Test method for inspection data of AOI device, and centralized determination integrated processing system

Abstract

A test method for inspection data of an AOI device, and a centralized determination integrated processing system. The test method comprises: acquiring in parallel a first test result and a second test result for inspection data of a plurality of AOI device nodes, wherein the first test result is a secondary determination result of an artificial intelligence (AI) server, and the second test result is an AOI value determination result; and obtaining a final test result for each AOI device node on the basis of the first test result and the second test result.

Description

AOI equipment detection data testing method and centralized judgment comprehensive processing system

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure is based on Chinese patent application CN202311762537.7, filed on December 19, 2023, entitled “Testing method and centralized judgment and comprehensive processing system for AOI equipment detection data”, and claims the priority of the patent application, and all the disclosed contents are incorporated into this disclosure by reference. Technical Field

[0003] The embodiments of the present disclosure relate to the field of automatic optical inspection technology, and more specifically, to a testing method for AOI equipment detection data and a centralized judgment and comprehensive processing system. Background Art

[0004] As the density of electronic component soldering increases and PCB (Printed Circuit Board) size grows, existing AOI (Automated Optical Inspection) equipment is increasingly unable to inspect all components. This can lead to defects and false alarms requiring secondary assessment. AOI manufacturers can push data and images from multiple AOI inspections to a single computer for manual assessment. The assessment results are then returned to the original AOI equipment, which then routes the boards to different bins based on an OK or NG decision. However, this approach relies solely on the AOI equipment vendor's own inspection algorithms; other AI (Artificial Intelligence) and third-party algorithms cannot be integrated. Furthermore, the large amount of manual effort involved creates the risk of fault disclosure.

[0005] In addition, the AOI detection module extracts image information of the object to be tested and uses sample training to determine in real time whether the object to be tested has defects. This machine learning sample training method requires a large number of positive and negative samples for training, which may not meet the quantity requirements for some small-batch products; and AI re-judgment also has the possibility of misjudgment and leakage.

[0006] Summary of the Invention

[0007] The embodiments of the present disclosure provide a testing method for AOI equipment detection data and a centralized judgment and comprehensive processing system to at least solve the problem of fault leakage risk in existing AOI detection methods in related technologies.

[0008] According to one embodiment of the present disclosure, a method for testing AOI device detection data is provided, comprising: obtaining first and second test results of detection data of multiple AOI device nodes in parallel, wherein 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; and obtaining a final test result for each AOI device node based on the first and second test results.

[0009] According to another embodiment of the present disclosure, a centralized determination and comprehensive processing system is provided, comprising: a first acquisition module configured to concurrently acquire first and second test results of detection data of multiple AOI device nodes, wherein 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; and a second acquisition module configured to obtain a final test result of each AOI device node based on the first and second test results.

[0010] According to another embodiment of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0011] According to another embodiment of the present disclosure, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 1 is a hardware structure block diagram of a network device for executing a test method for detecting data using an automatic optical inspection (AOI) device according to an embodiment of the present disclosure;

[0013] FIG2 is a network architecture diagram of an SMT test platform according to an embodiment of the present disclosure;

[0014] FIG3 is a schematic diagram of the connection relationship of the SMEMA controller according to an embodiment of the present disclosure;

[0015] FIG4 is a flow chart of a method for testing data detected by an AOI device according to an embodiment of the present disclosure;

[0016] FIG5 is a schematic diagram of a self-developed algorithm process according to an embodiment of the present disclosure;

[0017] FIG6 is a structural block diagram of a centralized determination and comprehensive processing system according to an embodiment of the present disclosure;

[0018] FIG7 is a schematic diagram of the logical relationship of the centralized determination comprehensive system according to an embodiment of the present disclosure;

[0019] FIG8 is a schematic diagram of a software block diagram of a centralized determination and comprehensive processing system according to an embodiment of the present disclosure;

[0020] FIG9 is a flowchart of enabling mutually exclusive scheduling of line cards for multiple AOI devices according to an embodiment of the present disclosure;

[0021] FIG10 is a flowchart of synchronous scheduling of power-off testing of multiple AOI devices according to an embodiment of the present disclosure;

[0022] FIG11 is a flow chart of a method for testing data detected by an AOI device according to an embodiment of the present disclosure;

[0023] FIG12 is a schematic diagram of the execution order of test items in a certain AOI device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings and in conjunction with embodiments.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0026] The method embodiments provided in the embodiments of the present disclosure can be executed in a network device, a computer terminal or a similar computing device. Taking operation on a network device as an example, FIG1 is a hardware structure block diagram of a network device for running a test method for detecting data of an automatic optical inspection (AOI) device according to an embodiment of the present disclosure. As shown in FIG1 , the network device may include one or more (only one is shown in FIG1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned network device may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that the structure shown in FIG1 is only for illustration and does not limit the structure of the above-mentioned network device. For example, the network device may also include more or fewer components than those shown in FIG1 , or have a configuration different from that shown in FIG1 .

[0027] 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 detecting data of the automatic optical inspection (AOI) equipment in the embodiment of the present disclosure. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to a network device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0028] The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by a communications provider of the network device. In one embodiment, the transmission device 106 may include a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] The embodiment of the present disclosure can run on the network architecture of the SMT test platform shown in Figure 2. As shown in Figure 2, the system includes: AOI equipment, a centralized judgment and comprehensive processing system, a SMEMA (Surface Mount Equipment Manufacturers Association) controller, and an automatic board collector. The SMEMA controller is installed between the AOI equipment and its downstream automatic board collector (or transition section), and each SMEMA controller is set with a unique module ID. The centralized judgment and comprehensive processing system uses the module ID to identify different AOI device nodes, thereby achieving the purpose of one-to-many and remote control. The SMEMA controller includes: a SMEMA interface module and an Internet of Things communication module.

[0030] As shown in Figure 3, control device A1 is connected in series between AOI equipment B1 and the board collector CI via the SMEMA interface. This means the SMEMA controller is connected in series between the AOI equipment and the automated board collector. This eliminates the need to modify existing equipment or develop specialized equipment. This system can be used in automated production lines by developing a software system as the master control software. This software remotely controls the SMEMA controller, assisting with data retrieval and analysis, opening up a wider range of applications.

[0031] Based on the aforementioned SMT test platform, a one-to-many message distribution mechanism is provided using the publish / subscribe messaging model of MQTT (an IoT protocol). In this mechanism, a centralized judgment and comprehensive processing system, acting as an MQTT client, publishes and subscribes to messages with multiple SMEMA controllers, also acting as MQTT clients. By converting publish / subscribe messages into SMEMA commands, the centralized judgment and comprehensive processing system controls the production rhythm of the upstream AOI equipment and downstream automatic board collectors of the SMEMA controllers. It receives real-time messages from the SMEMA controllers and extracts the latest AOI inspection data, including board barcodes and panel types, over the IP network. It also obtains AI judgment and inspection results, as well as the results of the AOI inspection value control algorithm. Finally, the centralized judgment and comprehensive processing system determines a comprehensive conclusion (OK or NG) based on the AI ​​judgment results and calculated AOI inspection values. Based on this comprehensive conclusion, the centralized judgment and comprehensive processing system controls the automatic board collector, moving OK boards to OK bins and NG boards to NG bins. If a board collector is not available, workers move boards according to the instructions on the centralized judgment and comprehensive processing system's interface.

[0032] The AOI equipment and automatic board collector in Figure 2 are connected to their upstream and downstream equipment via SMEMA cables (S21-S25).

[0033] In the disclosed embodiment, one person can control multiple machines and remotely control them. That is, after the SMEMA instructions are converted into IoT messages, the centralized judgment and comprehensive processing system can be placed in any location accessible by network communication, and multiple AOI devices can be controlled by one person at the same time.

[0034] In one embodiment, based on the technical solution in the above embodiment of the present disclosure, when 16 AOI devices are running at the same time on a certain floor of a production workshop, and the centralized judgment and integrated processing system computer is in the central control room on another different floor, with the cooperation of the board collector, one person can manage the judgment work of 16 AOIs at the same time (the existing technical solution requires 16 people), thereby achieving the purpose of saving manpower on site.

[0035] In this embodiment, a method for testing AOI device detection data running on the above-mentioned network device or network architecture is provided. FIG4 is a flow chart of the method for testing AOI device detection data according to an embodiment of the present disclosure. As shown in FIG4 , the process includes the following steps:

[0036] Step S402, obtaining first test results and second test results of 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;

[0037] 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 AI secondary determination through an AI secondary determination algorithm, and the second test performs AOI detection value determination through an AOI detection value control algorithm.

[0038] 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.

[0039] In one embodiment, the AOI inspection value control algorithm is a self-developed algorithm that can be superimposed on the AOI equipment's built-in algorithm. It includes at least one of the following inspection items: body detection, 3D height reference, 3D height contrast, brightness value, and solder paste detection.

[0040] The following describes the self-developed algorithm process using AOI inspection value determination of SPC data as an example. As shown in Figure 5, the algorithm includes: after enabling AOI test value calculation, checking the SPC test records in the SPC file one by one. The SPC file contains the detection value MeasureValue of all bit numbers RefName+test items InspectType of the tested board; and checking the SPC file through three detection branches to determine whether the tested board has missing parts, warped parts, or warped feet.

[0041] The three detection branches in Figure 5 correspond to different algorithms, including:

[0042] Branch 1, i.e., the missing component detection branch, obtains the detection value corresponding to the tested board through the detection body algorithm. If the detection value does not meet the preset first threshold, an NG message indicating missing components is generated;

[0043] Branch 2, i.e., the leg lift detection branch, obtains the detection value corresponding to the tested board through a 3D height reference algorithm. If the detection value is greater than a preset second threshold, an NG signal indicating leg lift is generated.

[0044] Branch 3, ie, the lifted component detection branch, obtains a detection value corresponding to the tested board through a 3D height comparison algorithm, and generates a lifted component NG information when the detection value is greater than a preset third threshold.

[0045] Through the above three detection branches, "missing parts", "legged parts" and "kicked parts" can be judged. These three adverse conditions are calculated by the detection data and do not rely on human judgment and AI calculation, which can play a role in intercepting human leakage; and each algorithm has a threshold, which will be continuously optimized during deployment and use to make the interception more accurate.

[0046] After the inspection is completed, the AOI inspection data shown in Table 1 can be obtained. Table 1 only shows part of the AOI inspection data. In addition, the AOI inspection data also includes at least: component code, component package, x coordinate, and y coordinate:

[0047] Table 1

[0048] In this embodiment, 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.

[0049] Components in a board can be classified and layered according to their location and function on the board. Components at different levels play different roles and functions in board design.

[0050] In one embodiment, there is an association relationship between the boards under test, and the association relationship includes at least one of the following: a mutually exclusive resource sharing relationship and a synchronization relationship.

[0051] Among them, when a test item between two tested boards needs to share the same instrument resources, at this time, after one of the tested boards occupies the instrument test, the other tested board must wait for it to finish before testing. In this case, there is a resource mutual exclusion relationship between the two tested boards.

[0052] When two boards under test need to execute certain operations (such as power off, power on, etc.) on the same node, for example, boards under test at the same level need to enter a certain test item at the same time, at this time, they are in a synchronous relationship.

[0053] In this embodiment, each of the device nodes includes: an AOI device, a SMEMA controller module, and an automatic board receiving machine, wherein the SMEMA controller module is serially connected between the AOI device and the automatic board receiving machine via a SMEMA interface.

[0054] Before step S402 of this embodiment, the method further includes: receiving an IoT board-available message sent by the SMEMA controller module corresponding to the multiple AOI device nodes, wherein the IoT board-available message carries an identifier of the SMEMA controller module; and retrieving detection data of the tested board of each AOI device node according to the identifier.

[0055] In this embodiment, the inspection data includes at least one of the following: a whole board image, a defect image, a manufacturing execution system (MES) data, and a statistical process control (SPC) data.

[0056] In step S402 of this embodiment, second test results of the test data of the tested boards of multiple AOI device nodes are obtained in parallel, including: performing AOI test value determination based on the SPC data of the multiple AOI device nodes and the whole board map to obtain the second test results.

[0057] 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 board, and the secondary determination is to confirm whether the tested board has defects based on the defect image.

[0058] In one embodiment, the final test result of each AOI device node is obtained based on the first test result and the second test result, including: when the tested board is secondarily determined by the AI ​​server to be a qualified board, the AOI detection value of the tested board is determined; the tested board whose AOI detection value exceeds a preset threshold is determined as a problem board (i.e., an NG board), and the tested board whose AOI detection value does not exceed the preset threshold is determined as a qualified board.

[0059] Step S404: Obtain the final test result of the tested board of each AOI device node according to the first test result and the second test result.

[0060] In one embodiment, when the AI ​​server is unable to confirm whether the tested board has defects, the method further includes: obtaining a third test result of the detection data of the tested boards of the multiple AOI device nodes, wherein the third test result is a manual judgment result, and the manual judgment result is obtained by manually judging the defective image that has not been identified by the AI ​​server.

[0061] Both manual and AI server-based re-determinations carry the potential for fault leakage. In this disclosed embodiment, a detection value management algorithm is added to both manual and AI re-determinations. This algorithm calculates an NG record based on the detection value, independent of the NG record of the AOI device. By continuously optimizing and adjusting the detection value algorithm threshold, real faults can be effectively intercepted.

[0062] After step S404 in this embodiment, the method further includes one of the following: sending a board available message and an OK / NG message to an automatic board receiving machine according to the final test result; sending a board requested message to the AOI device node according to the final test result.

[0063] 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 fault problem missed during AOI detection can be avoided. Therefore, the problem of an AOI device detection method in the related art that saves labor and avoids fault leakage can be solved, thereby achieving the effect of improving the detection efficiency of AOI equipment.

[0064] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by pure software, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0065] In the embodiments of the present disclosure, a centralized judgment and comprehensive processing system is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0066] FIG6 is a structural block diagram of a centralized determination and comprehensive processing system according to an embodiment of the present disclosure. As shown in FIG6 , the system includes: a first acquisition module 10 and a second acquisition module 20 .

[0067] A first acquisition module 10 is configured to obtain first test results and second test results of 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;

[0068] The second acquisition module 20 is configured to obtain a final test result of each AOI device node according to the first test result and the second test result.

[0069] In this embodiment, the centralized determination and comprehensive processing system further includes:

[0070] The detection module is configured to perform a first test and a second test on the detection data of multiple AOI device nodes, wherein the first test is a secondary determination by the AI ​​server, and the second test is an AOI detection value determination.

[0071] In one embodiment, the detection module may further perform a first test and a second test on the detection data of the AOI device node using other third-party algorithms.

[0072] FIG7 is a schematic diagram of the logical relationship of the centralized judgment comprehensive system according to an embodiment of the present disclosure. As shown in FIG7 , the centralized judgment comprehensive processing system exchanges messages with multiple AOI devices, and controls the production rhythm of the upstream SMEMA device AOI and the downstream SMEMA device automatic board collector in the manner of "publishing / subscribing messages into SMEMA instructions", and extracts the manual judgment results, AI secondary judgment results (i.e., the secondary judgment results of the AI ​​server), and the results of the AOI detection value control algorithm through the IP network. Finally, the centralized judgment comprehensive processing system controls the downstream SMEMA device automatic board collector based on the comprehensive conclusion, transporting OK boards to OK board boxes and NG boards to NG board boxes.

[0073] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0074] AOI (Automated Optical Inspection) technology is widely used in the electronics manufacturing industry. Its primary purpose is to improve production efficiency, reduce human error, and minimize manufacturing defects through visual inspection of products. However, with the increasing density of electronic component soldering and the increasing size of PCB boards, existing AOI equipment is increasingly unable to inspect all components. This is because some defects and false alarms generated by AOI equipment require secondary determination. The conventional secondary determination method involves outputting defects and false alarms generated by AOI equipment to an AI algorithm server (referred to as the AI ​​server) for secondary determination. If the AI ​​cannot provide a definitive conclusion, manual determination is performed. This is a serial processing mechanism.

[0075] The present disclosure provides a developmental SMT test platform for determining the presence of defects and controlling defects, thereby improving product quality. As shown in Figure 2, the SMT test platform includes: AOI equipment, a centralized judgment and comprehensive processing system, a SMEMA controller, and an automatic board collector. When the AOI equipment vendor does not provide data and control interfaces, the platform can superimpose self-developed algorithms such as the AOI secondary AI judgment algorithm (i.e., secondary judgment through the AI ​​server) and the AOI defect control algorithm on the AOI equipment's own algorithm, thereby breaking away from the reliance on the AOI supplier's algorithm iteration and achieving autonomous and controllable continuous iteration of the algorithm. The platform can also control the delivery of single boards to different boxes (OK boxes or NG boxes) based on the final conclusion. At the same time, the remote control technology of one person and multiple machines can be used to improve the automation level of the SMT production line, save on-site labor, and avoid the phenomenon of manual single board allocation and mis-assignment.

[0076] Based on the aforementioned SMT testing platform, the present disclosure provides a method for testing AOI equipment inspection data. This method is applied to the AOI equipment inspection process of an SMT production line. After a PCB has been inspected by the AOI equipment, this method can be used to further determine whether the PCB has passed the inspection. The method primarily involves the following technologies:

[0077] 1. Concurrent processing technology

[0078] Figure 8 is a schematic diagram of the software block diagram of the centralized judgment and comprehensive processing system according to an embodiment of the present disclosure. As shown in Figure 8, the "AOI device_B1" device node in the figure corresponds to the SMEMA controller represented by the "module id" in Figure 2. Each device node is tested independently and in parallel. The tested board can be plugged in and tested, and can be left after the test is completed. It can support real-time concurrent testing of 800 tested boards at the same time.

[0079] In this embodiment, in the user interface, when multiple AOI device nodes are tested concurrently, different AOI device nodes in FIG7 are displayed in different colors, and different colors represent different test statuses, for example: red: fault; yellow: alarm; pink: faulty and under test, etc.

[0080] As shown in the right side of FIG7 , for a certain AOI device node, the test item (1, 2, 3, ...) sequences within the AOI device node can be independent of each other to support concurrent testing of different test levels and different models of boards under test.

[0081] The disclosed embodiments support concurrent testing of multiple levels of tested boards. Tested boards at each level can be executed concurrently, and test items of tested boards at different levels can be customized through configuration.

[0082] Components in a single board can be classified and layered according to their location and function on the board. Components at different levels play different roles and functions in single board design. Generally speaking, components in a single board can be divided into the following levels:

[0083] Top-layer components: These components are located on the top layer of the board and are usually larger components such as processors, memory, and interface devices. Their design usually requires consideration of factors such as heat dissipation and power supply.

[0084] Middle-layer components: These components are located below the top-layer components and are mainly smaller devices such as capacitors, resistors, inductors, etc. They are mainly used for circuit filtering, voltage regulation, isolation and other functions.

[0085] Bottom-layer components: These components are located below the middle-layer components and are usually smaller devices such as transistors, diodes, resistors, etc. They are mainly used for circuit amplification, switching, current limiting and other functions.

[0086] In addition to the above three levels, there are some other levels, such as:

[0087] Internal layer components: These components are located on the internal layers of the board and are usually smaller devices such as capacitors and resistors. They are mainly used for signal coupling, isolation and other functions.

[0088] Baseboard components: These components are located on the baseboard of the board and are usually larger devices such as connectors and sockets. They are mainly used to connect the board to external devices.

[0089] The disclosed embodiment supports the simultaneous testing of different models of single boards. Each model can customize independent test items and mixed plug-in and mixed testing. The environment entity can be customized for environmental information collection and display, and environmental inspection before the single board is tested.

[0090] The disclosed embodiments also support a model in which the tested boards have an association relationship. The association relationship can be generated by tags in the configuration file and is flexible and variable, including the following scenarios:

[0091] Scenario 1: Multiple AOI devices enable mutually exclusive resource scheduling. At this time, there is a mutually exclusive resource sharing relationship between multiple AOI devices.

[0092] Figure 9 is a flowchart of mutually exclusive resource scheduling for multiple AOI devices according to an embodiment of the present disclosure. In this scenario, a test item between AOI device_B1 and AOI device_B2 shares instrument resources. Only one of B1 and B2 can occupy the instrument test. After B1 occupies the instrument, B2 waits. After B1 releases the instrument, B2 automatically starts the test.

[0093] For example, the resource enable test item of AOI device _B1 uses the custom tag Tag0, and the resource enable test item of AOI device _B2 uses the custom tag Tag0. By setting the mutex object of the Mutex tag to Tag0, mutual exclusion of resource enablement is achieved, meeting scenario 1.

[0094] In one embodiment, as shown in FIG9 , the process includes the following steps:

[0095] Step S901: Read the Tag and Mutex configurations to generate a mutually exclusive relationship between AOI device_B1 and AOI device_B2.

[0096] Step S902: AOI device_B1 applies to start resource testing.

[0097] Step S903: The scheduler determines that AOI device_B2 does not execute the test, and AOI device_B1 needs to obtain resources to start the instrument resource test item.

[0098] Step S904: AOI device_B2 applies to start instrument resource testing.

[0099] Step S905 , the scheduler determines that AOI device_B1 is executing a test and AOI device_B2 is mutually exclusive and needs to wait for the test.

[0100] Step S906: The test of AOI device_B1 is completed, and the test result is returned to the scheduling test module and AOI device_B1.

[0101] Step S907 : The dispatcher determines that the AOI device_B1 has completed the test, and enables the AOI device_B2 to obtain the resource start instrument resource test item.

[0102] Step S908: The test of AOI device_B2 is completed, and the test result is returned to the scheduling test module and AOI device_B2.

[0103] Scenario 2: Multiple AOI devices are powered off and tested synchronously. In this case, there is a synchronization relationship between the multiple AOI devices.

[0104] FIG10 is a flowchart of synchronous scheduling of power-off testing of multiple AOI devices according to an embodiment of the present disclosure. In this scenario, AOI device_B1 and AOI device_B2 need to perform certain operations at a certain point, such as power-off and power-on. This embodiment uses the power-off operation of the device as an example for detailed description:

[0105] For example, if the power-off test item for AOI device_B1 uses the SyncType tag and is set to Level 2, and the power-off test item for AOI device_B2 also uses the SyncType tag and is set to Level 2, Scenario 2 can be achieved. The definition of SyncType is that the test starts only when all boards under test at the same level enter the test item simultaneously, satisfying Scenario 2.

[0106] In one embodiment, as shown in FIG10 , the process includes the following steps:

[0107] Step S1001: read the SyncType configuration and generate a synchronization relationship between AOI device_B1 and AOI device_B2.

[0108] Step S1002: AOI device_B1 applies for power-off testing.

[0109] Step S1003, synchronously waiting for AOI device_B2 to enter.

[0110] Step S1004: AOI device_B2 applies for power-off testing.

[0111] Step S1005: The conditions for AOI device_B1 and AOI device_B2 to enter simultaneously are met.

[0112] Step S1006: Make the AOI device_B1 and the AOI device_B2 enter the power-off test.

[0113] Step S1007: The dispatcher determines that the AOI device_B1 and the AOI device_B2 have completed the power-off test, and returns the test results to the AOI device_B1 and the AOI device_B2.

[0114] FIG11 is a flow chart of a method for testing AOI equipment detection data according to an embodiment of the present disclosure. The method is a test step for a certain device node and is applied to the network architecture of FIG2 above. As shown in FIG11 , the method includes the following steps:

[0115] S1101: After the AOI equipment completes the inspection, the SMEMA interface outputs a board-present instruction, which is sent to the SMEMA controller via 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 via the IP network through message publishing.

[0116] S1102, after the centralized judgment integrated processing system receives the IoT board message through the message subscription method, it retrieves the detection data of the corresponding AOI device node according to the module ID carried by the IoT board message, extracts the single board barcode, and starts the test item.

[0117] The startup test item is to perform a secondary judgment on some defects and false alarms generated after AOI detection.

[0118] S1103, the defects and false alarms generated after AOI detection are sent to the AI ​​algorithm server. The AI ​​algorithm server makes a secondary judgment on the identifiable defects or false alarms. For defects that are uncertain, the AI ​​algorithm server will send them to manual secondary judgment.

[0119] In this embodiment, after the AI ​​algorithm server completes the secondary determination, the AI ​​processing status is extracted from the AI ​​algorithm server in real time.

[0120] S1104: For defects and false alarms that cannot be determined by AOI detection and AI algorithm server, manual secondary determination is performed.

[0121] In this embodiment, after the manual secondary determination is completed, the manual determination result is extracted in real time based on the barcode.

[0122] S1105, the centralized judgment integrated processing system extracts data from the AOI device node in real time according to the barcode.

[0123] S1106, the centralized judgment integrated processing system calculates the AOI detection value according to the AOI detection value control algorithm, and determines whether the single board is qualified based on whether it meets the AOI detection threshold.

[0124] In this embodiment, if the AOI detection value determines that there is an NG component, even if the AI ​​secondary determination is qualified or the manual determination is qualified, the board is still forced to be an NG board.

[0125] With technological advancements, especially the development of artificial intelligence, many AI algorithms can be applied to optical inspection of circuit boards or components. However, the existing architecture relies solely on the optimization of algorithms provided by AOI equipment vendors, which incurs significant procurement costs and often lags behind current technological developments in deployment time. In this embodiment, self-developed algorithms (AOI secondary AI determination algorithm, AOI defect control algorithm) can be superimposed on the algorithms provided by the AOI equipment, eliminating reliance on algorithm iterations from AOI vendors.

[0126] 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.

[0127] 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.

[0128] In step S1108, the centralized judgment and comprehensive processing system publishes the final result of the test item to the SMEMA controller in the form of an IoT message release as a "board request message". The SMEMA controller converts the message into a SMEMA "board request instruction" and transmits it to the AOI equipment via the SMEMA cable.

[0129] S1109, after receiving the "board request instruction", the AOI device transports the single board out of the AOI device.

[0130] At step S1110, the centralized judgment and comprehensive processing system publishes the final test results of the test items as "board presence messages and OK / NG messages" to the SMEMA controller via IoT message publishing. The SMEMA controller converts the messages into SMEMA "board presence instructions and OK / NG instructions" and transmits them to the automatic board collector via the SMEMA cable.

[0131] S1111, after the automatic board receiving machine receives the "board instruction and OK / NG instruction", after the single board comes out of the AOI equipment, it automatically separates the single board into the OK box or NG box according to the OK / NG instruction.

[0132] The above-mentioned process of S1101 to S1111 belongs to the process within a certain AOI equipment node. The centralized judgment integrated processing system can ensure that the processes within each AOI equipment node are tested independently and in parallel with the help of parallel processing technology. In addition, the test can be started immediately after receiving the "IoT board message". After the test is completed, the single board is immediately sent to the automatic board receiving machine.

[0133] The user interface of the centralized judgment and comprehensive processing system mainly includes the following areas:

[0134] 1. Manual judgment interface, used for manual judgment;

[0135] 2. Test item area: contains test items for each device node. The execution order of test items is shown in Figure 12.

[0136] 3. Device node interface, each AOI device node corresponds to a SMEMA controller on the hardware;

[0137] 4. Test log interface, used for real-time log printing for on-site personnel to refer to and observe the real-time test status;

[0138] 5. Automatic scanning interface, used for automatic scanning after successful testing, replacing the original manual scanning to complete the purpose of automatic transfer of production processes and accounts.

[0139] Compared with the existing technology, the above-mentioned embodiments of the present disclosure have the following beneficial effects: compatibility with various SMT equipment and scenarios, development of centralized judgment, one person multiple machines and other functions, meeting the demand for less manpower on the production site; compatibility with data formats of different AOI models, storage in the same format, standardization of control thresholds, and optimization from previous manual control to automatic control; superposition of self-developed algorithms (AOI secondary judgment AI algorithm, AOI detection value control algorithm) on the basis of the AOI equipment's own algorithm, getting rid of dependence on the AOI supplier's algorithm iteration, and continuously improving the SMT production quality through continuous iterative optimization of the algorithm.

[0140] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0141] 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.

[0142] An embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0143] 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.

[0144] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0145] Obviously, those skilled in the art should understand that the modules or steps of the present disclosure described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, 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 performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present disclosure is not limited to any particular combination of hardware and software.

[0146] The foregoing description is merely a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will readily appreciate that various modifications and variations of the present disclosure are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present disclosure shall be included within the scope of protection of the present disclosure.

Claims

1. A method for testing detection data of an automatic optical inspection (AOI) device, comprising: Acquire 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; According to the first test result and the second test result, a final test result of each AOI device node is obtained.

2. The method according to claim 1, wherein: The multiple AOI device nodes correspond to one or more tested boards, one tested board includes one functional module or multiple functional modules of different levels, and the multiple tested boards include tested boards of one or more models.

3. The method according to claim 2, wherein: There is an association relationship between the tested boards, and the association relationship includes at least one of the following: a resource mutually exclusive sharing relationship and a synchronization relationship.

4. The method according to claim 1, wherein: Each of the equipment nodes includes: AOI equipment, SMEMA controller module and automatic board receiving machine.

5. The method according to claim 4, wherein: Before obtaining the first test result and the second test result of the detection data of the plurality of AOI device nodes in parallel, the method further includes: Receive an Internet of Things (IoT) board message sent by the SMEMA controller module corresponding to the multiple AOI device nodes, wherein the IoT board message carries an identifier of the SMEMA controller module; The detection data of each AOI device node is retrieved according to the identifier.

6. The method according to claim 5, wherein: The inspection data includes at least one of the following: whole board map, defect picture, manufacturing execution system MES data, and statistical process control SPC data.

7. The method according to claim 6, wherein: The second test result of obtaining the detection data of multiple AOI device nodes in parallel includes: An AOI detection value is determined according to the SPC data of the multiple AOI device nodes and the whole board map to obtain the second test result.

8. The method according to claim 6, wherein: The secondary determination result of the AI ​​server is obtained by the AI ​​server performing secondary determination on the defect image, and the secondary determination is to confirm whether the tested board has defects based on the defect image.

9. The method according to claim 8, wherein: According to the first test result and the second test result, a final test result of each AOI device node is obtained, including: When the tested single board is secondarily determined by the AI ​​server to be a qualified single board, performing AOI detection value determination on the tested single board; The tested single board whose AOI detection value exceeds the preset threshold is determined as a problem single board, and the tested single board whose AOI detection value does not exceed the preset threshold is determined as a qualified single board.

10. The method according to claim 6, wherein: In the case where the AI ​​server cannot confirm whether the tested board has defects, the method further includes: Obtain a third test result of the detection data of the multiple AOI device nodes, wherein the third test result is a manual determination result, and the manual determination result is obtained by manually determining a defect image that is not recognized by the AI ​​server.

11. The method according to claim 1, wherein: After obtaining the final test results of each AOI device node, the method further includes one of the following: According to the final test result, a board-available message and an OK / NG message are sent to the automatic board receiving machine; and according to the final test result, a board-request message is sent to the AOI device node.

12. The method according to claim 1, wherein: The AOI detection value determination 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.

13. A centralized determination and comprehensive processing system, comprising: A first acquisition module is configured to acquire 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; The second acquisition module is configured to obtain a 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 having a computer program stored therein, wherein: 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 in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of claims 1 to 12 when executing the computer program.

Images