CN112881427A - Electronic component defect detection device and method based on visible light and infrared thermal imaging - Google Patents
Electronic component defect detection device and method based on visible light and infrared thermal imaging Download PDFInfo
- Publication number
- CN112881427A CN112881427A CN202110041762.6A CN202110041762A CN112881427A CN 112881427 A CN112881427 A CN 112881427A CN 202110041762 A CN202110041762 A CN 202110041762A CN 112881427 A CN112881427 A CN 112881427A
- Authority
- CN
- China
- Prior art keywords
- visible light
- camera system
- infrared
- electronic component
- defect
- 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
-
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- 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
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
-
- 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a defect detection device and method for electronic components based on visible light and infrared thermal imaging.A laser heater, a visible light camera system and an infrared camera system are sequentially arranged above a workpiece conveyor belt according to the conveying direction; the infrared camera system is arranged on the sliding rail in a sliding manner; the infrared camera system and the visible light camera system are both connected with an industrial personal computer; the visible light camera system is used for collecting visible light pictures and transmitting the visible light pictures to the industrial personal computer; the industrial personal computer controls the infrared camera system to move and take pictures. The invention adopts the visible light camera to identify and position the component workpiece, thereby effectively identifying the mixed workpiece and product impurities. After the type identification and the foreign matter identification of the electronic component are completed, the heated electronic component enters a shooting area of the infrared camera. The laser is adopted to heat the electronic components, in order to reduce the volume of the whole machine, the infrared heating area can be overlapped with the visible light shooting area, and the visible light camera is additionally provided with an infrared filter.
Description
Technical Field
The invention belongs to the technical field of electronic component detection, and particularly relates to a visible light and infrared thermal imaging electronic component defect detection device and method, which are used for quality detection of surface defects and internal defects of electronic component products.
Background
The current electronic component surface defect detection industry uses detection equipment for identifying simple defects and a manual auxiliary detection mode, the method has low automation degree, low efficiency and very high production cost, and the current equipment has limited detection capability and cannot identify complex defects such as dark stripes, cracks in background noise, internal injury and the like.
In the field of electronic component production and processing, an automatic assembly line is basically realized at present. Taking a precision winding inductor as an example, an electronic component is generally processed by the following steps: (1) materials such as a magnetic core and the like are sent into a production line from an equipment inlet, and coil winding is completed on a precision winding machine in sequence through a conveyor belt; (2) then the enameled wire is conveyed to laser paint removing equipment through a conveyor belt, and the surface coating of the enameled wire is removed; (3) then the welding wire is conveyed to an automatic pin welding table through a conveying belt to complete the welding of the paint removing wire end and the magnetic core welding point; (4) then the silk screen is sent to a laser silk screen printing machine through a conveyor belt to finish the etching of silk screen printing; (5) and finally, conveying the product to a quality detection station through a conveying belt, and finishing a detection process by CCD equipment or manpower to ensure the product to be intact.
The precision winding inductor has the advantages that knowledge in the machining process needs more than 5 times, the mechanical transmission process of a conveyor belt or a clamp is high in mechanical transmission efficiency, but the defect is obvious, namely, physical damage is caused to components, and the index, the precision and the performance of a product are influenced. When in the production process, once mechanical movement makes enameled coil receive the extrusion and pulls, can lead to coil deformation tensile, solder joint to become flexible, once the length of every circle coil is excessively inhomogeneous, can lead to the quality factor can not satisfy the product requirement. It can be seen that computationally tiny device defects may result in: (1) the basic parameter indexes of the product can not meet the requirements. (2) The index uniformity of the product is not good. (3) Product life and power consumption are also potentially problematic. Therefore, a general component processing device has a special detection unit.
The current mainstream detection methods include two types according to the defect complexity: one is simple defects, which are automatically identified by the machine after image processing using a CCD imaging detection or infrared imaging unit. The method comprises the steps of preprocessing images, comparing and judging whether defects exist or not through a template method, or separating defect images through angular point characteristic detection and an SVM classifier. The implementation method is also used by most products on the market at present, and is characterized by being capable of realizing complete automatic detection, but only effective to a few simple defects.
In the other method, aiming at complex defects, fine dark stripes on the surface of a component, cracks under a rough texture background, cracks on fine crack silk screen printing in a stain background and other complex defect characteristics, the current factory practice mainly displays a processed image on a display, and quality detection workers pick out defective products through naked eyes. For the detection of complex defects, important problems currently exist:
(1) manual defect detection has high requirements on workers, a product line needs to be provided with a plurality of workers every day to ensure the normal operation of the production line, and the payroll cost paid by enterprises is very high;
(2) the manual defect detection has high requirements on the degree of seriousness of workers, and the probability of mistaken scoring is greatly improved because the workers have the problems of dazzling, inattention, psychasthenia and the like after working for a long time every day;
(3) if the existing automatic detection technology is adopted, the complex defects have complex background noise, interference such as amplified porous texture characteristics, silk-screen false defects and the like cannot be eliminated, and the detection rate of the product is seriously influenced.
(4) The existing detection method can not be effective for the defects of dark lines, internal injuries and the like.
Disclosure of Invention
Aiming at a precise electronic component to be detected such as an inductor and the like, the invention provides a visible light and infrared thermal imaging electronic component defect detection device and method. The defects of scratches, broken corners, cracks, dark cracks and the like are also the key bottlenecks in the defect detection of the conventional electronic components, are common problems in the industry and have high value. The invention adopts the computer vision technology of infrared flaw detection and visible light fusion, improves the detection function of defects such as scratches, corner breakages, cracks, dark cracks and the like which are difficult to detect, and improves the defect detection rate of electronic components. Through the accurate electronic components after this equipment detects, need not artifical the detection, reach the requirement of product yields, provide production efficiency, reduction in production cost. Meanwhile, through the localization of the technology, the selling price of the equipment is reduced, and the technical upgrading in the field of the defect detection of the precise electronic components is further promoted.
The specific technical scheme is as follows:
the defect detection device for the electronic component based on visible light and infrared thermal imaging is characterized in that a laser heater, a visible light camera system and an infrared camera system are sequentially arranged above a workpiece conveyor belt in the conveying direction; the infrared camera system is arranged on the sliding rail in a sliding manner;
the infrared camera system and the visible light camera system are both connected with an industrial personal computer;
the visible light camera system is used for collecting visible light pictures and transmitting the visible light pictures to the industrial personal computer; the industrial personal computer controls the infrared camera system to move and take pictures.
The infrared camera system comprises an infrared camera and an optical lens, the infrared camera is fixed on the linear motor, and the linear motor is slidably mounted on the sliding rail; the linear motor is connected with the driver through a control flat cable, and the driver is connected with the industrial personal computer.
The visible light camera system comprises a visible light camera, a lens and a light supplement lamp.
The electronic component defect detection method based on visible light and infrared thermal imaging comprises the following steps:
a visible light camera system collects a visible light picture; the method comprises the steps that an industrial personal computer is uploaded after pictures are collected, the industrial personal computer adopts a target recognition neural network for recognition, whether a workpiece is of a specified type of an electronic component is judged, if the workpiece is of the specified type of the electronic component, the coordinate position (x, y) of the component is further calculated, the coordinate position is provided for an infrared camera system, the infrared camera system moves to a proper position and shoots surface images of the component heated by a laser heater, and a target detection unit carries out defect detection by utilizing the surface images; if the electronic component type is not the appointed type, judging that the electronic component is other electronic components or foreign matters, and providing the electronic component or the foreign matters for the sorting unit to clean;
after the target detection unit finishes classifying and positioning images of the defective electronic components, the position information (x, y), the defect size (w, h) and the defect category c of the defective electronic components are sent to the sorting unit, the sorting unit judges after receiving the information, whether the electronic components with the defects exist at the specified positions or not is determined, and the electronic components with the defects exist at the specified positions and are cleaned.
The target detection unit receives the surface image of the component heated by the laser heater 4 shot by the infrared camera system 2, and sends the image to the defect target detection convolutional neural network after image preprocessing, and the convolutional neural network outputs the coordinate position information (x, y), the defect size (w, h) and the defect type c of the workpiece;
the method for constructing the convolutional neural network comprises the following steps:
s1, collecting over 5000 infrared pictures of the defective workpiece and the normal workpiece respectively;
s2, manually marking the positions, sizes and types of the defects, wherein the types of the defects comprise seven types of scratches, broken corners, cracks, dark cracks, silk-screen printing, normal and other types;
s3, increasing the number of various samples to more than 5 thousands of samples by data enhancement methods such as rotation, scaling, gray level adjustment, noise increase, random cutting and the like;
s4, checking the number of various samples, and ensuring that the number of various images is close through the enhancement method in the step S3;
s5, sending the preprocessed infrared images as training set and test set data into a target detection network for training, wherein the target detection network is not limited to SSD, YOLO, FasterCNN and other target detection networks;
s6, storing the training model after the training is finished;
and S7, loading a training model for defect detection.
The invention adopts the visible light camera to identify and position the component workpiece, and can also effectively identify the mixed workpiece and product impurities. After the type identification and the foreign matter identification of the electronic component are completed, the heated electronic component enters a shooting area of the infrared camera. According to the invention, the laser is adopted to heat the electronic components, so that the size of the whole machine is reduced, the infrared heating area can be overlapped with the visible light shooting area, and in order to avoid interference, the visible light camera is additionally provided with the infrared filter so as to reduce the interference of infrared light on the visible light camera.
(1) According to the invention, through infrared thermal imaging, not only can defect characteristics such as scratches, broken corners, cracks and the like be obtained, but also dark crack characteristics can be captured, and target detection is carried out on image defects through a neural network, so that the detection efficiency is greatly improved.
(2) Compared with a visible light image, the infrared thermal imaging picture adopted by the invention is interfered by less noise points, and the surface silk-screen texture can be pressed to a certain degree, so that the interference of the noise points and the silk-screen on the defect detection is avoided.
(3) The method can distinguish the product defects, can identify the defect types directly on the basis of defect detection through the multi-classification neural network, is convenient for subsequent defect root analysis, and can reduce the interference of silk-screen on the defect detection accuracy by introducing the silk-screen defect types.
(4) The invention adopts the visible light camera for identifying and positioning a plurality of components, can inspect other workpieces and foreign matters, sends infrared images into the neural network to detect defects, reduces the calculated amount of the industrial personal computer by a high-speed moving shooting mode of the linear motor, and improves the detection efficiency of the workpieces.
The invention has the advantages of full-automatic detection, great improvement on production efficiency and capability of saving a large amount of labor cost. The invention can detect the defects that human eyes and the existing equipment can not observe, has more accurate classification and reduced error fraction rate, and improves the yield of products. And the defects can be qualitatively and quantitatively analyzed, the problem of production line can be quickly positioned and solved, and the production capacity of the production line can be improved.
Drawings
FIG. 1 is a schematic diagram of the apparatus of the present invention;
FIG. 2 is a schematic diagram of an infrared camera system according to the present invention;
FIG. 3 is a schematic view of the detection process of the present invention;
FIG. 4 is one of the detection schematics of the present invention;
FIG. 5 is a second schematic diagram of the detection of the present invention.
Detailed Description
The specific embodiments are incorporated in and constitute a part of this specification.
As shown in fig. 1, a defect detection device for electronic components based on visible light and infrared thermal imaging is provided with a laser heater 4, a visible light camera system 3 and an infrared camera system 2 above a workpiece conveyor belt 5 in sequence according to the conveying direction; the infrared camera system 2 is slidably mounted on the slide rail 1;
the infrared camera system 2 and the visible light camera system 3 are both connected with an industrial personal computer;
the visible light camera system 3 is used for collecting visible light pictures and transmitting the visible light pictures to the industrial personal computer; the industrial personal computer controls the infrared camera system 2 to move and take pictures.
As shown in fig. 2, the slide rail 1 is mounted on the support structure 21, the infrared camera system 2 includes an infrared camera 26 and an optical lens 27, the infrared camera 26 is fixed on the linear motor 23, and the linear motor 23 is slidably mounted on the slide rail 1; the linear motor 23 is connected with a driver 25 through a control flat cable 24, and the driver 25 is connected with an industrial personal computer.
The visible light camera system 3 includes a visible light camera, a lens and a fill-in light.
As shown in fig. 3, the method for detecting defects of electronic components by visible light and infrared thermal imaging comprises the following steps:
the visible light camera system 3 collects a visible light picture; the method comprises the steps that an industrial personal computer is uploaded after pictures are collected, the industrial personal computer adopts a target recognition neural network for recognition, whether a workpiece is of a specified type of electronic component is judged, if the workpiece is of the specified type of electronic component, the coordinate position (x, y) of the component is further calculated, the coordinate position is provided for an infrared camera system 2, the infrared camera system 2 moves to a proper position and shoots a surface image of the component heated by a laser heater 4, and a target detection unit utilizes the surface image for defect detection; if the electronic component type is not the appointed type, judging that the electronic component is other electronic components or foreign matters, and providing the electronic component or the foreign matters for the sorting unit to clean;
after the target detection unit finishes classifying and positioning images of the defective electronic components, the position information (x, y), the defect size (w, h) and the defect category c of the defective electronic components are sent to the sorting unit, the sorting unit judges after receiving the information, whether the electronic components with the defects exist at the specified positions or not is determined, and the electronic components with the defects exist at the specified positions and are cleaned.
The target detection unit receives the surface image of the component heated by the laser heater 4 shot by the infrared camera system 2, and sends the image to the defect target detection convolutional neural network after image preprocessing, and the convolutional neural network outputs the coordinate position information (x, y), the defect size (w, h) and the defect type c of the workpiece;
the method for constructing the convolutional neural network comprises the following steps:
s1, collecting over 5000 infrared pictures of the defective workpiece and the normal workpiece respectively;
s2, manually marking the positions, sizes and types of the defects, wherein the types of the defects comprise seven types of scratches, broken corners, cracks, dark cracks, silk-screen printing, normal and other types;
s3, increasing the number of various samples to more than 5 thousands of samples by data enhancement methods such as rotation, scaling, gray level adjustment, noise increase, random cutting and the like;
s4, checking the number of various samples, and ensuring that the number of various images is close through the enhancement method in the step S3;
s5, sending the preprocessed infrared images as training set and test set data into a target detection network for training, wherein the target detection network is not limited to SSD, YOLO, FasterCNN and other target detection networks;
s6, storing the training model after the training is finished;
and S7, loading a training model for defect detection.
In order to improve the detection efficiency of the system, the invention adds a visible light image sensor and a linear motor 23. The visible light image sensor is a visible light camera system 3 and is mainly used for detecting and positioning components, and the linear motor 23 is mainly used for driving the infrared image sensor unit, namely the infrared camera system 2 to move.
As shown in fig. 2, the slide rail 1 is fixed to the support structure 21, the linear motor 23 is mounted on the slide rail 1, the infrared camera 26 and the optical lens 27 are mounted on the bottom of the linear motor 23 through the structure, and the linear motor 23 is operated to move in a straight line with the infrared camera 26 and the optical lens 27.
The power supply, the infrared camera signal line and the linear motor control line are connected with a driver 25 arranged on the supporting structural member through a control flat cable 24, the driver 25 is communicated with the industrial personal computer through a USB interface, the industrial personal computer drives the linear motor 23 to pull the infrared camera 26 and the optical lens 27 to a specified position through positioning information, and the industrial personal computer is uploaded after photographing and used for defect positioning and recognition.
As shown in fig. 1, the visible light camera system 3 is located in front of the infrared camera system 2, the center position of the visible light camera system 3 is away from the center position s of the infrared camera system 2, and is used for identifying components and performing optical measurement, locating the center position (x, y) of the components, the conveyor belt moves at a constant speed according to the speed v after location, after the interval t is y/v time, the coordinate position of the components is (x,0), the components reach the positions below the infrared camera 26 and the optical lens 27, the infrared camera 26 and the optical lens 27 are driven by the linear motor 23 to move to the (x,0) positions, the component photos are taken, and the component photos are sent to the model for reasoning.
The infrared camera system 2 can take a picture of only one component at a time, and can identify the pictures by using a defect target identification network, so that the problem of processing simultaneous detection of a plurality of components is solved. By introducing the linear motor 23, the computational complexity is reduced.
As shown in fig. 4 and 5, the electronic component 6 is on the workpiece conveyor 5, and the workpiece conveyor 5 is rotated from right to left, and after laser heating by the laser heater 4, the surface temperature of the electronic component 6 rises, and the response of the defect to the temperature is different from that of the defect-free portion, and the response of different defects to the temperature is also different. Therefore, the defect feature maps seen by the pictures acquired through infrared thermal imaging have differences, and defect detection and defect classification can be carried out based on the features.
The electronic component 6 will generally identify the chip type using laser engraving techniques, which will form on the surface of the component, similar to the texture of scratch defects, and will reduce the accuracy of defect identification between them. In order to reduce the interference of the screen printing nicks on the accuracy, the screen printing area is used as an independent labeling class, so that the temperature response difference caused by the difference of screen printing etching can be prevented, the condition that the screen printing is mistakenly identified as a crack curve can be avoided, and the samples identified as the screen printing and the normal samples belong to normal samples in actual use.
Claims (9)
1. The electronic component defect detection device based on visible light and infrared thermal imaging is characterized in that a laser heater (4), a visible light camera system (3) and an infrared camera system (2) are sequentially arranged above a workpiece conveyor belt (5) according to a conveying direction; the infrared camera system (2) is arranged on the sliding rail (1) in a sliding manner;
the infrared camera system (2) and the visible light camera system (3) are both connected with an industrial personal computer;
the visible light camera system (3) is used for collecting visible light pictures and transmitting the visible light pictures to the industrial personal computer; the industrial personal computer controls the infrared camera system (2) to move and take pictures.
2. The electronic component defect detection device based on visible light and infrared thermal imaging as claimed in claim 1, wherein the slide rail (1) is mounted on the support structure (21), the infrared camera system (2) comprises an infrared camera (26) and an optical lens (27), the infrared camera (26) is fixed on the linear motor (23), and the linear motor (23) is slidably mounted on the slide rail (1); the linear motor (23) is connected with a driver (25) through a control flat cable (24), and the driver (25) is connected with an industrial personal computer.
3. The device for detecting the defects of the electronic components based on visible light and infrared thermal imaging as claimed in claim 1, wherein the visible light camera system (3) comprises a visible light camera, a lens and a light supplement lamp.
4. The method for detecting the defect detection device of the visible light and infrared thermal imaging electronic component as claimed in any one of claims 1 to 3, characterized by comprising the following steps:
a visible light camera system (3) collects a visible light picture; the method comprises the steps that an industrial personal computer is uploaded after pictures are collected, the industrial personal computer adopts a target recognition neural network for recognition, whether a workpiece is of a specified type of electronic component is judged, if the workpiece is of the specified type of electronic component, the coordinate position (x, y) of the component is further calculated, the coordinate position is provided for an infrared camera system (2), the infrared camera system (2) moves to a proper position and shoots surface images of the component heated by a laser heater (4), and a target detection unit utilizes the surface images for defect detection; if the electronic component type is not the appointed type, judging that the electronic component is other electronic components or foreign matters, and providing the electronic component or the foreign matters for the sorting unit to clean;
after the target detection unit finishes classifying and positioning images of the defective electronic components, the position information (x, y), the defect size (w, h) and the defect category c of the defective electronic components are sent to the sorting unit, the sorting unit judges after receiving the information, whether the electronic components with the defects exist at the specified positions or not is determined, and the electronic components with the defects exist at the specified positions and are cleaned.
5. The method for detecting the defect detection device of the visible light and infrared thermal imaging electronic component as claimed in claim 4, wherein the target detection unit receives the image of the surface of the component heated by the laser heater (4) shot by the infrared camera system (2), and after image preprocessing, the image is sent to a defect target detection convolutional neural network, and the convolutional neural network outputs the coordinate position information (x, y), the defect size (w, h) and the defect type c of the workpiece.
6. The detection method of the electronic component defect detection device based on visible light and infrared thermal imaging as claimed in claim 5, wherein the method for constructing the convolutional neural network comprises:
s1, collecting over 5000 infrared pictures of the defective workpiece and the normal workpiece respectively;
s2, manually marking the position, the size and the type of the defect;
s3, increasing the number of various samples to more than 5 thousands of samples by a data enhancement method;
s4, checking the number of various samples, and ensuring that the number of various images is close through the enhancement method in the step S3;
s5, sending the preprocessed infrared image as a training set and a test set data into a target detection network for training;
s6, storing the training model after the training is finished;
and S7, loading a training model for defect detection.
7. The detecting method of the electronic component defect detecting device based on visible light and infrared thermal imaging as claimed in claim 6, wherein the defect categories include scratch, chipping, crack, dark crack, silk screen, normal, and other seven categories.
8. The detecting method of the defect detecting device of the electronic component based on visible light and infrared thermal imaging as claimed in claim 6, wherein the data enhancing method comprises rotation, scaling, gray scale adjustment, noise increase, and random cropping.
9. The detecting method of the defect detecting device of the electronic component based on visible light and infrared thermal imaging as claimed in claim 6, wherein the target detecting network comprises SSD, YOLO, FasterCNN.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110041762.6A CN112881427B (en) | 2021-01-13 | 2021-01-13 | Electronic component defect detection device and method based on visible light and infrared thermal imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110041762.6A CN112881427B (en) | 2021-01-13 | 2021-01-13 | Electronic component defect detection device and method based on visible light and infrared thermal imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112881427A true CN112881427A (en) | 2021-06-01 |
| CN112881427B CN112881427B (en) | 2023-06-13 |
Family
ID=76045297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110041762.6A Active CN112881427B (en) | 2021-01-13 | 2021-01-13 | Electronic component defect detection device and method based on visible light and infrared thermal imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112881427B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113267508A (en) * | 2021-06-18 | 2021-08-17 | 苏州鹰蚁视觉科技有限公司 | Electronic component defect detection equipment and detection method |
| CN114487016A (en) * | 2021-09-23 | 2022-05-13 | 合肥维信诺科技有限公司 | Fracture detection device and fracture detection method |
| CN114585253A (en) * | 2022-03-15 | 2022-06-03 | 杭州测质成科技有限公司 | PCB component installation and rechecking system and method based on image recognition |
| CN115082434A (en) * | 2022-07-21 | 2022-09-20 | 浙江华是科技股份有限公司 | Multi-source feature-based magnetic core defect detection model training method and system |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010054693A1 (en) * | 1998-08-21 | 2001-12-27 | Trw Inc. | Method and apparatus for inspection of a substrate by use of a ring illuminator |
| US20030030002A1 (en) * | 2000-06-05 | 2003-02-13 | Morteza Safai | Infrared crack detection apparatus and method |
| JP2007271507A (en) * | 2006-03-31 | 2007-10-18 | Dainippon Printing Co Ltd | Defect detecting method, defect detector and defect detecting program |
| WO2009073014A1 (en) * | 2007-12-06 | 2009-06-11 | Lockheed Martin Corporation | Non-destructive inspection using laser- ultrasound and infrared thermography |
| CN101788500A (en) * | 2009-01-23 | 2010-07-28 | 宇创视觉科技股份有限公司 | Optical detection device for solar cell and method thereof |
| CN102472711A (en) * | 2009-07-15 | 2012-05-23 | 有限会社共同设计企画 | Substrate inspecting apparatus |
| CN105466945A (en) * | 2015-12-30 | 2016-04-06 | 深圳市创科自动化控制技术有限公司 | Infrared detecting method for automatically locating detecting position and detecting equipment |
| CN109060822A (en) * | 2018-07-17 | 2018-12-21 | 上海大学 | Long pulse Infrared Non-destructive Testing sequence specific primers-polymerase chain reaction method and system |
| US20190003983A1 (en) * | 2017-07-03 | 2019-01-03 | Saudi Arabian Oil Company | Apparatus and method for nondestructively inspecting fiberglass and nonmetallic pipes |
| CN110560377A (en) * | 2019-09-11 | 2019-12-13 | 河南奇测电子科技有限公司 | Cylindrical metal surface defect detection device based on machine vision |
| CN111103303A (en) * | 2018-10-27 | 2020-05-05 | 成都四加二驴途电子商务有限责任公司 | Automatic detection control system for micro precision bearing |
| CN111141741A (en) * | 2019-12-09 | 2020-05-12 | 合肥迪宏自动化有限公司 | Detection apparatus capable of identifying label defects of printer |
| CN111795977A (en) * | 2020-06-08 | 2020-10-20 | 武汉大学 | Online real-time monitoring system for multiple monitoring devices in metal additive manufacturing |
| CN111999308A (en) * | 2020-08-27 | 2020-11-27 | 银河水滴科技（北京）有限公司 | Defect detection control method, control device and control system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005016991A (en) * | 2003-06-24 | 2005-01-20 | Railway Technical Res Inst | Infrared structure diagnosis system |
| JP4607821B2 (en) * | 2006-05-26 | 2011-01-05 | 株式会社日立製作所 | Underwater defect inspection apparatus and underwater defect inspection method |
| CN205607877U (en) * | 2015-12-14 | 2016-09-28 | 昆明理工大学 | Utilize image acquisition device of auxiliary laser point formation of image |
| CN207908384U (en) * | 2017-10-13 | 2018-09-25 | 成都精工华耀科技有限公司 | A kind of double light spectrum image-forming rails and fastener abnormal detector |
| CN108732507A (en) * | 2018-05-21 | 2018-11-02 | 中国科学技术大学 | A kind of lithium battery defect detecting device based on battery temperature field and visible images |
-
2021
- 2021-01-13 CN CN202110041762.6A patent/CN112881427B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010054693A1 (en) * | 1998-08-21 | 2001-12-27 | Trw Inc. | Method and apparatus for inspection of a substrate by use of a ring illuminator |
| US20030030002A1 (en) * | 2000-06-05 | 2003-02-13 | Morteza Safai | Infrared crack detection apparatus and method |
| JP2007271507A (en) * | 2006-03-31 | 2007-10-18 | Dainippon Printing Co Ltd | Defect detecting method, defect detector and defect detecting program |
| WO2009073014A1 (en) * | 2007-12-06 | 2009-06-11 | Lockheed Martin Corporation | Non-destructive inspection using laser- ultrasound and infrared thermography |
| CN101788500A (en) * | 2009-01-23 | 2010-07-28 | 宇创视觉科技股份有限公司 | Optical detection device for solar cell and method thereof |
| CN102472711A (en) * | 2009-07-15 | 2012-05-23 | 有限会社共同设计企画 | Substrate inspecting apparatus |
| CN105466945A (en) * | 2015-12-30 | 2016-04-06 | 深圳市创科自动化控制技术有限公司 | Infrared detecting method for automatically locating detecting position and detecting equipment |
| US20190003983A1 (en) * | 2017-07-03 | 2019-01-03 | Saudi Arabian Oil Company | Apparatus and method for nondestructively inspecting fiberglass and nonmetallic pipes |
| US20200041420A1 (en) * | 2017-07-03 | 2020-02-06 | Saudi Arabian Oil Company | System for nondestructively inspecting fiberglass and nonmetallic pipes |
| CN109060822A (en) * | 2018-07-17 | 2018-12-21 | 上海大学 | Long pulse Infrared Non-destructive Testing sequence specific primers-polymerase chain reaction method and system |
| CN111103303A (en) * | 2018-10-27 | 2020-05-05 | 成都四加二驴途电子商务有限责任公司 | Automatic detection control system for micro precision bearing |
| CN110560377A (en) * | 2019-09-11 | 2019-12-13 | 河南奇测电子科技有限公司 | Cylindrical metal surface defect detection device based on machine vision |
| CN111141741A (en) * | 2019-12-09 | 2020-05-12 | 合肥迪宏自动化有限公司 | Detection apparatus capable of identifying label defects of printer |
| CN111795977A (en) * | 2020-06-08 | 2020-10-20 | 武汉大学 | Online real-time monitoring system for multiple monitoring devices in metal additive manufacturing |
| CN111999308A (en) * | 2020-08-27 | 2020-11-27 | 银河水滴科技（北京）有限公司 | Defect detection control method, control device and control system |
Non-Patent Citations (1)
| Title |
|---|
| 李文璞等: "基于Faster RCNN变电设备红外图像缺陷识别方法", 《南方电网技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113267508A (en) * | 2021-06-18 | 2021-08-17 | 苏州鹰蚁视觉科技有限公司 | Electronic component defect detection equipment and detection method |
| CN114487016A (en) * | 2021-09-23 | 2022-05-13 | 合肥维信诺科技有限公司 | Fracture detection device and fracture detection method |
| CN114487016B (en) * | 2021-09-23 | 2024-07-09 | 合肥维信诺科技有限公司 | Fracture detection device and fracture detection method |
| CN114585253A (en) * | 2022-03-15 | 2022-06-03 | 杭州测质成科技有限公司 | PCB component installation and rechecking system and method based on image recognition |
| CN115082434A (en) * | 2022-07-21 | 2022-09-20 | 浙江华是科技股份有限公司 | Multi-source feature-based magnetic core defect detection model training method and system |
| CN115082434B (en) * | 2022-07-21 | 2022-12-09 | 浙江华是科技股份有限公司 | Multi-source feature-based magnetic core defect detection model training method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112881427B (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112881427B (en) | Electronic component defect detection device and method based on visible light and infrared thermal imaging | |
| CN109724984B (en) | Defect detection and identification device and method based on deep learning algorithm | |
| CN108465648A (en) | A kind of magnetic core Automated Sorting System based on machine vision | |
| CN106670127A (en) | Full-automatic visual inspection system for screen defects | |
| CN201218723Y (en) | Optoelectronic non-contact type image detection apparatus | |
| CN110216080A (en) | Quality monitoring system of PCB processing production line based on image contrast | |
| CN111220544A (en) | Lens quality detection device and detection method | |
| CN109142509B (en) | Round steel magnetic powder flaw detection method and device | |
| CN112150439B (en) | Automatic sorting equipment and sorting method for injection molding parts | |
| CN113894055A (en) | Hardware surface defect detection and classification system and method based on machine vision | |
| CN203245133U (en) | Lens defect detecting system | |
| CN106353336A (en) | Lens coating automatic detection system | |
| CN212301356U (en) | Wheel hub welding seam visual detection device | |
| CN111060518A (en) | Stamping part defect identification method based on instance segmentation | |
| CN115436394A (en) | Appearance defect detection system and method | |
| CN116448780A (en) | Chip defect detection device, method and equipment | |
| CN113744247A (en) | PCB welding spot defect identification method and system | |
| CN115060742A (en) | Printed circuit board defect detection system and method based on visual edge calculation | |
| CN114571287A (en) | Machine tool workpiece online detection and analysis system based on big data | |
| CN111307817B (en) | Online detection method and system for PCB production process of intelligent production line | |
| CN107121063A (en) | The method for detecting workpiece | |
| CN111239162A (en) | Full-automatic glasses lens check out test set | |
| CN114392940B (en) | Pin detection method and device for special-shaped component | |
| CN211905142U (en) | Full-automatic glasses lens check out test set | |
| CN116078704A (en) | Appearance detection equipment based on CCD |
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 |