A method, apparatus, device, and storage medium for joint detection of multiple AOI devices.

Abstract

This application relates to a method, apparatus, device, and storage medium for joint inspection using multiple AOI devices. The method includes obtaining an initial inspection result for each AOI device after initial inspection is completed; extracting initial defect information of the target object based on the initial inspection results of each AOI device; generating backtracking inspection parameters by combining the inspection parameters of each AOI device and the initial defect information; performing backtracking inspection based on the backtracking inspection parameters to obtain backtracking inspection results; and obtaining a final inspection result by combining the initial inspection results and the backtracking inspection results. This application effectively reduces the probability of misjudgment and improves inspection accuracy when using multiple AOI devices for joint inspection.

Description

Technical Field

[0001] This invention relates to the technical field of AOI equipment, and in particular to a method, apparatus, device, and storage medium for joint detection of multiple AOI devices. Background Technology

[0002] AOI (Automatic Optical Inspection) is a technology that uses optical principles to inspect electronic products such as PCBs and semiconductor devices. AOI equipment typically consists of a light source, optical system, image processing system, and mechanical system, enabling it to quickly and accurately detect various defects in electronic products.

[0003] Currently, AOI equipment is widely used in the field of electronic manufacturing, especially in the production of electronic products with high precision and high reliability requirements. The application of AOI technology can greatly improve product quality and reliability, and reduce production costs and human error rates.

[0004] With the rapid development of the electronics manufacturing industry, AOI technology has become a key element in ensuring product quality. However, existing AOI equipment often has viewing angle limitations during the inspection process, resulting in certain areas becoming inspection "blind spots," thus affecting the accuracy and comprehensiveness of the inspection results. To solve the viewing angle limitation problem, common practices include increasing the number of AOI devices or performing multiple inspections from different angles. However, this method is inefficient, and due to the increased number of AOI devices, the inspection results from multiple devices are independent. It is necessary to synthesize the inspection results from multiple AOI devices. If the inspection results from multiple AOI devices cannot be synthesized well, it will lead to a decrease in the accuracy of the inspection results and an increase in the probability of misjudgment. Summary of the Invention

[0005] To reduce the probability of misjudgment and improve detection accuracy when using multiple AOI devices for joint detection, this application provides a method, apparatus, device, and storage medium for joint detection using multiple AOI devices.

[0006] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution:

[0007] A method for joint detection of multiple AOI devices, the method comprising:

[0008] After the initial detection of each of the AOI devices is completed, the initial detection result of each of the AOI devices is obtained;

[0009] Based on the initial detection results of each AOI device, extract the initial defect information of the target object;

[0010] By combining the detection parameters of each AOI device and the initial defect information, backtracking detection parameters are generated;

[0011] Perform backtracking detection based on the backtracking detection parameters to obtain backtracking detection results;

[0012] The detection result is obtained by combining the initial detection result and the backtracking detection result.

[0013] By adopting the above technical solution and combining multiple AOI devices for inspection, the advantages and characteristics of each device can be fully utilized, covering a wider inspection range and angle. Different devices may use different light sources, cameras, and algorithms to capture the feature information of the inspected object under different conditions. Initial inspection is combined with retrospective inspection. After the initial inspection is completed, the initial defect information is extracted based on the initial inspection results of each device, and retrospective inspection parameters are generated to identify defects that may be missed or misjudged. Retrospective inspection is used to further confirm and correct these defects, thereby improving the accuracy of the inspection. The entire inspection process is highly automated. From initial inspection to retrospective inspection and the final output of results, everything relies on the control of computers and algorithms, reducing the need for manual intervention and improving inspection efficiency and consistency. Through the retrospective inspection mechanism, targeted re-inspection can be performed on suspected defects, rather than a comprehensive re-inspection of the entire inspected object. Moreover, the inspection parameters of each AOI device (such as light angle, light intensity, camera angle, etc.) are usually adjustable. For inspected objects with complex structures and multiple defect types, joint inspection of multiple AOI devices can provide a more comprehensive inspection perspective and more accurate inspection results.

[0014] In a preferred embodiment, this application can be further configured such that: the generation of retrospective detection parameters by combining the detection parameters of each of the AOI devices and the initial defect information includes:

[0015] Based on the detection parameters of each AOI device, generate symmetrical detection parameters for each AOI device;

[0016] Based on the symmetrical detection parameters of each AOI device, it is determined whether the initial defect information can be detected, and backtracking detection parameters are generated based on the determination result.

[0017] By adopting the above technical solution and generating symmetrical detection parameters for each AOI device, the detection effect under opposite or symmetrical conditions can be simulated or predicted. This facilitates the discovery of minute defects or hidden problems that are difficult to detect under conventional detection conditions, thereby improving the accuracy and sensitivity of the detection. Using symmetrical detection parameters, it is possible to ensure a comprehensive evaluation of the initial defect information from different angles and conditions, reducing missed detections caused by blind spots or angle limitations, and improving the comprehensiveness of the detection. Based on the degree of matching between the symmetrical detection parameters and the initial defect information, the subsequent backtracking detection parameters can also be dynamically adjusted. By continuously accumulating and analyzing the data of symmetrical detection parameters and backtracking detection results, the existing detection algorithm can be optimized and improved, enhancing its adaptability and robustness, making it more suitable for complex and ever-changing detection tasks.

[0018] In a preferred embodiment, this application can be further configured such that: generating symmetric detection parameters for each AOI device based on the detection parameters of each AOI device includes:

[0019] Based on the detection parameters of each AOI device, complementary detection features of each AOI device are obtained.

[0020] Determine whether the complementary detection features of each AOI device can be symmetrically set. Replace the detection parameters of the AOI devices that can be symmetrically set, and retain the detection parameters of the AOI devices that cannot be symmetrically set.

[0021] By combining the detection parameters of the AOI device based on symmetric replacement and the retained detection parameters of the AOI device, it is determined whether the symmetry rate is greater than a preset symmetry rate threshold. When the symmetry rate is not greater than the preset symmetry rate threshold, the retained detection parameters of the AOI device are symmetrically replaced based on preset alternative replacement rules. By combining the symmetrically replaced detection parameters of the AOI device, the symmetric detection parameters of each AOI device are obtained.

[0022] By adopting the above technical solution and obtaining the complementary detection features of each AOI device, it is possible to fully utilize the detection advantages of different devices when generating symmetrical detection parameters. Symmetrical replacement of the detection parameters of AOI devices that can be symmetrically set can further expand the detection perspective and range, reduce detection blind spots, and thus optimize the overall detection coverage. By calculating the symmetry rate and comparing it with the preset symmetry rate threshold, the detection strategy can be flexibly adjusted. When the symmetry rate does not meet the requirements, alternative replacement rules can be automatically triggered to seek a better combination of symmetrical detection parameters. Alternative replacement rules provide multiple possibilities for adjusting detection parameters, enabling more flexible responses to complex detection tasks and improving the adaptability and flexibility of the detection strategy. Therefore, by generating symmetrical detection parameters, it is no longer entirely dependent on the detection performance of a specific AOI device. Even if the detection parameters of a certain device cannot be set completely symmetrically, they can be supplemented and replaced by the detection parameters of other devices, thereby enhancing the replaceability of the entire detection system. Furthermore, in the event of equipment failure or performance fluctuations, the setting of symmetrical detection parameters can ensure that the detection process is not affected by the state of a single device, maintaining the continuity and stability of the detection.

[0023] In a preferred embodiment, this application can be further configured such that: the generation of retrospective detection parameters by combining the detection parameters of each of the AOI devices and the initial defect information includes:

[0024] Determine the detection parameter range of each AOI device, and generate an initial defect segmentation range based on the detection parameter range of each AOI device and the initial defect information;

[0025] The detection parameter range and the initial defect segmentation range are input into a preset defect segmentation model to generate initial defect segmentation information and segmentation detection parameters for each AOI device.

[0026] By associating the initial defect segmentation information and segmentation detection parameters of each AOI device, backtracking detection parameters are obtained.

[0027] By employing the above technical solution, the detection parameter range of each AOI device is determined, and combined with initial defect information, the specific location range of the initial defect in the detection space can be accurately determined, enabling rapid defect localization and providing a fine search area for subsequent detection. Using a preset defect segmentation model, the initial defect can be further refined and segmented, generating more detailed initial defect segmentation information, including the specific shape, size, and location of the defect. This provides a finer search area for subsequent accurate detection. Furthermore, by generating the initial defect segmentation range, invalid detection areas during the detection process can be significantly reduced, allowing detection resources to be more concentrated on the search and confirmation of potential defects, improving detection efficiency and reducing detection costs. Cost; By associating the initial defect segmentation information and segmentation detection parameters of each AOI device, backtracking detection parameters for specific defects can be obtained. These parameters are more targeted and accurate, and can more accurately reflect the characteristics and state of defects, thereby improving detection accuracy. During the detection process, if it is found that the initial defect segmentation range or segmentation detection parameters do not match the actual detection situation, these parameters can be adjusted in real time. By continuously accumulating and analyzing detection data, the detection process and parameter settings can be continuously optimized. For example, the parameters of the defect segmentation model can be adjusted according to historical detection data to improve its segmentation accuracy and generalization ability; or the priority and weight of backtracking detection parameters can be adjusted according to the characteristics of the current detection task.

[0028] In a preferred embodiment, this application can be further configured such that: the backtracking detection based on the backtracking detection parameters, and the obtaining of the backtracking detection result, includes:

[0029] Perform backtracking detection based on the backtracking detection parameters to obtain initial backtracking detection results;

[0030] By combining the initial backtracking detection results and the initial detection results, suspected defect information is generated, and backtracking recovery detection parameters are generated based on the suspected defect information;

[0031] Perform backtracking recovery detection based on the backtracking recovery detection parameters to obtain backtracking recovery detection results;

[0032] The backtracking detection result is obtained by combining the backtracking recovery detection result and the initial backtracking detection result.

[0033] By adopting the above technical solution, and through two stages of detection—initial backtracking detection and backtracking recovery detection—dual verification of suspected defects is achieved, significantly improving the accuracy and reliability of defect identification and reducing false alarms and missed alarms. Based on the initial backtracking detection results, suspected defect information is generated in conjunction with the initial detection results, and backtracking recovery detection parameters are further generated to provide a more refined analysis and description of suspected defects, providing more accurate targets for subsequent detection. In addition, since the generation of backtracking recovery detection parameters is based on suspected defect information, detection resources can be more concentrated on in-depth detection and verification of suspected defects. Targeted detection helps optimize the allocation of detection resources and improve detection efficiency. By combining backtracking detection and backtracking recovery detection, repeated detection of known non-defect areas can be avoided, thereby reducing redundant detection and saving detection time and costs. For complex or difficult-to-identify defects, the combination of backtracking detection and backtracking recovery detection can gradually narrow the detection range, gradually approaching the true defect, and better addressing the detection challenges of complex defects.

[0034] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions:

[0035] A multi-AOI equipment joint inspection device, the multi-AOI equipment joint inspection device comprising:

[0036] An initial detection module is used to obtain the initial detection result of each AOI device after the initial detection of each AOI device is completed;

[0037] The initial defect extraction module is used to extract the initial defect information of the target object based on the initial detection results of each AOI device.

[0038] The backtracking parameter module is used to generate backtracking detection parameters by combining the detection parameters of each AOI device and the initial defect information;

[0039] The backtracking detection module is used to perform backtracking detection based on the backtracking detection parameters and obtain backtracking detection results;

[0040] The detection result module is used to combine the initial detection result and the backtracking detection result to obtain the detection result.

[0041] Optionally, the backtracking parameter module includes:

[0042] The symmetry analysis submodule is used to generate symmetry detection parameters for each AOI device based on the detection parameters of each AOI device.

[0043] The backtracking analysis submodule is used to determine whether the initial defect information can be detected based on the symmetrical detection parameters of each AOI device, and to generate backtracking detection parameters based on the determination result.

[0044] Optionally, the symmetry analysis submodule includes:

[0045] A complementary analysis unit is used to obtain complementary detection features of each AOI device based on the detection parameters of each AOI device.

[0046] The parameter replacement unit is used to determine whether the complementary detection features of each AOI device can be symmetrically set, and to symmetrically replace the detection parameters of the AOI devices that can be symmetrically set, while retaining the detection parameters of the AOI devices that cannot be symmetrically set.

[0047] The symmetry analysis unit is used to combine the detection parameters of the AOI device based on symmetry replacement and the retained detection parameters of the AOI device to determine whether the symmetry rate is greater than a preset symmetry rate threshold. When the symmetry rate is not greater than the preset symmetry rate threshold, the retained detection parameters of the AOI device are symmetrically replaced based on preset alternative replacement rules. Combined with the symmetrically replaced detection parameters of the AOI device, the symmetry detection parameters of each AOI device are obtained.

[0048] Thirdly, the above-mentioned inventive objective of this application is achieved through the following technical solutions:

[0049] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described multi-AOI device joint detection method.

[0050] Fourthly, the above-mentioned inventive objective of this application is achieved through the following technical solutions:

[0051] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described multi-AOI device joint detection method.

[0052] In summary, this application includes at least one of the following beneficial technical effects:

[0053] 1. Combining multiple AOI devices for inspection fully leverages the advantages and characteristics of each device, covering a wider inspection range and angle. Different devices may employ different light sources, cameras, and algorithms, enabling them to capture feature information of the inspected object under different conditions. The combination of initial and retrospective inspections allows for the extraction of initial defect information based on the initial inspection results of each device after the initial inspection, generating retrospective inspection parameters to identify potentially missed or misjudged defects. Further confirmation and correction through retrospective inspection improves inspection accuracy. The entire inspection process is highly automated, from initial inspection to retrospective inspection and final result output, relying on computer and algorithm control. This reduces the need for manual intervention, improving inspection efficiency and consistency. The retrospective inspection mechanism allows for targeted re-inspection of suspected defects, rather than a complete re-inspection of the entire inspected object. Furthermore, the inspection parameters of each AOI device (such as light angle, light intensity, camera angle, etc.) are usually adjustable. For inspected objects with complex structures and multiple defect types, combined inspection with multiple AOI devices provides a more comprehensive inspection perspective and more accurate results.

[0054] 2. By generating symmetrical detection parameters for each AOI device, the detection effect under opposite or symmetrical conditions can be simulated or predicted. This facilitates the discovery of minute defects or hidden problems that are difficult to detect under conventional detection conditions, thereby improving the accuracy and sensitivity of the detection. Using symmetrical detection parameters, it is possible to ensure a comprehensive evaluation of the initial defect information from different angles and conditions, reducing missed detections caused by blind spots or angle limitations, and improving the comprehensiveness of the detection. Based on the degree of matching between the symmetrical detection parameters and the initial defect information, the subsequent backtracking detection parameters can also be dynamically adjusted. By continuously accumulating and analyzing the data of symmetrical detection parameters and backtracking detection results, the existing detection algorithm can be optimized and improved, enhancing its adaptability and robustness, making it more suitable for complex and ever-changing detection tasks.

[0055] 3. Obtaining complementary detection features for each AOI device ensures that the detection advantages of different devices can be fully utilized when generating symmetrical detection parameters. Symmetrical replacement of detection parameters of AOI devices that can be symmetrically set can further expand the detection perspective and range, reduce detection blind spots, and thus optimize overall detection coverage. By calculating the symmetry rate and comparing it with a preset symmetry rate threshold, the detection strategy can be flexibly adjusted. When the symmetry rate does not meet the requirements, alternative replacement rules can be automatically triggered to seek a better combination of symmetrical detection parameters. Alternative replacement rules provide multiple possibilities for adjusting detection parameters, enabling more flexible responses to complex detection tasks and improving the adaptability and flexibility of the detection strategy. Therefore, by generating symmetrical detection parameters, the system is no longer entirely dependent on the detection performance of a specific AOI device. Even if the detection parameters of a certain device cannot be set symmetrically, they can be supplemented and replaced by the detection parameters of other devices, thereby enhancing the replaceability of the entire detection system. Furthermore, in the event of equipment failure or performance fluctuations, the setting of symmetrical detection parameters can ensure that the detection process is not affected by the state of a single device, maintaining the continuity and stability of the detection. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating an implementation of the multi-AOI device joint detection method in this application embodiment;

[0057] Figure 2 This is a flowchart of the first implementation of S30 of the multi-AOI device joint detection method in the embodiments of this application;

[0058] Figure 3 This is a flowchart illustrating the implementation of S031 of the multi-AOI device joint detection method in this application embodiment;

[0059] Figure 4 This is a second implementation flowchart of S30 of the multi-AOI device joint detection method in the embodiments of this application;

[0060] Figure 5 This is a flowchart illustrating the implementation of S40 of the multi-AOI device joint detection method in this application embodiment;

[0061] Figure 6 This is a schematic diagram of a multi-AOI device joint detection device in the embodiments of this application;

[0062] Figure 7 This is an internal structural diagram of the computer device in the embodiments of this application. Detailed Implementation

[0063] The following is in conjunction with the appendix Figure 1-7 This application will be described in further detail.

[0064] In one embodiment, such as Figure 1 As shown, this application discloses a method for joint detection by multiple AOI devices, which specifically includes the following steps:

[0065] S10: After the initial detection of each AOI device is completed, obtain the initial detection result of each AOI device.

[0066] In this embodiment, the multi-AOI device joint inspection method is applied to a central control system. This central control system controls a joint inspection system composed of multiple AOI devices deployed at different locations or stages in a production process. These AOI devices are distributed at different locations on the inspection line or around the inspection object at different angles to ensure image data is acquired from multiple perspectives. Each AOI device has independent image acquisition, processing, and analysis capabilities, enabling it to identify and report detected defects. Different AOI devices may employ different detection principles or technologies (such as white light, colored light, infrared, ultraviolet, etc.), covering a wider range of defect types. Multiple AOI devices can establish network connections to achieve real-time sharing and collaborative processing of inspection data, further improving inspection efficiency and accuracy. The central control system is the core of the entire joint inspection system, responsible for coordinating the work of each AOI device. The central control system receives inspection data from each AOI device, summarizes, analyzes, and processes it, ultimately generating a comprehensive inspection report. The central control system also has functions such as remote monitoring, fault diagnosis, and automatic parameter adjustment to improve inspection efficiency and accuracy.

[0067] For example, the basic working principle of a joint detection system can be:

[0068] Each AOI device acquires images of the target object through its built-in camera and lighting system. The image data captured by the camera is transmitted to its respective image processing unit for preliminary processing. The image processing unit preprocesses the received images, such as denoising and enhancing contrast, to improve image quality. Subsequently, image processing algorithms are used to extract features and compare templates to identify defects that do not conform to the standard template. Each AOI device sends the detected defect data to the central control system. The central control system summarizes, analyzes, and processes the received data to generate a report containing all detection results. The report can list in detail the location, type, size, and other information of defects for each detected object for subsequent processing reference. The central control system also has a remote monitoring function, which can view the working status and detection results of each AOI device in real time. When a fault is found in an AOI device or the detection effect is not good, the central control system can perform fault diagnosis and parameter adjustment to ensure the stable operation and efficient work of the entire detection system.

[0069] A schematic diagram of the joint detection system can be:

[0070] On a circular or U-shaped production line, multiple AOI devices are installed in different positions, rotating or moving around the target object (such as a lead frame or circuit board). Each AOI device is equipped with a camera and lighting system, which can capture images of the target object from different angles and distances. The central control system is located at the center or one side of the production line and is connected to each AOI device via wired or wireless means, and is responsible for receiving and processing the detection data.

[0071] Specifically, during the operation of the joint inspection system, the object to be inspected will pass through each AOI device in sequence and be inspected by each AOI device for defects. That is, the image of the target object to be inspected is compared with the standard template to identify defects that do not conform to the standard template. Therefore, after the initial inspection of each AOI device is completed, that is, after the first inspection of the target object by each AOI device in the current generation process, the initial inspection results of each AOI device on the target object to be inspected are obtained.

[0072] S20: Extract the initial defect information of the target object based on the initial detection results of each AOI device.

[0073] Specifically, the initial inspection results of each AOI device will show the defects exposed by the target object in the initial inspection. Therefore, based on the initial inspection results of each AOI device, the initial defect information of the target object corresponding to each AOI device is extracted.

[0074] S30: Combine the detection parameters of each AOI device with the initial defect information to generate backtracking detection parameters.

[0075] Specifically, in a joint inspection system, the usual inspection method is that each AOI device sequentially inspects the target object to complete one round of inspection. For example, when multiple AOI devices in a joint inspection system are arranged sequentially on a production line, the target object completes one round of inspection after it passes through the production line. However, due to factors such as equipment accuracy, algorithm differences, equipment layout, inspection angle, or algorithm limitations, there may be some misjudgments, which will lead to a decrease in the inspection accuracy of the joint inspection system and affect the overall production process. Therefore, it is necessary to improve the inspection accuracy of the target object.

[0076] Based on this, according to the initial defect information of each AOI device, the locations of all initially detected defects on the target object are determined. Then, based on the detection parameters of each AOI device, the key detection areas of each AOI device are determined. Because there are multiple AOI devices in the joint inspection system, each AOI device has a key detection area. That is, not every AOI device performs a comprehensive inspection of the target object, but rather each AOI device is responsible for inspecting a specific area of ​​the target object. Therefore, by combining the locations of all initially detected defects on the target object and the key detection areas of each AOI device, it is determined whether it is possible to trace the locations of all initially detected defects during the backtracking inspection. In the backtracking detection process, if it is determined that the locations of all initially detected defects can be detected, the parameters of each AOI device do not need to be adjusted. However, if it is determined that the locations of all initially detected defects cannot be detected, it means that some AOI devices can detect the initial defects during backtracking detection, while others cannot. Therefore, based on the determined locations of defects that cannot be detected backtracking, and considering the AOI devices that cannot detect the initial defects during backtracking detection, the detection parameters of these AOI devices are adjusted so that they can detect the corresponding defect locations, thereby ensuring that all initially detected defects can be detected.

[0077] Alternatively, when it is determined that it is not possible to detect the location of all initially detected defects, the detection parameters of each AOI device are adjusted so that each AOI device can detect the corresponding defect location. In this case, the detection location of each AOI device may be different from the location detected during the initial detection.

[0078] In this embodiment, when the joint detection system performs backtracking detection, it can perform backtracking detection in reverse order of the initial detection, or it can perform backtracking detection in a specific order. For example, when performing backtracking detection in reverse order of the initial detection, only some AOI devices can be called, or only some AOI devices can be called to perform multiple rounds of detection with different detection parameters. Therefore, the backtracking detection parameters include not only the detection parameters of each AOI device, but also the order in which the joint detection system performs backtracking detection and the detection time point of each AOI device.

[0079] S40: Perform backtracking detection based on backtracking detection parameters to obtain backtracking detection results.

[0080] Specifically, after obtaining the backtracking detection parameters, backtracking detection is performed based on the backtracking detection parameters to obtain the backtracking detection results.

[0081] S50: Combine the initial detection results and the retrospective detection results to obtain the detection results.

[0082] Specifically, since backtracking inspection is performed on the defects detected initially, the backtracking inspection results are also for the defects detected initially. By combining the initial inspection results and the backtracking inspection results, the same defects that appear in both the initial inspection results and the backtracking inspection results are identified and marked as measurement defects. Defects that appear only in the initial inspection results or only in the backtracking inspection results can be marked as test defects, thereby obtaining the inspection results.

[0083] In one embodiment, such as Figure 2 As shown, in step S30, by combining the detection parameters of each AOI device and the initial defect information, retrospective detection parameters are generated, including:

[0084] S031: Generate symmetrical detection parameters for each AOI device based on the detection parameters of each AOI device.

[0085] Specifically, during the initial inspection, each AOI device targets a specific area on the target object, i.e., the initial area. Therefore, based on the initial area on the target object targeted by each AOI device during the initial inspection, the area on the target object that is symmetrical to the initial area of ​​each corresponding AOI device can be determined, i.e., the symmetrical area. Then, the detection parameters when each AOI device needs to detect the symmetrical area can be determined to obtain the symmetrical detection parameters. It should be noted that if adjusting the detection parameters of the AOI device cannot detect the symmetrical area, no adjustment is required.

[0086] Alternatively, based on the pre-defined backtracking detection sequence of the joint detection system, determine the detection area of ​​each AOI device during backtracking detection without changing the current detection parameters of each AOI device, and then determine whether the detection area of ​​each AOI device is symmetrical with the initial area without changing the current detection parameters of each AOI device, and then adjust the detection parameters of the AOI devices that are judged to be asymmetrical.

[0087] S032: Based on the symmetrical detection parameters of each AOI device, determine whether the initial defect information can be detected, and generate backtracking detection parameters based on the judgment result.

[0088] Specifically, based on the symmetrical detection parameters of each AOI device, it is determined whether all initial defect information can be detected during backtracking detection based on the symmetrical detection parameters of each AOI device, and the judgment result is obtained. According to the judgment result, for the initial defect information that is judged to be undetectable, the symmetrical detection parameters of one or more AOI devices are adjusted. That is, the symmetrical detection parameters of each AOI device can be adjusted to the detection parameters at the time of initial detection, remain unchanged, or be set to empty. In this way, by simulating and judging different combinations of detection parameters of all AOI devices, it is determined under what combination all initial defect information can be detected during backtracking detection, thereby generating backtracking detection parameters that can detect all initial defect information during backtracking detection.

[0089] In one embodiment, such as Figure 3 As shown, in step S031, based on the detection parameters of each AOI device, symmetrical detection parameters for each AOI device are generated, including:

[0090] S0311: Based on the detection parameters of each AOI device, obtain the complementary detection features of each AOI device.

[0091] Specifically, based on the detection parameters of each AOI device, the detection characteristics of each AOI device are determined according to the current detection parameters of each AOI device. This means determining the detection area of ​​each AOI device for the target object and the detection parameter type of each AOI device. This is because the multi-dimensional detection requirements for different types of target objects vary accordingly. For example, for a lead frame, it is necessary to check whether the surface of the lead frame is flat and free from defects such as scratches, dents, deformation, and stains. It is also necessary to verify whether the dimensions of the lead frame meet the design requirements, including length, width, height, and the diameter, position, and spacing of the lead holes. The detection parameter type is essentially the detection requirement. Therefore, it is necessary to... To meet these inspection requirements, inspection parameters are generated for each AOI device, enabling each AOI device to detect one or more types of inspection parameters. Once the inspection parameters for each AOI device are determined, the inspection characteristics of each AOI device are analyzed based on these parameters. For example, the inspection area, inspection angle, and inspection dimension (two-dimensional or three-dimensional) of each AOI device are analyzed. These inspection characteristics correspond to the inspection requirements. However, for other items such as PCB boards, the focus may be more on the installation quality, soldering quality, and electrical performance of components. Therefore, the inspection characteristics of each AOI device may differ for different target inspection items or for the same target inspection item but different batches of target inspection items.

[0092] In addition, complementary detection features refer to those that correspond to the current detection requirements of the target object but not to the current detection features. In other words, each AOI device can obtain other detection features that correspond to the current detection requirements of the target object by changing the detection parameters, in addition to the current detection features.

[0093] S0312: Determine whether the complementary detection features of each AOI device can be set symmetrically, replace the detection parameters of AOI devices that can be set symmetrically, and retain the detection parameters of AOI devices that cannot be set symmetrically.

[0094] Specifically, since an AOI device may have one or more complementary detection features, and corresponding detection parameters may be one or more sets, when setting symmetrical detection parameters, it is necessary to meet the current detection requirements and minimize the symmetry condition of adjusting the detection parameters of each AOI device as a whole. This ensures that there is only one complementary detection feature for each AOI device and that excessive parameter adjustments are not required, thus guaranteeing system stability. Therefore, it is necessary to determine whether the complementary detection features of each AOI device can be symmetrically set. That is, under the condition of meeting the symmetry condition, it is necessary to determine whether each AOI device can replace the detection feature with the complementary detection feature by changing the parameters. For those that can replace the detection feature with the complementary detection feature by changing the parameters, the parameters are changed and replaced. For those that cannot replace the detection feature with the complementary detection feature by changing the parameters, they are retained. At this time, the detection parameters of each AOI device can meet the symmetry condition, that is, meet the current detection requirements and minimize the symmetry condition of adjusting the detection parameters of each AOI device as a whole.

[0095] S0313: By combining the detection parameters of the AOI device based on symmetric replacement and the detection parameters of the retained AOI device, determine whether the symmetry rate is greater than a preset symmetry rate threshold. When the symmetry rate is not greater than the preset symmetry rate threshold, based on the preset alternative replacement rules, symmetrically replace the detection parameters of the retained AOI device, and combine the detection parameters of the symmetrically replaced AOI device to obtain the symmetric detection parameters of each AOI device.

[0096] Specifically, by combining the detection parameters of the AOI device based on symmetric replacement and the detection parameters of the retained AOI device, it is determined whether the symmetry rate is greater than a preset symmetry rate threshold. In other words, it is determined whether the number of detection parameters to be replaced by parameter changes is greater than the preset symmetry rate threshold. When the symmetry rate is not greater than the preset symmetry rate threshold, that is, when the number of detection parameters to be replaced by parameter changes is small, it indicates that the number of detection parameters to be replaced by parameter changes is small and cannot meet the preset symmetry requirements. Therefore, based on the preset alternative replacement rules, the detection parameters of the retained AOI device are symmetrically replaced. That is, under the condition of satisfying the symmetry, different complementary detection features that can replace the detection features with complementary detection features through parameter changes are reselected from multiple complementary detection features of some AOI devices. Then, parameter changes are performed based on the reselected complementary detection features. Combined with the detection parameters of the AOI devices that have already undergone symmetric replacement, the symmetric detection parameters of each AOI device are obtained.

[0097] In one embodiment, such as Figure 4 As shown, in step S30, by combining the detection parameters of each AOI device and the initial defect information, retrospective detection parameters are generated, including:

[0098] S131: Determine the detection parameter range of each AOI device, and generate the initial defect segmentation range based on the detection parameter range of each AOI device and the initial defect information.

[0099] Specifically, the range of detection parameters for each AOI device is determined, that is, the adjustable range of each type of detection parameter for each AOI device, such as the angle of the light source shining on the target object, the camera angle, and the intensity of the light source. In addition, the defects on the target object represented by the initial defect information usually have a certain area. Therefore, the defects on the target object represented by the initial defect information can be segmented. By utilizing the characteristic of multiple AOI devices for joint detection, the defects on the segmented target object can be detected more precisely.

[0100] Based on this, according to the current detection parameters and corresponding detection parameter range of each AOI device, the area size of the defect region on the target object corresponding to the initial defect information that can be detected when the detection parameters of each AOI device are adjusted within the detection parameter range is determined, and the initial defect segmentation range is obtained.

[0101] S132: Input the detection parameter range and the initial defect segmentation range into the preset defect segmentation model to generate the initial defect segmentation information and segmentation detection parameters corresponding to each AOI device.

[0102] Specifically, the detection parameter range and the initial defect segmentation range are input into a preset defect segmentation model. Through the defect segmentation model, the most suitable area size of the initial defect region is found within the initial defect segmentation range of each AOI device. In other words, the detection volume of each AOI device is determined by the defect segmentation model when the area size of the initial defect region corresponds to different AOI devices. The corresponding defect segmentation range of each AOI device is found when the detection volume of all AOI devices is minimized. Because after the defects on the target object are segmented, one defect becomes multiple defects, and the number of inspections required will increase. Therefore, in order to save detection resources, the defect segmentation range of each AOI device with the minimum detection volume of all AOI devices is found through the defect segmentation model with the optimal solution algorithm. This is used as the initial defect segmentation information for each AOI device, that is, the area detected by each AOI device during backtracking inspection. Then, based on the area detected by each AOI device during backtracking inspection, detection parameters suitable for detecting that area are generated, that is, segmentation detection parameters.

[0103] S133: Associate the initial defect segmentation information and segmentation detection parameters of each AOI device to obtain backtracking detection parameters.

[0104] Specifically, the initial defect segmentation information and segmentation detection parameters of each AOI device are associated to obtain the backtracking detection parameters for each AOI device.

[0105] In one embodiment, such as Figure 5 As shown, in step S40, backtracking detection is performed based on the backtracking detection parameters to obtain the backtracking detection result, including:

[0106] S41: Perform backtracking detection based on backtracking detection parameters to obtain initial backtracking detection results.

[0107] Specifically, backtracking detection is performed based on backtracking detection parameters to obtain the detection results obtained by using the backtracking detection parameters, i.e., the initial backtracking detection results.

[0108] S42: Combine the initial backtracking detection results and the initial detection results to generate suspected defect information, and generate backtracking recovery detection parameters based on the suspected defect information.

[0109] Specifically, by combining the initial backtracking detection results and the initial detection results, defects appearing in both can be considered defects, while defects appearing only in the initial backtracking detection results or only in the initial detection results can be considered suspected defects. Furthermore, during backtracking detection, the target object returns to the vicinity of the preceding AOI device in the joint detection system, i.e., near the feed inlet of the joint detection system. To complete the AOI detection, the target object needs to be transported a distance, passing through multiple subsequent AOI devices. Therefore, for suspected defects, the target object can be re-detected during transport. Thus, based on the suspected defects, backtracking recovery detection parameters suitable for detecting the corresponding defects in subsequent AOI devices are generated.

[0110] S43: Perform backtracking recovery detection based on backtracking recovery detection parameters to obtain backtracking recovery detection results.

[0111] Specifically, backtracking recovery detection is performed based on backtracking recovery detection parameters to obtain the detection results obtained by using the backtracking recovery detection parameters, i.e., the backtracking recovery detection results.

[0112] S44: Combine the backtracking recovery detection results and the initial backtracking detection results to obtain the backtracking detection results.

[0113] Specifically, since the detection directions of the retrospective recovery detection results and the initial retrospective detection results are the same, that is, the movement directions of the target object are the same, by combining the retrospective recovery detection results and the initial retrospective detection results, defects that appear in both the retrospective recovery detection results and the initial retrospective detection results can be considered as defects, thereby obtaining the retrospective detection results.

[0114] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0115] In one embodiment, a multi-AOI device joint detection apparatus is provided, which corresponds one-to-one with the multi-AOI device joint detection method described in the above embodiments. For example... Figure 6 As shown, this multi-AOI equipment joint inspection device includes an initial inspection module, an initial defect extraction module, a backtracking parameter module, a backtracking inspection module, and an inspection result module. Detailed descriptions of each functional module are as follows:

[0116] The initial detection module is used to obtain the initial detection results of each AOI device after the initial detection of each AOI device is completed;

[0117] The initial defect extraction module is used to extract the initial defect information of the target object based on the initial detection results of each AOI device.

[0118] The retrospective parameter module is used to generate retrospective detection parameters by combining the detection parameters of each AOI device and the initial defect information;

[0119] The backtracking detection module is used to perform backtracking detection based on backtracking detection parameters and obtain backtracking detection results.

[0120] The detection results module is used to combine the initial detection results and the retrospective detection results to obtain the detection results.

[0121] Optionally, the backtracking parameter module includes:

[0122] The symmetry analysis submodule is used to generate symmetry detection parameters for each AOI device based on the detection parameters of each AOI device.

[0123] The backtracking analysis submodule is used to determine whether initial defect information can be detected based on the symmetrical detection parameters of each AOI device, and to generate backtracking detection parameters based on the judgment result.

[0124] Optional, the symmetry analysis submodule includes;

[0125] The complementary analysis unit is used to obtain the complementary detection features of each AOI device based on the detection parameters of each AOI device.

[0126] The parameter replacement unit is used to determine whether the complementary detection features of each AOI device can be set symmetrically. The detection parameters of the AOI devices that can be set symmetrically are replaced symmetrically, while the detection parameters of the AOI devices that cannot be set symmetrically are retained.

[0127] The symmetry analysis unit is used to combine the detection parameters of the AOI device based on symmetry replacement and the detection parameters of the retained AOI device to determine whether the symmetry ratio is greater than a preset symmetry ratio threshold. When the symmetry ratio is not greater than the preset symmetry ratio threshold, the detection parameters of the retained AOI device are symmetrically replaced based on the preset alternative replacement rules. Combined with the detection parameters of the symmetrically replaced AOI device, the symmetry detection parameters of each AOI device are obtained.

[0128] Optionally, the backtracking parameter module includes:

[0129] The segmentation range submodule is used to determine the detection parameter range of each AOI device and generate the initial defect segmentation range based on the detection parameter range of each AOI device and the initial defect information.

[0130] The segmentation determination submodule is used to input the detection parameter range and the initial defect segmentation range into the preset defect segmentation model to generate the initial defect segmentation information and segmentation detection parameters corresponding to each AOI device.

[0131] The association submodule is used to associate the initial defect segmentation information and segmentation detection parameters of each AOI device to obtain backtracking detection parameters.

[0132] Optionally, the backtracking detection module includes:

[0133] The initial backtracking result submodule is used to perform backtracking detection based on backtracking detection parameters and obtain the initial backtracking detection result.

[0134] The suspected defect submodule is used to combine the initial backtracking detection results and the initial detection results to generate suspected defect information, and based on the suspected defect information, generate backtracking recovery detection parameters;

[0135] The backtracking recovery detection submodule is used to perform backtracking recovery detection based on backtracking recovery detection parameters and obtain backtracking recovery detection results.

[0136] The integrated backtracking submodule is used to combine the backtracking recovery detection results and the initial backtracking detection results to obtain the backtracking detection results.

[0137] Specific limitations regarding the multi-AOI equipment joint testing device can be found in the limitations of the multi-AOI equipment joint testing method described above, and will not be repeated here. Each module in the aforementioned multi-AOI equipment joint testing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0138] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores initial detection results, initial defect information, retrospective detection parameters, retrospective detection results, and detection results. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a multi-AOI device joint detection method.

[0139] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0140] After the initial detection of each AOI device is completed, the initial detection results of each AOI device are obtained;

[0141] Based on the initial detection results of each AOI device, extract the initial defect information of the target object;

[0142] By combining the detection parameters and initial defect information of each AOI device, backtracking detection parameters are generated;

[0143] Backtracking detection is performed based on backtracking detection parameters to obtain backtracking detection results;

[0144] The test results are obtained by combining the initial test results and the retrospective test results.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0146] After the initial detection of each AOI device is completed, the initial detection results of each AOI device are obtained;

[0147] Based on the initial detection results of each AOI device, extract the initial defect information of the target object;

[0148] By combining the detection parameters and initial defect information of each AOI device, backtracking detection parameters are generated;

[0149] Backtracking detection is performed based on backtracking detection parameters to obtain backtracking detection results;

[0150] The test results are obtained by combining the initial test results and the retrospective test results.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0152] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0153] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for joint detection using multiple AOI devices, characterized in that, The multi-AOI device joint detection method includes: After the initial detection of each of the AOI devices is completed, the initial detection result of each of the AOI devices is obtained; Based on the initial detection results of each AOI device, extract the initial defect information of the target object; By combining the detection parameters of each AOI device and the initial defect information, backtracking detection parameters are generated; wherein, the step of combining the detection parameters of each AOI device and the initial defect information to generate backtracking detection parameters includes: generating symmetrical detection parameters for each AOI device based on the detection parameters of each AOI device; determining whether the initial defect information can be detected based on the symmetrical detection parameters of each AOI device; and generating backtracking detection parameters based on the determination result. Perform backtracking detection based on the backtracking detection parameters to obtain backtracking detection results; The detection result is obtained by combining the initial detection result and the backtracking detection result.

2. The multi-AOI equipment joint detection method according to claim 1, characterized in that, The step of generating symmetric detection parameters for each AOI device based on the detection parameters of each AOI device includes: Based on the detection parameters of each AOI device, complementary detection features of each AOI device are obtained. Determine whether the complementary detection features of each AOI device can be symmetrically set. Replace the detection parameters of the AOI devices that can be symmetrically set, and retain the detection parameters of the AOI devices that cannot be symmetrically set. By combining the detection parameters of the AOI device based on symmetric replacement and the retained detection parameters of the AOI device, it is determined whether the symmetry rate is greater than a preset symmetry rate threshold. When the symmetry rate is not greater than the preset symmetry rate threshold, the retained detection parameters of the AOI device are symmetrically replaced based on preset alternative replacement rules. By combining the symmetrically replaced detection parameters of the AOI device, the symmetric detection parameters of each AOI device are obtained.

3. The multi-AOI equipment joint detection method according to claim 1, characterized in that, The backtracking detection based on the backtracking detection parameters, to obtain the backtracking detection result, includes: Perform backtracking detection based on the backtracking detection parameters to obtain initial backtracking detection results; By combining the initial backtracking detection results and the initial detection results, suspected defect information is generated, and backtracking recovery detection parameters are generated based on the suspected defect information; Perform backtracking recovery detection based on the backtracking recovery detection parameters to obtain backtracking recovery detection results; The backtracking detection result is obtained by combining the backtracking recovery detection result and the initial backtracking detection result.

4. A multi-AOI equipment joint inspection device, characterized in that, The multi-AOI equipment joint detection device includes: An initial detection module is used to obtain the initial detection result of each AOI device after the initial detection of each AOI device is completed; The initial defect extraction module is used to extract the initial defect information of the target object based on the initial detection results of each AOI device. The backtracking parameter module is used to generate backtracking detection parameters by combining the detection parameters of each AOI device and the initial defect information; The backtracking detection module is used to perform backtracking detection based on the backtracking detection parameters and obtain backtracking detection results; The detection result module is used to combine the initial detection result and the backtracking detection result to obtain the detection result; The backtracking parameter module includes: The symmetry analysis submodule is used to generate symmetry detection parameters for each AOI device based on the detection parameters of each AOI device. The backtracking analysis submodule is used to determine whether the initial defect information can be detected based on the symmetrical detection parameters of each AOI device, and to generate backtracking detection parameters based on the determination result.

5. The multi-AOI equipment joint detection device according to claim 4, characterized in that, The symmetry analysis submodule includes: A complementary analysis unit is used to obtain complementary detection features of each AOI device based on the detection parameters of each AOI device. The parameter replacement unit is used to determine whether the complementary detection features of each AOI device can be symmetrically set, and to symmetrically replace the detection parameters of the AOI devices that can be symmetrically set, while retaining the detection parameters of the AOI devices that cannot be symmetrically set. The symmetry analysis unit is used to combine the detection parameters of the AOI device based on symmetry replacement and the retained detection parameters of the AOI device to determine whether the symmetry rate is greater than a preset symmetry rate threshold. When the symmetry rate is not greater than the preset symmetry rate threshold, the retained detection parameters of the AOI device are symmetrically replaced based on preset alternative replacement rules. Combined with the symmetrically replaced detection parameters of the AOI device, the symmetry detection parameters of each AOI device are obtained.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the multi-AOI device joint detection method as described in any one of claims 1 to 3.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the multi-AOI device joint detection method as described in any one of claims 1 to 3.

Images