Plate production management method and device and plate production equipment

Abstract

The invention relates to the technical field of automatic detection, and discloses a plate production management method and device and plate production equipment. The method comprises the steps that a plate production device is controlled to conduct defect detection on a plate, detection data are obtained, the detection data comprise attribute information of the plate, defect information, defect detection results and device information of the plate production device, and the defect detection results comprise qualification, badness and abnormity; based on the detection data, controlling the panel production equipment to intercept the panel with the defect detection result being poor; analyzing the detection data in a preset time period, and determining the reject ratio of the plates under different dimensions; and on the basis of the plate reject ratio under different dimensions, early warning information is generated, and the early warning information is used for improving the plate production quality. According to the method and the device, the bad plates can be intercepted, and the early warning information is generated, so that technicians can improve the production quality of the plates based on the early warning information, and generation of bad problems is reduced from the source.

Description

Technical Field

[0001] The present application relates to the field of automated detection technology, and more specifically, to a production management method and device for panels, and panel production equipment. Background Art

[0002] Panel furniture refers to detachable and modular furniture with artificial boards as the main base material and panels as the basic structure. During the production process of panel furniture, the quality of panels needs to be inspected. However, with the surge in order volume, manual inspection of quality interception management can no longer meet the development needs of panel furniture production inspection and manufacturing. Summary of the invention

[0003] In view of the above situation, the embodiments of the present application provide a panel production management method and device, and panel production equipment, which aim to solve the above problems or at least partially solve the above problems.

[0004] In the first aspect, an embodiment of the present application provides a production management method for a panel, the method comprising: performing defect detection on the panel based on preset detection standards to obtain detection data; wherein, the method of determining the defect detection result of the panel under different preset detection standards is different; the detection data comprises attribute information, defect information, defect detection results and equipment information of the panel production equipment, the defect detection results comprising qualified, defective and abnormal; based on the detection data, controlling the panel production equipment to intercept the panel with the defect detection result being defective; analyzing the detection data within a preset time period to determine the panel defect rate under different dimensions; generating early warning information based on the panel defect rate under different dimensions, and the early warning information is used to improve the production quality of the panel.

[0005] In the second aspect, an embodiment of the present application also provides a production management device for panels, characterized in that the device includes: an acquisition module, used to perform defect detection on panels based on preset detection standards and acquire detection data; wherein the method of determining the defect detection results of panels under different preset detection standards is different; the detection data includes attribute information, production information, defect information, defect detection results and equipment information of panel production equipment, and the defect detection results include qualified, poor and abnormal; a control module, used to control the panel production equipment to intercept panels with poor defect detection results based on the detection data; a processing module, used to analyze the detection data within a preset time period and determine the defective rate of panels under different dimensions; based on the defective rate of panels under different dimensions, generate early warning information, and the early warning information is used to improve the production quality of the panels.

[0006] In the third aspect, the embodiment of the present application also provides a panel production equipment for implementing the method described in the first aspect above, the equipment comprising a feed port, an edge banding machine and a discharge table; wherein a scanning device is provided in the feed port, and the scanning device is used to scan the mark on the panel; a detection device is provided in the edge banding machine, and the detection device is used to perform defect detection on the panel based on a preset detection standard, and generate detection data of the panel; wherein the method of determining the defect detection result of the panel under different preset detection standards is different; the detection data includes attribute information, production information, defect information, defect detection results of the panel and equipment information of the production equipment; a labeling machine and a telescopic fluent strip bracket are provided at the outlet end of the discharge table, the labeling machine is used to mark the defect detection result on the panel, and the telescopic fluent strip bracket is used to intercept panels with poor defect detection results.

[0007] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the steps of the first aspect described above.

[0008] In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the steps of the first aspect above.

[0009] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: Defect detection of panels is performed through preset detection standards, and different preset detection standards are used to determine bad panels in different ways, thereby meeting various production needs and reducing production costs; Through the defect detection results of panels, bad panels are intercepted, replacing traditional manual inspections, realizing product automated detection and interception work, improving the quality input-output ratio, controlling bad panels within the factory, reducing production carryovers, and reducing personnel rework. Furthermore, by analyzing the detection data, the defective rate of panels under different dimensions is determined, and early warning information is generated based on this, so that technical personnel can improve the production quality of panels based on the early warning information and reduce the occurrence of bad problems from the root. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0011] Figure 1 A schematic diagram of the structure of a panel production device provided in an embodiment of the present application is shown;

[0012] Figure 2 A schematic diagram of the structure of a panel production device provided in an embodiment of the present application is shown;

[0013] Figure 3 A flow chart showing a method for production management of panels provided in an embodiment of the present application is shown;

[0014] Figure 4 A flow chart showing a method for production management of panels provided by another embodiment of the present application is shown;

[0015] Figure 5 A flow chart showing a method for determining improvement measures provided by an embodiment of the present application;

[0016] Figure 6 A structural diagram of a panel production management device provided in an embodiment of the present application is shown;

[0017] Figure 7 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such use is interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0020] As described in the background technology, with the surge in demand for panel furniture, the current manual inspection and interception of panel quality can no longer meet the production inspection and manufacturing development needs of panel furniture. It is mainly reflected in the following aspects: (1) There is serious subjectivity in manual quality inspection and defect judgment; (2) The number of panels continues to increase rapidly, making it impossible to effectively curb the outflow of quality problems by manpower alone, which will cause an increase in production carryover; if a large amount of manpower is invested in inspection and interception to reduce the outflow of defective panels, it will cause a large amount of manpower costs; (3) With the increasing investment in automated production lines, the degree of automation of production line layout is also getting higher and higher. It is not suitable for too many people to intervene in the production process, which will affect the automated production process. Therefore, in terms of production quality inspection, it is necessary to quickly invest in inspection equipment and synchronize the production process with the production flow to realize product automated inspection and interception work. Through automated inspection, panels with quality problems can be controlled within the factory to reduce production carryover.

[0021] Most of the solutions in the related technologies are aimed at improving the accuracy of defect recognition and detection results of automated detection equipment. As for the research on detection methods, a related solution provides a plate edge defect detection method, a controller and a computer-readable storage medium. First, a barcode scanner, a fiber optic sensor and an encoder are used to obtain information such as plate properties and spatial position, and then a line scan camera is used to obtain an image of the plate edge. Finally, the image is analyzed and processed to obtain the plate edge defect information, thereby realizing intelligent plate edge defect detection and improving detection efficiency.

[0022] However, the research of the above technical solutions is limited to the discovery and interception of production defects, and the defect detection in the solution only targets defects such as edge height and whitening on the surface of the plate. However, there are obvious deficiencies in the research on the collection and storage of detection data and its real-time feedback on the current production status, analysis, tracing and improvement of production quality problems, and optimization of production management methods. Therefore, its application of automated detection technology is incomplete.

[0023] Based on this, the present application proposes a production management method for panels, which detects defects on panels through preset inspection standards. Different preset inspection standards have different ways of determining defective panels, thereby meeting various production needs and reducing production costs; through the defect detection results of panels, defective panels are intercepted, replacing traditional manual inspections, realizing automated product detection and interception work, improving the quality input-output ratio, controlling defective panels within the factory, reducing production carryovers, and reducing personnel rework. Furthermore, by analyzing the inspection data, the defective rate of panels under different dimensions is determined, and early warning information is generated based on this, so that technical personnel can improve the production quality of panels based on the early warning information and reduce the occurrence of defective problems from the root.

[0024] The present application is described in detail below through specific embodiments.

[0025] Figure 1 A schematic diagram of the structure of a panel production device according to an embodiment of the present application is shown. The panel production management method provided in the embodiment of the present application can be implemented by Figure 1 device implementation.

[0026] from Figure 1 It can be seen that the panel production equipment includes an inlet, an edge banding machine and an outfeed table. The panels enter from the inlet, are edge banded by the edge banding machine, and flow out from the outfeed table.

[0027] In some embodiments, a scanning device is provided in the feed port, and the scanning device is used to scan the mark on the plate. In one embodiment, the scanning device is an automatic barcode scanner, which is installed at the front end of the feed port, and the position of the scanning device can be set based on the actual situation.

[0028] In some embodiments, a detection device is provided in the edge banding machine, and the detection device is used to perform defect detection on the plate to obtain detection data of the plate. In one embodiment, a space greater than or equal to 200 mm is reserved at the rear of the edge banding machine for installing the detection device. Optionally, the detection device is embedded in the edge banding machine in an embedded installation manner to stabilize the detection result.

[0029] In some embodiments, the detection device includes a display, a camera, and a conveyor belt. The display is used to display the detection data of the board; the camera is used to collect the edge banding image of the board; and the conveyor belt is used to convey the board, so that the detection device can realize through-type online monitoring.

[0030] In some embodiments, the detection object specifications of the detection equipment are: length ≥250mm, width ≥100mm, thickness 12-36mm, the detection accuracy is: length ±0.3mm, width ±0.3mm, size detection range length = standard size position ±30mm, width = 20mm, 20mm inside the corner.

[0031] It is worth noting that the detection device in the embodiment of the present application can be set in the edge banding machine based on the actual situation, and the position of the detection device is not fixed. It only needs to be able to realize the function of the detection device in the embodiment of the present application.

[0032] In some embodiments, Figure 2 As shown, a labeling machine and a telescopic fluent strip bracket are provided at the outlet end of the discharge port. The labeling machine is used to mark the defect detection result on the plate, and the telescopic fluent strip bracket is used to intercept the plate with a bad defect detection result.

[0033] In one embodiment, the telescopic fluent bar bracket is adjusted by a point-actuated pneumatic telescopic method. Optionally, when the defect detection result of the plate is bad, the telescopic fluent bar bracket rotates a preset angle to transfer the bad plate out of the production line from the bad product outlet. After the bad plate is transferred, the telescopic fluent bar bracket rotates a preset angle in the opposite direction to continue to transfer qualified plates and abnormal ones. The preset angle can be 90 degrees.

[0034] In some embodiments, Figure 2 As shown, the panel production equipment also includes a safety fence, which is arranged on the outside of the labeling machine to isolate the production personnel and the panel production equipment to protect the production personnel.

[0035] In some embodiments, the panel production equipment further includes an indicator light and / or a sound. In one embodiment, the indicator light and / or the sound is used to issue an interception reminder when a panel with a defect detection result of poor detection is detected. In another embodiment, the indicator light and / or the sound is used to issue an interception reminder when panels with a defect detection result of poor detection are continuously detected, so that production personnel can find and improve problems in time to avoid the generation of a large number of defective panels.

[0036] In the embodiment of the present application, by improving the panel production equipment, the panel production equipment can detect the quality status of the panel in real time, obtain the inspection data of the panel, and intercept defective panels.

[0037] Figure 3 A schematic diagram of the process flow of the panel production management method provided in the embodiment of the present application is shown, from Figure 3 It can be seen that the present application at least includes steps S101 to S104:

[0038] Step S101: Perform defect detection on the panel based on preset detection standards to obtain detection data.

[0039] In some embodiments, different inspection standards are used to inspect defects on panels in different ways, that is, different ways of determining whether a panel is defective are used.

[0040] In some embodiments, the inspection data includes property information of the panel, defect information, defect inspection results, and equipment information of the panel production equipment.

[0041] In one embodiment, the attribute information of the board includes the board type, board thickness, board pattern, board standard length, board standard width, board standard height, etc. The defect information of the board includes defect length, defect width, defect position, defect coordinates, and defect image. The defect detection results include qualified, poor, and abnormal. The equipment information of the board production equipment includes the detection time, the base, the factory, the workshop, the equipment number, the detection standard, the processing type, the edge banding machine type, the saw table type, the production mode, and the creation time.

[0042] Step S102: Based on the detection data, the panel production equipment is controlled to intercept panels with defect detection results being bad.

[0043] In some embodiments, the telescopic fluent strip bracket of the panel production equipment is controlled to rotate at a preset angle to intercept defective panels from the production line. Specifically, the reversing command is controlled by a programmable logic controller (PLC), and the panels with qualified and abnormal defect detection results continue to be conveyed forward in the conveying direction of the normal production line, and the panels with defect detection results as defective continue to be conveyed in the direction after the telescopic fluent strip bracket is rotated at a preset angle, thereby intercepting the defective panels.

[0044] Step S103: Analyze the detection data within a preset time period to determine the panel defect rate under different dimensions.

[0045] Step S104: Generate warning information based on the panel defect rates in different dimensions.

[0046] In some embodiments, when the panel defect rate under a certain dimension triggers the warning target threshold, warning information is generated and the warning information is fed back to relevant personnel.

[0047] In some embodiments, the content of the warning message includes the warning subject, the total amount of inspection data under the current dimension, the panel defect rate, the warning threshold of the panel defect rate, the panel defect rate under each inspection standard, the target defect type, the target defect machine, the target panel pattern, the target defect location, the defect picture, the person responsible for the warning, etc.

[0048] Among them, the warning subject refers to a specific machine, workshop, factory, base, business line, etc.; the panel defect rate refers to the ratio of panels with defect detection results as defective to the total number of panels detected; the panel defect rate under each detection standard is the ratio of defective panels to the total detection data under different detection standards; the target defect type refers to the defect type and its defect rate value corresponding to the maximum value of the ratio of the number of panels under each defect type to the total number of panels detected; the target defect machine refers to the machine and its defect rate value corresponding to the maximum value of the ratio of the defective panels of each machine under the warning subject to the total number of panels detected; the target panel pattern refers to the pattern and its defect rate value corresponding to the maximum value of the ratio of the number of panels judged as defective under each pattern to the total number of panels detected for that pattern; the target defect position refers to the defect position and its defect rate value corresponding to the maximum value of the ratio of the number of defective panels under each defect position to the total number of detection data.

[0049] In some embodiments, defective panels, panel production equipment, production processes, etc. are analyzed based on the early warning information to improve the panel production quality. For example, the panel production equipment is repaired or some hardware is upgraded, or the raw materials for producing panels are updated, and the production process is improved.

[0050] In some embodiments, a year-month-day trend analysis is performed based on the early warning information to analyze the fluctuations in production defects and the differences from the target values; the defect types and defect attributes of the defective products are analyzed based on the early warning information; the electronic saws and edge banding machines where the defective products are concentrated are analyzed based on the early warning information; the door panels, cabinet bodies, and length and width ranges of the defective products are analyzed based on the early warning information; the defect distribution positions of the defective panels are determined based on the early warning information, and the defect distribution positions include horizontal positions: front end, middle end, and rear end; and vertical positions: top, middle, and bottom.

[0051] Furthermore, the production process is analyzed based on the early warning information, such as the tool changing method, thick and thin edges, glue / tools, etc.; the production process is analyzed based on the early warning information, such as the production lines, machines, and team members where defective panels are concentrated; the production equipment is analyzed based on the early warning information, such as the difference analysis between new and old equipment; the production status is analyzed based on the early warning information, such as whether secondary edge banding or secondary panel filling is required; the operating actions of the panel production equipment are analyzed based on the early warning information, such as whether the leaning action and cleaning and maintenance actions are accurate; the equipment units of the panel production equipment are analyzed based on the early warning information, such as whether the clamps, tools or other equipment parameters of the panel production equipment are used correctly; the production process of the panel production equipment is analyzed based on the early warning information, such as whether the pre-milling amount and saw blade compensation amount are correct.

[0052] from Figure 3It can be seen from the method shown that the embodiment of the present application performs defect detection on the panel by using preset detection standards. Different preset detection standards have different ways of determining defective panels, thereby meeting various production needs and reducing production costs; through the defect detection results of the panel, the defective panel is intercepted, replacing the traditional manual inspection, realizing the automated detection and interception of products, improving the quality input-output ratio, controlling the defective panels within the factory, reducing production legacy, and reducing personnel rework. Furthermore, by analyzing the detection data, the defective rate of panels under different dimensions is determined, and early warning information is generated based on this, so that technical personnel can improve the production quality of panels based on the early warning information and reduce the occurrence of defective problems from the root.

[0053] In some embodiments of the present application, the intercepted panels with defect detection results as bad are re-judged as bad. In one implementation, the bad re-judgment method includes manual re-judgment and detection system re-judgment.

[0054] In some embodiments, the panels with OK re-judgment results are classified as qualified panels, and the test data are classified as qualified test data. In some embodiments, the panels with bad re-judgment results are further divided into treatment methods, such as repair or re-board.

[0055] Furthermore, after the re-judgment is completed, the state of the panel is marked to form rework data. In some embodiments, the rework data includes defect information such as panel inspection type, defect type, defect attribute, and panel state information, wherein the panel state information includes states such as awaiting re-judgment, awaiting repair, awaiting repair, repaired, repaired, and qualified re-judgment, and the state information of the panel can be set according to actual needs.

[0056] In some embodiments, a rework mark is set in the inspection data of the panel with a re-judgment result of OK, and it can be known that the panel is a re-judged panel by checking the inspection data.

[0057] In the embodiment of the present application, the occurrence of misjudgment is avoided by re-judging the panels with defect detection results being bad.

[0058] In some embodiments of the present application, in the above method, the detection data is obtained in step S101 in the following manner: Figure 4 As shown, the following steps are included:

[0059] Step S201: Scanning the mark on the board by a scanning device to obtain the attribute information of the board.

[0060] The mark on the board may be a QR code mark, a bar code mark, etc. The mark on the board is associated with the attribute information of the board.

[0061] The attribute information includes the type of panel, thickness of panel, pattern of panel, standard length of panel, standard width of panel and standard height of panel.

[0062] Step S202: Capturing edge banding images of panels using a photographing device.

[0063] Step S203: Determine the defect detection result of the panel based on the edge banding image, attribute information and preset detection standard of the panel.

[0064] In some embodiments, defect information of the panel is determined based on the edge banding image and property information of the panel.

[0065] Specifically, the edge banding image and attribute information of the board are input into the pre-built neural network model, and the defect information of the board is output. Among them, the defect information includes a defect image with a defect mark, a defect type, a defect attribute, a defect length, a defect width, a defect position, and a defect coordinate. Optionally, the defect types that can be detected by the embodiment of the present application include parallelograms, large and small heads, large size, small size, collapse, debonding, glue seams, dirt / residual glue, edge band damage, long bands, short bands, edge scratches, R-angle defects, high edge banding, low edge banding, etc. The embodiment of the present application can detect boards of all colors, including but not limited to 18 midsummer gray odorless formaldehyde-free comfortable core board, 18 silver star gray double-pasted odorless particle board, 18 Nieder oak odorless formaldehyde-free comfortable core board, 18 Hyde oak double-pasted odorless formaldehyde-free comfortable core board, and 18 glimpse double-pasted odorless particle board.

[0066] In one embodiment, training samples are pre-constructed, including multiple edge banding images and their corresponding defect information, and a neural network model is trained using the training samples so that the neural network model can output the defect information of the panel based on the edge banding images and attribute information of the panel.

[0067] Furthermore, based on the defect information of the panel and the preset detection standard, the defect detection result of the panel is determined.

[0068] Since a single testing standard is not applicable to all actual production environments, it will cause a large number of products to be difficult to meet production requirements and result in rework and interception. Therefore, the embodiment of the present application adds testing standard management on the basis of interception, thereby reducing production costs on the basis of meeting production needs.

[0069] In some embodiments, the preset inspection standard is used to indicate a target difference between an actual production size of a panel and a target production size, and the target difference between the actual production size of a panel and the target production size is different under different preset inspection standards.

[0070] In one embodiment, the preset inspection standards include explicit inspection standards, visual inspection standards, precision inspection standards, and excellent inspection standards. Among them, the explicit inspection standard is applicable to eliminating processing errors and product failure problems, improving the success rate of one-time installation, and reducing customer complaints. The target difference between the actual production size of the panel and the target production size is ≥2mm; the visual inspection standard is applicable to eliminating visual sensory problems, solving defects that are easily found by the naked eye, and reducing negative customer feedback. The target difference between the actual production size of the panel and the target production size is ≥1.5mm; the precision inspection standard is applicable to improving sensory experience and fine quality. The defects are basically invisible to the naked eye. The target difference between the actual production size of the panel and the target production size is ≥1mm; the excellent inspection standard is applicable to achieving excellent quality and improving customer reputation. Its quantitative standard is the target difference between the actual production size of the panel and the target production size is ≥0.8mm.

[0071] Specifically, the actual difference between the actual production size of the panel and the target production size is determined based on the defect information of the panel, the target difference between the actual production size of the panel and the target production size is determined based on the preset inspection standard, and the defect detection result of the panel is determined based on the target difference and actual difference between the actual production size of the panel and the target production size.

[0072] In one implementation, if the actual difference is greater than or equal to the target difference, the defect detection result of the panel is determined to be poor; if the actual difference is less than the target difference, the defect detection result of the panel is determined to be qualified.

[0073] In some embodiments, during the inspection of a panel, if the attribute information and / or defect information of the panel is abnormal, the defect inspection result of the panel is abnormal. For example, if the attribute information of the panel is empty, it means that the label or scanning device on the panel is abnormal; for another example, if the defect information of the panel is empty, it means that the inspection device may be abnormal and the inspection data of the panel is not obtained.

[0074] In the embodiment of the present application, defective panel detection is performed by setting preset detection standards and a pre-built neural network model to achieve multi-demand detection management.

[0075] In some embodiments of the present application, after acquiring the detection data, the detection data within the historical time period is stored in the cloud platform, the detection data is extracted from the cloud platform at a regular interval, and the extracted detection data is cleaned for abnormal data, and the data after the abnormal data cleaning is stored in the data lake and the data warehouse to permanently store the detection data.

[0076] In one implementation, data extraction, conversion, loading (Extract-Transform-Load, ETL), open source message systems (e.g., Kalfka) and other data synchronization tools are used to periodically extract detection data from the cloud platform and aggregate and synchronize it to the data storage module. After receiving the detection data, the data storage module determines the data format and data interval, performs abnormal data analysis and cleaning, data partitioning and other processing, and then stores it in the data lake and the massively parallel processing (Massively Parallel Processing, MPP) architecture distributed data warehouse to permanently store the detection data.

[0077] Among them, abnormal data analysis and cleaning include detection data of unarchived machines and detection data with logical abnormalities, such as detection data where defect information is not empty but the defect detection results are qualified.

[0078] In some embodiments, the detection data within a preset time period is obtained from the data warehouse, and the detection data within the preset time period is analyzed to determine the panel defect rate under different dimensions and visualize it in the form of a BI report. Optionally, the different dimensions include organizational level dimensions such as machine level, shift level, workshop level, factory level, base level, business line level, group level, etc.; time dimensions such as hour, day, week, month, quarter, year, etc.; basic information dimensions such as panel type, panel color, defect type, defect location, and processing equipment.

[0079] In the embodiment of the present application, the detection data is displayed in the form of a report so that the staff can clearly understand the status of the detection data.

[0080] In some embodiments of the present application, reference Figure 5 As shown, when defects are found in the panel, the cause of the defect is located and the production quality of the panel is improved in time.

[0081] In some embodiments, a rule knowledge base is constructed based on historical data and expert experience, and associations between entities such as defects, data distribution characteristics, key influencing factors, defect phenomena, defect causes, and improvement measures are established.

[0082] In one implementation, a large model is used to perform data fusion processing on the collected expert experience data to form a unified knowledge description to eliminate knowledge redundancy and build a complete rule knowledge base.

[0083] Specifically, the construction of the rule knowledge base includes three processes: knowledge representation, similarity calculation and knowledge fusion. Among them, the process of knowledge representation is different from the traditional semantic random initialization method. The long text entities in the embodiment of the present application are initialized and encoded using large language models (LLMs), that is, e=LLMs(e), r=LLMs(r) (where e represents the entity vector and r represents the relationship vector), and then the entities and relationships are mapped to the vector space for representation through the knowledge embedding model. Optionally, the knowledge embedding model includes but is not limited to TransE, TransH, DistMult, CompIEx, and RotatE.

[0084] In one implementation, the loss function of the knowledge embedding model is:

[0085] L=γ+f(e1,r,e2)-f(e′1,r′,e′2)

[0086] Among them, γ is the hyperparameter of the loss function, e1 and e2 represent two entity vectors, r represents the association relationship between e1 and e2, e′1 and e′2 represent two negative sample entity vectors, r′ represents the association relationship between e′1 and e′2, and f() represents a linear function.

[0087] It is worth noting that the negative sample entity vector represents two entity vectors with low correlation.

[0088] Furthermore, the similarity of the semantic vector representations of the entity relationships is calculated, for example, the similarity is calculated based on Euclidean distance, cosine similarity, Pearson correlation coefficient, etc.

[0089] In one implementation, cosine similarity is selected to calculate the similarity:

[0090]

[0091] Next, knowledge fusion is performed, and by setting a similarity threshold, knowledge data with similarity exceeding the threshold is fused, and those with similarity below the threshold are retained, so as to achieve alignment and fusion processing of all knowledge rule data. Optionally, the similarity threshold is 0.9.

[0092] In an embodiment of the present application, by constructing a rule knowledge base, defect types, data distribution, key influencing factors, defect causes, defect phenomena, improvement measures, etc. are associated, so that the panel production quality can be subsequently improved based on the rule knowledge base.

[0093] In some embodiments of the present application, the cause of the defect is located based on the data distribution matching algorithm model in combination with the expert rule knowledge base, and the target key influencing factors causing the defect are determined, thereby determining improvement measures for the panel production equipment based on the target key influencing factors.

[0094] In some embodiments, based on the data distribution of the current defect under different analysis dimensions, a data feature vector is generated by grouping and aggregating to obtain a first distribution feature vector (X, Y);

[0095] (X,Y)=[[x1,y1],[x2,y2],[x3,y3],…[x N-1 ,y N-1 ],[x N ,y N ]]

[0096] Among them, x N Indicates defect characteristics, such as defect size, defect location, defect shape, etc.; y N Indicates the data distribution corresponding to the defect characteristics.

[0097] Furthermore, a grouping aggregation method is used to generate data features for the data distribution corresponding to the rule knowledge consistent with the current defect in the rule knowledge base, and a second distribution feature vector (X′, Y′) is obtained;

[0098] (X′,Y′)=[[x′1,y′1],[x′2,y′2],[x′3,y′3],…[x′ N-1 ,y′ N-1 ],[x′ N ,y′ N ]]

[0099] Among them, x′ N represents the defect features in the rule knowledge base, y′ N Represents the data distribution in the rule knowledge base.

[0100] Further, a matching algorithm is constructed based on a bilinear similarity function to calculate the feature similarity between the first distribution feature and the second distribution feature to obtain a matching value. In one implementation, the feature matching value is calculated based on the following method:

[0101]

[0102] Among them, w i represents the weight coefficient, and b represents the bias parameter.

[0103] Finally, find the rule knowledge with the closest match, that is, the largest output result, as the most likely associated knowledge data, and the key influencing factor data it contains as the most likely key factors affecting the current quality problem, and further obtain the corresponding defect causes and improvement measures knowledge to generate knowledge feedback.

[0104] In the embodiments of the present application, on-site physical analysis is conducted on the distribution of data phenomena and adverse phenomena in combination with historical knowledge feedback, the correctness of key influencing factors is confirmed in the actual production scenario, improvement measures are implemented, and the improvement effects are tracked. After the measures are implemented, the occurrence of adverse conditions is monitored regularly, and the application and promotion of improvement measures are strengthened to complete the quality management closed loop.

[0105] In some embodiments of the present application, a production management device for a panel is provided, and the production management device for a panel corresponds one-to-one to the production management method for a panel in the above embodiment. Figure 6 As shown, the panel production management device includes: an acquisition module 501, a control module 502 and a processing module 503. The detailed description of each functional module is as follows:

[0106] The acquisition module 501 is used to perform defect detection on the panel based on the preset detection standard and obtain detection data; wherein the method of determining the defect detection result of the panel under different preset detection standards is different; the detection data includes the attribute information, production information, defect information, defect detection result of the panel and equipment information of the panel production equipment, and the defect detection result includes qualified, bad and abnormal;

[0107] The control module 502 is used to control the panel production equipment to intercept the panels with defect detection results as bad based on the detection data;

[0108] The processing module 503 is used to analyze the detection data within a preset time period to determine the panel defect rate in different dimensions; based on the panel defect rate in different dimensions, generate warning information, and the warning information is used to improve the panel production quality.

[0109] In some embodiments of the present application, in the above-mentioned device, the acquisition module 501 is specifically used to obtain attribute information of the board based on scanning the mark on the board by a scanning device, the attribute information including the type of board, thickness of the board, pattern of the board, standard length of the board, standard width of the board, and standard height of the board; to collect the edge banding image of the board based on the shooting device; and to determine the defect detection result of the board based on the edge banding image of the board, the attribute information and the preset detection standard.

[0110] In some embodiments of the present application, in the above-mentioned device, the acquisition module 501 is specifically used to input the edge banding image and attribute information of the panel into a pre-built neural network model, and output the defect information of the panel, wherein the defect information includes a defect image with defect marks, defect type, defect attribute, defect length, defect width, defect position, and defect coordinates; based on the defect information of the panel and the preset detection standard, the defect detection result of the panel is determined.

[0111] In some embodiments of the present application, in the above-mentioned device, the acquisition module 501 is specifically used to determine the actual difference between the actual production size of the panel and the target production size based on the defect information of the panel; determine the target difference between the actual production size of the panel and the target production size based on the preset inspection standard; determine the defect detection result of the panel based on the target difference and actual difference between the actual production size of the panel and the target production size.

[0112] In some embodiments of the present application, in the above-mentioned device, the acquisition module 501 is specifically used to determine that the defect detection result of the panel is poor when the actual difference is greater than or equal to the target difference; and to determine that the defect detection result of the panel is qualified when the actual difference is less than the target difference.

[0113] In some embodiments of the present application, in the above-mentioned device, the acquisition module 501 is specifically used to determine that the defect detection result of the panel is abnormal if the attribute information and / or defect information of the panel is abnormal.

[0114] In some embodiments of the present application, in the above-mentioned device, the storage module 504 is used to store the detection data within the historical time period in the cloud platform; extract the detection data from the cloud platform at a regular interval, and clean the extracted detection data for abnormal data; and store the data after the abnormal data cleaning in the data lake and the data warehouse.

[0115] In some embodiments of the present application, in the above-mentioned device, the abnormal data includes detection data of unarchived machines, defect information, and detection data of logical abnormalities of defect detection results.

[0116] In some embodiments of the present application, in the above-mentioned device, the warning information includes the warning subject, the total amount of detection data under the current dimension, the panel defect rate, the warning threshold of the panel defect rate, the panel defect rate under each preset detection standard, the target defect type, the target defect machine, the target panel pattern, the target defect position, the defect picture, and the warning responsible person; wherein, the target defect type refers to the defect type corresponding to the maximum value of the ratio of the panel quantity under each defect type to the total detected panel quantity; the target defect machine refers to the machine corresponding to the maximum value of the ratio of the defective panels of each machine to the total detected panel quantity under the current warning subject; the target panel pattern refers to the pattern corresponding to the maximum value of the ratio of the quantity of panels judged as defective under each pattern to the total detected panel quantity of the pattern; the target defect position refers to the defect position corresponding to the maximum value of the ratio of the quantity of defective panels under each defect position to the total detection data quantity.

[0117] In some embodiments of the present application, in the above-mentioned device, the different dimensions include organizational hierarchy dimension, time dimension, and detection data dimension; wherein the organizational hierarchy dimension includes machine level, shift level, workshop level, factory level, base level, business line level, and group level; the time dimension includes hours, days, weeks, months, quarters, and years; the detection data dimension includes panel type, defect type, defect location, and processing equipment.

[0118] In some embodiments of the present application, in the above-mentioned device, the processing module 503 is used to re-judge the intercepted panels with defect detection results as defective and generate rework data; the rework data includes panel status information, and the panel status information includes waiting for re-judgement, waiting for repair, waiting for repair, repaired, repaired, and qualified after re-judgement.

[0119] In some embodiments of the present application, in the above-mentioned device, the processing module 503 is used to obtain historical data; perform knowledge fusion on the historical data to construct a rule knowledge base, and the rule knowledge base is used to represent the correlation between data distribution, key influencing points, defect causes, defect phenomena, and improvement measures.

[0120] In some embodiments of the present application, in the above-mentioned device, the processing module 503 is used to extract long text entities in the experience data, and the long text entities include data distribution, key influencing points, defect causes, defect phenomena, and improvement measures; map the long text entities and their relationships to the vector space for representation; calculate the similarity between each entity vector; based on the similarity threshold, merge the entity vectors whose similarity is greater than the similarity threshold to generate a rule knowledge base.

[0121] In some embodiments of the present application, in the above-mentioned device, the processing module 503 is used to locate the cause of defects of panels with defect detection results as poor based on the rule knowledge base, and determine the target key influencing factors; based on the target key influencing factors, determine the improvement measures for the production quality of the panels.

[0122] In some embodiments of the present application, in the above-mentioned device, the processing module 503 is used to generate a first distribution feature vector based on the data distribution of the defect type of the current panel in different dimensions; generate a second distribution feature vector based on the data distribution of the defect type of the current panel in the rule knowledge base; calculate the feature similarity between the first distribution feature vector and the second distribution feature vector, and determine the feature matching value; and use the rule knowledge with the largest feature matching value as the target key influencing factor.

[0123] It should be noted that any of the above-mentioned panel production management devices can implement the above-mentioned panel production management method one-to-one, which will not be repeated here.

[0124] Figure 7 FIG. 1 is a schematic diagram showing the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown, at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0125] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0126] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0127] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a production management device for panels at the logical level. The processor executes the program stored in the memory and is specifically used to execute the above method.

[0128] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor to be executed. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0129] The electronic device can execute the production management method of the panel provided in multiple embodiments of the present application, and realize the production management device of the panel in Figure 6 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0130] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, the electronic device can execute the production management method of panels provided by multiple embodiments of the present application.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0137] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0139] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0140] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A production management method for panels, characterized in that: The method comprises: Perform defect detection on the panel based on the preset detection standard to obtain detection data; wherein the method of determining the defect detection result of the panel under different preset detection standards is different; the detection data includes attribute information, defect information, defect detection result of the panel and equipment information of the panel production equipment, and the defect detection result includes qualified, bad and abnormal; Based on the detection data, controlling the panel production equipment to intercept the panels with defect detection results being bad; Analyze the inspection data within the preset time period to determine the defective rate of panels in different dimensions; Based on the defective rates of panels in different dimensions, early warning information is generated, and the early warning information is used to improve the production quality of the panels.

2. The method according to claim 1, characterized in that The defect detection of the panel based on the preset detection standard and obtaining the detection data includes: Scanning the mark on the board by a scanning device to obtain attribute information of the board, wherein the attribute information includes board type, board thickness, board pattern, board standard length, board standard width, and board standard height; Acquiring an edge banding image of the panel based on a photographing device; Based on the edge banding image, attribute information and the preset detection standard of the panel, the defect detection result of the panel is determined.

3. The method according to claim 2, characterized in that The step of determining the defect detection result of the panel based on the edge banding image, the attribute information and the preset detection standard of the panel includes: Inputting the edge banding image and attribute information of the panel into a pre-built neural network model, and outputting defect information of the panel, wherein the defect information includes a defect image with a defect mark, a defect type, a defect attribute, a defect length, a defect width, a defect position, and a defect coordinate; Based on the defect information of the panel and the preset detection standard, a defect detection result of the panel is determined.

4. The method according to claim 3, characterized in that The step of determining the defect detection result of the panel based on the defect information of the panel and the preset detection standard includes: Determining an actual difference between an actual production size of the panel and a target production size based on the defect information of the panel; Determining a target difference between an actual production size of the panel and a target production size based on the preset inspection standard; Based on a target difference and an actual difference between an actual production size of the plate and a target production size, a defect detection result of the plate is determined.

5. The method according to claim 4, characterized in that The step of determining the defect detection result of the plate based on the target difference and the actual difference between the actual production size of the plate and the target production size includes: The actual difference is greater than or equal to the target difference, and the defect detection result of the plate is determined to be poor; The actual difference is smaller than the target difference, and the defect detection result of the plate is determined to be qualified.

6. The method according to claim 1, characterized in that The defect detection of the plate and acquisition of detection data also includes: If the property information and / or defect information of the panel is abnormal, it is determined that the defect detection result of the panel is abnormal.

7. A production management device for panels, characterized in that: The device comprises: An acquisition module is used to perform defect detection on the panel based on a preset detection standard and obtain detection data; wherein the method of determining the defect detection result of the panel under different preset detection standards is different; the detection data includes attribute information, production information, defect information, defect detection result of the panel and equipment information of the panel production equipment, and the defect detection result includes qualified, bad and abnormal; A control module, configured to control the panel production equipment to intercept the panels with defect detection results being bad based on the detection data; The processing module is used to analyze the detection data within a preset time period to determine the defective rate of panels in different dimensions; based on the defective rate of panels in different dimensions, generate early warning information, and the early warning information is used to improve the production quality of the panels.

8. A panel production equipment, characterized in that: The panel production equipment includes a material inlet, an edge banding machine and a material discharging platform; Wherein, a scanning device is provided in the feed port, and the scanning device is used to scan the mark on the plate; The edge banding machine is provided with a detection device, which is used to perform defect detection on the plate based on a preset detection standard to generate detection data of the plate; wherein the method of determining the defect detection result of the plate under different preset detection standards is different; the detection data includes attribute information of the plate, production information, defect information, defect detection result and equipment information of the production equipment; A labeling machine and a telescopic fluent strip bracket are provided at the outlet end of the discharging platform, wherein the labeling machine is used to mark the defect detection result on the plate, and the telescopic fluent strip bracket is used to intercept the plate with a defect detection result of poor detection.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the steps of the panel production management method as described in any one of claims 1-6.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the steps of the panel production management method as described in any one of claims 1-6.

Images