Panel furniture processing production line control system

Abstract

The invention relates to the technical field of intelligent control, in particular to a panel furniture processing production line control system, which comprises an upper computer which stores order information, order panels and scheduling information of the panels in each process, and the upper computer is also connected with a cutting control subsystem which is used for dynamically balancing the cutting progress of the panels through a genetic algorithm, the edge sealing control subsystem is used for recognizing a lossless area of a plate based on an image classification algorithm so as to carry out edge sealing control, the drilling control subsystem is used for machining drill bit moving path planning based on artificial intelligence and carrying out drilling control on the edge-sealed plate, and the sorting control subsystem is used for automatically matching the drilled plate with a sorting frame. And the packaging control subsystem is used for carrying out plate stacking and packaging according to the order information. According to the scheme, the labor input is reduced as much as possible in each process, and the production efficiency of the plate is improved.

Description

Technical Field

[0001] The present invention generally relates to the field of intelligent control technology, and more specifically, to a control system for a panel furniture processing production line. Background Art

[0002] The manufacturing process of furniture includes the board (or panel) processing technology, which generally includes board cutting, edge banding, waste material processing, board drilling, board cleaning, board sorting, packaging and other processes, which belong to the front-end process of furniture manufacturing.

[0003] At present, the sheet material processing process is mostly operated manually, with cutting equipment, edge banding equipment, and hole punching equipment. At the beginning, the sheet material needs to be manually transported to the cutting equipment for cutting. After the cutting is completed, it needs to be transported to the edge banding equipment for edge banding. After the edge banding is completed, the sheet material needs to be manually transported to the hole punching equipment for drilling. After the drilling is completed, the sheet material needs to be manually sorted, packaged, and stacked. Each of the above links requires manual participation and operation, which is slow and inefficient. At the same time, the labor intensity is high, the production cost is high, and it is difficult to achieve the goal of efficient production. In order to improve production efficiency, some manufacturers currently use intelligent production equipment for intelligent operation to improve productivity, but usually intelligent design is carried out for a single process, and there is currently no better solution for the fully automated production of the entire processing flow of sheet materials.

[0004] Based on this, what needs to be urgently solved is the problem of low intelligence level and low production efficiency of current plate processing technology. Summary of the invention

[0005] In order to solve the above-mentioned technical problems of low intelligence level and low production efficiency of current plate processing technology, the present invention provides the following technical solutions.

[0006] The present invention provides a control system for a panel furniture processing production line, comprising a host computer storing order information, order panels and scheduling information of the panels in various processes, the host computer is also connected to: a cutting control subsystem for dynamically balancing the progress of panel cutting through a genetic algorithm, an edge banding control subsystem for identifying non-destructive areas of panels based on an image classification algorithm for edge banding control, a drilling control subsystem for planning the movement path of a processing drill based on artificial intelligence and for drilling control of edge banded panels, a sorting control subsystem for automatically matching sorting racks to drilled panels, and a packaging control subsystem for stacking and packaging panels according to order information.

[0007] The present invention realizes full-process automatic control of the panel furniture processing production line through unified scheduling of multiple control subsystems by the host computer, effectively reduces manual input, and improves the production efficiency of panel furniture. The host computer comprehensively controls and orderly schedules each production line, ensuring the flexibility and controllability of the production process and reducing the waste of time and resources. At the same time, various algorithms are used to improve the production process of each production line, effectively improving production efficiency.

[0008] Preferably, the cutting control subsystem includes a cutting control unit for connecting to a host computer, wherein the cutting control unit is connected to the cutting equipment, and is used to determine the machinable panels in the order information according to the types of machinable panels, obtain multiple layout schemes of the initial standard panels, obtain the initial cutting sequence based on a genetic algorithm, and dynamically adjust the layout of the standard panels and the cutting sequence during the cutting process to complete the panel processing of all orders in the same batch.

[0009] Preferably, the initial cutting sequence is obtained based on a genetic algorithm, and the standard panel layout and the cutting sequence are dynamically adjusted during the cutting process, including: obtaining a plurality of layout schemes for the main panel types of the current batch based on the panel types and the layout schemes of historical panel cutting, obtaining the initial cutting sequence using a genetic algorithm based on the plurality of layout schemes, and sending all panels of the current batch into the cutting equipment in turn for cutting according to the layout scheme set in the initial cutting sequence; wherein each chromosome in the genetic algorithm represents a cutting sequence, and the information encoded by the gene in the chromosome includes: the serial number of the layout scheme, the number of times the layout scheme appears in the production line, and the serial number of the cutting equipment; the order of the gene code in the chromosome represents the order of the panel processing layout scheme corresponding to the code in the entire processing flow.

[0010] Preferably, it also includes: supplementing and limiting the crossover and mutation operations of the genetic algorithm based on the first strategy, the second strategy and the third strategy, the first strategy refers to scheduling the diversion of panels to the production line of the cutting equipment that is not blocked or faulty by monitoring the production quantity of the equipment; the second strategy adjusts the order of panels within the layout plan to make it conform to the spacing between the dual-head cutting equipment; the third strategy refers to adjusting the cutting order so that the number of panels in the layout plan of the two panels on the double gantry cutting equipment is the same or similar.

[0011] The present invention obtains the types of panels that can be processed by the factory based on equipment parameters and the types of panels ordered by customers, and then uses genetic algorithms to optimize the cutting order, and finally generates the layout plan for the current batch of panels and performs cutting operations. Compared with the prior art, the present invention significantly improves the flexibility and efficiency of factory production. Specifically, by optimizing a variety of layout plans through genetic algorithms, the present invention can dynamically adjust the layout order and cutting strategy according to actual working conditions, ensuring the best match between the processing technology and equipment capabilities of each batch, thereby reducing material waste, reducing equipment idle time, and improving the overall processing efficiency of the production line.

[0012] Preferably, the edge banding control subsystem includes an edge banding control unit connected to a host computer, wherein the edge banding control unit is connected to the edge banding device, and is used to process the collected images of the panels to be edge banded to obtain a gradient map, and to detect the area to be tested by clustering the gradient map and merging the clustering clusters, and to calculate the ratio of the mean pixel value of the pixel points in the area to be tested to the mean pixel value of the pixel points in the preset standard edge banding area, and use the absolute value of the difference between the ratio and 1 as the classification coefficient, and mark the area to be tested whose classification coefficient is less than the preset coefficient threshold as a lossless area; make the minimum circumscribed rectangle of the lossless area the edge banding area, and output 0 in response to the pixel values ​​of the pixel points between the edge banding area and the lossless area being the same, and output 1 otherwise, to obtain a defective area.

[0013] Compared with directly using edge calculation to determine the edge of the edge-banding area, the edge-banding control scheme of the present invention makes the boundary division between the edge-banding area and the non-edge-banding area more accurate, thereby improving the accuracy of subsequent defect identification, especially for damage on the boundary, the identification accuracy is higher.

[0014] Preferably, the drilling control subsystem includes a drilling control unit connected to a host computer, wherein the drilling control unit is connected to the drilling equipment and is used to generate a movement path of the processing drill bit according to an artificial intelligence algorithm, and to optimize the drilling action of the processing drill bit according to an improved greedy algorithm, and to control the drilling equipment to perform drilling control on the edge banding panel according to the optimized drilling action.

[0015] Preferably, the processing drill bit movement path is generated according to the artificial intelligence algorithm, including: obtaining a minimum action set based on the hole position information to be processed and the drill bit information on the drill package; using an ant colony algorithm and a genetic algorithm to sort the drilling actions in the minimum action set respectively, so that the total length of the movement path of the drilling equipment head is minimized, and a first sorting result and a second sorting result are obtained; comparing the total length of the movement path of the drilling equipment head corresponding to the first sorting result and the second sorting result, selecting the sorting result with the smaller total length of the movement path as the optimal sorting result, and using the movement path of the head corresponding to the optimal sorting result as the plate drilling path.

[0016] Preferably, the drilling action of the drill bit is optimized according to an improved greedy algorithm, including: obtaining hole position data and drill bit data to generate a hole position table and a drill bit table; establishing a machine head action data table based on the hole position table and the drill bit table; constructing an action matrix of hole positions and machine head actions according to the machine head action data table; simplifying the action matrix, and using the simplified action matrix to drill the plate.

[0017] The use of the drilling path generation method based on artificial intelligence of the present invention can greatly improve the efficiency of drilling and greatly reduce the energy consumption of drilling equipment.

[0018] Preferably, the sorting control subsystem includes a sorting control unit for connecting to a host computer, wherein the sorting control unit is connected to the sorting equipment, and is used to size cluster the panels according to the size information of the panels after cutting in each batch of orders in history to obtain size clustering results, and to cluster the historical orders according to the size clustering results to obtain order clustering results, determine the type and number of sorting racks, match the panels in the orders that need to be matched, complete the matching of the sorting racks when the mismatch of the panels is minimized, and stack the panels according to the matched sorting racks.

[0019] Preferably, the calculation formula for the mismatch degree of the plate is: ,in, Indicates the mismatch of the panels. Indicates the number of panel types in the order. Indicates the order The number of panels, Indicates The number of sorting racks corresponding to the order clusters, Indicates The order clusters correspond to the sorting rack storage The number of panels of the same type.

[0020] The beneficial effect of the present invention is that by connecting the host computer with the sub-control systems of multiple devices in the furniture processing production line, and starting to control each production process from the moment an order is received, the control subsystems of each part are used for full automation control, so that the manual input in each process is minimized and the production efficiency of the panels is improved. At the same time, by connecting the host computer with the sub-control systems of each part, the comprehensive control and scheduling of the automated production line can be realized, the production time of each part can be coordinated in an orderly manner, and the production process can be highly intelligent, so that the entire process can be produced in an orderly manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is a schematic diagram schematically showing the composition structure of a control system for a panel furniture processing production line according to an embodiment of the present invention; Figure 2 is a schematic diagram showing the composition structure of a material cutting control subsystem according to an embodiment of the present invention; Figure 3 is a schematic structural diagram showing the composition of an edge banding control subsystem according to an embodiment of the present invention; Figure 4 is a structural diagram schematically showing a component of a drilling control subsystem according to an embodiment of the present invention; Figure 5 FIG. 4 is a structural diagram schematically showing a composition of a sorting control subsystem according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0023] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 It is a schematic diagram schematically showing the composition structure of a control system for a panel furniture processing production line according to an embodiment of the present invention.

[0025] like Figure 1 As shown, the control system of the panel furniture processing production line includes a host computer that stores order information, order panels and scheduling information of panels in various processes, and a cutting control subsystem, an edge banding control subsystem, a drilling control subsystem, a sorting control subsystem and a packaging control subsystem connected to the host computer. The cutting control subsystem is used to dynamically balance the progress of panel cutting through a genetic algorithm, the edge banding control subsystem identifies the non-destructive area of ​​the panel based on an image classification algorithm for edge banding control, the drilling control subsystem plans the movement path of the processing drill based on artificial intelligence and controls the drilling of edge banded panels, the sorting control subsystem is used to automatically match the sorting racks for the drilled panels, and the packaging control subsystem is used to stack and pack the panels according to the order information.

[0026] Furthermore, the host computer can also be connected to the control subsystem of the transportation equipment in each production process, so as to realize the scheduling and control of the transportation process between each production process, such as the control subsystem of the AGV cart, conveyor belt, grabbing robot and other equipment between each production process.

[0027] In some embodiments, the host computer can also be connected to various monitoring devices in the production workshop to monitor the environmental information of the entire production process to ensure safe and orderly production. For example, the host computer is connected to monitoring devices such as temperature sensors, humidity sensors, smoke sensors, and cameras.

[0028] The cutting control subsystem, edge banding control subsystem, drilling control subsystem, sorting control subsystem and packaging control subsystem are the core control parts of each process. Figures 2 to 5 Each control system is described in detail.

[0029] When processing panels on the production line, the stacked standard panels are first placed on the hydraulic loading platform for labeling. One of the functions of labeling is to ensure that subsequent panels can be traced. The code also contains the cutting layout plan of the standard panel. Then the labeled standard panels are sent to the cutting equipment. After scanning the code, the equipment cuts according to the set layout plan and sends the cut panels to the edge banding line. Then the edge banding line will perform edge banding operations on all panels one by one. After the edge banding is completed, the panels enter the drilling equipment, and the equipment performs drilling operations according to the set path. Finally, the drilled panels enter the sorting workstation, and the panels are automatically sorted according to the information contained in the code, that is, to ensure that the panels of the same order are placed in one area for subsequent transportation.

[0030] In most processing plants, orders from multiple customers will be processed as the same batch of work orders to improve the utilization rate and processing efficiency of panels. The panels refer to the standard panels of the processing plant, which can be cut according to a certain layout plan to obtain multiple panels required by customers. The panels mentioned in the subsequent content of this embodiment all refer to standard panels used for cutting panels, and the rest will not be repeated.

[0031] Before cutting, the host computer first obtains different customer orders. By analyzing the orders, it can obtain the number of panels in the order and the type and quantity of each panel, which facilitates subsequent typesetting.

[0032] like Figure 2As shown, the cutting control subsystem includes a cutting control unit for connecting to a host computer. The cutting control unit is connected to the cutting equipment and is used to determine the machinable panels in the order information according to the types of machinable panels, obtain multiple layout schemes of the initial standard panels, obtain the initial cutting sequence based on the genetic algorithm, and dynamically adjust the standard panel layout and the cutting sequence during the cutting process to complete the panel processing of all orders in the same batch.

[0033] In this embodiment, a greedy algorithm can be used to obtain multiple layout schemes for the current batch of work order panel cutting. The input of the algorithm is a set of historical layout schemes, the main panel types of the current batch, and the quantity of each panel type. The output of the algorithm is multiple layout schemes including the main panel types of the current batch.

[0034] In some embodiments, the initial cutting sequence is obtained based on a genetic algorithm, and the standard panel layout and the cutting sequence are dynamically adjusted during the cutting process, including: obtaining multiple layout schemes for the main panel types of the current batch based on the panel type and the historical panel cutting layout scheme. The initial cutting sequence is obtained using a genetic algorithm based on multiple layout schemes, and all panels of the current batch are sequentially sent to the cutting equipment for cutting according to the layout scheme set in the initial cutting sequence. Each chromosome in the genetic algorithm represents a cutting sequence, and the information encoded by the gene in the chromosome includes: the serial number of the layout scheme, the number of times the layout scheme appears in the production line, and the serial number of the cutting equipment; the order of the gene code in the chromosome represents the order of the panel processing layout scheme corresponding to the code in the entire processing flow.

[0035] Specifically, in this embodiment, the layout scheme and cutting order of the panel are encoded by real number coding, wherein the integer digit of the real number represents the layout scheme sequence number of the current panel, and the decimal digit represents the sequence of the layout scheme represented by the integer digit in the processing equipment. Then, binary coding is used to represent the cutting equipment sequence number that is preferentially assigned to the current panel.

[0036] In the genetic algorithm, after obtaining the initialized population, it is also necessary to set the fitness function to judge the quality of individual chromosomes, that is, to determine which chromosomes can be crossed and mutated. In this embodiment, the fitness function is mainly reflected by the processing efficiency, so it can be initially set as the inverse of the average cutting time, and the specific calculation is:

[0037] in Indicates chromosome The fitness function value of Indicates the total number of "genes" contained in the chromosome, that is, the total number of panels that need to be cut on the production line; It means the Chromosome gene, i.e. A cut plate; It means the The time required to cut a plate. The larger the fitness function value of a chromosome is, the better the gene it contains is, and the more likely the individual is to produce offspring chromosomes.

[0038] Furthermore, based on the first strategy, the second strategy and the third strategy, the crossover and mutation operations of the genetic algorithm are supplemented and limited. The first strategy refers to scheduling the diversion of panels to the cutting equipment production line that is not blocked or faulty by monitoring the production quantity of the equipment; the second strategy adjusts the order of panels within the layout plan to make it conform to the spacing between the dual-head cutting equipment; the third strategy refers to adjusting the cutting order so that the number of panels in the layout plan of the two panels on the double gantry cutting equipment is the same or similar.

[0039] After the cutting is completed, the plate needs to be sent to the edge banding equipment for edge banding. The edge banding subsystem controls the edge banding equipment to complete the edge banding operation.

[0040] like Figure 3 As shown, the edge banding control subsystem includes an edge banding control unit connected to a host computer. The edge banding control unit is connected to an edge banding device and is used to process the collected images of the panels to be edge banded to obtain a gradient map, and to detect the area to be tested by clustering the gradient map and merging the cluster clusters.

[0041] In some embodiments, a camera is used to capture a captured image including the edge-sealed area, and the captured image is grayed to obtain a grayscale image. The maximum value of the pixel value ratio between each pixel point and the pixel points in the eight neighborhoods is calculated, and the maximum value is used as the maximum gradient value. The pixel value of each pixel point is replaced by the maximum gradient value to obtain a gradient image.

[0042] The gradient map is clustered to obtain multiple clusters, and the clustering algorithm used is DBSCAN (Density-Based Spatial Clustering of Applications with Noise, density-based spatial clustering algorithm). DBSCAN is an existing technology and will not be described in detail here.

[0043] After the above clustering step, multiple clusters are obtained, and the merging coefficient of any two clusters is calculated. When the merging coefficient is greater than a preset merging threshold, the clusters are merged.

[0044] In one embodiment, the merging process may be: merging adjacent clusters, obtaining a new cluster each time, performing clustering again after merging, and repeating the above operation until there is no merging coefficient greater than a preset merging threshold, then stopping merging clusters to obtain the area to be tested. Exemplarily, the merging threshold may be: 0.75.

[0045] In one embodiment, the calculation formula of the merging coefficient is: ,in, is the merging coefficient, is the number of pixel values ​​of the first cluster, is the number of pixel values ​​of the second cluster, The pixel value in the first cluster is The ratio of the pixel point to all the pixels of the first cluster, The pixel value in the second cluster is The ratio of the pixel of to all the pixels of the second cluster. represents the hyperbolic tangent function.

[0046] It indicates the difference in the number of pixel values ​​in the clusters. If the difference in the number of pixels between the two clusters is small, The value will be close to 1, indicating that the two clusters are similar in size. If the difference is large, The value of will approach 0, indicating two clusters.

[0047] Used to measure the similarity between two clusters in pixel value distribution. It indicated and The difference between them, namely KL divergence, is used to measure the similarity between two clusters in pixel value distribution. The larger the value, the smaller the difference between the two distributions. The value of is close to 1.

[0048] Merge coefficient The larger the value of is, the more similar the two clusters are in the number and distribution of pixel values, so the possibility of merging is greater, and vice versa, the possibility of merging is smaller.

[0049] In other embodiments, only The merging coefficient will not be elaborated here.

[0050] The edge sealing control unit is also used to calculate the ratio of the average pixel value of the pixel points in the test area to the average pixel value of the preset standard edge sealing area, and use the absolute value of the difference between the ratio and 1 as the classification coefficient, and mark the test area with a classification coefficient less than the preset coefficient threshold as a lossless area. The minimum circumscribed rectangle of the lossless area is the edge sealing area, and in response to the pixel values ​​of the pixel points between the edge sealing area and the lossless area being the same, 0 is output, otherwise 1 is output, and the defective area is obtained.

[0051] After the edge banding is completed, drilling equipment is needed to drill holes in the panel to complete the processing.

[0052] like Figure 4 As shown, the drilling control subsystem includes a drilling control unit connected to a host computer, the drilling control unit is connected to a drilling device, and is used to generate a movement path of a processing drill bit according to an artificial intelligence algorithm, and to optimize the drilling action of the processing drill bit according to an improved greedy algorithm, and to control the drilling device to perform drilling control on the edge banding panel according to the optimized drilling action.

[0053] In some embodiments, the processing drill bit movement path is generated according to the artificial intelligence algorithm, including obtaining a minimum action set according to the hole position information to be processed and the drill bit information on the drill bag. The drilling actions in the minimum action set are sorted by using an ant colony algorithm and a genetic algorithm respectively, so that the total length of the movement path of the drilling equipment head is minimized, and a first sorting result and a second sorting result are obtained.

[0054] Specifically, the hole position information to be processed includes the working surface where the hole position to be processed is located, the hole position type, the hole diameter, the hole depth, and whether a specific tool is specified. The drill bit information on the drill package includes the drill bit type, the relative position coordinates of the drill bit on the drill package, the drill bit type, the drill bit working surface, the maximum drilling depth, and the travel coordinate limit of the drill bit. The drill bit corresponding to each hole position to be processed can be obtained based on the hole position information to be processed and the drill bit information on the drill package. The drill bit corresponding to the hole position to be processed refers to the drill bit that can be used to process the hole position. After screening out the hole position combinations that can be processed simultaneously under the same drill package, the combination with the least number and covering all the hole positions to be processed can be screened out from all the hole position combinations, thereby obtaining the minimum action set.

[0055] The drilling actions in the minimum action set are sorted by using an ant colony algorithm, so that the total length of the moving path of the drilling device head after each drilling action in the minimum action set is the smallest, and a first sorting result is obtained. The drilling actions in the minimum action set are sorted by using a genetic algorithm, so that the total length of the moving path of the drilling device head after each drilling action in the minimum action set is the smallest, and a second sorting result is obtained.

[0056] Compare the total lengths of the moving paths of the drilling equipment heads corresponding to the first sorting result and the second sorting result, select the sorting result with the smaller total length of the moving paths as the optimal sorting result, and use the moving path of the head corresponding to the optimal sorting result as the plate drilling path. Specifically, compare the total length of the moving paths of the drilling equipment heads corresponding to the first sorting result and the total length of the moving paths of the drilling equipment heads corresponding to the second sorting result, select the sorting result with the smaller total length of the moving paths as the optimal sorting result, and use the moving path of the head corresponding to the optimal sorting result as the plate drilling path. The total length of the moving path of the head is equal to the sum of the total length of the moving path of the gantry and the total length of the moving path of the drill bag on the gantry.

[0057] Furthermore, the drilling action of the machining drill is optimized according to the improved greedy algorithm, including obtaining hole position data and drill bit data to generate a hole position table and a drill bit table. A machine head action data table is established based on the hole position table and the drill bit table. An action matrix of hole positions and machine head actions is constructed according to the data table of machine head actions. The action matrix is ​​simplified, and the simplified action matrix is ​​used to perform drilling processing on the plate.

[0058] Furthermore, the hand safety area can also be determined according to the hand that fixes the plate during the actual drilling process and the situation where drilling is required. Specifically, a hand safety area is generated for each drilling action, and the hand is used to clamp the plate to fix it during drilling. Using the hand safety area corresponding to each drilling action, the hand safety areas of adjacent drilling actions in the optimal sorting result are continuously intersected to obtain the optimal hand safety area. The plate is drilled according to the optimal sorting result and the optimal hand safety area.

[0059] After the drilling process is completed, the panels need to be sorted and packaged to complete the order task. The control process of sorting and packaging will be described below.

[0060] like Figure 5 As shown, the sorting control subsystem includes a sorting control unit for connecting to the host computer, and the sorting control unit is connected to the sorting equipment, and is used to cluster the size of the panels according to the size information of the panels after the panels are cut in each batch of orders in the history, so as to obtain the size clustering result, cluster the historical orders according to the size clustering result, obtain the order clustering result, determine the type and number of sorting racks, match the panels in the orders that need to be matched, complete the sorting rack matching when the mismatch of the panels is the smallest, and stack the panels according to the matching sorting racks. For irregularly shaped panels, the size of their minimum circumscribed rectangle is used instead, that is, the length and width of this minimum circumscribed rectangle are measured and recorded.

[0061] Specifically, the size clustering of the panels is performed according to the size information, including: selecting a preset number of initial center points, selecting a panel, and calculating the distance between the panel and each initial center point. The size clustering formula satisfies the relationship: ,in, Indicates the plate and panels The distance between and Respectively represent the plate Length and plate Length, and Respectively represent the plate Length and plate Width.

[0062] The selected plate and the initial center point with the shortest distance are constructed into a size cluster.

[0063] Update the size cluster center to satisfy the relationship: ,in, The length of the plate representing the center of the size cluster, Indicates the size of the cluster. The number of panels, Indicates the size of the cluster. The length of the plate.

[0064] Similarly, the width of the panel at the size clustering center is obtained; the calculated panel length and panel width are used as the size clustering center.

[0065] Then select a new plate to calculate the distance from the three center points, which include an updated size cluster center and two initial center points. Traverse all plates to complete size clustering. After clustering, use the silhouette coefficient method to select the best clustering result as the size clustering result.

[0066] For example, the formula for order clustering satisfies the relationship: ,in, Indicates order and Orders The distance between Indicates order Middle The probability of the occurrence of similar panels, Indicates order Middle The probability of the occurrence of similar panels.

[0067] Calculate the order cluster center, which satisfies the relationship: ,in, Indicates The order cluster Order clustering center for panel-like parts, Indicates Orders in clusters Middle The number of panels, Indicates the total number of orders.

[0068] The type of sorting rack is equal to the order plate distribution corresponding to the order cluster center; the ratio of the number of each sorting rack is equal to the ratio of the number of orders in each order cluster.

[0069] Obtain the size information of the panels in the order to be matched, and calculate the size cluster to which each panel belongs. Obtain the panel distribution of the order to be matched, determine the best combination of sorting racks based on the panel distribution of the order to be matched and the number of panels that can be stored in different sorting racks, and calculate the panel mismatch degree, where the calculation formula for the panel mismatch degree is: ,in, Indicates the mismatch of the panels. Indicates the number of panel types in the order. Indicates the order The number of panels, Indicates The number of sorting racks corresponding to the order clusters, Indicates The order clusters correspond to the sorting rack storage The number of panels of the same type.

[0070] When the mismatch of panels is minimal, the best sorting rack combination is obtained and the sorting rack matching is completed. After the matching is completed, the sorting control subsystem will control the corresponding equipment or transmission channel according to the order information to sort the panels and send them to the corresponding positions. The packaging control subsystem will control the packaging equipment to stack and package the corresponding panels, thereby completing the furniture processing process.

[0071] The present invention provides a complete control system for the panel furniture processing production line, thereby achieving full-process monitoring and scheduling of the entire production process, effectively improving production efficiency and reducing labor costs.

[0072] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0073] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A panel furniture processing production line control system, characterized in that: It includes a host computer that stores order information, order panels and scheduling information of panels in various processes. The host computer is also connected to: a cutting control subsystem for dynamically balancing the progress of panel cutting through a genetic algorithm, an edge banding control subsystem for identifying non-destructive areas of panels based on an image classification algorithm for edge banding control, a drilling control subsystem for planning the movement path of a machining drill based on artificial intelligence and for drilling control of edge banded panels, a sorting control subsystem for automatically matching sorting racks to drilled panels, and a packaging control subsystem for stacking and packaging panels according to order information.

2. The panel furniture processing production line control system according to claim 1 is characterized in that: The cutting control subsystem includes a cutting control unit connected to a host computer, wherein the cutting control unit is connected to the cutting equipment, and is used to determine the machinable panels in the order information according to the types of machinable panels, obtain multiple layout schemes of the initial standard panels, obtain the initial cutting sequence based on the genetic algorithm, and dynamically adjust the standard panel layout and cutting sequence during the cutting process to complete the panel processing of all orders in the same batch.

3. The panel furniture processing production line control system according to claim 2 is characterized in that: The initial cutting sequence is obtained based on the genetic algorithm, and the standard panel layout and cutting sequence are dynamically adjusted during the cutting process, including: Based on the panel type and the layout scheme of historical panel cutting, multiple layout schemes for the main panel types of the current batch are obtained, and based on the multiple layout schemes, a genetic algorithm is used to obtain an initial cutting sequence, and all panels of the current batch are sent to the cutting equipment in turn for cutting according to the layout scheme set in the initial cutting sequence; wherein each chromosome in the genetic algorithm represents a cutting sequence, and the information encoded by the gene in the chromosome includes: the serial number of the layout scheme, the number of times the layout scheme appears in the production line, and the serial number of the cutting equipment; the order of the gene code in the chromosome represents the order of the panel processing layout scheme corresponding to the code in the entire processing flow.

4. The panel furniture processing production line control system according to claim 3 is characterized in that: Also includes: Based on the first strategy, the second strategy and the third strategy, the crossover and mutation operations of the genetic algorithm are supplemented and limited. The first strategy refers to scheduling the diversion of panels to the production lines of the cutting equipment that are not blocked or faulty by monitoring the production quantity of the equipment; the second strategy adjusts the order of panels within the layout plan to make it conform to the spacing between the dual-head cutting equipment; the third strategy refers to adjusting the cutting order so that the number of panels in the layout plan of the two panels on the double gantry cutting equipment is the same or similar.

5. The panel furniture processing production line control system according to claim 1 is characterized in that: The edge banding control subsystem includes an edge banding control unit connected to a host computer, wherein the edge banding control unit is connected to an edge banding device, and is used to process the collected image of the plate to be edge banded to obtain a gradient map, and realize detection of the area to be tested by clustering the gradient map and merging the clustering clusters, and calculate the ratio of the mean pixel value of the pixel points in the area to be tested to the mean pixel value of the pixel points in the preset standard edge banding area, and use the absolute value of the difference between the ratio and 1 as the classification coefficient, and mark the area to be tested whose classification coefficient is less than the preset coefficient threshold as a lossless area; make the minimum circumscribed rectangle of the lossless area the edge banding area, and output 0 in response to the pixel values ​​of the pixel points between the edge banding area and the lossless area being the same, and output 1 otherwise, to obtain a defective area.

6. The panel furniture processing production line control system according to claim 1, characterized in that: The drilling control subsystem includes a drilling control unit connected to a host computer, wherein the drilling control unit is connected to a drilling device and is used to generate a movement path of a processing drill bit according to an artificial intelligence algorithm, optimize the drilling action of the processing drill bit according to an improved greedy algorithm, and control the drilling device to perform drilling control on the edge banding panel according to the optimized drilling action.

7. The panel furniture processing production line control system according to claim 6 is characterized in that: The processing drill bit movement path is generated according to the artificial intelligence algorithm, including: According to the hole position information to be processed and the drill bit information on the drill bag, a minimum action set is obtained; the drilling actions in the minimum action set are sorted by using an ant colony algorithm and a genetic algorithm, respectively, so that the total length of the moving path of the drilling equipment head is minimized, and a first sorting result and a second sorting result are obtained; Compare the total lengths of the movement paths of the drilling equipment heads corresponding to the first sorting result and the second sorting result, select the sorting result with the smaller total length of the movement path as the optimal sorting result, and use the movement path of the head corresponding to the optimal sorting result as the plate drilling path.

8. The panel furniture processing production line control system according to claim 6, characterized in that: The drilling action of the drill bit is optimized according to the improved greedy algorithm, including: Acquire hole position data and drill bit data to generate a hole position table and a drill bit table; Establish a machine head motion data table based on the hole position table and drill bit table; Construct the action matrix of hole position and machine head action according to the data table of machine head action; The action matrix is ​​simplified, and the simplified action matrix is ​​used to perform drilling on the plate.

9. The panel furniture processing production line control system according to claim 1, characterized in that: The sorting control subsystem includes a sorting control unit connected to a host computer, wherein the sorting control unit is connected to a sorting device, and is used to size cluster the panels according to the size information of the panels after cutting in each batch of orders in history to obtain size clustering results, and to cluster the historical orders according to the size clustering results to obtain order clustering results, determine the type and number of sorting racks, match the panels in the orders that need to be matched, complete the sorting rack matching when the panel mismatch is the smallest, and stack the panels according to the matched sorting racks.

10. The panel furniture processing production line control system according to claim 9, characterized in that: The calculation formula for the mismatch of the panels is: ,in, Indicates the mismatch of the panels. Indicates the number of panel types in the order. Indicates the order The number of panels, Indicates The number of sorting racks corresponding to the order clusters, Indicates The order clusters correspond to the sorting rack storage The number of panels of the same type.

Images