Automatic processing technology for non-standard plates

Abstract

The invention belongs to the technical field of plate machining, and particularly relates to a non-standard plate automatic machining process which comprises the steps that a drawing is drawn according to a plate body, and the size, specification and shape of the drawing serve as operation instruction parameters of a numerical control machine tool; through cooperation of the structure, automatic machining of non-standard plates can be achieved through automatic machining, different specifications of the plates are achieved, the competitiveness is effectively improved through the functions of automatic data reading, data processing, automatic feeding, automatic machining and automatic discharging, and the production efficiency is improved. And through the arranged intelligent identification system module, the plates can be rapidly collected and analyzed according to the materials of the plates, the optimal corresponding machining process method is selected, the machining parameters most suitable for the materials are automatically adjusted, the human intervention time is shortened, the overall operation efficiency of the production line is improved, and the production efficiency is improved. And the intelligent identification system module can select the most suitable processing method according to the accurate material information, so that the consistency and high quality of products are ensured.

Description

Technical Field

[0001] The invention belongs to the technical field of plate processing, in particular to an automatic processing technology for non-standard plates. Background Art

[0002] Non-standard panels generally refer to panels that do not conform to standard sizes, shapes or specifications. Panels refer to flat materials that have been processed and treated. Such panels are widely used in various industrial and construction fields with customized needs.

[0003] A Chinese invention patent publication numbered CN109130254B discloses a process for processing environmentally friendly PVC sheets. The key technical aspects of the process are as follows: (1) mixing the raw materials in a certain proportion, heating and stirring them evenly; (2) cooling them to 60°C before feeding them into a screw extruder to extrude a blank; (3) heating and pressing the blank, the wear-resistant layer, and the mite-removing layer together to form a composite layer; (4) cutting the composite layer into a specified size using a cutting device, and then milling one end face using a feeding device; (5) flipping the composite layer using a flipping device, and milling the other end face a second time; and (6) shipping the milled sheets. The present invention has a high degree of automation in the environmentally friendly PVC sheet processing process, saving labor and improving efficiency.

[0004] However, the above technologies often have the following defects: the traditional grooving processing method is to manually take the board and put it into the machine, manually set the depth of the board to be planed, and manually input the depth of the board to be processed and the width of the interval. The machine does not have the function of continuous automatic loading and unloading to process non-standard specifications. It requires a lot of personnel, low processing efficiency, poor processing quality stability, and is not convenient for automatic processing of non-standard sizes, resulting in high processing costs and unstable quality.

[0005] To this end, the present invention provides an automatic processing technology for non-standard plates. Summary of the Invention

[0006] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0007] The technical solution adopted by the present invention to solve the technical problem is: the automatic processing technology of non-standard plate materials described in the present invention comprises the following steps:

[0008] S1: Draw a drawing based on the plate body, and use its size, specifications and shape as the operating instruction parameters of the CNC machine tool;

[0009] S2: Material preparation: Based on the material of the plate to be processed, the intelligent recognition system module analyzes and identifies the plate and calculates the corresponding processing technology, automatically processes it, and uses the intelligent planning model to perform design optimization, path planning, and fault prediction;

[0010] S3: After completion, post-processing is performed again and data recording and analysis are performed.

[0011] As a preferred technical solution of the present invention, the intelligent recognition system module includes a plate acquisition module, a model intelligent recognition module, and a recognition result classification and process selection module. The plate acquisition module is used to collect and extract features of the material and texture of the plate. The model intelligent recognition module completes feature recognition based on the established recognition model. The recognition result classification and process selection module is used to analyze the recognition results and match the process selection.

[0012] As a preferred technical solution of the present invention, the plate acquisition module collects and identifies the type and texture of the plate, and the types of the plate include wooden plates, metal plates, plastic plates, glass plates, stone plates and composite plates. The image recognition acquisition is completed based on a convolutional neural network, and the type and texture of the plate are collected and identified through image recognition.

[0013] As a preferred technical solution of the present invention, the recognition result classification and process selection module is used to collect the specific material of the identified plate, classify it and select the corresponding processing technology.

[0014] As a preferred technical solution of the present invention, after the collection and identification of the board materials are completed, a specific processing technology is selected according to their type. The wooden board materials can be processed by cutting, planing, splicing, hot pressing and gluing. The metal board materials can be processed by stamping, bending and welding. The plastic board materials can be processed by injection molding and extrusion. The glass board materials can be processed by cutting, grinding, tempering and laminating. The stone board materials can be processed by laser cutting and polishing. The composite material board materials can be processed by lamination, stamping and melt compounding.

[0015] As a preferred technical solution of the present invention, the convolutional neural network includes the following steps:

[0016] Step 1: Pre-collect training data on plate types and textures. The training data includes feature data and corresponding plate texture type labels. Calibrate the plate texture type labels, setting texture type A to 1 and texture type B to 2. Collect the plate texture feature information through image processing.

[0017] Step 2: Set the model structure parameters: Set the structural parameters of the neural network model;

[0018] Step 3: Initialize weights and biases: Initialize the weights and biases in the neural network model;

[0019] Step 4: Divide the data set: Divide the collected training data into a training set and a validation set in a ratio of 8:2;

[0020] Step 5: Model training: Input the training set into the neural network model for training to obtain the trained neural network model;

[0021] Step 6: Model Validation: Import the validation set data into the trained neural network model, obtain the plate texture type label number predicted by the model output, and calculate the error between the actual plate texture type label of the validation set and the predicted label;

[0022] Step 7: Determine and adjust: Determine whether the error is within the preset error range. If so, stop training and output the trained neural network model. If not, adjust the weights and biases of the neural network model according to the error and return to step 5 to continue training.

[0023] Step 8: Practical application: Use the trained neural network model to classify and identify the plate texture type in the detection area.

[0024] As a preferred technical solution of the present invention, the design optimization in the intelligent planning model dynamically adjusts the parameters of laser cutting power and punching speed by real-time analysis of the plate material and equipment status.

[0025] As a preferred technical solution of the present invention, path planning optimizes the cutting path based on a multi-axis linkage algorithm based on reinforcement learning, reduces spatial travel, simulates the AGV transportation route on the digital twin platform, adjusts the path based on real-time order priority, and implements path planning based on the input standard plate size. The fault prediction realizes full-dimensional monitoring of the equipment operation status by deploying high-precision sensors and industrial cameras, predicts the remaining life of the equipment based on the LSTM time series analysis model, associates historical maintenance records with real-time working conditions, and generates maintenance recommendations.

[0026] As a preferred technical solution of the present invention, data recording and analysis include:

[0027] Data collection: record key data during the processing, including the time, energy consumption and scrap rate of sheet metal processing;

[0028] Performance evaluation: Based on the collected data, the processing efficiency and product quality are evaluated.

[0029] As a preferred technical solution of the present invention, automatic processing is based on automatic loading of plates, and the intelligent recognition system module is used to automatically select the processing method for the plates, cut the plates, and process the depth and width of the intervals according to the specific material of the plates during cutting, and automatically unload the plates after processing.

[0030] The beneficial effects of the present invention are as follows:

[0031] Compared with the existing technology, the beneficial effects of the present invention are: non-standard plates can be automatically processed through automatic processing, and different specifications of each plate can be achieved. The competitiveness is effectively improved through the functions of automatic data reading, data processing, automatic loading, automatic processing, and automatic unloading. The intelligent recognition system module is set up to facilitate rapid collection and analysis of the plate material, and select the best corresponding processing method, and automatically adjust to the processing parameters that are most suitable for the material, reducing the time of human intervention and improving the overall operation efficiency of the production line. The intelligent recognition system module can select the most appropriate processing method according to accurate material information, thereby ensuring product consistency and high quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention will be further described below with reference to the accompanying drawings.

[0033] Figure 1 This is a schematic diagram of the rear guide block structure in an automatic processing technology for non-standard plates;

[0034] Figure 2 This is a schematic diagram of the structure of a sheet material stop sensor in an automatic processing technology for non-standard sheet materials;

[0035] Figure 3 This is a side sectional view of equipment used in an automatic processing technology for non-standard plates;

[0036] Figure 4 This is a top-down cross-sectional view of equipment used in an automatic processing technology for non-standard plates;

[0037] Figure 5 This is a schematic diagram of the steps of an automatic processing process for non-standard plates;

[0038] Figure 6 The figure is a flow chart of the intelligent identification system module in the automatic processing technology of non-standard plates.

[0039] In the picture:

[0040] 1. Robot No. 2; 2. Slotting machine; 3. Positioning table; 4. Barcode scanner; 5. Roller line; 6. Robot No. 1; 7. Incoming material cart; 8. Slotting machine No. 1; 9. Scanned sheet material; 10. Sheet material to be scanned; 11. Processing cart; 12. Scanned sheet material; 13. Slotting machine No. 2; 14. Barcode scanner No. 2; 15. Roller line No. 2; 16. Barcode scanner No. 1; 17. Roller line No. 1; 18. Sheet material stop sensor; 19. In-position signal device; 21. Rear guide block; 22. Front guide block. DETAILED DESCRIPTION

[0041] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0042] Reference Figure 1 - Figure 6 , the present invention provides three technical solutions:

[0043] Example 1:

[0044] An automatic processing technology for non-standard plates includes the following steps:

[0045] S1: Draw a drawing based on the plate body, and use its size, specifications and shape as the operating instruction parameters of the CNC machine tool to realize automatic processing and reading of data;

[0046] S2: Material preparation: Based on the material of the plate to be processed, the intelligent recognition system module analyzes and identifies the plate and calculates the corresponding processing technology, automatically processes it, and uses the intelligent planning model to perform design optimization, path planning, and fault prediction;

[0047] S3: After completion, post-processing is performed again and data recording and analysis are performed.

[0048] Example 2:

[0049] The intelligent recognition system module includes a plate acquisition module, a model intelligent recognition module, and a recognition result classification and process selection module. The plate acquisition module is used to collect and extract features of the material and texture of the plate. The model intelligent recognition module completes feature recognition based on the established recognition model. The recognition result classification and process selection module is used to analyze the recognition results and match the process selection. Selecting the appropriate processing technology is conducive to improving the final quality of the product and reducing the number of damaged plates.

[0050] The plate collection module collects and identifies the type and texture of the plate. The types of plates include wooden plates, metal plates, plastic plates, glass plates, stone plates and composite plates. The type and texture of the plate can be collected and identified through image recognition technology. The image recognition collection is completed based on the convolutional neural network. The type and texture of the plate can be collected and identified through image recognition, which effectively improves the production efficiency and product quality of plate processing, reduces labor costs and resource waste, and improves the quality of the final product of the plate.

[0051] The recognition result classification and process selection module is used to collect the specific material of the plate after recognition, classify it and select the corresponding processing technology. The processing technology can be divided into CNC multi-axis linkage processing, laser intelligent cutting and stamping forming, so as to complete the selection of the processing technology for the plate.

[0052] After completing the collection and identification of the boards, the specific processing technology is selected according to their type. Wooden boards can be processed by cutting, planing, splicing, hot pressing and gluing. Metal boards can be processed by stamping, bending and welding. Plastic boards can be processed by injection molding and extrusion. Glass boards can be processed by cutting, grinding, tempering and laminating. Stone boards can be processed by laser cutting and polishing. Composite materials can be processed by lamination, stamping and melt compounding. Choosing a processing method suitable for the board material can help reduce material waste and energy consumption. By matching the most appropriate processing technology, it can be ensured that the board will not be damaged during the processing, thereby ensuring the quality of the final product.

[0053] A convolutional neural network consists of the following steps:

[0054] Step 1: Pre-collect training data on plate types and textures. The training data includes feature data and corresponding plate texture type labels. Calibrate the plate texture type labels, setting texture type A to 1 and texture type B to 2. Collect the plate texture feature information through image processing.

[0055] Step 2: Set the model structure parameters: Set the structural parameters of the neural network model;

[0056] Step 3: Initialize weights and biases: Initialize the weights and biases in the neural network model;

[0057] Step 4: Divide the data set: Divide the collected training data into a training set and a validation set in a ratio of 8:2;

[0058] Step 5: Model training: Input the training set into the neural network model for training to obtain the trained neural network model;

[0059] Step 6: Model Validation: Import the validation set data into the trained neural network model, obtain the plate texture type label number predicted by the model output, and calculate the error between the actual plate texture type label of the validation set and the predicted label;

[0060] Step 7: Determine and adjust: Determine whether the error is within the preset error range. If so, stop training and output the trained neural network model. If not, adjust the weights and biases of the neural network model according to the error and return to step 5 to continue training.

[0061] Step 8: Practical application: Use the trained neural network model to classify and identify the plate texture type in the detection area.

[0062] Design optimization in the intelligent planning model dynamically adjusts the parameters of laser cutting power and punching speed by real-time analysis of sheet material and equipment status.

[0063] Among them, path planning is based on a multi-axis linkage algorithm based on reinforcement learning to optimize the cutting path and reduce spatial travel. The digital twin platform simulates the AGV transport route, adjusts the path based on real-time order priorities, and implements path planning based on the input standard plate size. Fault prediction achieves full-dimensional monitoring of equipment operation status by deploying high-precision sensors and industrial cameras. The LSTM-based time series analysis model predicts the remaining life of the equipment, associates historical maintenance records with real-time working conditions, and generates maintenance recommendations. In path planning, the path set first can be combined with the plate material to make the best path planning, so as to complete the standard size processing and cutting of the plate. Fault prediction can avoid problems encountered by the equipment during processing, reduce accidents, improve work efficiency, and reduce jams during plate processing, which affects the final quality of the plate. The path planning formula is as follows:

[0064] F=α·U+β·θ

[0065] Where U is the material utilization rate of the board, θ is the proportion of the cutting area along the grain, and the weight coefficients α and β are dynamically adjusted according to the bending strength requirements of the wood.

[0066] Data recording and analysis include:

[0067] Data collection: record key data during the processing, including the time, energy consumption and scrap rate of sheet metal processing;

[0068] Performance evaluation: Based on the collected data, the processing efficiency and product quality are evaluated. Through data collection and performance evaluation during processing, the best processing method for sheet metal processing can be made again to improve the final quality of the product.

[0069] The automatic processing is based on automatic loading of plates. The intelligent recognition system module is used to automatically select the processing method for the plates, cut the plates, and process the depth and width of the intervals according to the specific material of the plates during cutting. The plates are automatically unloaded after processing. The process matching and path planning of the plates are completed in the above manner. The cutting depth and interval width required for the plates during processing can be directly obtained, thereby achieving the effect of automatic processing and effectively improving competitiveness.

[0070] Example 3:

[0071] The No. 1 material-picking robot takes the sheet material with the QR code from the incoming material cart 7 and takes it to the No. 1 roller line 17 and the No. 2 roller line 15 to be scanned sheet material 10. The roller line 5 conveys the sheet material forward and passes over the No. 1 scanner 16 and the No. 2 scanner 14 respectively. The scanner completes the scanning and uploads the data to the server. The No. 2 robot 1 grabs the scanned sheet material 9 on the No. 1 roller line 17 and places it on the positioning table 3 for origin positioning. After the positioning is completed, the No. 2 robot 1 puts the positioned sheet material into the No. 1 slotting machine 8 and triggers the in-place signal device 19. The slotting machine 2 clamping platform is provided with front and rear guide blocks 22, which starts the clamping plate. The No. 2 robot 1 releases the sheet material and returns to the standby position. At the same time, the No. 1 robot 6 brings the material from the incoming material cart 7. Grab the sheet material 12 from the No. 2 roller line 15 and put it into the No. 2 groover 13 while the No. 1 groover 8 is processing. The No. 2 robot 1 grabs the scanned sheet material 12 from the No. 2 roller line 15 and puts it into the No. 2 groover 13 and triggers the in-place signal device 19. The groover 2 starts the clamping plate. The No. 2 robot 1 releases the sheet material and returns to the standby position. At the same time, the No. 1 robot will grab the material on the material cart 7 and put it into the No. 2 roller line 15 for replenishment. At this time, the No. 1 groover 8 and the No. 2 groover 13 are both performing processing operations. The No. 2 robot 1 will automatically put the processed sheet material into the position of the completed processing cart 11 in order according to the processing signals completed by the two machines, and the machine will automatically run in a cycle.

[0072] The above-mentioned front, back, left, right, up and down are all based on the Figure 1 As a benchmark, according to the person's observation perspective, the side of the device facing the observer is defined as the front, the left side of the observer is defined as the left, and so on.

[0073] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present invention.

[0074] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An automatic processing technology for non-standard plates, characterized by: The following steps are involved: S1: Draw a drawing based on the plate body, and use its size, specifications and shape as the operating instruction parameters of the CNC machine tool; S2: Material preparation: Based on the material of the plate to be processed, the intelligent recognition system module analyzes and identifies the plate and calculates the corresponding processing technology, automatically processes it, and uses the intelligent planning model to perform design optimization, path planning, and fault prediction; S3: After completion, post-processing is performed again and data recording and analysis are performed.

2. The automatic processing technology for non-standard plates according to claim 1, characterized in that: The intelligent recognition system module includes a plate collection module, a model intelligent recognition module, and a recognition result classification and process selection module. The plate collection module is used to collect and extract features of the material and texture of the plate. The model intelligent recognition module completes feature recognition based on the established recognition model. The recognition result classification and process selection module is used to analyze the recognition results and match the process selection.

3. The automatic processing technology for non-standard plates according to claim 2, characterized in that: The plate acquisition module collects and identifies the type and texture of the plate, which includes wooden plates, metal plates, plastic plates, glass plates, stone plates and composite plates. The image recognition acquisition is completed based on the convolutional neural network, and the type and texture of the plate are collected and identified through image recognition.

4. The automatic processing technology for non-standard plates according to claim 1 is characterized in that: The recognition result classification and process selection module is used to collect the specific material of the identified plate, classify it and select the corresponding processing technology.

5. The automatic processing technology for non-standard plates according to claim 1 is characterized in that: After the collection and identification of the panels are completed, a specific processing technology is selected according to their type. The wooden panels can be processed by cutting, planing, splicing, hot pressing and gluing. The metal panels can be processed by stamping, bending and welding. The plastic panels can be processed by injection molding and extrusion. The glass panels can be processed by cutting, grinding, tempering and laminating. The stone panels can be processed by laser cutting and polishing. The composite panels can be processed by lamination, stamping and melt compounding.

6. The automatic processing technology for non-standard plates according to claim 3 is characterized by: The convolutional neural network includes the following steps: Step 1: Pre-collect training data on plate types and textures. The training data includes feature data and corresponding plate texture type labels. Calibrate the plate texture type labels, setting texture type A to 1 and texture type B to 2. Collect the plate texture feature information through image processing. Step 2: Set the model structure parameters: Set the structural parameters of the neural network model; Step 3: Initialize weights and biases: Initialize the weights and biases in the neural network model; Step 4: Divide the data set: Divide the collected training data into a training set and a validation set in a ratio of 8:2; Step 5: Model training: Input the training set into the neural network model for training to obtain the trained neural network model; Step 6: Model Validation: Import the validation set data into the trained neural network model, obtain the plate texture type label number predicted by the model output, and calculate the error between the actual plate texture type label of the validation set and the predicted label; Step 7: Determine and adjust: Determine whether the error is within the preset error range. If so, stop training and output the trained neural network model. If not, adjust the weights and biases of the neural network model according to the error and return to step 5 to continue training. Step 8: Practical application: Use the trained neural network model to classify and identify the plate texture type in the detection area.

7. The automatic processing technology for non-standard plates according to claim 1 is characterized in that: The design optimization in the intelligent planning model dynamically adjusts the parameters of laser cutting power and punching speed by real-time analysis of the sheet material and equipment status.

8. The automatic processing technology for non-standard plates according to claim 1, characterized in that: Among them, path planning uses a multi-axis linkage algorithm based on reinforcement learning to optimize the cutting path and reduce idle strokes. The digital twin platform simulates the AGV transportation route, adjusts the path based on real-time order priorities, and implements path planning based on the input standard plate size. The fault prediction achieves full-dimensional monitoring of the equipment operation status by deploying high-precision sensors and industrial cameras. The LSTM-based time series analysis model predicts the remaining life of the equipment, associates historical maintenance records with real-time working conditions, and generates maintenance recommendations.

9. The automatic processing technology for non-standard plates according to claim 1, characterized in that: Data recording and analysis include: Data collection: record key data during the processing, including the time, energy consumption and scrap rate of sheet metal processing; Performance evaluation: Based on the collected data, the processing efficiency and product quality are evaluated.

10. The automatic processing technology for non-standard plates according to claim 1, characterized in that: The automatic processing is based on automatic loading of plates. The intelligent recognition system module is used to automatically select the processing method for the plates and cut the plates. During cutting, the depth and width of the intervals are processed according to the specific material of the plates, and the plates are automatically unloaded after processing.

Images