensated central current value, and if the current value of the edge is smaller, marking with 1; otherwise, it is marked as 0. The marking results of the edge positions of the array are then concatenated to form a discrimination vector. Repeating the above flow for a plurality of defect local arrays to obtain a plurality of discrimination vectors. If there is a position marked 0 in the vector, indicating that the edge current value of the position is not lower than the center, it is determined that the position marked 1 is a true defect position. In contrast, if the discrimination vectors are all 1, it is indicated that the edge current values are all lower than the center, and the center position is determined as the defective position. The plurality of discrimination vectors are processed to obtain a plurality of defect positions.
Based on the defect analysis part, acquiring images of a plurality of defect positions, carrying out graying treatment, and identifying the plurality of graying images to obtain a defect point set;
further, as shown in fig. 2, the method further includes:
collecting images of a plurality of defect positions and carrying out graying treatment to obtain a plurality of graying images;
constructing a defect point identification path, and embedding the defect point identification path into the defect analysis component;
and obtaining a defect point set, wherein the defect point set is obtained by inputting a plurality of grayscale images into the defect point identification path for image feature extraction and identification.
Further, constructing the defect point identification path specifically includes:
calling an image of a defect position of a copper-plated welding wire with a surface defect to obtain a defect graying image set;
marking the defects in each defect graying image in the defect graying image set to obtain a defect marking result set;
constructing a defect point identification path based on a deep convolution network;
and training the defect point identification path by adopting the defect graying image set and the defect marking result set until convergence.
In a preferred embodiment, the defect analysis component has integrated therein an image acquisition unit comprising illumination, an image sensor, an image processor, etc. The image sensor is sequentially aligned to a plurality of defect positions through the defect analysis component, the illumination light source is turned on and adjusted to proper illumination, reflected light is acquired by the image sensor and is converted into a digital image signal, the digital image signal is input into the image processor, and an RGB-to-gray conversion algorithm is executed to obtain a plurality of gray images.
Meanwhile, a defect point identification path is constructed and embedded into the defect analysis component, so that the defect analysis component has the capability of identifying grayscale images and obtaining defect points. Firstly, calling a defect position image corresponding to a copper-plated welding wire with a surface defect from a database, and carrying out graying treatment to obtain a defect graying image set containing defect characteristics; manually marking the defect position of each defect grey-scale image in the defect grey-scale image set, if the defect position is marked by a small square box, generating a defect marking result set containing manual marking information; and constructing a defect point identification path by using a convolutional neural network algorithm in deep learning, performing a great amount of training on the defect point identification path by using the prepared defect graying image set and the defect marking result set, continuously adjusting a model parameter optimization model until a training loss value converges to obtain the defect point identification path capable of automatically identifying the defect point on the surface of the copper-plated welding wire, and embedding the path into a defect analysis component so as to improve detection precision and efficiency.
Then, the defect analysis unit sequentially uses the obtained plurality of gray-scale images containing defects as input defect point recognition paths, the recognition paths perform feature extraction on the input gray-scale images, low-level features such as textures and edges of the images are extracted through convolution operation, and then the low-level features are combined into high-level semantic features through multi-level feature conversion and synthesis to recognize defect point areas in the images. And repeating the processing on each image, and finally summarizing the identification results of each image to form a defect point set containing all defect point information, thereby providing support for generating accurate defect detection results.
And generating a defect detection result of the surface of the copper-plated welding wire based on the defect point set.
In the embodiment of the application, firstly, the copper-plated welding wire is digitally modeled, mapping is carried out on the digital model of the copper-plated welding wire according to the data of the defect point set, and all the defect points at the corresponding positions are marked. And then, calculating and obtaining key statistical parameters such as the number, density distribution, maximum and minimum defect areas and the like of the surface defects of the copper-plated welding wire. And finally, generating a defect detection result by using the copper-plated welding wire model with the defect point marks and each obtained defect evaluation parameter through statistics. The detection result comprehensively reflects the surface defect condition of the copper-plated welding wire, and comprises the results of position labeling, defect statistics and the like, and the results are intuitively displayed to quality control personnel to serve as the basis for judging the quality of the copper-plated welding wire.
In summary, the method for detecting the defects on the surface of the copper plating layer of the product provided by the embodiment of the application has the following technical effects:
adopting a resistance testing component, feeding a copper-plated welding wire to be tested, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve, so as to provide a basis for obtaining defect scale information of the copper-plated welding wire; calculating and obtaining a comprehensive curve change angle of a wire feeding resistance change curve, analyzing and obtaining defect scale information of the copper-plated welding wire according to the comprehensive curve change angle, and providing support for setting a detection operator; setting a detection operator for detecting surface defects according to the defect scale information so as to ensure detection accuracy; based on the defect test part, performing electrical test at a plurality of positions on the surface of the copper-plated welding wire, constructing an electrical test result array, dividing the electrical test result array by adopting a detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule so as to position specific areas of defects on the copper-plated surface; based on the defect analysis component, acquiring images of a plurality of defect positions, carrying out gray processing, identifying the plurality of gray images to obtain a defect point set, and providing support for generating a defect detection result of the surface of the copper-plated welding wire; based on the defect point set, a defect detection result of the surface of the copper-plated welding wire is generated, and the purpose of improving the defect detection accuracy of the copper-plated surface is achieved.
Example two
Based on the same inventive concept as the defect detection method of a product copper plating layer surface in the foregoing embodiments, as shown in fig. 3, an embodiment of the present application provides a defect detection system of a product copper plating layer surface, which is applied to a defect detection apparatus of a product copper plating layer surface, the apparatus including a resistance test part, a defect test part, and a defect analysis part, the system including:
the resistance change curve module 11 is used for feeding the copper-plated welding wire to be tested to the wire by adopting a resistance test component, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve;
the defect scale information module 12 is used for calculating and acquiring the comprehensive curve change angle of the wire feeding resistance change curve and analyzing and acquiring the defect scale information of the copper-plated welding wire according to the comprehensive curve change angle;
a defect detection operator module 13, configured to set a detection operator for performing surface defect detection according to the defect scale information;
the surface electrical testing module 14 is configured to perform electrical testing at a plurality of positions on the surface of the copper-plated welding wire based on the defect testing component, construct an electrical testing result array, divide the electrical testing result array by using the detection operator to obtain a plurality of local arrays, and judge to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule;
a defect point collection module 15, configured to collect images of a plurality of defect positions based on the defect analysis unit, perform grayscale processing, and identify the plurality of grayscale images to obtain a defect point collection;
and a defect detection result module 16, configured to generate a defect detection result of the surface of the copper-plated welding wire based on the defect point set.
Further, the defect-size information module 12 includes the following steps:
acquiring a time interval for testing wire feeding resistance;
determining a plurality of calculation points in the wire feeding resistance change curve according to the time interval;
calculating the included angles of tangent lines of the wire feeding resistance change curves at a plurality of groups of two adjacent calculation points to obtain a curve change angle set;
and calculating the average value of the defect change angle set to obtain the comprehensive curve change angle.
Further, the defect-size information module 12 further includes the following steps:
the method comprises the steps of calling historical detection data of a plurality of copper-plated welding wires, processing to obtain a sample comprehensive defect change angle record, and setting to obtain a sample defect scale information record according to defect areas of the plurality of copper-plated welding wires;
constructing a defect scale analysis path based on the sample comprehensive defect change angle record and the sample defect scale information record;
and inputting the defect scale analysis path according to the change angle of the comprehensive curve for analysis, and obtaining the defect scale information.
Further, the surface electrical test module 14 includes the following execution steps:
performing electrical tests on a plurality of positions on the surface of the copper-plated welding wire to obtain a plurality of electrical test results, and constructing an electrical test result array, wherein each electrical test result comprises current;
dividing an electrical test result array according to the detection operator to obtain a plurality of local arrays;
judging whether the maximum value and the minimum value of the electrical test result in each local array are larger than an electrical test difference threshold value according to a first judging rule, if so, judging the local array as a defective local array, and if not, calculating to obtain an electrical test result mean value in the local array;
judging whether the average value of the electrical test results is larger than or equal to an electrical test average value threshold value, if so, judging the electrical test results to be a normal local array, and if not, judging the electrical test results to be a special defect local array, wherein all positions in the special defect local array are defect positions;
a plurality of defect local arrays are statistically obtained.
Further, the surface electrical test module 14 further comprises the following execution steps:
judging whether the electrical test result of the edge position in the defect local array is smaller than the electrical test result of the central position after tolerance compensation according to a second judging rule based on the plurality of defect local arrays, if so, marking as 1, and if not, marking as 0, so as to obtain a plurality of judging vectors;
if the judgment vector is 0, the position marked as 1 is taken as a defect position, and if the judgment vector is not 0, the central position is taken as a defect position;
and counting to obtain a plurality of defect positions.
Further, the defect point collecting module 15 includes the following steps:
collecting images of a plurality of defect positions and carrying out graying treatment to obtain a plurality of graying images;
constructing a defect point identification path, and embedding the defect point identification path into the defect analysis component;
and obtaining a defect point set, wherein the defect point set is obtained by inputting a plurality of grayscale images into the defect point identification path for image feature extraction and identification.
Further, the defect point collecting module 15 further includes the following steps:
calling an image of a defect position of a copper-plated welding wire with a surface defect to obtain a defect graying image set;
marking the defects in each defect graying image in the defect graying image set to obtain a defect marking result set;
constructing a defect point identification path based on a deep convolution network;
and training the defect point identification path by adopting the defect graying image set and the defect marking result set until convergence.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. A method for detecting defects on a copper plating surface of a product, the method being applied to a defect detecting device for a copper plating surface of a product, the device including a resistance test part, a defect test part, and a defect analysis part, the method comprising:
adopting a resistance testing component, feeding copper-plated welding wires to be tested, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve;
calculating and obtaining a comprehensive curve change angle of a wire feeding resistance change curve, and analyzing and obtaining defect scale information of the copper-plated welding wire according to the comprehensive curve change angle;
setting a detection operator for detecting the surface defects according to the defect scale information;
based on the defect testing component, performing electrical testing at a plurality of positions on the surface of the copper-plated welding wire, constructing an electrical testing result array, dividing the electrical testing result array by adopting the detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule;
based on the defect analysis part, acquiring images of a plurality of defect positions, carrying out graying treatment, and identifying the plurality of graying images to obtain a defect point set;
and generating a defect detection result of the surface of the copper-plated welding wire based on the defect point set.
2. The method according to claim 1, characterized in that the method comprises:
acquiring a time interval for testing wire feeding resistance;
determining a plurality of calculation points in the wire feeding resistance change curve according to the time interval;
calculating the included angles of tangent lines of the wire feeding resistance change curves at a plurality of groups of two adjacent calculation points to obtain a curve change angle set;
and calculating the average value of the defect change angle set to obtain the comprehensive curve change angle.
3. The method according to claim 1, characterized in that the method comprises:
the method comprises the steps of calling historical detection data of a plurality of copper-plated welding wires, processing to obtain a sample comprehensive defect change angle record, and setting to obtain a sample defect scale information record according to defect areas of the plurality of copper-plated welding wires;
constructing a defect scale analysis path based on the sample comprehensive defect change angle record and the sample defect scale information record;
and inputting the defect scale analysis path according to the change angle of the comprehensive curve for analysis, and obtaining the defect scale information.
4. The method according to claim 1, characterized in that the method comprises:
performing electrical tests on a plurality of positions on the surface of the copper-plated welding wire to obtain a plurality of electrical test results, and constructing an electrical test result array, wherein each electrical test result comprises current;
dividing an electrical test result array according to the detection operator to obtain a plurality of local arrays;
judging whether the maximum value and the minimum value of the electrical test result in each local array are larger than an electrical test difference threshold value according to a first judging rule, if so, judging the local array as a defective local array, and if not, calculating to obtain an electrical test result mean value in the local array;
judging whether the average value of the electrical test results is larger than or equal to an electrical test average value threshold value, if so, judging the electrical test results to be a normal local array, and if not, judging the electrical test results to be a special defect local array, wherein all positions in the special defect local array are defect positions;
a plurality of defect local arrays are statistically obtained.
5. The method according to claim 4, characterized in that the method comprises:
judging whether the electrical test result of the edge position in the defect local array is smaller than the electrical test result of the central position after tolerance compensation according to a second judging rule based on the plurality of defect local arrays, if so, marking as 1, and if not, marking as 0, so as to obtain a plurality of judging vectors;
if the judgment vector is 0, the position marked as 1 is taken as a defect position, and if the judgment vector is not 0, the central position is taken as a defect position;
and counting to obtain a plurality of defect positions.
6. The method according to claim 1, characterized in that the method comprises:
collecting images of a plurality of defect positions and carrying out graying treatment to obtain a plurality of graying images;
constructing a defect point identification path, and embedding the defect point identification path into the defect analysis component;
and obtaining a defect point set, wherein the defect point set is obtained by inputting a plurality of grayscale images into the defect point identification path for image feature extraction and identification.
7. The method according to claim 6, characterized in that the method comprises:
calling an image of a defect position of a copper-plated welding wire with a surface defect to obtain a defect graying image set;
marking the defects in each defect graying image in the defect graying image set to obtain a defect marking result set;
constructing a defect point identification path based on a deep convolution network;
and training the defect point identification path by adopting the defect graying image set and the defect marking result set until convergence.
8. A defect inspection system for a copper clad surface of a product for performing a defect inspection method for a copper clad surface of a product according to any one of claims 1 to 7, the system being applied to a defect inspection apparatus for a copper clad surface of a product, the apparatus including a resistance test part, a defect test part, and a defect analysis part, the system comprising:
the resistance change curve module is used for feeding the copper-plated welding wire to be tested to the wire by adopting a resistance test component, testing and obtaining wire feeding resistance, obtaining a wire feeding resistance sequence, and fitting to obtain a wire feeding resistance change curve;
the defect scale information module is used for calculating and acquiring a comprehensive curve change angle of a wire feeding resistance change curve and analyzing and acquiring defect scale information of the copper-plated welding wire according to the comprehensive curve change angle;
the defect detection operator module is used for setting a detection operator for detecting surface defects according to the defect scale information;
the surface electrical testing module is used for carrying out electrical testing on a plurality of positions on the surface of the copper-plated welding wire based on the defect testing component, constructing an electrical testing result array, dividing the electrical testing result array by adopting the detection operator to obtain a plurality of local arrays, and judging to obtain a plurality of defect local arrays and a plurality of defect positions according to a first judging rule and a second judging rule;
the defect point collecting module is used for collecting images of a plurality of defect positions based on the defect analyzing component, carrying out graying treatment, and identifying a plurality of graying images to obtain a defect point set;
and the defect detection result module is used for generating a defect detection result of the surface of the copper-plated welding wire based on the defect point set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311247637.6A CN116990229B (en) | 2023-09-26 | 2023-09-26 | Defect detection method and system for copper plating layer surface of product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311247637.6A CN116990229B (en) | 2023-09-26 | 2023-09-26 | Defect detection method and system for copper plating layer surface of product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116990229A true CN116990229A (en) | 2023-11-03 |
| CN116990229B CN116990229B (en) | 2023-12-08 |
Family
ID=88530514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311247637.6A Active CN116990229B (en) | 2023-09-26 | 2023-09-26 | Defect detection method and system for copper plating layer surface of product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116990229B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102998314A (en) * | 2012-11-26 | 2013-03-27 | 杭州电子科技大学 | Surface defect detecting device of copper-plating layer of gravure cylinder |
| JP2013167596A (en) * | 2012-02-17 | 2013-08-29 | Honda Motor Co Ltd | Defect inspection device, defect inspection method, and program |
| CN103909325A (en) * | 2014-03-26 | 2014-07-09 | 河海大学 | Welding quality monitoring system |
| CN106596587A (en) * | 2017-01-03 | 2017-04-26 | 山东广富集团有限公司 | Testing evaluation method for welding wire copper plate quality |
| CN109454006A (en) * | 2018-10-08 | 2019-03-12 | 杭州慧知连科技有限公司 | Chemical fiber wire ingot is stumbled the device and its detection stage division of a defect on-line checking and classification |
| CN114463329A (en) * | 2022-04-12 | 2022-05-10 | 苏芯物联技术(南京)有限公司 | Welding defect detection method and system based on image and time sequence data fusion |
| CN115766901A (en) * | 2023-01-09 | 2023-03-07 | 武汉精测电子集团股份有限公司 | Data transmission equipment and method of image sensor |
| CN116298768A (en) * | 2023-03-22 | 2023-06-23 | 中国科学院微电子研究所 | Defect test system and test method for carbon nano tube thin film transistor |
| CN116448181A (en) * | 2023-04-23 | 2023-07-18 | 中达科技(浙江)有限公司 | System and method for measuring welding stability of welding wire |
| CN116563641A (en) * | 2023-05-30 | 2023-08-08 | 江西软件职业技术大学 | Surface defect identification method and system based on small target detection |
-
2023
- 2023-09-26 CN CN202311247637.6A patent/CN116990229B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013167596A (en) * | 2012-02-17 | 2013-08-29 | Honda Motor Co Ltd | Defect inspection device, defect inspection method, and program |
| CN102998314A (en) * | 2012-11-26 | 2013-03-27 | 杭州电子科技大学 | Surface defect detecting device of copper-plating layer of gravure cylinder |
| CN103909325A (en) * | 2014-03-26 | 2014-07-09 | 河海大学 | Welding quality monitoring system |
| CN106596587A (en) * | 2017-01-03 | 2017-04-26 | 山东广富集团有限公司 | Testing evaluation method for welding wire copper plate quality |
| CN109454006A (en) * | 2018-10-08 | 2019-03-12 | 杭州慧知连科技有限公司 | Chemical fiber wire ingot is stumbled the device and its detection stage division of a defect on-line checking and classification |
| CN114463329A (en) * | 2022-04-12 | 2022-05-10 | 苏芯物联技术(南京)有限公司 | Welding defect detection method and system based on image and time sequence data fusion |
| CN115766901A (en) * | 2023-01-09 | 2023-03-07 | 武汉精测电子集团股份有限公司 | Data transmission equipment and method of image sensor |
| CN116298768A (en) * | 2023-03-22 | 2023-06-23 | 中国科学院微电子研究所 | Defect test system and test method for carbon nano tube thin film transistor |
| CN116448181A (en) * | 2023-04-23 | 2023-07-18 | 中达科技(浙江)有限公司 | System and method for measuring welding stability of welding wire |
| CN116563641A (en) * | 2023-05-30 | 2023-08-08 | 江西软件职业技术大学 | Surface defect identification method and system based on small target detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116990229B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111862064B (en) | Silver wire surface flaw identification method based on deep learning | |
| JP3733094B2 (en) | Pass / fail judgment device, pass / fail judgment program, and pass / fail judgment method | |
| CN111024728B (en) | Railway detection method and system based on computer vision and ultrasonic flaw detection | |
| CN102473660A (en) | Automatic fault detection and classification in a plasma processing system and methods thereof | |
| KR20210150970A (en) | Detecting defects in semiconductor specimens using weak labeling | |
| CN113487533B (en) | Part assembly quality digital detection system and method based on machine learning | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN115311629B (en) | Abnormal bending precision monitoring system of bending machine | |
| CN111783616B (en) | Nondestructive testing method based on data-driven self-learning | |
| CN110568082A (en) | cable wire breakage distinguishing method based on acoustic emission signals | |
| CN112529109A (en) | Unsupervised multi-model-based anomaly detection method and system | |
| CN111753877B (en) | Product quality detection method based on deep neural network migration learning | |
| CN114022715A (en) | Method and device for detecting lead sealing defect of high-voltage cable terminal | |
| CN110728269A (en) | High-speed rail contact net support pole number plate identification method | |
| CN113554645B (en) | Industrial anomaly detection method and device based on WGAN | |
| CN112215307B (en) | Method for automatically detecting signal abnormality of earthquake instrument by machine learning | |
| CN116990229B (en) | Defect detection method and system for copper plating layer surface of product | |
| CN115625317B (en) | Surface water wave optimization processing method and system for die casting regulation and control | |
| CN116662800A (en) | Rolling bearing fault diagnosis method based on self-adaptive attention mechanism | |
| CN116756372A (en) | Cigarette defect detection method and device | |
| CN115830514A (en) | Method and system for calculating surface flow velocity of whole river section of riverway with curve | |
| CN111189906B (en) | On-line intelligent judging and classifying identification method for alternating current magnetic field defects | |
| CN115255567A (en) | Welding deviation real-time detection method and system based on frequency domain and time-frequency domain characteristics | |
| CN114911085A (en) | Method for analyzing defects | |
| CN117289075B (en) | Cable performance detection method and system |
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 |