Defect detection method and device based on ET leakage prevention and storage medium

Abstract

The invention provides a defect detection method and device based on ET leakage prevention and a storage medium, and the method comprises the steps: obtaining an image of a to-be-detected Strip, and obtaining the ET information of the to-be-detected Strip according to the identification information of the to-be-detected Strip; identifying the Pcs marked with the ET bad mark in the image, and performing de-duplication processing on the Pcs with the ET bad mark in combination with the ET information to determine all the Pcs with the ET bad mark in the Strip to be detected; detecting appearance defects of the Pcs in the image, and determining whether the corresponding Pcs are scrapped or not; and generating a detection result of the to-be-detected Strip based on a preset Strip scrapping rule according to the Pcs scrapped due to appearance defects and the Pcs with poor ET. According to the technical scheme provided by the invention, when the ET information is acquired, the Pcs with poor ET are detected by utilizing vision, so that the material scrapping misjudgment caused by the lack of the ET information of the previous work station can be avoided.

Description

Technical Field

[0001] The present application relates to the field of defect detection technology, and specifically to a defect detection method, device and storage medium based on ET leakage prevention. Background Art

[0002] With the rapid development of electronic technology, electronic products are increasingly used in people's lives and various industries, and the importance of printed circuit boards (PCBs) as key basic components of electronic products is self-evident. From consumer electronic products such as smartphones and computers to professional fields such as industrial control equipment and communication base stations, the performance and quality of PCBs directly affect the reliability and functional realization of the entire electronic product. In the fierce market competition environment, various electronic manufacturing companies have increasingly stringent quality requirements for PCBs. In order to ensure the high-quality delivery of the final electronic products, PCBs must undergo strict yield testing during the production process to screen out qualified products and eliminate defective PCBs, thereby ensuring the stability of the entire electronic product supply chain and the consistency of product quality.

[0003] Electronic testing (ET) has always been an important means of evaluating the electrical performance of PCBs. By measuring various electrical parameters of the circuit network on the PCB, such as resistance, capacitance, inductance, conductivity, etc., many potential electrical performance defects can be found, such as line breaks, short circuits, abnormal component parameters, etc. Electronic testing equipment can usually only detect problems related to electrical performance, and cannot directly detect some non-electrical appearance defects, such as poor solder joint shape, scratches on the component surface, stains on the PCB board surface, etc. Visual appearance defect detection has emerged as a supplementary means. Using optical imaging equipment and image processing technology, a comprehensive and detailed inspection of the appearance of the PCB can detect various appearance defects such as solder joints, leaking solder joints, continuous solder joints, missing and misaligned components, scratches, stains, holes on the PCB board surface, etc.

[0004] In the PCB production process, visual appearance defect detection is usually arranged as a post-process of electronic testing. This arrangement aims to first ensure that the basic electrical performance of the PCB is qualified through electronic testing, and then further check the appearance defects through visual appearance defect detection, so as to achieve more comprehensive quality control of the PCB.

[0005] The inventors have found that when visual appearance defect detection is completed, it is usually necessary to determine whether the entire material (Strip) needs to be scrapped based on the NG single unit (Pcs). However, since ET detection and visual inspection are not performed at the same workstation, in the process of synchronizing ET detection data to the visual inspection workstation, data transmission loss, data transmission delay and other reasons result in missing ET defective Pcs when the Strip is judged as NG and scrapped, thereby affecting the accuracy of the NG judgment result of the Strip. Summary of the invention

[0006] In view of this, the present application provides a defect detection method, device and storage medium based on ET leakage prevention to solve the technical problem of inaccurate Strip scrap judgment results in the prior art.

[0007] In a first aspect, the present application provides a defect detection method based on ET leakage prevention, the method comprising:

[0008] Acquire an image of the strip to be detected, and acquire ET information of the strip to be detected according to the identification information of the strip to be detected;

[0009] Identify the PCs marked with ET bad marks in the image, and perform deduplication processing on the ET bad PCs in combination with the ET information to determine all the ET bad PCs in the strip to be detected;

[0010] Detect the appearance defects of the Pcs in the image and determine whether the corresponding Pcs are scrapped; according to the Pcs scrapped due to appearance defects and the Pcs with poor ET, based on the preset Strip scrapping rules, generate the detection results of the Strip to be detected.

[0011] Preferably, the identifying of the Pcs in the image marked with ET bad marks comprises:

[0012] Based on the trained neural network model, all ET bad features in the image are identified, and the Pcs where the ET bad features are located are determined as the Pcs marked with ET bad marks.

[0013] Preferably, the detecting appearance defects of the PCs in the image and determining whether the corresponding PCs are scrapped comprises:

[0014] Based on the trained neural network model, the appearance defects on the PCs are detected, and combined with the preset PCs scrapping rules, it is determined whether the PCs have reached the scrapping conditions;

[0015] If the scrap condition is reached, the PCs is determined to be scrapped due to appearance defects.

[0016] Preferably, the method generates the detection result of the strip to be detected based on the PCs scrapped due to appearance defects and PCs with poor ET and the preset strip scrapping rules, including:

[0017] Determine whether the number of PCs with poor ET has reached a first preset threshold;

[0018] If the first preset threshold is reached, the strip to be detected is determined to be scrapped.

[0019] Preferably, the defect detection method based on ET leakage prevention further includes:

[0020] If the number of Pcs with bad ET does not reach the first preset threshold, it is determined whether the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches the second preset threshold;

[0021] If the second preset threshold is reached, the strip to be detected is determined to be scrapped.

[0022] Preferably, the defect detection method based on ET leakage prevention further includes:

[0023] If the number of Pcs with poor ET reaches the first preset threshold, a pop-up window prompt including the number of Pcs with poor ET is generated;

[0024] If the triggering of the cancel ET scrapping event is monitored, the determination of the scrapping of the to-be-detected Strip is cancelled.

[0025] Preferably, the defect detection method based on ET leakage prevention further includes:

[0026] If the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches a second preset threshold, a pop-up window prompt containing the total number of currently scrapped Pcs is generated;

[0027] If the triggering of the Strip scrap cancellation event is monitored, the determination of the Strip scrapping to be detected is cancelled, and the second preset threshold is modified.

[0028] In a second aspect, the present application provides a defect detection device based on ET leakage prevention, the device comprising:

[0029] An ET acquisition module is used to acquire an image of the strip to be detected, and acquire ET information of the strip to be detected according to the identification information of the strip to be detected;

[0030] The ET recognition module recognizes the Pcs marked with ET bad marks in the image, and performs deduplication processing on the ET bad Pcs in combination with the ET information to determine all the ET bad Pcs in the strip to be detected;

[0031] The Strip detection module is used to detect the appearance defects of the Pcs in the image and determine whether the corresponding Pcs are scrapped; according to the Pcs scrapped due to appearance defects and Pcs with poor ET, based on the preset Strip scrapping rules, the detection results of the Strip to be detected are generated.

[0032] In a third aspect, the present application provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor implements the defect detection method based on ET leakage prevention described in the first aspect by executing the computer instructions.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the defect detection method based on ET leakage prevention described in the first aspect is implemented.

[0034] The defect detection method, device and storage medium based on ET leakage prevention provided in this application have at least the following beneficial effects:

[0035] The technical solution provided by the present application can avoid the misjudgment of scrapping of materials due to the lack of ET information in the previous workstation by visually inspecting PCs with poor ET while obtaining ET information. Multi-dimensional detection not only pays attention to the appearance defects of PCs, but also considers whether its electrical performance is poor. This comprehensive detection method can more accurately evaluate the overall quality of PCs in the strip to be detected, avoiding quality problems that may be missed by only detecting from a single dimension, thereby providing a solid foundation for subsequent accurate judgment of the quality of the strip. When identifying PCs with poor ET, deduplication processing is performed in combination with the marking marks in the image and the ET information, which can effectively eliminate errors that may be caused by factors such as repeated marking or missing misjudged ET information, and more accurately determine the PCs that actually have poor ET in the strip to be detected. At the same time, the appearance defects are detected to determine whether the corresponding PCs are scrapped, and the accuracy of the quality status judgment of each PCs is improved, so that the final generated material detection result is more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the prior art descriptions. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings without creative work. It should be noted that the drawings described below are schematic and should not be understood as any limitation to the present application. In the drawings:

[0037] Figure 1 A schematic diagram of a defect detection method based on ET leakage prevention in one embodiment of the present application is shown;

[0038] Figure 2 A schematic diagram of a defect detection device based on ET leakage prevention in one embodiment of the present application is shown;

[0039] Figure 3 A schematic diagram of a computer device in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0041] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0042] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0043] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0044] Although the processes described below include multiple operations that appear in a specific order, it should be clearly understood that these processes may also include more or fewer operations, and these operations may be performed sequentially or in parallel.

[0045] Example 1

[0046] The defect detection method based on ET leakage prevention provided in this application can be applied to PCB defect detection application scenarios. In this scenario, the previous ET station uploads the detected ET information (for example, including ET-defective Pcs information) to the production line management system, and the subsequent visual inspection station can download the corresponding ET information from the production line management system according to the Strip's identification information. After ET is completed, the ET-defective Pcs will be marked with an ET bad mark on the Strip, such as an "X" mark.

[0047] See also Figure 1 , a defect detection method based on ET leakage prevention provided in one embodiment of the present application may include the following steps.

[0048] S101 , obtaining an image of a strip to be detected, and obtaining ET information of the strip to be detected according to identification information of the strip to be detected.

[0049] Specifically, determine the appropriate image acquisition device, such as an industrial camera, to ensure that it can clearly and accurately capture the image of the strip to be inspected. Select a camera with appropriate resolution, focal length and other parameters based on the size, shape, and detection accuracy requirements of the strip to be inspected. Install the image acquisition device in a suitable position so that it can stably capture the area where the strip to be inspected is placed. It is usually necessary to consider lighting conditions to ensure that the shooting area has uniform and sufficient light to avoid shadows affecting the image quality. Special lighting equipment can be equipped and arranged reasonably.

[0050] Specifically, the identification information may be in the form of a barcode, a QR code, a serial number, etc. The obtained identification information is interpreted by corresponding recognition technology (such as a barcode scanner, a QR code recognition software, a character recognition algorithm, etc.) and converted into a processable data format.

[0051] S102, identifying the Pcs marked with ET bad marks in the image, and deduplicating the ET bad Pcs in combination with the ET information to determine all the ET bad Pcs in the strip to be detected.

[0052] Specifically, the Pcs of the marked ET bad marks in the image can be identified by knowing that the marked ET bad marks have some specific visual features, such as specific shapes (circles, squares, X-shaped, etc.), colors (colors that contrast sharply with the surrounding areas, such as red) or textures, etc., which can be marked by a marker pen, and these features can be used to locate the target area. For shape features, shape detection algorithms, such as Hough transform (commonly used to detect shapes such as circles and lines) can be used to find areas in the image that meet specific shapes; for color features, by setting a color threshold range, the pixel areas in the image that fall within the color threshold range can be extracted as areas where bad marks may exist; for texture features, texture analysis algorithms can be used, such as texture analysis methods based on grayscale co-occurrence matrices, to locate areas with specific textures by analyzing the texture relationship between pixel points.

[0053] Specifically, the Pcs marked with ET bad marks in the image can also be identified based on positioning by machine learning or deep learning, such as training a support vector machine (SVM) model or a convolutional neural network (CNN) model, taking the image as input, and letting the model learn the positional features of the ET bad marks in the image. The trained model can quickly and accurately locate the area where the ET bad marks may exist in the new image. After determining the area where the ET bad marks exist in the image, it is necessary to associate these ET bad marks with the corresponding Pcs to determine the Pcs to which the bad marks belong.

[0054] Specifically, the deduplication of ET bad Pcs can be based on the Pcs' own identification information. The Pcs marked with ET bad marks can be identified and matched with the corresponding identification information by Pcs position, so as to perform deduplication based on the identification information. The deduplication of ET bad Pcs can also be based on the position information of Pcs in the Strip. For example, coordinate conversion is performed based on the identification of bad Pcs in the ET information to obtain the position of bad Pcs on the Strip, and then the repeated bad Pcs at the same position are deduplicated.

[0055] Specifically, by identifying the Pcs marked with ET defective marks in the strip to be inspected, the ET defective Pcs in the strip can be determined. Even if the ET information of the previous workstation cannot be obtained, the ET defective Pcs can be identified at the visual inspection station, thus avoiding the missed detection of ET defective Pcs.

[0056] S103, detecting appearance defects of the Pcs in the image, and determining whether the corresponding Pcs are scrapped; generating a detection result of the strip to be detected based on the Pcs scrapped due to appearance defects and the Pcs with poor ET and the preset Strip scrapping rules.

[0057] Specifically, the appearance defects of Pcs can be detected by using the trained neural network model for AI defect recognition, or by using the template matching recognition method based on computer vision. There is no limitation here. The confirmation of whether the Pcs are scrapped should be based on the specific acceptance rules. The Pcs can also be scrapped by manually confirming the scrapping in the re-inspection system. Statistics are taken for Pcs scrapped due to appearance defects and Pcs with poor ET. The preset Strip scrapping rule can be understood as that when the total number of Pcs with poor ET on a single Strip reaches the corresponding range, the entire material needs to be scrapped, or when the total number of Pcs with poor ET does not reach the total scrapped number, but the total number of Pcs scrapped due to appearance defects reaches the corresponding range, the entire material needs to be scrapped.

[0058] In this embodiment, by visually inspecting PCs with poor ET while acquiring ET information, the omission and misjudgment of materials caused by the lack of ET information in the previous workstation can be avoided. Multi-dimensional detection not only focuses on the appearance defects of PCs, but also considers whether its electrical performance is poor. This comprehensive detection method can more accurately evaluate the overall quality of PCs in the detection strip, avoid quality problems that may be missed by only detecting from a single dimension, and thus provide a solid foundation for subsequent accurate judgment of the quality of the strip. When identifying PCs with poor ET, deduplication processing is performed in combination with the marking marks in the image and the ET information, which can effectively eliminate errors that may be caused by factors such as repeated marking or missing ET information, and more accurately determine the PCs that actually have poor ET in the strip to be detected. At the same time, the appearance defects are detected to determine whether the corresponding PCs are scrapped, and the accuracy of the quality status judgment of each PCs is improved, so that the final generated material detection result is more reliable. The accuracy and efficiency of material yield detection are further improved.

[0059] In a preferred embodiment, the identifying of the Pcs in the image marked with ET bad marks includes:

[0060] Based on the trained neural network model, all ET bad features in the image are identified, and the Pcs where the ET bad features are located are determined as the Pcs marked with ET bad marks.

[0061] In this embodiment, the trained neural network model can effectively identify all ET defect features in the image. After learning and optimizing a large amount of data, the marking form of ET defect features can be accurately captured to avoid omissions and misjudgments. It can avoid the loss of ET caused by the failure of ET information transmission at the front station, provide a reliable data basis for subsequent processing and decision-making, and avoid subsequent omissions and misjudgments of materials. It further improves the accuracy and efficiency of material defect detection.

[0062] In a preferred embodiment, the detecting appearance defects of the PCs in the image and determining whether the corresponding PCs are scrapped includes:

[0063] Based on the trained neural network model, the appearance defects on the PCs are detected, and combined with the preset PCs scrapping rules, it is determined whether the PCs have reached the scrapping conditions;

[0064] If the scrap condition is reached, the PCs is determined to be scrapped due to appearance defects.

[0065] In this embodiment, the appearance of the PCs is detected using a trained neural network model. The neural network model is trained in the early stage with a large amount of labeled PC image data of normal appearance and various defects, so that it has the ability to identify different types of appearance defects. In the actual detection process, the appearance image of the PC to be detected is input into the neural network model, and the model will analyze the image based on the feature pattern it has learned, and can accurately identify a variety of common appearance defects such as scratches, bumps, deformations, uneven colors, surface flaws, etc. In addition, the accuracy of its detection will continue to improve with the richness of training data and the optimization of the model's own structure and algorithm, which can effectively avoid missed detection or false detection caused by factors such as visual fatigue and subjective judgment differences during manual detection.

[0066] Specifically, after detecting the appearance defects on the PCs, the preset PCs scrapping rules will be combined to further determine whether the PCs have reached the scrapping conditions. These preset scrapping rules are usually formulated based on multiple factors such as the specific use of the product, quality standards, safety requirements, etc. For example, if there are tiny scratch defects on the surface, the scrapping rules will clearly stipulate that the PCs will be scrapped when such scratches reach a certain level. By comparing the detected appearance defects with these detailed and targeted scrapping rules one by one, an accurate conclusion can be drawn as to whether the PC needs to be scrapped.

[0067] In this embodiment, the trained neural network model can perform high-precision detection of various appearance defects on PCs. With its powerful image analysis capabilities, it can accurately capture a variety of appearance problems such as subtle scratches, slight deformations, and imperceptible color differences, effectively avoiding omissions or misjudgments that may occur in manual inspections. Through this precise defect identification, PCs with appearance quality problems can be effectively detected, and then combined with PCs with poor ET, a reliable data basis is provided for subsequent processing and decision-making, and whether the entire material to be inspected is scrapped is accurately detected, avoiding subsequent omissions and misjudgments of materials. The accuracy and efficiency of material defect detection are further improved.

[0068] In a preferred embodiment, the method generates the detection result of the strip to be detected based on the PCs scrapped due to appearance defects and the PCs with poor ET and the preset strip scrapping rules, including:

[0069] Determine whether the number of PCs with poor ET has reached a first preset threshold;

[0070] If the first preset threshold is reached, the strip to be detected is determined to be scrapped.

[0071] In a preferred embodiment, the defect detection method based on ET leakage prevention further includes:

[0072] If the number of Pcs with bad ET does not reach the first preset threshold, it is determined whether the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches the second preset threshold;

[0073] If the second preset threshold is reached, the strip to be detected is determined to be scrapped.

[0074] In this embodiment, for example, the preset Strip scrapping rule is that if there are m ET-bad Pcs or n bad Pcs on a single Strip, the entire Strip is scrapped. When judging whether a Strip is scrapped, firstly judge whether the number of ET-bad Pcs reaches m, if it reaches m, the entire Strip is scrapped, if it does not reach m, then judge whether the total number of Pcs scrapped due to ET-bad and appearance defects reaches n, if it reaches n, the entire Strip is scrapped.

[0075] In this embodiment, by generating the detection result of the strip to be detected based on the number of Pcs scrapped due to appearance defects and Pcs with poor ET, and based on the preset Strip scrapping rules, it is possible to achieve an accurate assessment of the quality status of the strip to be detected. This judgment method based on a clear quantity threshold helps to accurately screen out Strips with quality problems, prevent bad Strips from flowing into subsequent production links or reaching customers, thereby effectively ensuring the quality of the final product and improving the competitiveness of the product in the market. A multi-level detection judgment logic is set up, first judging whether the number of Pcs with poor ET reaches the first preset threshold, and if it does not reach it, further judging whether the total number of Pcs with poor ET and Pcs currently scrapped due to appearance defects reaches the second preset threshold. This multi-level detection mechanism can more comprehensively and meticulously consider the possible quality risks of the Strip, avoid missing bad Strips due to the limitations of single factor judgment, greatly improve the reliability of detection, and make the detection results more truly reflect the actual quality status of the Strip. Through accurate and reliable detection and judgment, the Strip that should be scrapped can be identified in time. This means that unnecessary subsequent processing or handling of Strips with obvious quality problems can be avoided, thereby rationally allocating production resources such as manpower, material resources, and time. Concentrating resources on the production of qualified products reduces the additional costs incurred by handling defective products, helps improve production efficiency, and effectively reduces production costs. Accurately detect whether the entire material to be tested is scrapped to avoid subsequent missed judgments and misjudgments of materials. Further improve the accuracy and efficiency of material defect detection.

[0076] In a preferred embodiment, the defect detection method based on ET leakage prevention further includes:

[0077] If the number of Pcs with poor ET reaches the first preset threshold, a pop-up window prompt including the number of Pcs with poor ET is generated;

[0078] If the triggering of the cancel ET scrapping event is monitored, the determination of the scrapping of the to-be-detected Strip is cancelled.

[0079] In a preferred embodiment, the defect detection method based on ET leakage prevention further includes:

[0080] If the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches a second preset threshold, a pop-up window prompt containing the total number of currently scrapped Pcs is generated;

[0081] If the triggering of the Strip scrap cancellation event is monitored, the determination of the Strip scrapping to be detected is cancelled, and the second preset threshold is modified.

[0082] In this embodiment, a pop-up window prompt containing the number of ET-defective Pcs is generated to prompt the inspector of the number of ET-defective Pcs at present. For example, the first threshold value initially set by the system is relatively small, such as 2, and the number of ET-defective Pcs that actually reaches the scrapping of the entire Strip is 5. At this time, the scrapping of the entire Strip should be cancelled, and then the total number of defective Pcs should be continued to be judged. If the first threshold value initially set by the system is 5, and the value of the pop-up window prompt is greater than or equal to 5, the entire Strip can be confirmed to be scrapped through the confirmation button. The setting and modification of the second preset threshold value should be understood in the same way. For example, if the second threshold value set by the system is relatively small, when the pop-up window prompt of the current total number of scrapped Pcs pops up, the inspector can modify it according to the total number of defective Pcs that reaches the scrapping of the entire Strip. It can be understood that the appearance defects of each Pcs on the entire Strip are scrapped one by one. Once the total number of defective Pcs reaches the second threshold value, the entire piece of material can be immediately confirmed to be scrapped, and the subsequent Pcs on it will no longer be judged.

[0083] In this embodiment, when the number of Pcs with bad ET reaches the first preset threshold, or the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches the second preset threshold, the system will generate a corresponding pop-up window prompt containing specific quantity information. This enables the inspection personnel to intuitively obtain the key inspection data at the first time, and clearly understand the bad condition of the material of the current piece, without the need for tedious manual statistics and search for relevant data, which greatly improves the efficiency of information acquisition, ensures that the inspection personnel have a clear understanding of the inspection situation, and facilitates the subsequent confirmation of scrapping or cancellation of scrapping, as well as the subsequent modification of the threshold operation. In the case where the number of Pcs with bad ET reaches the first preset threshold or the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches the second preset threshold and the strip to be inspected is determined to be scrapped, if the cancellation of ET scrapping event triggering and the cancellation of Strip scrapping event triggering are respectively monitored, the system can cancel the corresponding scrapping judgment. This mechanism gives operators the opportunity to re-evaluate and correct possible misjudgments under specific circumstances, avoiding the wrong scrapping of originally repairable or usable Strips due to some temporary factors or special circumstances (such as too small threshold settings, etc.), effectively reducing the risk of wrong scrapping, thereby reducing unnecessary cost losses. When the Strip scrap cancellation event is monitored, not only the scrapping of the strip to be detected is cancelled, but also the second preset threshold can be modified. This means that it has a certain adjustment and optimization capability, and the detection rules can be dynamically adjusted according to the actual situation to make it more in line with the actual situation in the production process. For example, if it is found in the detection of a batch of products that the total number reaches the second preset threshold and is frequently triggered to be scrapped, but it is actually found that some of the Strips that are judged to be scrapped are usable after review, through this operation of canceling the scrapping and modifying the threshold, the subsequent detection can more accurately adapt to the characteristics of this batch of products, reduce the recurrence of similar misjudgments, and improve the adaptability and accuracy of the detection rules for different batches of products. Improving the accuracy of the quality judgment of each piece of material makes the final generated material detection result more reliable, and further improves the accuracy and efficiency of material yield detection.

[0084] Example 2

[0085] This embodiment provides a defect detection device based on ET leakage prevention, which is described by applying the defect detection method based on ET leakage prevention provided in the above embodiment 1. Figure 2 As shown, a defect detection device based on ET leakage prevention provided by one embodiment of the present application may include the following multiple modules.

[0086] An ET acquisition module is used to acquire an image of the strip to be detected, and acquire ET information of the strip to be detected according to the identification information of the strip to be detected;

[0087] The ET recognition module recognizes the Pcs marked with ET bad marks in the image, and performs deduplication processing on the ET bad Pcs in combination with the ET information to determine all the ET bad Pcs in the strip to be detected;

[0088] The Strip detection module is used to detect the appearance defects of the Pcs in the image and determine whether the corresponding Pcs are scrapped; according to the Pcs scrapped due to appearance defects and Pcs with poor ET, based on the preset Strip scrapping rules, the detection results of the Strip to be detected are generated.

[0089] The defect detection device based on ET leakage prevention provided in the embodiment of the present application can be applied to the defect detection method based on ET leakage prevention provided in the above-mentioned embodiment 1. For relevant details, refer to the above-mentioned method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0090] It should be noted that: when the defect detection device based on ET leakage prevention provided in the embodiment of the present application performs defect detection based on ET leakage prevention, only the division of the above-mentioned functional modules / functional units is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules / functional units as needed, that is, the internal structure of the defect detection device based on ET leakage prevention is divided into different functional modules / functional units to complete all or part of the functions described above. In addition, the implementation method of the defect detection method based on ET leakage prevention provided in the above-mentioned method embodiment 1 and the implementation method of the defect detection device based on ET leakage prevention provided in this embodiment 2 belong to the same concept. The specific implementation process of the defect detection device based on ET leakage prevention provided in this embodiment 2 is detailed in the above-mentioned method embodiment 1, which will not be repeated here.

[0091] Example 3

[0092] See also Figure 3 As shown, one embodiment of the present application also provides a computer device, which can be a computer device such as a desktop computer, a laptop computer, a handheld computer, and a cloud server. The computer device can include, but is not limited to, a processor and a memory. The processor and the memory are connected via a bus or other means.

[0093] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, graphics processing units (GPU), embedded neural network processors (NPU) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above chips.

[0094] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as program instructions / modules corresponding to the methods in the above-mentioned embodiments of the present application. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory, that is, implementing the methods in the above-mentioned method embodiments.

[0095] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.

[0096] One embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program. When the computer program is executed by a processor, the method in the above method embodiment is implemented.

[0097] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned implementation methods of the present application can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the implementation methods of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0098] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] Although the embodiments of the present application are described in conjunction with the accompanying drawings, they cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, other different forms of changes or modifications can be made on the basis of the above description without departing from the concept of the present application. It is not necessary and impossible to list all the embodiments here. The obvious changes or modifications derived from this are still within the scope of protection created by the present application. Therefore, the scope of protection of the patent application shall be based on the attached claims.

Claims

1. A defect detection method based on ET leakage prevention, characterized in that: The method comprises: Acquire an image of the strip to be detected, and acquire ET information of the strip to be detected according to the identification information of the strip to be detected; Identify the PCs marked with ET bad marks in the image, and perform deduplication processing on the ET bad PCs in combination with the ET information to determine all the ET bad PCs in the strip to be detected; Detect the appearance defects of the Pcs in the image and determine whether the corresponding Pcs are scrapped; according to the Pcs scrapped due to appearance defects and the Pcs with poor ET, based on the preset Strip scrapping rules, generate the detection results of the Strip to be detected.

2. The defect detection method based on ET leakage prevention according to claim 1 is characterized in that: The identifying of the PCs marked with ET bad marks in the image includes: Based on the trained neural network model, all ET bad features in the image are identified, and the Pcs where the ET bad features are located are determined as the Pcs marked with ET bad marks.

3. The defect detection method based on ET leakage prevention according to claim 1 is characterized in that: The detecting the appearance defects of the PCs in the image and determining whether the corresponding PCs are scrapped includes: Based on the trained neural network model, the appearance defects on the PCs are detected, and combined with the preset PCs scrapping rules, it is determined whether the PCs have reached the scrapping conditions; If the scrap condition is reached, the PCs is determined to be scrapped due to appearance defects.

4. The defect detection method based on ET leakage prevention according to claim 1 is characterized in that: The method generates the detection result of the strip to be detected based on the PCs scrapped due to appearance defects and PCs with poor ET and the preset strip scrapping rules, including: Determine whether the number of PCs with poor ET has reached a first preset threshold; If the first preset threshold is reached, the strip to be detected is determined to be scrapped.

5. The defect detection method based on ET leakage prevention according to claim 4 is characterized in that: Also includes: If the number of Pcs with bad ET does not reach the first preset threshold, it is determined whether the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches the second preset threshold; If the second preset threshold is reached, the strip to be detected is determined to be scrapped.

6. The defect detection method based on ET leakage prevention according to claim 4 is characterized in that: Also includes: If the number of Pcs with poor ET reaches the first preset threshold, a pop-up window prompt including the number of Pcs with poor ET is generated; If the triggering of the cancel ET scrapping event is monitored, the determination of the scrapping of the to-be-detected Strip is cancelled.

7. The defect detection method based on ET leakage prevention according to claim 5 or 6, characterized in that: Also includes: If the total number of Pcs with bad ET and Pcs currently scrapped due to appearance defects reaches a second preset threshold, a pop-up window prompt containing the total number of currently scrapped Pcs is generated; If the triggering of the Strip scrap cancellation event is monitored, the determination of the Strip scrapping to be detected is cancelled, and the second preset threshold is modified.

8. A defect detection method based on ET leakage prevention, characterized in that: The device comprises: An ET acquisition module is used to acquire an image of the strip to be detected, and acquire ET information of the strip to be detected according to the identification information of the strip to be detected; The ET recognition module recognizes the Pcs marked with ET bad marks in the image, and performs deduplication processing on the ET bad Pcs in combination with the ET information to determine all the ET bad Pcs in the strip to be detected; The Strip detection module is used to detect the appearance defects of the Pcs in the image and determine whether the corresponding Pcs are scrapped; according to the Pcs scrapped due to appearance defects and Pcs with poor ET, based on the preset Strip scrapping rules, the detection results of the Strip to be detected are generated.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor implements the defect detection method based on ET leakage prevention as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the defect detection method based on ET leakage prevention as described in any one of claims 1 to 7 is implemented.

Images