A linkage detection method, device and storage medium for material drop defects

Abstract

The present application provides a method, device, and storage medium for the linked detection of material drop defects. The method comprises: obtaining image information of a hanger to be detected in the detection area of ​​a current workstation; based on the image information, obtaining target material hanging information corresponding to the hanger to be detected and the current workstation; identifying the material plate outline in the image information based on a trained neural network model, and generating actual material hanging information corresponding to the hanger to be detected and the current workstation; and generating a material drop defect identification result for the hanger to be detected at the current workstation based on the target material hanging information and the actual material hanging information. The technical solution provided by the present application can solve the technical problems of low efficiency and accuracy in the prior art of material drop defect detection.

Description

Technical Field

[0001] The present application relates to the technical field of circuit board production, and in particular to a method, device and storage medium for detecting material drop defects. Background Art

[0002] Double Vertical Continuity Plating (DVCP) is used to electroplate copper on circuit boards and is widely used in printed circuit board production processes.

[0003] Before electroplating the copper-plated plate material, the copper-plated plate needs to be placed on a hanger. The inventor found that due to reasons such as improper material placement or failure of the hanger clamp, the copper-plated plate on the hanger may fall off (drop material). However, since the double-row vertical copper plating line contains multiple different functional areas, that is, the copper-plated plate may fall off in different functional areas, the falling of the copper-plated plate will cause problems such as material plate leakage and material plate damage. Therefore, it is necessary to detect whether there is a drop defect in the production line and the work station where the drop defect occurs.

[0004] The existing copper-plated plate drop defect detection solution is implemented through manual inspection. However, this method not only has low detection efficiency and accuracy, but also cannot achieve automatic detection of drop defects on a 24-hour production line. In addition, the double-row vertical copper-plated line requires at least two people to inspect, which is costly.

[0005] The above problems need to be solved urgently. Summary of the Invention

[0006] In view of this, the present application provides a linkage detection method, device and storage medium for material drop defects to solve the technical problems of low efficiency and accuracy of material drop defect detection in the prior art.

[0007] In a first aspect, the present application provides a method for detecting a drop defect, the method comprising:

[0008] Obtain image information of the inspection area of ​​the rack to be inspected at the current workstation;

[0009] Based on the image information, obtaining target hanging material information corresponding to the hanger to be detected and the current work station;

[0010] Recognize the outline of the material plate in the image information based on the trained neural network model, and generate actual hanging material information corresponding to the hanger to be detected and the current work station;

[0011] A material drop defect recognition result of the hanger to be detected at the current workstation is generated according to the target hanging material information and the actual hanging material information.

[0012] In one embodiment, before acquiring the target hanging material information corresponding to the hanger to be detected and the current work station, the method further includes:

[0013] Determine whether the current workstation is a loading station;

[0014] If the current workstation is a loading station, the target material hanging information corresponding to the rack to be detected and the loading station is determined according to the material hanging demand information of the rack to be detected;

[0015] If the current workstation is not a loading station, target material hanging information corresponding to the to-be-detected hanger and the current workstation is determined according to actual material hanging information corresponding to the to-be-detected hanger and the previous workstation.

[0016] In one embodiment, obtaining target hanging material information corresponding to the hanger to be detected and the current workstation based on the image information includes:

[0017] Acquire rack identification information corresponding to the image information;

[0018] According to the rack identification information, the workstation identification information and the column identification information contained in the image information, obtaining target hanging material information corresponding to the rack to be detected and the current workstation;

[0019] The column identification information included in the target hanging material information is consistent with the column identification information included in the image information.

[0020] In one embodiment, the trained neural network model is used to identify the outline of the material plate in the image information and generate actual material hanging information corresponding to the hanger to be detected and the current work station, including:

[0021] Identifying whether a material plate outline exists in the image information based on the trained neural network model;

[0022] If it is recognized that the material plate outline does not exist in the image information, the generated actual hanging material information includes "no material on the hanger";

[0023] If the image information is identified to contain a material plate outline, the generated actual material hanging information includes that there is material on the hanger.

[0024] In one embodiment, generating a material drop defect recognition result of the hanger to be inspected at the current workstation based on the target hanging material information and the actual hanging material information includes:

[0025] If the target hanging material information includes that the hanger has material and the actual hanging material information includes that the hanger has no material, it is determined that there is a material drop defect, and an identification result of the material drop defect of the hanger to be detected at the current work station is generated.

[0026] In one embodiment, the trained neural network model is used to identify the outline of the material plate in the image information and generate actual material hanging information corresponding to the hanger to be detected and the current work station, including:

[0027] Identify, based on the trained neural network model, whether the material plate outline exists in areas a and b in the image information;

[0028] If it is recognized that the material plate outline exists in both area a and area b in the image information, the generated actual hanging material information includes that there is material in area a and there is material in area b;

[0029] If it is recognized that there is no material plate outline in area a and area b in the image information, the generated actual hanging material information includes no material in area a and no material in area b;

[0030] If it is recognized that there is a material plate outline in area a and no material plate outline in area b in the image information, the actual hanging material information generated includes that there is material in area a and there is no material in area b;

[0031] If it is identified that there is no material plate outline in area a and no material plate outline in area b in the image information, the generated actual hanging material information includes that there is no material in area a and there is material in area b.

[0032] In one embodiment, generating a material drop defect recognition result of the hanger to be detected at the current workstation based on the target hanging material information and the actual hanging material information includes:

[0033] If the target hanging material information contains that there is material in area a, and the actual hanging material information contains that there is no material in area a, it is determined that there is a material drop defect in area a;

[0034] If the target hanging material information contains that there is material in area B, and the actual hanging material information contains that there is no material in area B, it is determined that there is a material drop defect in area B;

[0035] If it is determined that there is a material drop defect in area a and there is no material drop defect in area b, then an identification result is generated that the hanger to be inspected has material drop in area a at the current workstation;

[0036] If it is determined that there is a material drop defect in area a and a material drop defect in area b, an identification result is generated that the hanger to be inspected has material drop in area b at the current work station;

[0037] If it is determined that there is a material drop defect in area a and a material drop defect in area b, an identification result is generated that the hanger to be inspected has material drop defects in both area a and area b at the current workstation.

[0038] In a second aspect, the present application provides a linkage detection device for material drop defects, the device comprising:

[0039] An image acquisition module is used to acquire image information of the inspection area of ​​the rack to be inspected at the current workstation;

[0040] A target acquisition module is used to acquire target hanging material information corresponding to the hanger to be detected and the current work station based on the image information;

[0041] an actual generation module, configured to recognize the outline of the material plate in the image information based on the trained neural network model, and generate actual material hanging information corresponding to the hanger to be detected and the current work station;

[0042] The result recognition module is used to generate a material drop defect recognition result of the hanger to be detected at the current work station according to the target hanging material information and the actual hanging material information.

[0043] 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, computer instructions are stored in the memory, and the processor executes the computer instructions to implement the linkage detection method for material drop defects described in the first aspect.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed by a processor, the linked detection method for material drop defects described in the first aspect is implemented.

[0045] The method, device, and storage medium for detecting drop defects provided by this application have at least the following beneficial effects:

[0046] The technical solution provided by this application can generate actual material hanging information by acquiring image information collected by an image acquisition device and using a trained neural network model to identify the outline of the material plate in the image information, thereby determining the actual state of the material plate clamped by the clamp of the to-be-detected hanger at the current workstation. By acquiring the target material hanging information, the required state of the material plate clamped by the clamp of the to-be-detected hanger at the current workstation can be determined. By comparing the actual material hanging information with the target material hanging information, that is, comparing the required state and actual state of the material plate clamped by the clamp of the to-be-detected hanger at the current workstation, it can be identified whether the material plate originally clamped by the clamp has fallen at the current workstation, thereby identifying the material drop defect at the current workstation and generating an identification result. Through this solution, material drop defects can be detected and identified at each workstation, linking the various workstations of the vertical copper plating line, thereby determining whether the to-be-detected hanger has a material drop defect, and detecting at which workstation the material drop defect occurred. The efficiency and accuracy of detecting material drop defects in vertical copper plating lines are improved, eliminating the need for manual inspections and reducing human resources. Link each workstation to perform automatic inspection and promptly detect material drop defects, so as to promptly discover and solve problems on the production line and improve the product yield and production efficiency of the production line.

[0047] It can be seen that the above-mentioned method can solve the technical problem of low efficiency and accuracy of material drop defect detection in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For those of ordinary skill in the art, other drawings can 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 limiting the present application in any way. In the drawings:

[0049] Figure 1 A schematic diagram showing a method for detecting material drop defects in an embodiment of the present application is shown;

[0050] Figure 2 A schematic diagram of a double row of vertical copper-plated lines in one embodiment of the present application is shown;

[0051] Figure 3 A schematic diagram showing a material plate held by a single set of grippers in one embodiment of the present application is shown;

[0052] Figure 4 A schematic diagram showing a single set of clamping jaws without clamping a material plate in one embodiment of the present application is shown;

[0053] Figure 5A schematic diagram showing a material plate clamped by two sets of clamping jaws in one embodiment of the present application is shown;

[0054] Figure 6 A schematic diagram showing a material plate held by only the left clamping jaw of the two sets of clamping jaws in one embodiment of the present application is shown;

[0055] Figure 7 A schematic diagram showing a material plate being clamped by only the right clamp of the two sets of clamps in one embodiment of the present application is shown;

[0056] Figure 8 A schematic diagram showing an embodiment of the present application in which both sets of clamping jaws do not clamp a material plate;

[0057] Figure 9 A schematic diagram of a linkage detection device for material drop defects in one embodiment of the present application is shown;

[0058] Figure 10 A schematic diagram of a computer device in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0059] 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 of the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0060] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate the description of this application and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0061] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; they can refer to internal connections between two components; they can refer to wireless connections or wired connections. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0062] 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.

[0063] 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.

[0064] Example 1

[0065] The linked detection method for material drop defects provided in this application can be applied to, but not limited to, vertical copper plating line scenarios.

[0066] See also Figure 1 , an embodiment of the present application provides a linkage detection method for material drop defects, which may include the following steps.

[0067] S101 , obtaining image information of a rack to be inspected in an inspection area of ​​a current workstation.

[0068] In this embodiment, the vertical copper plating line generally includes multiple stations, see Figure 2 As shown, for example, the loading station, pre-processing area, copper plating pool, unloading station, receiving station, etc. Figure 2 The vertical copper plating line shown in the figure is a double-column vertical copper plating line, which includes column A and column B. In actual applications, a double-column synchronous hanger is generally used, that is, clamps are set on both sides of the same beam, and the beam moves along the production line direction. The clamps in column A are used to clamp the material board on the column A side, and the clamps in column B are used to clamp the material board on the column B side. Figure 2 It can be seen that the detection areas corresponding to columns A and B of each workstation are equipped with image acquisition devices. The image acquisition devices are used to collect image information of the material plate clamped by the rack. Figure 3 As shown in the figure, if the clamping jaws hold a material plate, the captured image contains the clamping jaws and the material plate. Figure 4As shown in FIG, if the gripper does not hold a material board, the captured image only includes the gripper. In actual applications, a single row of the rack may not only include grippers for holding a single material board, but may also include multiple groups of grippers for holding multiple material boards. Figure 5 As shown, Figure 5 The figure shows two sets of grippers holding two material plates. The same applies to more than two sets of grippers.

[0069] It should be noted that the unloading station needs to unload the material plate clamped on the hanger, and the hanger will not be transferred to the receiving station. In other words, the receiving station does not need to detect the material plate's material drop defects. Therefore, there is no image acquisition device installed at the receiving station. The linkage detection scheme for material drop defects involved in this application does not take the receiving station into consideration and will not be discussed in detail here.

[0070] S102: Based on the image information, obtain target hanging material information corresponding to the hanger to be detected and the current work station.

[0071] In this embodiment, the acquired image information is the image acquired by the corresponding image acquisition device, and the corresponding image acquisition device is set at the corresponding workstation and the corresponding column. Therefore, the image information is related to the workstation and the column, that is, the workstation identification information and the column identification information contained in the image information, or the image information carries the corresponding workstation identification information and the column identification information. The image information also corresponds to the rack information. In actual applications, for example, if the racks are arranged in a predetermined order, the rack information corresponding to the image information can be determined according to the order of the acquired images. In actual applications, it is also possible to acquire image information containing the rack identification while acquiring image information containing the rack and the material plate clamped therein, and identify the rack identification information by using optical character recognition (OCR), and then determine the rack identification information corresponding to the image information.

[0072] In this embodiment, the target hanging material information corresponding to the current workstation is used to indicate the required state of the hanger to be detected at the current workstation. For example, taking a single set of grippers as an example, see Figure 3 As shown, if the hanger to be inspected has been holding the material plate since the first station and no material drop defects have occurred at the current station, the required state of the hanger to be inspected at the current station should also be the hanging state (the opposite of the drop state). If material drop occurs at the current station, refer to Figure 4 As shown, Figure 4 If only the gripper is collected but the material plate is not collected, a material drop defect will be detected at the current workstation and an alarm will be issued, and the material hanging requirement status of the next workstation will be changed to a material drop status.

[0073] S103: Identify the outline of the material plate in the image information based on the trained neural network model, and generate actual material hanging information corresponding to the hanger to be detected and the current work station.

[0074] In this embodiment, the actual material hanging information corresponding to the current workstation is used to indicate the actual material hanging status of the rack to be inspected at the current workstation, that is, whether the rack to be inspected is holding a material plate on the clamping jaws at the current workstation.

[0075] In this embodiment, when applied to a scenario where a single set of grippers is gripping a single material board, the material board outline recognition involved simply determining the presence of the material board outline in the image—that is, determining whether the grippers are gripping the material board. No specific requirements are placed on the accuracy of the material board outline recognition. In other words, based on any existing contour recognition model, using the material board outline as the object to be recognized, it is possible to identify the presence of the material board outline in the image and generate the corresponding actual material hanging information.

[0076] In this embodiment, if applied to a scenario where multiple sets of grippers are holding multiple material plates, then based on the trained neural network model, the material plate outlines in the image information need to be identified by dividing the image information into multiple corresponding regions according to the number of gripper groups. For example, this can also be understood as cutting a single image into multiple images, and then identifying the presence or absence of the material plate outline in each of the images. The corresponding actual material hanging information is then generated by combining the contour identification results corresponding to the multiple regions. It should be noted that the input of the trained neural network model can be the entire image information or a segmented image sequence that has been pre-processed, and this is not limited in this article.

[0077] S104 , generating a material drop defect recognition result of the hanger to be detected at the current workstation according to the target hanging material information and the actual hanging material information.

[0078] In this embodiment, it can be understood that if the corresponding clamp in the target hanging material information does not clamp the material plate, it means that the corresponding clamp initially does not clamp the material or material has been dropped (not occurring in the current workstation), so there is no need to identify whether the rack to be inspected has a material drop defect at the current workstation. If the corresponding clamp in the target hanging material information clamps the material plate, it means that the corresponding clamp should continue to clamp the material plate at the current workstation to avoid material drop. If the corresponding clamp in the actual hanging material information clamps the material plate, the rack to be inspected has not had a material drop defect at the current workstation. If the corresponding clamp in the actual hanging material information does not clamp the material plate, it means that the material plate has a material drop defect at the current workstation, then the material drop defect can be identified and an identification result can be generated.

[0079] In this embodiment, by acquiring image information captured by an image acquisition device and using a trained neural network model to identify the material plate outline within the image information, actual material hanging information can be generated, thereby determining the actual state of the material plate being gripped by the jaws of the rack to be inspected at the current workstation. By acquiring target material hanging information, the desired state of the material plate being gripped by the jaws of the rack to be inspected at the current workstation can be determined. By comparing the actual material hanging information with the target material hanging information—that is, comparing the desired and actual states of the material plate being gripped by the jaws of the rack to be inspected at the current workstation—it is possible to determine whether the material plate originally gripped by the jaws has fallen at the current workstation, thereby identifying a material drop defect at the current workstation and generating an identification result. This solution allows for detection and identification of material drop defects at each workstation, linking all workstations in a vertical copper plating line to determine whether a material drop defect has occurred on the rack to be inspected, and to identify the workstation at which the material drop defect occurred. This improves the efficiency and accuracy of detecting material drop defects in vertical copper plating lines, eliminating the need for manual inspections and reducing human resources. Link each workstation to perform automatic inspection and promptly detect material drop defects, so as to promptly discover and solve problems on the production line and improve the product yield and production efficiency of the production line.

[0080] In one embodiment, before acquiring the target hanging material information corresponding to the hanger to be detected and the current work station, the method further includes:

[0081] Determine whether the current workstation is a loading station;

[0082] If the current workstation is a loading station, the target material hanging information corresponding to the rack to be detected and the loading station is determined according to the material hanging demand information of the rack to be detected;

[0083] If the current workstation is not a loading station, target material hanging information corresponding to the to-be-detected hanger and the current workstation is determined according to actual material hanging information corresponding to the to-be-detected hanger and the previous workstation.

[0084] In this embodiment, the loading station is the starting station, and the target loading information corresponding to the rack to be inspected at the loading station corresponds to the actual loading demand. For example, if the rack to be inspected is operating empty (not loading), the target loading information indicates that the rack has no material. If the rack to be inspected is operating normally, the target loading information indicates that the rack has material.

[0085] In this embodiment, specifically, if the current workstation is not a loading station, the actual material hanging information of the rack to be tested corresponding to the previous workstation is the actual material hanging information of the rack to be tested corresponding to the current workstation. For example, if the current workstation is a pre-processing area, the actual material hanging information of the rack to be tested at the loading station can be determined as the target material hanging information of the rack to be tested in the pre-processing area. Specifically, if the rack to be tested is running empty (no material hanging) or the rack to be tested has already experienced a material drop defect at the loading station, that is, the material plate is not clamped on the clamping jaws, that is, the rack to be tested has no material in the actual material hanging information at the loading station, and at this time, the rack to be tested has no material in the target material hanging information of the rack to be tested in the pre-processing area. If the rack to be inspected operates normally and no material drop defect occurs at the loading station, that is, the clamp holds a material plate, which means that the rack to be inspected has material in the actual material hanging information of the loading station. At this time, the rack to be inspected also has material in the target material hanging information of the pre-processing area.

[0086] In this embodiment, by distinguishing the initial workstation and using the current workstation to link with the adjacent workstation, the target material hanging information corresponding to the rack to be inspected at the current workstation can be determined. This facilitates the determination of the target material hanging information for each independent workstation in the vertical copper plating line, and further facilitates the subsequent determination of whether the rack to be inspected has material drop defects at each workstation. This further improves the efficiency and accuracy of material drop defect detection in vertical copper plating lines.

[0087] In one embodiment, obtaining target hanging material information corresponding to the hanger to be detected and the current workstation based on the image information includes:

[0088] Acquire rack identification information corresponding to the image information;

[0089] According to the rack identification information, the workstation identification information and the column identification information contained in the image information, obtaining target hanging material information corresponding to the rack to be detected and the current workstation;

[0090] The column identification information included in the target hanging material information is consistent with the column identification information included in the image information.

[0091] In this embodiment, the rack identification information corresponding to the image information is obtained. Specifically, when collecting image information including the rack and the material plate clamped thereon, the image information including the rack identification is also collected. The rack identification information is recognized through optical character recognition (OCR), and the rack identification information corresponding to the image information can be determined.

[0092] In one embodiment, the trained neural network model is used to identify the outline of the material plate in the image information and generate actual material hanging information corresponding to the hanger to be detected and the current work station, including:

[0093] Identifying whether a material plate outline exists in the image information based on the trained neural network model;

[0094] If the image information contains a material plate outline, see Figure 3 As shown, the actual hanging material information generated includes that the hanger has material;

[0095] If the image information does not contain a material plate outline, see Figure 4 As shown, the actual hanging material information generated includes that the hanger has no material.

[0096] In one embodiment, generating a material drop defect recognition result of the hanger to be inspected at the current workstation based on the target hanging material information and the actual hanging material information includes:

[0097] If the target hanging material information includes that the hanger has material and the actual hanging material information includes that the hanger has no material, it is determined that there is a material drop defect, and an identification result of the material drop defect of the hanger to be detected at the current work station is generated.

[0098] In one embodiment, the trained neural network model is used to identify the outline of the material plate in the image information and generate actual material hanging information corresponding to the hanger to be detected and the current work station, including:

[0099] Identify, based on the trained neural network model, whether the material plate outline exists in areas a and b in the image information;

[0100] If it is recognized that the material plate outline exists in both area a and area b in the image information, see Figure 5 As shown, the actual material hanging information generated includes that there is material in area a and there is material in area b;

[0101] If it is recognized that the material board outline exists in area a of the image information and no material board outline exists in area b, refer to Figure 6 As shown, the actual material hanging information generated includes that there is material in area a and no material in area b;

[0102] If it is recognized that there is no material board outline in area a and no material board outline in area b in the image information, refer to Figure 7 As shown, the actual hanging material information generated includes no material in area a and material in area b;

[0103] If it is recognized that there is no material plate outline in area a and area b in the image information, see Figure 8 As shown, the actual hanging material information generated includes no material in area a and no material in area b;

[0104] in, Figure 5-Figure 8Area a in the middle is the left half of the image, and area b is the right half of the image.

[0105] In one embodiment, generating a material drop defect recognition result of the hanger to be inspected at the current workstation based on the target hanging material information and the actual hanging material information includes:

[0106] If the target material information contains material in area a (see Figure 5 Or see Figure 6 ), the actual hanging material information includes no material in area a (see Figure 7 Or see Figure 8 ), it is determined that there is a drop defect in area a;

[0107] If the target material information contains material in area b (see Figure 5 Or see Figure 7 ), the actual hanging material information includes no material in area b (see Figure 6 Or see Figure 8 ), it is determined that there is a drop defect in area b;

[0108] If it is determined that there is a drop defect in area a and there is no drop defect in area b, refer to Figure 5 and see Figure 7 (or see Figure 5 and see Figure 8 )(or see Figure 6 and see Figure 7 )(or see Figure 6 and see Figure 8 ), then generate an identification result that the hanger to be detected has material dropped in area a at the current workstation;

[0109] If it is determined that there is a drop defect in area a and a drop defect in area b, refer to Figure 5 and see Figure 6 (or see Figure 5 and see Figure 8 )(or see Figure 7 and see Figure 6 )(or see Figure 7 and see Figure 8 ) generates an identification result that the hanger to be detected has material dropped in area b at the current work station;

[0110] If it is determined that there is a drop defect in area a and a drop defect in area b, refer to Figure 5 and Figure 8 , then an identification result is generated that the hanger to be detected has dropped materials in area a and area b at the current workstation at the same time.

[0111] In this embodiment, by using two sets of clamping jaws to clamp two material plates, the actual hanging material information and the target hanging material information are judged and identified. This makes this solution applicable to application scenarios where a single rack with two sets of clamping jaws in a single row has improved the applicability of material drop defect detection and further improved the efficiency and accuracy of material drop defect detection in vertical copper plating lines. This helps to identify and resolve problems in production lines with a single rack with two sets of clamping jaws in a single row, further improving the product yield and production efficiency of the production line.

[0112] In addition, it should be noted that if the image information also includes area c, that is, it includes three sets of grippers, it should be understood in the same way as the scenario of the above two sets of grippers, and will not be repeated here.

[0113] Example 2

[0114] This embodiment provides a linkage detection device for drop defects, which is described by applying the linkage detection method for drop defects provided in the above embodiment 1. Figure 9 As shown, a linkage detection device for material drop defects provided by one embodiment of the present application may include the following multiple modules.

[0115] An image acquisition module is used to acquire image information of the inspection area of ​​the rack to be inspected at the current workstation;

[0116] A target acquisition module is used to acquire target hanging material information corresponding to the hanger to be detected and the current work station based on the image information;

[0117] an actual generation module, configured to recognize the outline of the material plate in the image information based on the trained neural network model, and generate actual material hanging information corresponding to the hanger to be detected and the current work station;

[0118] The result recognition module is used to generate a material drop defect recognition result of the hanger to be detected at the current work station according to the target hanging material information and the actual hanging material information.

[0119] The linkage detection device for material drop defects provided in the embodiment of the present application can be applied to the linkage detection method for material drop defects provided in the above-mentioned embodiment 1. For relevant details, please refer to the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0120] It should be noted that: the linkage detection device for material drop defects provided in the embodiment of the present application only uses the division of the above-mentioned functional modules / functional units as an example when performing linkage detection of material drop defects. 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 linkage detection device for material drop defects 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 linkage detection method for material drop defects provided in the above-mentioned method embodiment 1 and the implementation method of the linkage detection device for material drop defects provided in this embodiment 2 belong to the same concept. The specific implementation process of the linkage detection device for material drop defects provided in this embodiment 2 is detailed in the above-mentioned method embodiment 1 and will not be repeated here.

[0121] Example 3

[0122] See also Figure 10 As shown, one embodiment of the present application further provides a computer device, which can be a desktop computer, a laptop computer, a PDA, a cloud server, or other computer device. The computer device can include, but is not limited to, a processor and a memory. The processor and the memory can be connected via a bus or other means.

[0123] 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 processing units (NPU) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0124] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as the program instructions / modules corresponding to the methods in the above-mentioned embodiments of this application. The processor executes the non-transitory software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the processor, that is, to implement the methods in the above-mentioned method embodiments.

[0125] 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 located 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.

[0126] 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.

[0127] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD). The storage medium can also include a combination of the above-mentioned types of memory.

[0128] The technical features of the above embodiments can be combined arbitrarily. In order 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.

[0129] Although the embodiments of the present application are described in conjunction with the accompanying drawings, this should not be construed as limiting the scope of the patent application. It should be noted that, for those skilled in the art, other variations or modifications may be made based on the above description without departing from the concept of the present application. It is not necessary and impossible to list all embodiments here. Obvious variations or modifications derived therefrom remain within the scope of protection created by the present application. Therefore, the scope of protection of the patent application shall be based on the appended claims.

Claims

1. A linkage detection method for material drop defects, characterized in that: The method comprises: Obtain image information of the inspection area of ​​the rack to be inspected at the current workstation; Based on the image information, obtaining target hanging material information corresponding to the hanger to be detected and the current work station; Recognize the outline of the material plate in the image information based on the trained neural network model, and generate actual hanging material information corresponding to the hanger to be detected and the current work station; Generate a material drop defect recognition result of the hanger to be detected at the current workstation according to the target hanging material information and the actual hanging material information; Before acquiring the target hanging material information corresponding to the hanger to be detected and the current work station, the method further includes: Determine whether the current workstation is a loading station; If the current workstation is a loading station, the target material hanging information corresponding to the rack to be detected and the loading station is determined according to the material hanging demand information of the rack to be detected; If the current workstation is not a loading station, target material hanging information corresponding to the to-be-detected hanger and the current workstation is determined according to actual material hanging information corresponding to the to-be-detected hanger and the previous workstation.

2. The linkage detection method for material drop defects according to claim 1, characterized in that: The acquiring, based on the image information, target hanging material information corresponding to the hanger to be detected and the current workstation includes: Acquire rack identification information corresponding to the image information; According to the rack identification information, the workstation identification information and the column identification information contained in the image information, obtaining target hanging material information corresponding to the rack to be detected and the current workstation; The column identification information included in the target hanging material information is consistent with the column identification information included in the image information.

3. The linkage detection method for material drop defects according to claim 2, characterized in that: The trained neural network model is used to identify the outline of the material plate in the image information, and to generate actual material hanging information corresponding to the hanger to be detected and the current work station, including: Identifying whether a material plate outline exists in the image information based on the trained neural network model; If it is recognized that the material plate outline does not exist in the image information, the generated actual hanging material information includes "no material on the hanger"; If the image information is identified to contain a material plate outline, the generated actual material hanging information includes that there is material on the hanger.

4. The linkage detection method for material drop defects according to claim 3 is characterized in that: The step of generating a material drop defect recognition result of the hanger to be detected at the current workstation according to the target hanging material information and the actual hanging material information includes: If the target hanging material information includes that the hanger has material and the actual hanging material information includes that the hanger has no material, it is determined that there is a material drop defect, and an identification result of the material drop defect of the hanger to be detected at the current work station is generated.

5. The linkage detection method for material drop defects according to claim 2, characterized in that: The trained neural network model is used to identify the outline of the material plate in the image information, and to generate actual material hanging information corresponding to the hanger to be detected and the current work station, including: Identify, based on the trained neural network model, whether the material plate outline exists in areas a and b in the image information; If it is recognized that the material plate outline exists in both area a and area b in the image information, the generated actual hanging material information includes that there is material in area a and there is material in area b; If it is recognized that there is no material plate outline in area a and area b in the image information, the generated actual hanging material information includes no material in area a and no material in area b; If it is recognized that there is a material plate outline in area a and no material plate outline in area b in the image information, the actual hanging material information generated includes that there is material in area a and there is no material in area b; If it is identified that there is no material plate outline in area a and no material plate outline in area b in the image information, the generated actual hanging material information includes that there is no material in area a and there is material in area b.

6. The linkage detection method for material drop defects according to claim 5, characterized in that: The step of generating a material drop defect recognition result of the hanger to be detected at the current workstation according to the target hanging material information and the actual hanging material information includes: If the target hanging material information contains that there is material in area a, and the actual hanging material information contains that there is no material in area a, it is determined that there is a material drop defect in area a; If the target hanging material information contains that there is material in area B, and the actual hanging material information contains that there is no material in area B, it is determined that there is a material drop defect in area B; If it is determined that there is a material drop defect in area a and there is no material drop defect in area b, then an identification result is generated that the hanger to be inspected has material drop in area a at the current workstation; If it is determined that there is a material drop defect in area a and a material drop defect in area b, an identification result is generated that the hanger to be inspected has material drop in area b at the current work station; If it is determined that there is a material drop defect in area a and a material drop defect in area b, an identification result is generated that the hanger to be inspected has material drop defects in both area a and area b at the current workstation.

7. A linkage detection device for material drop defects, characterized in that: The device comprises: An image acquisition module is used to acquire image information of the inspection area of ​​the rack to be inspected at the current workstation; A target acquisition module is configured to acquire target material hanging information corresponding to the hanger to be detected and the current workstation based on the image information; before acquiring the target material hanging information corresponding to the hanger to be detected and the current workstation, the module further includes: Determine whether the current workstation is a loading station; If the current workstation is a loading station, the target material hanging information corresponding to the rack to be detected and the loading station is determined according to the material hanging demand information of the rack to be detected; If the current workstation is not a loading station, the target material hanging information corresponding to the rack to be detected and the current workstation is determined according to the actual material hanging information corresponding to the rack to be detected and the previous workstation; an actual generation module, configured to recognize the outline of the material plate in the image information based on the trained neural network model, and generate actual material hanging information corresponding to the hanger to be detected and the current work station; The result recognition module is used to generate a material drop defect recognition result of the hanger to be detected at the current work station according to the target hanging material information and the actual hanging material information.

8. 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 linkage detection method for material drop defects according to any one of claims 1 to 6 by executing the computer instructions.

9. 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 linked detection method for material drop defects according to any one of claims 1 to 6 is implemented.

Images