Intelligent detection method and system of flying probe machine for large-scale circuit board testing
By identifying the circuit board testing environment and performing intelligent path planning, the test cost and accuracy problems caused by the change of probe paths in the circuit board detection of the flying needle tester is solved, and more efficient circuit board detection is achieved, reducing energy consumption and maintenance is achieved. cost.
Patent Information
- Application Number
- CN202410652403.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-24
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-05-24
AI Technical Summary
In the circuit board detection, the existing fly needle tester has caused changes in probe paths to increase testing costs, reduce test accuracy and extend test time due to circuit board layout and physical limitations. The existing open-circuit pairing algorithm has a high complexity, which affects efficiency.
By identifying the circuit board test environment, adaptive overall image capture and functional area division, building feature image sets, identifying and classifying defect fault features, performing three-dimensional geometric modeling to intelligently plan probe paths, predict detection progress in real time, and pass The optical lens and the robotic arm are visually displayed.
Improves test coverage and accuracy, reduces test time and robotic arm movement, reduces energy consumption and maintenance costs, and extends equipment life.
Smart Images

Figure CN118330443B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of intelligent detection, and relates to an intelligent detection method and system of a flying probe machine for large-scale circuit board testing. Background Art
[0002] A flying probe is an automated test device used for circuit board inspection. It can perform fast and flexible comprehensive circuit board testing without the need to make test fixtures. It is widely used in the production of printed circuit boards. Online testing verifies whether the electrical and electronic components of the circuit board have been correctly soldered. When testing with a flying probe, several probes move simultaneously on the circuit board to reach and contact multiple test points. Taking into account the layout of the circuit board, the characteristics of the tester, and some other physical limitations, not all probe movements are compatible with each other, nor can they always be performed in a simple straight line. Since the cost of the test is mainly related to its length, and patching the path of one probe may create new incompatibilities with the tracks of other probes, the time required to find the tracks should be carefully weighed against the time required for the probe to track them.
[0003] In the existing disclosed invention technology, for example, the patent with application publication number CN105911450A discloses a method for optimizing the open circuit test path of a flying probe tester, and the method includes the following steps: A. Read and organize the information required for path optimization; B. Pair the points of each network in a loop, and then merge the pairings; B1. Establish the first to thirteenth containers; B2. Read the front points and back points of the same network from the front testable point container and the back testable point container, respectively, and save them in the first container and the second container, respectively; B3. Rearrange the points in the first and second containers; B4. Perform open circuit pairing; B7. Merge the pairs and put them into the thirteenth container after merging; C. Open circuit optimization; D. Generate a test file: After the open circuit optimization is completed, generate a new CONTI.LST file.
[0004] The above patent lacks a clear open-circuit pairing algorithm, which may lead to inaccurate or incomplete pairing results, and the cyclic pairing and merging operations may lead to higher algorithm complexity, especially when the number of test points is large, which may affect the efficiency of test path optimization, and there are technical problems mentioned in the background technology. Summary of the invention
[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.
[0006] The technical problem to be solved by the present invention is that in the prior art, when a flying probe is used for testing, if several probes move simultaneously on a circuit board to reach and contact multiple test points, the test path of the probe will change due to the layout of the circuit board, the function of the flying probe machine and some other physical limitations, thereby increasing the test cost, test accuracy and test time. An intelligent detection method and system of a flying probe machine for large-scale circuit board testing are proposed.
[0007] In order to achieve the above object, the technical solution of the flying probe machine intelligent detection method for large-scale circuit board testing of the present invention comprises the following steps:
[0008] S1: Identify the test environment of the large-scale circuit board to be tested, adaptively capture and detect the overall image of the large-scale circuit board to be tested through an optical lens, and divide the overall image into functional areas;
[0009] S2: Construct a feature image set of a large-scale circuit board to be tested, and perform defect fault feature recognition and classification on the circuit board component images;
[0010] S3: 3D geometric modeling of the flying probe machine’s robotic arm and intelligent planning of the test path of the detection probe;
[0011] S4: According to the test path length of each detection probe, the detection progress of the flying probe machine is predicted in real time, and the detection completion degree is judged;
[0012] S5: Collect and extract the defects and faults of the large-scale circuit boards to be tested, and visualize them in the manual operation interface.
[0013] Specifically, in S1, the identification of the test environment of the large-scale circuit board to be tested includes: scanning and capturing the large-scale circuit board to be tested as a whole through the built-in optical lenses on the four robotic arms of the flying probe machine, and dividing the flying probe area, the no-fly zone and the flying probe machine test area according to the component functions of the large-scale circuit board to be tested, wherein the no-fly zone of the flying probe machine includes: high voltage zone, sensitive component zone, and RF zone. In three-dimensional geometric modeling, a no-fly zone of a flying probe machine is a single small rectangle; each of the four robotic arms of the flying probe machine carries a detection probe.
[0014] Specifically, S2 includes the following specific steps:
[0015] S21: combining the flying probe machine test areas after the functional area division in S1, obtaining a test area training image set of the large-scale circuit board to be tested, and graying the images in the image set;
[0016] S22: Divide each test area training image into X detection squares with an area of s, wherein the feature vector of each detection square represents the defect fault feature of the detection square;
[0017] S23: performing data dimensionality reduction processing on the test area training image set by using a principal component analysis algorithm, and forming a low-dimensional vector set of the test area training image, including: X feature vectors;
[0018] S24: projecting the low-dimensional vector set of the test area training image into the vector space, wherein the test area training images of different grayscales correspond to standard orthogonal bases of sine waves of different frequencies;
[0019] S25: Using a feature classifier, the low-dimensional vector set of the test area training image on the vector space is compared with the standard vector space corresponding to the predefined standard circuit board to perform defect fault classification search.
[0020] Specifically, in S3, the three-dimensional geometric modeling of the robot arm of the flying needle machine includes: taking the first robot arm fixed on the large-scale circuit board to be tested as the origin O, and the remaining three robot arms move along three dimensions in the three-dimensional geometric space respectively, and the coordinate points of the real-time movement are ; The detection source is , the detection target point is .
[0021] Specifically, the intelligent planning of the test path of the detection probe includes:
[0022] S31: Identify the source of detection Number of no-fly zones around the flying needle area H , where the number of no-fly zones in the flying needle area H satisfy ;
[0023] S32: Determine the detection source Is there a no-fly zone around the flying needle area? If not, the intelligent optimal planning path is the detection source. To the detection target point If there is a straight line path, execute step S33;
[0024] S33: When detecting the source Number of no-fly zones around the flying needle area When the source is detected, step S34 is executed; Number of no-fly zones around the flying needle area When , execute step S35;
[0025] S34: Determine the detection source To the detection target point The geometric relationship between the straight line path and the two edges of the small rectangle intersecting the no-fly zone of the flying needle area in the three-dimensional geometric modeling;
[0026] When the geometric relationship between two intersecting edges is perpendicular, the source of the detection To the detection target point The detection path is planned into two path segments, including: detection source To the intersection of two intersecting edges The intersection of two intersecting edges To the detection target point ;
[0027] When the geometric relationship between two intersecting edges is parallel, the source of the detection To the detection target point The detection path is planned into three path segments, including: detection source To the vertex of the small rectangle , the vertices of the small rectangle To the vertex of the small rectangle and the vertices of the small rectangle To the detection target point ;
[0028] S35: Detecting the source To the detection target point The detection path is planned into four path segments, including: detection source Go to the first no-fly zone small rectangle vertex , the first no-fly zone small rectangle vertex Go to the first no-fly zone small rectangle vertex , the first no-fly zone small rectangle vertex To the second no-fly zone small rectangle vertex and the second no-fly zone small rectangle vertex To the detection target point .
[0029] In S4, the calculation strategy of the regional detection progress a of each robotic arm of the flying needle machine is as follows:
[0030] ;
[0031] Among them, Perform dimensionless processing;
[0032] is the sum of the lengths of the detection paths of all detection points of the large-scale circuit board to be tested;
[0033] The length of the test path between the test points in the large-scale circuit board to be tested that do not pass through the no-fly zone of the flying probe machine;
[0034] is the length of the test path between the test points that pass through the no-fly zone of the flying probe machine in the large-scale circuit board to be tested;
[0035] It is the movement coefficient of the detection probe on the flying probe machine robot arm between the detection points passing through the flying probe machine's no-fly zone;
[0036] is the number of small rectangular vertices involved when the detection path between the detection points passing through the no-fly zone of the flying probe machine in the large-scale circuit board to be tested is divided into path segments;
[0037] Specifically, in S5, the defect failures of the large-scale circuit board include: assembly defects and test defects; wherein the assembly defects include: missing parts, centering, wrong parts, reversed parts, and solder paste accumulation.
[0038] In addition, the flying probe machine intelligent detection system for large-scale circuit board testing of the present invention includes the following modules:
[0039] Overall image capture module, feature recognition module, intelligent path planning module, detection progress judgment module, and visualization module;
[0040] The overall image capture module is used to identify the test environment of the large-scale circuit board to be tested, adaptively capture and detect the overall image of the large-scale circuit board to be tested through an optical lens, and divide the overall image into functional areas;
[0041] The feature recognition module is used to construct a feature image set of a large-scale circuit board to be tested, and to perform defect fault feature recognition and classification on the circuit board component image;
[0042] The intelligent path planning module is used to perform three-dimensional geometric modeling on the mechanical arm of the flying probe machine and to intelligently plan the test path of the detection probe;
[0043] The detection progress judgment module predicts the regional detection progress of each mechanical arm of the flying probe machine in real time according to the test path length of each detection probe, and makes a detection progress judgment;
[0044] The visualization module is used to collect and extract the defects and faults of the large-scale circuit boards to be tested, and visualize them on a manual operation interface.
[0045] The visualization module includes: an image display unit, a functional area display module, a path planning display unit, and a defect data display unit.
[0046] A storage medium stores instructions, and when a computer reads the instructions, the computer is enabled to execute any one of the above-mentioned flying probe machine intelligent detection methods for large-scale circuit board testing.
[0047] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the above-mentioned flying probe machine intelligent detection methods for large-scale circuit board testing is implemented.
[0048] Compared with the prior art, the technical effects of the present invention are as follows:
[0049] 1. The present invention uses an optical lens to adaptively capture and detect the overall image of a large-scale circuit board to be tested in a manner similar to the characteristic face decomposition method of face recognition. The goal is to achieve a wider range of defect detection and reduce inspection time, thereby improving the test coverage and accuracy of the flying probe machine.
[0050] 2. The present invention performs three-dimensional geometric modeling on the robotic arm of the flying probe machine and intelligently plans the test path of the detection probe; the optimal test path can be found to minimize the test time and reduce the trajectory length of the robotic arm movement, which can improve the test efficiency, reduce the movement time of the robotic arm, and improve production efficiency. At the same time, it can avoid unnecessary movement and repetition of the robotic arm, reduce the wear and energy consumption of the robotic arm, extend the life of the equipment, and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0052] Figure 1 It is a flow chart of the intelligent detection method of the flying probe machine for large-scale circuit board testing of the present invention;
[0053] Figure 2 A schematic diagram of a process of identifying and classifying defect fault features of a circuit board component image according to the present invention;
[0054] Figure 3 An example diagram of intelligent planning of a test path of a detection probe of the present invention;
[0055] Figure 4 The schematic diagram of the structure of the flying probe machine intelligent detection system for large-scale circuit board testing of the present invention. DETAILED DESCRIPTION
[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments. Example
[0059] like Figure 1 , 2 , 3, the flying probe machine intelligent detection method for large-scale circuit board testing according to the embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:
[0060] S1: Identify the test environment of the large-scale circuit board to be tested, adaptively capture and detect the overall image of the large-scale circuit board to be tested through an optical lens, and divide the overall image into functional areas;
[0061] In S1, the identification of the test environment of the large-scale circuit board to be tested includes: scanning and capturing the large-scale circuit board to be tested as a whole through the built-in optical lenses on the four robotic arms of the flying probe machine, and dividing the flying probe area, the no-fly zone and the flying probe machine test area according to the component functions of the large-scale circuit board to be tested, wherein the no-fly zone of the flying probe machine includes: high voltage zone, sensitive component zone, and RF zone. In three-dimensional geometric modeling, a no-fly zone of a flying probe machine is a single small rectangle; each of the four robotic arms of the flying probe machine carries a detection probe.
[0062] S2: Construct a feature image set of a large-scale circuit board to be tested, and perform defect fault feature recognition and classification on the circuit board component images;
[0063] S2 includes the following specific steps:
[0064] S21: combining the flying probe machine test areas after the functional area division in S1, obtaining a test area training image set of the large-scale circuit board to be tested, and graying the images in the image set;
[0065] S22: Divide each test area training image into X detection squares with an area of s, wherein the feature vector of each detection square represents the defect fault feature of the detection square;
[0066] S23: performing data dimensionality reduction processing on the test area training image set by using a principal component analysis algorithm, and forming a low-dimensional vector set of the test area training image, including: X feature vectors;
[0067] S24: projecting the low-dimensional vector set of the test area training image into the vector space, wherein the test area training images of different grayscales correspond to standard orthogonal bases of sine waves of different frequencies;
[0068] S25: Using a feature classifier, the low-dimensional vector set of the test area training image on the vector space is compared with the standard vector space corresponding to the predefined standard circuit board to perform defect fault classification search.
[0069] S3: 3D geometric modeling of the flying probe machine’s robotic arm and intelligent planning of the test path of the detection probe;
[0070] In S3, the three-dimensional geometric modeling of the robot arm of the flying needle machine includes: taking the first robot arm fixed on the large-scale circuit board to be tested as the origin O, and the remaining three robot arms move along three dimensions in the three-dimensional geometric space respectively, and the coordinate points of the real-time movement are ; The detection source is , the detection target point is .
[0071] Intelligent planning of the test path for the detection probe includes:
[0072] S31: Identify the source of detection Number of no-fly zones around the flying needle area H , where the number of no-fly zones in the flying needle area H satisfy ;
[0073] S32: Determine the detection source Is there a no-fly zone around the flying needle area? If not, the intelligent optimal planning path is the detection source. To the detection target point If there is a straight line path, execute step S33;
[0074] S33: When detecting the source Number of no-fly zones around the flying needle area When the source is detected, step S34 is executed; Number of no-fly zones around the flying needle area When , execute step S35;
[0075] S34: Determine the detection source To the detection target point The geometric relationship between the straight line path and the two edges of the small rectangle intersecting the no-fly zone of the flying needle area in the three-dimensional geometric modeling;
[0076] When the geometric relationship between two intersecting edges is perpendicular, the source of the detection To the detection target point The detection path is planned into two path segments, including: detection source To the intersection of two intersecting edges The intersection of two intersecting edges To the detection target point ;
[0077] When the geometric relationship between two intersecting edges is parallel, the source of the detection To the detection target point The detection path is planned into three path segments, including: detection source To the vertex of the small rectangle , the vertices of the small rectangle To the vertex of the small rectangle and the vertices of the small rectangle To the detection target point ;
[0078] S35: Detecting the source To the detection target point The detection path is planned into four path segments, including: detection source Go to the first no-fly zone small rectangle vertex , the first no-fly zone small rectangle vertex Go to the first no-fly zone small rectangle vertex , the first no-fly zone small rectangle vertex To the second no-fly zone small rectangle vertex and the second no-fly zone small rectangle vertex To the detection target point .
[0079] S4: According to the test path length of each detection probe, the detection progress of the flying probe machine is predicted in real time, and the detection completion degree is judged;
[0080] In S4, the calculation strategy of the regional detection progress a of each robotic arm of the flying needle machine is as follows:
[0081] ;
[0082] Among them, Perform dimensionless processing;
[0083] is the sum of the lengths of the detection paths of all detection points of the large-scale circuit board to be tested;
[0084] The length of the test path between the test points in the large-scale circuit board to be tested that do not pass through the no-fly zone of the flying probe machine;
[0085] is the length of the test path between the test points that pass through the no-fly zone of the flying probe machine in the large-scale circuit board to be tested;
[0086] It is the movement coefficient of the detection probe on the flying probe machine robot arm between the detection points passing through the flying probe machine's no-fly zone;
[0087] is the number of small rectangular vertices involved when the detection path between the detection points passing through the no-fly zone of the flying probe machine in the large-scale circuit board to be tested is divided into path segments;
[0088] in, .
[0089] S5: Collect and extract the defects and faults of the large-scale circuit boards to be tested, and visualize them in the manual operation interface.
[0090] In S5, the defect failures of the large-scale circuit board include: assembly defects and test defects; wherein the assembly defects include: missing parts, centering, wrong parts, reversed parts, and solder paste accumulation.
[0091] Embodiment 2:
[0092] like Figure 4 As shown, the flying probe machine intelligent detection system for large-scale circuit board testing according to the embodiment of the present invention is as follows: Figure 4 As shown, it includes the following modules:
[0093] Overall image capture module, feature recognition module, intelligent path planning module, detection progress judgment module, and visualization module;
[0094] The overall image capture module is used to identify the test environment of the large-scale circuit board to be tested, adaptively capture and detect the overall image of the large-scale circuit board to be tested through an optical lens, and divide the overall image into functional areas;
[0095] The feature recognition module is used to construct a feature image set of a large-scale circuit board to be tested, and to perform defect fault feature recognition and classification on the circuit board component image;
[0096] The intelligent path planning module is used to perform three-dimensional geometric modeling on the mechanical arm of the flying probe machine and to intelligently plan the test path of the detection probe;
[0097] The detection progress judgment module predicts the regional detection progress of each mechanical arm of the flying probe machine in real time according to the test path length of each detection probe, and makes a detection progress judgment;
[0098] The visualization module is used to collect and extract the defects and faults of the large-scale circuit boards to be tested, and visualize them on a manual operation interface.
[0099] The visualization module includes: an image display unit, a functional area display module, a path planning display unit, and a defect data display unit.
[0100] Embodiment three:
[0101] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;
[0102] The processor executes the above-mentioned flying probe machine intelligent detection method for large-scale circuit board testing by calling the computer program stored in the memory.
[0103] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the flying probe machine intelligent detection method for large-scale circuit board testing provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.
[0104] Embodiment 4:
[0105] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;
[0106] When the computer program runs on a computer device, the computer device is enabled to execute the above-mentioned flying probe machine intelligent detection method for large-scale circuit board testing.
[0107] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.
[0108] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0109] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.
[0110] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0111] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0113] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0116] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0117] In summary, compared with the prior art, the technical effects of the present invention are as follows:
[0118] 1. The present invention uses an optical lens to adaptively capture and detect the overall image of a large-scale circuit board to be tested in a manner similar to the characteristic face decomposition method of face recognition. The goal is to achieve a wider range of defect detection and reduce inspection time, thereby improving the test coverage and accuracy of the flying probe machine.
[0119] 2. The present invention performs three-dimensional geometric modeling on the robotic arm of the flying probe machine and intelligently plans the test path of the detection probe; the optimal test path can be found to minimize the test time and reduce the trajectory length of the robotic arm movement, which can improve the test efficiency, reduce the movement time of the robotic arm, and improve production efficiency. At the same time, it can avoid unnecessary movement and repetition of the robotic arm, reduce the wear and energy consumption of the robotic arm, extend the life of the equipment, and reduce maintenance costs.
[0120] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. The flying probe machine intelligent detection method for large-scale circuit board testing is characterized by: The method comprises the following specific steps: S1: Identify the test environment of the large-scale circuit board to be tested, adaptively capture and detect the overall image of the large-scale circuit board to be tested through an optical lens, and divide the overall image into functional areas; S2: Construct a feature image set of a large-scale circuit board to be tested, and perform defect fault feature recognition and classification on the circuit board component images; S3: 3D geometric modeling of the flying probe machine’s robotic arm and intelligent planning of the test path of the detection probe; S4: According to the test path length of each detection probe, the detection progress of the flying probe machine is predicted in real time, and the detection completion degree is judged; S5: Collect and extract the defects and faults of the large-scale circuit boards to be tested, and visualize them in the manual operation interface; In S1, the identification of the test environment of the large-scale circuit board to be tested includes: scanning and capturing the large-scale circuit board to be tested as a whole through the built-in optical lenses on the four mechanical arms of the flying probe machine, and dividing the flying probe area, the no-fly zone and the flying probe machine test area according to the component functions of the large-scale circuit board to be tested, wherein the no-fly zone of the flying probe machine includes: high voltage zone, sensitive component zone, RF zone, and in three-dimensional geometric modeling, a no-fly zone of the flying probe machine is a single small rectangle; each of the four mechanical arms of the flying probe machine carries a detection probe; S2 includes the following specific steps: S21: combining the flying probe machine test areas after the functional area division in S1, obtaining a test area training image set of the large-scale circuit board to be tested, and graying the images in the image set; S22: Divide each test area training image into X detection squares with an area of s, wherein the feature vector of each detection square represents the defect fault feature of the detection square; S23: performing data dimensionality reduction processing on the test area training image set by using a principal component analysis algorithm, and forming a low-dimensional vector set of the test area training image, including: X feature vectors; S24: projecting the low-dimensional vector set of the test area training image into the vector space, wherein the test area training images of different grayscales correspond to standard orthogonal bases of sine waves of different frequencies; S25: using a feature classifier, performing defect fault classification search on the low-dimensional vector set of the test area training image on the vector space and the standard vector space corresponding to the predefined standard circuit board; In S3, the three-dimensional geometric modeling of the robot arm of the flying needle machine includes: taking the first robot arm fixed on the large-scale circuit board to be tested as the origin O, and the remaining three robot arms move along three dimensions in the three-dimensional geometric space respectively, and the coordinate points of the real-time movement are ; The detection source is , the detection target point is ; Intelligent planning of the test path for the detection probe includes: S31: Identify the source of detection The number H of the no-fly zones in the surrounding flying probe area, where the number H of the no-fly zones in the flying probe area satisfies H=0,1,2,3; S32: Determine the detection source Is there a no-fly zone around the flying needle area? If not, the intelligent optimal planning path is the detection source. To the detection target point If there is a straight line path, execute step S33; S33: When detecting the source When the number of no-fly zones in the surrounding flying probe area is H=1, step S34 is executed; when the detection source When the number of no-fly zones in the surrounding flying needle area is H=2,3, execute step S35; S34: Determine the detection source To the detection target point The geometric relationship between the straight line path and the two edges of the small rectangle intersecting the no-fly zone of the flying needle area in the three-dimensional geometric modeling; When the geometric relationship between two intersecting edges is perpendicular, the source of the detection To the detection target point The detection path is planned into two path segments, including: detection source To the intersection of two intersecting edges The intersection of two intersecting edges To the detection target point ; When the geometric relationship between two intersecting edges is parallel, the source of the detection To the detection target point The detection path is planned into three path segments, including: detection source To the vertex of the small rectangle , the vertices of the small rectangle To the vertex of the small rectangle and the vertices of the small rectangle To the detection target point ; S35: Detecting the source To the detection target point The detection path is planned into four path segments, including: detection source Go to the first no-fly zone small rectangle vertex , the first no-fly zone small rectangle vertex Go to the first no-fly zone small rectangle vertex , the first no-fly zone small rectangle vertex To the second no-fly zone small rectangle vertex and the second no-fly zone small rectangle vertex To the detection target point ; In S4, the regional inspection progress of each robot arm of the flying needle machine The calculation strategy is as follows: ; Among them, Perform dimensionless processing; is the sum of the lengths of the detection paths of all detection points of the large-scale circuit board to be tested; The length of the test path between the test points in the large-scale circuit board to be tested that do not pass through the no-fly zone of the flying probe machine; is the length of the test path between the test points that pass through the no-fly zone of the flying probe machine in the large-scale circuit board to be tested; It is the movement coefficient of the detection probe on the flying probe machine robot arm between the detection points passing through the flying probe machine's no-fly zone; It is the number of small rectangular vertices involved when the detection path between detection points passing through the no-fly zone of the flying probe machine in the large-scale circuit board to be tested is divided into path segments.
2. The flying probe machine intelligent detection method for large-scale circuit board testing according to claim 1 is characterized in that: In S5, the defect failures of the large-scale circuit board include: assembly defects and test defects; wherein the assembly defects include: missing parts, centering, wrong parts, reversed parts, and solder paste accumulation.
3. A flying probe machine intelligent detection method system for large-scale circuit board testing, which is implemented based on a vehicle driving trajectory control method based on a game engine as described in any one of claims 1-2, characterized in that: The system includes the following modules: Overall image capture module, feature recognition module, intelligent path planning module, detection progress judgment module, and visualization module; The overall image capture module is used to identify the test environment of the large-scale circuit board to be tested, adaptively capture and detect the overall image of the large-scale circuit board to be tested through an optical lens, and divide the overall image into functional areas; The feature recognition module is used to construct a feature image set of a large-scale circuit board to be tested, and to perform defect fault feature recognition and classification on the circuit board component image; The intelligent path planning module is used to perform three-dimensional geometric modeling on the mechanical arm of the flying probe machine and to intelligently plan the test path of the detection probe; The detection progress judgment module predicts the regional detection progress of each mechanical arm of the flying probe machine in real time according to the test path length of each detection probe, and makes a detection progress judgment; The visualization module is used to collect and extract the defects and faults of the large-scale circuit boards to be tested, and visualize them on a manual operation interface.
4. The flying probe machine intelligent detection system for large-scale circuit board testing according to claim 3 is characterized in that: The visualization module includes: an image display unit, a functional area display module, a path planning display unit, and a defect data display unit.
5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the flying probe machine intelligent detection method for large-scale circuit board testing as described in any one of claims 1-2 is implemented.
Citation Information
Patent Citations
Flying probe tester open-circuit test path optimization method
CN105911450A
Aperture testing method of optical chip of integrated circuit
CN110031188A
Artificial potential field path planning method of flexible needle based on obstacle grading and device
CN110111880A
Flying probe test method, flying probe test device, computer equipment and storage medium
CN114910778A
Winding equipment for carbon fiber plate
CN115385146A
