Testing method for AOI equipment detection data and centralized judgment comprehensive processing system

Abstract

The embodiment of the invention provides an AOI equipment detection data testing method and a centralized judgment comprehensive processing system. The method comprises the steps that a first test result and a second test result of detection data of a plurality of AOI equipment nodes are acquired in parallel, the first test result is a secondary judgment result of an artificial intelligence AI server, and the second test result is an AOI detection value judgment result; and obtaining a final test result of each AOI equipment node according to the first test result and the second test result. According to the embodiment of the invention, the method can solve a problem that a fault leakage risk exists in an existing AOI detection method in the related technology, and achieves the effect of improving the detection efficiency of the AOI equipment.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of automated optical inspection. Specifically, the embodiments relate to a test method for inspection data of an AOI device and a centralized determination integrated processing system. Background Art

[0002] With the increasing welding density of electronic components and the growing size of PCB (Printed Circuit Board), existing AOI (Automated Optical Inspection) devices are increasingly unable to cover the inspection of all components. As a result, some defects and false alarms may occur and require secondary determination. AOI manufacturers can push the inspection data and pictures of multiple AOI devices to the same computer for manual determination, and then return the determination results to the original AOI devices. The AOI devices control the single boards to be sent to different boxes according to the conclusions of OK or NG. However, the detection algorithm of this solution can only be the built-in algorithm of the AOI device manufacturer, and other AI (Artificial Intelligence) algorithms and third-party algorithms cannot be incorporated. Moreover, a large amount of manual labor is involved, which poses a risk of fault leakage.

[0003] In addition, based on the AOI detection module, the image information of the object to be measured is extracted, and whether the object to be measured has defects is judged in real time through sample training. This sample training method of machine learning requires a large number of positive samples and negative samples for training, and may not be able to meet the quantity requirements for some small-batch products. Moreover, there is also a possibility of misjudgment and leakage in AI rejudgment. Summary of the Invention

[0004] The embodiments of the present application provide a test method for inspection data of an AOI device and a centralized determination integrated processing system, so as to at least solve the problem of the risk of fault leakage existing in the existing AOI inspection method in the related art.

[0005] According to an embodiment of the present application, a test method for inspection data of an AOI device is provided, including: obtaining the first test result and the second test result of the inspection data of multiple AOI device nodes in parallel, where the first test result is the secondary determination result of an artificial intelligence AI server, and the second test result is the AOI detection value determination result; obtaining the final test result of each AOI device node according to the first test result and the second test result.

[0006] According to another embodiment of the present application, a centralized determination comprehensive processing system is provided, including: a first acquisition module, configured to concurrently acquire a first test result and a second test result of detection data of multiple AOI device nodes, where the first test result is a secondary determination result of an artificial intelligence (AI) server, and the second test result is an AOI detection value determination result; a second acquisition module, configured to obtain a final test result of each AOI device node according to the first test result and the second test result.

[0007] According to still another embodiment of the present application, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0008] According to still another embodiment of the present application, an electronic device is further provided, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0009] Through the above embodiments of the present application, since the detection data of multiple AOI device nodes can be acquired in parallel, the detection efficiency can be effectively improved; by further performing AI testing and AOI detection value determination on the detection data of the AOI device nodes, the fault problems missed during AOI detection can be avoided. Therefore, the problem of the risk of fault leakage existing in the existing AOI detection method in the related art can be solved, and the effect of improving the detection efficiency of the AOI device can be achieved. Description of the Drawings

[0010] Figure 1 is a hardware structure block diagram of a network device for testing the detection data of an automatic optical inspection (AOI) device according to an embodiment of the present application;

[0011] Figure 2 is a network architecture diagram of an SMT test platform according to an embodiment of the present application;

[0012] Figure 3 is a schematic diagram of the connection relationship of an SMEMA controller according to an embodiment of the present application;

[0013] Figure 4 is a flowchart of a method for testing the detection data of an AOI device according to an embodiment of the present application;

[0014] Figure 5 is a schematic diagram of a self-developed algorithm process according to an embodiment of the present invention;

[0015] Figure 6 is a structure block diagram of a centralized determination comprehensive processing system according to an embodiment of the present application;

[0016] Figure 7 is a schematic diagram of the logical relationship of the centralized determination integrated system according to an embodiment of the present application;

[0017] Figure 8 is a schematic diagram of the software block diagram of the centralized determination integrated processing system according to an embodiment of the present application;

[0018] Figure 9 is a flowchart of the mutual exclusion scheduling of the line cards when multiple AOI devices are turned on according to an embodiment of the present application;

[0019] Figure 10 is a flowchart of the synchronous scheduling of the power-off tests of multiple AOI devices according to an embodiment of the present application;

[0020] Figure 11 is a flowchart of the test method for the detection data of AOI devices according to an embodiment of the present application;

[0021] Figure 12 is a schematic diagram of the execution order of test items in a certain AOI device according to an embodiment of the present application. Detailed implementation manners

[0022] In the following, embodiments of the present application will be described in detail with reference to the accompanying drawings and in conjunction with the embodiments.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence.

[0024] The method embodiments provided in the embodiments of the present application can be executed in a network device, a computer terminal, or a similar computing device. Taking running on a network device as an example, Figure 1 is a hardware structure block diagram of a network device for running the test method for the detection data of an automatic optical inspection (AOI) device according to an embodiment of the present application. As Figure 1 shown, the network device may include one or more ( Figure 1 only one is shown in Figure 1 processors 102 (the processors 102 may include, but are not limited to, processing devices such as a microprocessor MCU or a field programmable gate array FPGA) and a memory 104 for storing data. Among them, the above-mentioned network device may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown in Figure 1 is only schematic and does not limit the structure of the above-mentioned network device. For example, the network device may further include more or fewer components than

[0025] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the test method for the detection data of the automatic optical inspection (AOI) device in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, the above-mentioned method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the network device through a network. Examples of the above-mentioned network include but are not limited to the Internet, intranet, local area network, mobile communication network, and their combinations.

[0026] The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the network device. In one instance, the transmission device 106 includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0027] The embodiments of the present application can run on Figure 2 the network architecture of the SMT test platform shown, as Figure 2 shown, the system includes: an AOI device, a centralized decision-making comprehensive processing system, a SMEMA (Surface Mount Equipment Manufacturers Association) controller, and an automatic board collector. Among them, the SMEMA controller is installed between the AOI device and its downstream automatic board collector (or transition section), and a unique module id is set for each SMEMA controller. The centralized decision-making comprehensive processing system identifies different AOI device nodes by the module id, so as to achieve the purpose of one-to-many and remote control; the SMEMA controller includes: a SMEMA interface module and an Internet of Things communication module.

[0028] As Figure 3As shown in the figure, the control device A1 is connected in series between the AOI device B1 and the board receiving machine CI through the SMEMA interface, that is, the SMEMA controller is connected in series between the AOI device and the automatic board receiving machine, and no modification is required for the existing equipment, nor is it necessary to develop specific equipment. It can be used in an automated production line. By developing a software system as the main control software, the "SMEMA controller" can be remotely controlled by the software. With the assistance of data retrieval and analysis, more application scenarios can be developed.

[0029] Based on the above SMT test platform, in the publish / subscribe message mode of MQTT (an Internet of Things protocol), a one-to-many message distribution mechanism is provided. In this distribution mechanism, the centralized decision-making comprehensive processing system publishes and subscribes messages with multiple SMEMA controllers, both of which are MQTT clients. The centralized decision-making comprehensive processing system controls the production rhythm of the AOI device upstream of the SMEMA controller and the automatic board receiving machine downstream in the way of "converting publish / subscribe messages into SMEMA instructions", receives the messages reported by the SMEMA controller in real time, and extracts the latest detection data of the AOI, the single-board barcode and the face identification through the IP network, and obtains the AI decision result, the AI detection result, and the result of the AOI detection value control algorithm. Finally, the centralized decision-making comprehensive processing system calculates the AOI detection value according to the AI decision result, determines the comprehensive conclusion (OK or NG), and then controls the automatic board receiving machine according to the comprehensive conclusion to transport the OK single boards to the OK single-board box and the NG single boards to the NG single-board box. If there is no board receiving machine, the worker transports the single boards according to the interface prompt of the centralized decision-making comprehensive processing system.

[0030] Figure 2 In the AOI device and the automatic board receiving machine in [description], they are connected to their upstream and downstream devices through SMEMA cables (S21 - S25).

[0031] In the embodiment of the present application, one-person multi-machine and remote control can be realized. That is, after converting the SMEMA instruction into an Internet of Things message, the centralized decision-making comprehensive processing system can be placed anywhere where network communication is reachable, and one person can control multiple AOI devices at the same time.

[0032] In a practical case, based on the technical solution in the above embodiment of the present application, when 16 AOI devices are running simultaneously on a certain floor of a production workshop, and the centralized decision-making comprehensive processing system computer is in the central control room on another different floor, with the cooperation of the board receiving machine, one person can manage the decision-making work of 16 AOI devices at the same time (the existing technical solution requires 16 people), thus achieving the purpose of saving manpower on site.

[0033] In this embodiment, a test method for the detection data of the AOI device running on the above network device or network architecture is provided. Figure 4is a flow chart of a test method for detecting data of an AOI device according to an embodiment of the present application. Figure 4 As shown, the process includes the following steps:

[0034] Step S402, obtaining a first test result and a second test result of the detection data of multiple AOI device nodes in parallel, wherein the first test result is a secondary determination result of the artificial intelligence AI server, and the second test result is an AOI detection value determination result;

[0035] Before step S402 of this embodiment, the method further includes: performing a first test and a second test on the detection data, wherein the first test performs an AI secondary determination through an AI secondary determination algorithm, and the second test performs an AOI detection value determination through an AOI detection value control algorithm.

[0036] In this embodiment, in addition to the AI ​​secondary determination algorithm and the AOI detection value control algorithm, other third-party algorithms can also be used to further test the detection data.

[0037] In one embodiment, the AOI detection value control algorithm is a self-developed algorithm, which can be superimposed on the algorithm of the AOI equipment. It includes at least one of the following detection items: detection of the body, 3D height reference, 3D height comparison, brightness value, and detection of solder paste.

[0038] The following describes the self-developed algorithm process by taking AOI detection value determination of SPC data as an example. Figure 5 As shown, the algorithm includes: after starting the AOI test value calculation, checking the SPC test records in the SPC file one by one, wherein the SPC file contains the detection value MeasureValue of all the bit numbers RefName+test items InspectType of the tested board; and checking the SPC file through three detection branches respectively to determine whether the tested board has missing parts, warped parts or warped feet problems.

[0039] in, Figure 5 The three detection branches in correspond to different algorithms, including:

[0040] Branch 1, i.e., the missing component detection branch, obtains the detection value corresponding to the tested board by detecting the main body algorithm, and generates NG information of missing components when the detection value does not meet the preset first threshold value;

[0041] Branch 2, i.e., the leg lift detection branch, obtains the detection value corresponding to the tested board through the 3D height reference algorithm, and generates leg lift NG information when the detection value is greater than a preset second threshold;

[0042] Branch 3, i.e., the warpage detection branch, obtains the detection value corresponding to the single board under test through a 3D height comparison algorithm. When the detection value is greater than a preset third threshold, NG information of warpage is generated.

[0043] Through the above three detection branches, "missing components", "warped pins", and "warped components" can be judged. These three types of defective conditions are calculated from the detection data and do not rely on manual judgment or AI calculation, which can play a role in intercepting human leakage; and each algorithm has a threshold, and the threshold will be continuously optimized during the deployment and use process to make the interception more accurate.

[0044] After the detection, the AOI detection data as shown in Table 1 can be obtained. Among them, Table 1 only shows part of the AOI detection data. In addition, the AOI detection data at least further includes: component code, component package, x coordinate, y coordinate:

[0045] Table 1

[0046]

[0047] In this embodiment, the multiple AOI device nodes correspond to one or more single boards under test. One single board under test includes one functional module or multiple functional modules at different levels, and the multiple single boards under test include single boards under test of one or more models.

[0048] The components in the single board can be classified and layered according to their positions and functions on the single board. Components at different levels play different roles and functions in the single board design.

[0049] In one embodiment, there is an association relationship between the single boards under test, and the association relationship at least includes one of the following: resource mutual exclusion and sharing relationship, synchronization relationship.

[0050] Among them, when a certain test item between two single boards under test needs to share the same instrument resource, at this time, after one single board under test occupies the instrument for testing, the other single board under test needs to wait for it to end before conducting the test. In this case, there is a resource mutual exclusion relationship between the two single boards under test.

[0051] When two single boards under test need to execute to the same node for certain operations (such as: power off, power on, etc.), for example: single boards under test at the same level need to enter a certain test item simultaneously. At this time, they have a synchronization relationship.

[0052] In this embodiment, each device node includes: an AOI device, an SMEMA controller module, and an automatic board collector. Among them, the SMEMA controller module is connected in series between the AOI device and the automatic board collector through an SMEMA interface.

[0053] Before step S402 of this embodiment, the method further includes: receiving an Internet of Things on-board message sent by the SMEMA controller module corresponding to the multiple AOI device nodes, where the Internet of Things on-board message carries an identifier of the SMEMA controller module; retrieving the detection data of the tested single boards of each AOI device node according to the identifier.

[0054] In this embodiment, the detection data at least includes one of the following: a whole-board image, a defect image, Manufacturing Execution System (MES) data, and Statistical Process Control (SPC) data.

[0055] In step S402 of this embodiment, obtaining a second test result of the detection data of the tested single boards of multiple AOI device nodes in parallel includes: determining an AOI detection value according to the SPC data and the whole-board image of the multiple AOI device nodes to obtain the second test result.

[0056] In this embodiment, the secondary determination result of the AI server is obtained by the AI server performing a secondary determination on the defect image of the tested single board, and the secondary determination is to confirm whether there is a defect in the tested single board according to the defect image.

[0057] In one embodiment, obtaining the final test result of each AOI device node according to the first test result and the second test result includes: when the tested single board is determined by the AI server to be a qualified single board in the secondary determination, performing an AOI detection value determination on the tested single board; determining the tested single board with an AOI detection value exceeding a preset threshold as a problem single board (i.e., an NG single board), and determining the tested single board with an AOI detection value not exceeding the preset threshold as a qualified single board.

[0058] Step S404, obtaining the final test result of the tested single board of each AOI device node according to the first test result and the second test result.

[0059] In one embodiment, when the AI server cannot confirm whether there is a defect in the tested single board, the method further includes: obtaining a third test result of the detection data of the tested single boards of the multiple AOI device nodes, where the third test result is a manual determination result, and the manual determination result is obtained by manually determining the defect image not recognized by the AI server.

[0060] There is a possibility of malfunction leakage in both manual determination and the secondary determination of the AI server. In the embodiments of the present application, a detection value control algorithm is added on the basis of manual determination and AI secondary determination, and an additional NG record is calculated according to the detection value. This record is independent of the NG record of the AOI device. By continuously optimizing and adjusting the threshold of the detection value algorithm, real malfunctions can be effectively intercepted.

[0061] After step S404 of this embodiment, the method further includes one of the following: sending a board presence message and an OK / NG message to the automatic board collector according to the final test result; sending a board request message to the AOI device node according to the final test result.

[0062] Through the above steps, since the detection data of multiple AOI device nodes can be obtained in parallel, the detection efficiency can be effectively improved; by further performing AI testing and AOI detection value determination on the detection data of the AOI device nodes, the malfunction problems missed during AOI detection can be avoided. Therefore, it is possible to solve the problem of an AOI device detection method in the related art that saves labor and can avoid malfunction leakage, and achieve the effect of improving the detection efficiency of the AOI device.

[0063] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by pure software, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0064] In the embodiments of the present application, a centralized determination comprehensive processing system is also provided. This system is used to implement the above embodiments and preferred implementation methods, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0065] Figure 6 is a structural block diagram of the centralized determination comprehensive processing system according to the embodiments of the present application. As Figure 6 shown, the system includes: a first acquisition module 10 and a second acquisition module 20.

[0066] The first acquisition module 10 is configured to acquire the first test result and the second test result of the detection data of multiple AOI device nodes in parallel, where the first test result is the secondary determination result of the artificial intelligence (AI) server, and the second test result is the AOI detection value determination result;

[0067] The second acquisition module 20 obtains the final test result of each AOI device node according to the first test result and the second test result.

[0068] In this embodiment, the centralized determination comprehensive processing system further includes:

[0069] The detection module is configured to perform the first test and the second test on the detection data of multiple AOI device nodes, where the first test is the secondary determination of the AI server, and the second test is the AOI detection value determination.

[0070] In one embodiment, the detection module may also perform the first test and the second test on the detection data of the AOI device node through other third-party algorithms.

[0071] Figure 7 It is a schematic diagram of the logical relationship of the centralized determination comprehensive system according to an embodiment of the present application. As Figure 7 shown, message interaction is performed between the centralized determination comprehensive processing system and multiple AOI devices. In the way of "converting the publish / subscribe message into the SMEMA instruction", the production rhythm of the upstream SMEMA device AOI and the downstream SMEMA device automatic board collector is controlled, and the manual determination result, the AI secondary determination result (i.e., the secondary determination result of the AI server), and the AOI detection value control algorithm result are extracted through the IP network. Finally, the centralized determination comprehensive processing system controls the downstream SMEMA device automatic board collector according to the comprehensive conclusion, transports the OK single boards to the OK single board box, and transports the NG single boards to the NG single board box.

[0072] It should be noted that the above-mentioned each module can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to this: all the above-mentioned modules are located in the same processor; or, the above-mentioned each module is located in different processors in any combination form.

[0073] AOI (Automated Optical Inspection) detection technology is widely used in the electronics manufacturing industry. Its main purpose is to improve production efficiency, reduce human errors, and reduce manufacturing defects through visual inspection of products. However, with the increase in the soldering density of electronic components and the increasing size of PCB boards, existing AOI equipment is increasingly unable to cover the detection of all components, because some defects and false alarms will be generated and require secondary judgment. The conventional secondary judgment method includes: some defects and false alarms generated after AOI equipment detection are output to the AI ​​algorithm server (referred to as AI server) for secondary judgment. If AI cannot give a definite conclusion, it will be judged manually. This is a serial processing mechanism.

[0074] The present application provides a developmental SMT testing platform for determining the presence of defects and controlling defects, thereby improving product quality. Figure 2 As shown, the SMT test platform includes: AOI equipment, centralized judgment and comprehensive processing system, SMEMA controller, automatic board receiving machine. When the AOI equipment vendor does not provide data and control interfaces, the AOI secondary AI judgment algorithm (i.e., secondary judgment through the AI ​​server), AOI defect control algorithm and other self-developed algorithms can be superimposed on the AOI equipment's own algorithm, getting rid of the dependence on the AOI supplier's algorithm iteration and realizing the continuous iteration of the algorithm under autonomous control; and according to the final conclusion, the single board can be controlled to be sent to different boxes (OK box or NG box); at the same time, the remote control technology of one person and multiple machines can be used to improve the automation degree of the SMT production line, save on-site labor, and avoid the phenomenon of manual distribution of single boards and wrong board distribution.

[0075] Based on the above-mentioned SMT test platform, the embodiment of the present application provides a test method for AOI equipment detection data, which is applied to the AOI equipment detection process of the SMT production line. After the PCB board is tested by the AOI equipment, the method can be used to further determine whether the board is qualified; it mainly involves the following technologies:

[0076] 1. Concurrent processing technology

[0077] Figure 8 is a schematic diagram of a software block diagram of a centralized determination and comprehensive processing system according to an embodiment of the present application, such as Figure 8 As shown, the "AOI device_B1" device node in the figure corresponds to Figure 2 The "module id" in the figure represents the SMEMA controller. Each device node is tested independently and in parallel. The tested board can be plugged in and tested immediately, and can be left immediately after the test. It can support real-time concurrent testing of 800 tested boards at the same time.

[0078] In this embodiment, in the user interface, when multiple AOI device nodes are tested concurrently, Figure 7 different AOI device nodes in

[0079] are displayed in different colors, and different colors represent different test statuses. For example: red: failure; yellow: warning; pink: having a fault and under test, etc. Figure 7 As shown on the right, for a certain AOI device node, the sequence of test items (1, 2, 3...) within the AOI device node can be independent of each other to support concurrent testing of different test levels and different models of the device under test.

[0080] The embodiment of the present application supports concurrent testing of device under test at multiple levels. The device under test at each level can be executed concurrently, and the test items of the device under test at different levels can be customized through configuration.

[0081] The components in the device under test can be classified and layered according to their positions and functions on the device under test. Components at different levels play different roles and functions in the design of the device under test. Generally speaking, the components in the device under test can be divided into the following levels:

[0082] Top-level components: These components are located on the top layer of the device under test and are usually larger components, such as processors, memories, interface devices, etc. Heat dissipation, power supply and other factors usually need to be considered in the design.

[0083] Middle-level components: These components are located below the top-level components and are mainly some smaller devices, such as capacitors, resistors, inductors, etc. They are mainly used for functions such as filtering, voltage regulation, and isolation of the circuit.

[0084] Bottom-level components: These components are located below the middle-level components and are usually some smaller devices, such as transistors, diodes, resistors, etc. They are mainly used for functions such as amplification, switching, and current limiting of the circuit.

[0085] In addition to the above three levels, there are also some other levels, such as:

[0086] Internal-layer components: These components are located in the internal layer of the device under test and are usually some smaller devices, such as capacitors, resistors, etc. They are mainly used for functions such as signal coupling and isolation.

[0087] Bottom-board components: These components are located on the bottom board of the device under test and are usually some larger devices, such as connectors, sockets, etc. They are mainly used for connecting the device under test to external devices.

[0088] The embodiments of the present application support concurrent testing of the DUT single boards of different models at the same time. Each model can customize independent test items for mixed insertion and mixed testing. The environmental entities can be customized for environmental information collection and display, as well as environmental inspection of the DUT single board before testing.

[0089] The embodiments of the present application also support models with association relationships between DUT single boards. The association relationships can be generated through the tags in the configuration file, which are flexible and variable, including the following scenarios:

[0090] Scenario 1: Multiple AOI devices enable resource exclusive scheduling. At this time, there is a resource exclusive sharing relationship between multiple AOI devices.

[0091] Figure 9 is a flowchart of multiple AOI devices enabling resource exclusive scheduling according to the embodiments of the present application. In this scenario, a certain test item between AOI device _B1 and AOI device _B2 shares the instrument resources. Only one of B1 and B2 can occupy the instrument for testing. After B1 occupies it, B2 waits. After B1 releases it, B2 automatically starts testing.

[0092] For example: The resource opening test item of AOI device _B1 uses the custom tag Tag0, and the resource opening test item of AOI device _B2 uses the custom Tag0. By setting the mutex object of the Mutex tag to Tag0, the mutual exclusion of resource opening is realized, meeting Scenario 1. Specifically, as Figure 9 shown, the process includes the following steps:

[0093] Step S901, read the Tag and Mutex configurations to generate the mutual exclusion relationship between AOI device _B1 and AOI device _B2.

[0094] Step S902, AOI device _B1 applies for resource opening test.

[0095] Step S903, the scheduler determines that AOI device _B2 does not execute the test, and AOI device _B1 needs to obtain the resources to open the instrument resource test item.

[0096] Step S904, AOI device _B2 applies for opening the instrument resource test.

[0097] Step S905, the scheduler determines that AOI device _B1 is executing the test, and AOI device _B2 needs to wait for the test due to mutual exclusion.

[0098] Step S906, the test of AOI device _B1 ends, and the test results are returned to the scheduler test module and AOI device _B1.

[0099] Step S907, the scheduler determines that AOI device _B1 has completed the test, enabling AOI device _B2 to obtain the resources to open the instrument resource test item.

[0100] Step S908, the AOI device _B2 test ends, and the test result is returned to the scheduling test module and the AOI device _B2.

[0101] Scenario 2: The power-down tests of multiple AOI devices are synchronously scheduled. At this time, there is a synchronization relationship between multiple AOI devices.

[0102] Figure 10 It is a flowchart of the synchronous scheduling of the power-down tests of multiple AOI devices according to an embodiment of the present application. In this scenario, between the AOI device _B1 and the AOI device _B2, certain operations need to be performed up to a certain point, such as power-down, power-on, etc. In this embodiment, the device power-down operation is taken as an example for detailed description:

[0103] For example: The power-down test item of the AOI device _B1 uses the SyncType label and sets the level to Level2. The power-down test item of the AOI device _B2 also uses the SyncType label and sets the level to Level2, and Scenario 2 can be realized. The definition of SyncType is: For this test item of all the DUTs at the same level, the test starts only when they all enter simultaneously, meeting Scenario 2. Specifically, as Figure 10 shown, this process includes the following steps:

[0104] Step S1001, read the SyncType configuration to generate the synchronization relationship between the AOI device _B1 and the AOI device _B2.

[0105] Step S1002, the AOI device _B1 applies for a power-down test.

[0106] Step S1003, synchronously wait for the AOI device _B2 to enter.

[0107] Step S1004, the AOI device _B2 applies for a power-down test.

[0108] Step S1005, the condition that the AOI device _B1 and the AOI device _B2 enter simultaneously is met.

[0109] Step S1006, make the AOI device _B1 and the AOI device _B2 enter the power-down test.

[0110] Step S1007, the scheduler determines that the AOI device _B1 and the AOI device _B2 have completed the power-down test, and returns the test result to the AOI device _B1 and the AOI device _B2.

[0111] Figure 11 It is a flowchart of the test method for the AOI device detection data according to an embodiment of the present application. This method is the test steps for a certain device node and is applied to the above Figure 2In the network architecture, as Figure 11 shown, the method includes the following steps:

[0112] S1101, after the AOI device finishes detection, the SMEMA interface outputs a board-present instruction. The board-present instruction is sent to the SMEMA controller through the SMEMA cable. The SMEMA controller converts it into an IoT board-present message and sends it to the centralized judgment and comprehensive processing system through the IP network by means of message publishing;

[0113] S1102, after the centralized judgment and comprehensive processing system receives the IoT board-present message through message subscription, according to the module id carried in the IoT board-present message, it retrieves the detection data of the corresponding AOI device node, extracts the single-board barcode, and starts the test items.

[0114] Starting the test items means making a secondary judgment on some defects and false alarms generated after AOI detection.

[0115] S1103, send the defects and false alarms generated after AOI detection to the AI algorithm server. The AI algorithm server makes a secondary judgment on the defects or false alarms that can be recognized. For the defects that are not sure, the AI algorithm server will send them for manual secondary judgment.

[0116] In this embodiment, after the AI algorithm server completes the secondary judgment, the AI processing situation is extracted from the AI algorithm server in real time.

[0117] S1104, for the defects and false alarms that cannot be judged by both AOI detection and the AI algorithm server, perform manual secondary judgment.

[0118] In this embodiment, after the manual secondary judgment ends, the manual judgment result is extracted in real time according to the barcode.

[0119] S1105, the centralized judgment and comprehensive processing system extracts data from the AOI device node in real time according to the barcode.

[0120] S1106, the centralized judgment and comprehensive processing system calculates the AOI detection value according to the AOI detection value control algorithm, and judges whether the single board is qualified according to whether it meets the AOI detection threshold.

[0121] In this embodiment, if it is judged that there are NG components through the AOI detection value, even if the AI secondary judgment is qualified or the manual judgment is qualified, this single board will still be forced to be an NG single board.

[0122] With the advancement of technology, especially the development of artificial intelligence technology, many AI algorithms can be applied to optical inspection of circuit boards or components. However, in the original architecture, we can only rely on the optimization of algorithms provided by AOI equipment vendors, which requires a large procurement cost, and the time it takes to deploy and land often lags behind the development of current technology. In this embodiment, self-developed algorithms (AOI secondary AI judgment algorithm, AOI defect control algorithm) can be superimposed on the algorithms provided by AOI equipment to get rid of the dependence on algorithm iteration of AOI suppliers.

[0123] In this embodiment, the AOI detection value control algorithm is only one of the algorithms of the centralized judgment and comprehensive processing system, and can also be compatible with other self-developed algorithms. The self-developed algorithms can be independently developed and iterated, and other third-party algorithms can also be introduced.

[0124] S1107, combining the secondary determination result of the AI ​​server, the manual determination result, and the AOI detection value determination result to determine the final result of this single board test item.

[0125] S1108, the centralized judgment integrated processing system publishes the final result of the test item to the SMEMA controller in the form of IoT message publishing as a "board request message", and the SMEMA controller converts the message into a SMEMA "board request instruction" and transmits it to the AOI equipment through the SMEMA cable.

[0126] S1109, after receiving the "board request instruction", the AOI device transports the single board out of the AOI device.

[0127] S1110, the centralized judgment integrated processing system publishes the final result of the test item in the form of IoT message publishing, namely, "board available message and OK / NG message" to the SMEMA controller, and the SMEMA controller converts the message into SMEMA's "board available instruction and OK / NG instruction" and transmits it to the automatic board receiving machine through the SMEMA cable;

[0128] S1111, after the automatic board receiving machine receives the "board instruction and OK / NG instruction", after the single board comes out of the AOI device, it automatically separates the single board into the OK box or NG box according to the OK / NG instruction.

[0129] The above-mentioned processes of S1101 to S1111 belong to the processes within a certain AOI device node. The centralized judgment integrated processing system can ensure that the processes within each AOI device node are tested independently and in parallel with the help of parallel processing technology, and can start the test immediately after receiving the "IoT board message". After the test, the single board is immediately sent to the automatic board receiving machine.

[0130] The user interface of the centralized judgment and comprehensive processing system mainly includes the following areas:

[0131] 1. Manual judgment interface, used to provide manual judgment;

[0132] 2. Test item area, which is the test item for each device node. The execution order of the test items is as follows: Figure 12 As shown;

[0133] 3. Device node interface, each AOI device node corresponds to a SMEMA controller on the hardware;

[0134] 4. Test log interface, used for real-time log printing for on-site personnel to refer to and observe the real-time test situation;

[0135] 5. Automatic scanning interface is used for automatic scanning after successful testing, replacing the original manual scanning to complete the automatic transfer of production processes and accounts.

[0136] Compared with the prior art, the above-mentioned embodiments of the present application have the following beneficial effects: compatible with various SMT equipment and scenarios, and developing functions such as centralized judgment and one person with multiple machines to meet the needs of less-managed production sites; compatible with data formats of different AOI models, stored in the same format, and standardized control thresholds, and optimized from previous manual control to automatic control; on the basis of the built-in algorithm of the AOI equipment, self-developed algorithms (AOI secondary judgment AI algorithm, AOI detection value control algorithm) are superimposed to get rid of the dependence on the algorithm iteration of AOI suppliers, and the SMT production quality is continuously improved through continuous iterative optimization of the algorithm.

[0137] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0138] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0139] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0140] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0141] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details thereof will not be repeated here.

[0142] Obviously, those skilled in the art should understand that the various modules or steps of the present application described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed over a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a sequence different from that here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0143] The above are only the preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. A test method for the detection data of an automatic optical inspection (AOI) device, characterized in that, Including: Parallelly obtaining a first test result and a second test result of detection data of multiple AOI device nodes, where the first test result is a secondary determination result of an artificial intelligence (AI) server, and the second test result is an AOI detection value determination result; Obtaining a final test result of each AOI device node according to the first test result and the second test result.

2. The method according to claim 1, characterized in that, Wherein, The multiple AOI device nodes correspond to one or more boards under test, one board under test includes one functional module or multiple functional modules at different levels, and the multiple boards under test include boards under test of one or more models.

3. The method according to claim 2, characterized in that, Wherein, There is an association relationship between the boards under test, and the association relationship includes at least one of the following: resource mutually exclusive sharing relationship, synchronization relationship.

4. The method according to claim 1, characterized in that, Wherein, Each device node includes: an AOI device, an SMEMA controller module, and an automatic board collector.

5. The method according to claim 4, characterized in that, Before parallelly obtaining the first test result and the second test result of the detection data of the multiple AOI device nodes, the method further includes: Receiving an Internet of Things (IoT) board-present message sent by the SMEMA controller module corresponding to the multiple AOI device nodes, where the IoT board-present message carries an identifier of the SMEMA controller module; Retrieving the detection data of each AOI device node according to the identifier.

6. The method according to claim 5, characterized in that, Wherein, The detection data includes at least one of the following: a whole-board image, a defect image, manufacturing execution system (MES) data, and statistical process control (SPC) data.

7. The method according to claim 6, characterized in that, Parallelly obtaining the second test result of the detection data of the multiple AOI device nodes includes: Performing AOI detection value determination according to the SPC data and the whole-board image of the multiple AOI device nodes to obtain the second test result.

8. The method according to claim 6, characterized in that, Wherein, The secondary determination result of the AI server is obtained by the AI server performing a secondary determination on the defect image, and the secondary determination is to confirm whether there is a defect on the board under test according to the defect image.

9. The method according to claim 8, characterized in that, Obtaining the final test result of each AOI device node according to the first test result and the second test result includes: When the board under test is secondarily determined by the AI server to be a qualified board, performing AOI detection value determination on the board under test; Determining a board under test with an AOI detection value exceeding a preset threshold as a problem board, and determining a board under test with an AOI detection value not exceeding the preset threshold as a qualified board.

10. The method according to claim 6, characterized in that, When the AI server cannot confirm whether there is a defect on the board under test, the method further includes: Obtaining a third test result of the detection data of the multiple AOI device nodes, where the third test result is an artificial determination result, and the artificial determination result is obtained by manually determining the defect images not recognized by the AI server.

11. The method according to claim 1, characterized in that, After obtaining the final test result of each AOI device node, the method further includes one of the following: Sending a board-present message and an OK / NG message to the automatic board collector according to the final test result; sending a board-request message to the AOI device node according to the final test result.

12. The method according to claim 1, characterized in that, Wherein, The AOI detection value determination includes at least one of the following detection items: detected body, 3D height reference, 3D height comparison, brightness value, detected solder paste.

13. A centralized determination and comprehensive processing system, characterized in that, Including: A first acquisition module, configured to concurrently acquire a first test result and a second test result of the detection data of multiple AOI device nodes, where the first test result is the secondary determination result of the artificial intelligence AI server, and the second test result is the AOI detection value determination result; A second acquisition module, configured to obtain the final test result of each AOI device node according to the first test result and the second test result.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, where when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 12 are implemented.

15. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method described in any one of claims 1 to 12 are implemented.

Images