DXF file exporting method and system

Abstract

The invention provides a DXF file exporting method and system. The method comprises the steps that a three-dimensional drawing of a target metal plate product is obtained; inputting the target metal plate product three-dimensional drawing into a metal plate split part recognition model, and obtaining a corresponding target metal plate split part recognition result in the target metal plate product three-dimensional drawing output by the metal plate split part recognition model, the metal plate split part identification model is obtained by training a neural network model based on a sample metal plate product splitting drawing marked with a metal plate split part label; and obtaining a target DXF file according to the target sheet metal split part identification result, and importing the target DXF file into a target folder. The export efficiency and accuracy of the sheet metal DXF file are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent processing technology, and particularly to a method and system for exporting DXF files. Background Art

[0002] In the field of sheet metal drawing operations, efficiency improvement has always been the core concern of the industry's development. With the continuous growth of the manufacturing industry's demand for refined and efficient production, sheet metal drawing, as a key link connecting design and production, directly affects the entire production process with its work efficiency.

[0003] In the current sheet metal drawing industry, during the process of converting three-dimensional drawings to two-dimensional DXF (Drawing Exchange Format) files, it relies on manual unfolding of three-dimensional drawings one by one, and then based on the unfolded two-dimensional drawings, manually exports the corresponding DXF files of the sheet metal split parts in each part or component one by one. This process is not only cumbersome and highly repetitive, but also extremely prone to redundant actions, resulting in a relatively low overall drawing efficiency.

[0004] Therefore, there is an urgent need for a method and system for exporting DXF files to solve the above problems. Summary of the Invention

[0005] Aiming at the problems existing in the prior art, the present invention provides a method and system for exporting DXF files.

[0006] The present invention provides a method for exporting DXF files, including: Obtaining a three-dimensional drawing of a target sheet metal product; Inputting the three-dimensional drawing of the target sheet metal product into a sheet metal split part recognition model to obtain a recognition result of the target sheet metal split part corresponding to the three-dimensional drawing of the target sheet metal product output by the sheet metal split part recognition model, wherein the sheet metal split part recognition model is trained based on a sample sheet metal product split drawing marked with a sheet metal split part label for a neural network model; Obtaining a target DXF file according to the recognition result of the target sheet metal split part, and importing the target DXF file into a target folder.

[0007] According to a method for exporting DXF files provided by the present invention, the sheet metal split part recognition model is trained through the following steps: Obtaining a sample sheet metal product split drawing and sheet metal table data corresponding to the sample sheet metal product split drawing, wherein the corresponding relationship between the sheet metal table data and the sample sheet metal product split drawing is constructed based on sheet metal key parameters, and the sheet metal key parameters include sheet metal coding parameters, sheet metal material parameters, and sheet metal thickness parameters; the sample sheet metal product split drawing is a three-dimensional drawing corresponding to a sheet metal split part; Based on the key sheet metal parameters marked as sheet metal split parts in the sheet metal table data, mark the sheet metal split part labels in the corresponding sheet metal split part drawing area of the sample sheet metal product split drawing to obtain the first training sample set; Train the neural network model according to the first training sample set to obtain the sheet metal split part recognition model.

[0008] According to a DXF file export method provided by the present invention, the method further includes: Update the sheet metal split part recognition model according to the second training sample set to obtain an updated sheet metal split part recognition model, where the second training sample set is constructed based on a new sheet metal product split drawing and the sheet metal table data corresponding to the new sheet metal product split drawing.

[0009] According to a DXF file export method provided by the present invention, the obtaining the target DXF file according to the target sheet metal split part recognition result includes: Obtain the target sheet metal product split drawing corresponding to the target sheet metal split part recognition result, and unfold the target sheet metal product split drawing to obtain a design drawing DXF file, where the design drawing DXF file is the DXF file of the sheet metal two-dimensional drawing corresponding to the target sheet metal product split drawing; Judge whether there is a blank drawing area in the design drawing DXF file that meets the preset dimension information, where the blank drawing area is an area in the design drawing area of the design drawing DXF file where no graphic objects or annotations are drawn; If there is the blank drawing area, generate the two-dimensional code information corresponding to the design drawing DXF file according to the sheet metal coding parameters; Generate the file name information corresponding to the design drawing DXF file according to the sheet metal material parameters, the sheet metal coding parameters, and the sheet metal thickness parameters; Construct the target DXF file according to the design drawing DXF file, the two-dimensional code information, and the file name information.

[0010] According to a DXF file export method provided by the present invention, after obtaining the target DXF file according to the target sheet metal split part recognition result, the method further includes: Judge whether the target DXF file meets the industrial requirements based on the preset sheet metal split drawing. If not, generate a corresponding abnormal data prompt message; Receive a first input, where the first input includes the drawing modification instruction corresponding to the target DXF file constructed based on the abnormal data prompt message; In response to the first input, the target DXF file is modified in drawing design to obtain a modified target DXF file.

[0011] According to a DXF file export method provided by the present invention, the obtaining of the three-dimensional drawing of the target sheet metal product includes: Based on the drawing import interaction interface constructed by WinForm, the three-dimensional drawing of the target sheet metal product is obtained.

[0012] The present invention also provides a DXF file export system, including: An interaction module, configured to obtain the three-dimensional drawing of the target sheet metal product; A data processing module, configured to input the three-dimensional drawing of the target sheet metal product into a sheet metal split part recognition model, and obtain the corresponding target sheet metal split part recognition result in the three-dimensional drawing of the target sheet metal product output by the sheet metal split part recognition model. Wherein, the sheet metal split part recognition model is trained by a neural network model based on the sample sheet metal product split drawings marked with sheet metal split part labels; A file export module, configured to obtain a target DXF file according to the target sheet metal split part recognition result, and import the target DXF file into a target folder.

[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the DXF file export method described in any one of the above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the DXF file export method described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the DXF file export method described in any one of the above is implemented.

[0016] The DXF file export method and system provided by the present invention, through the sheet metal split part recognition model trained by a neural network model, identify the target sheet metal split part recognition result in the three-dimensional drawing of the target sheet metal product, and finally obtain the target DXF file according to the recognition result and import it into the target folder, thereby improving the export efficiency and accuracy of the sheet metal DXF file. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of the process of exporting a DXF file provided by the present invention; Figure 2 A schematic diagram of the overall process of the DXF file export method provided by the present invention; Figure 3 A schematic diagram of the structure of the DXF file export system provided by the present invention; Figure 4 This is a schematic structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0020] Currently, the conventional method for converting sheet metal 3D drawings into DXF files is for operators to open the drawings using SolidWorks software, use its sheet metal unfolding function to flatten the 3D model until it is facing the export surface, and then manually convert the format and export the DXF format file, and save it to a predetermined folder. Due to the diverse types and large number of sheet metal parts, they can only be exported in sequence, and the progress of the operation must be monitored at all times. The large number of repetitive operations and redundant actions in this process limits the overall drawing efficiency. In addition, it is difficult for manual operation to maintain consistent concentration. Repeated export operations for a long time are prone to fatigue and lack of concentration, resulting in problems such as inaccurate lines and missing marking lines in the exported DXF files during subsequent processing; or setting an incorrect save path will cause confusion in the file save location. Once the erroneous drawings flow into subsequent links, it will lead to material waste, production delays and increased costs.

[0021] In view of the problems existing in the above-mentioned prior art, the present invention provides a method for exporting DXF files, constructs a corresponding macro program based on this method, uses a Winform window to select the target sheet metal product three-dimensional drawing of the DXF file of the sheet metal split parts to be exported, and then realizes the automatic batch export of DXF files after determining the folder for saving the DXF files. In the present invention, the macro program constructed based on the DXF file export method automatically opens the three-dimensional drawing and unfolds it into the corresponding two-dimensional drawing, and then exports the required DXF files, and can automatically select appropriate points in the engineering sketch corresponding to the exported DXF files to generate two-dimensional codes for the subsequent sheet metal processing links, and finally save them as target DXF files to complete the drawing work, thereby greatly shortening the drawing time of the sheet metal drawing operation and greatly improving the drawing efficiency.

[0022] Figure 1 It is a schematic flow chart of the DXF file export method provided by the present invention. As Figure 1 shown, the present invention provides a method for exporting DXF files, including: Step 101, obtain the three-dimensional drawing of the target sheet metal product.

[0023] In the present invention, the three-dimensional drawing of the target sheet metal product can be obtained from sources such as design software, design files, or product databases. The three-dimensional drawing of the sheet metal product contains all the geometric information of the sheet metal product, such as shape, size, and positional relationship.

[0024] In sheet metal processing, since sheet metal split parts are usually processed from flat materials (such as metal plates), it is necessary to unfold the sheet metal split parts in the three-dimensional drawing into a flat shape for subsequent cutting, bending, and other processing operations. Specifically, the unfolding operation takes into account factors such as the bending radius, bending angle, and material thickness of the sheet metal part, and uses a specific algorithm or software tool (such as using the sheet metal unfolding function in SolidWorks) to accurately unfold the sheet metal split parts in the three-dimensional drawing into a two-dimensional flat shape, and each sheet metal split part will correspond to a two-dimensional drawing.

[0025] Step 102, input the three-dimensional drawing of the target sheet metal product into the sheet metal split part recognition model to obtain the recognition result of the target sheet metal split part corresponding to the three-dimensional drawing of the target sheet metal product output by the sheet metal split part recognition model, where the sheet metal split part recognition model is obtained by training a neural network model based on the sample sheet metal product split drawings marked with sheet metal split part labels.

[0026] In the present invention, after obtaining the three-dimensional drawing of the target sheet metal product, the three-dimensional drawing of the target sheet metal product is input into a sheet metal part recognition model, which is used to recognize each sheet metal part in the three-dimensional drawing of the target sheet metal product. In the present invention, a sheet metal part is the smallest processing part in a sheet metal product. After obtaining these sheet metal parts through sheet metal processing, the corresponding sheet metal product can be assembled using these sheet metal parts.

[0027] In the present invention, after processing the input three-dimensional drawing of the target sheet metal product, the sheet metal part recognition model outputs the recognition results of the target sheet metal parts. These recognition results of the target sheet metal parts specifically indicate the corresponding sheet metal parts in the three-dimensional drawing of the target sheet metal product, and may include information such as the position, shape, and size of the parts. In the present invention, the sheet metal part recognition model is trained using a large number of sample sheet metal product disassembly drawings, and these sample sheet metal product disassembly drawings are all marked, that is, each part is clearly labeled. Using these marked data, through the training of the neural network model, the neural network model can learn how to accurately recognize and disassemble sheet metal parts.

[0028] Step 103: Obtain the target DXF file according to the recognition results of the target sheet metal parts, and import the target DXF file into the target folder.

[0029] In the present invention, through the sheet metal part recognition model, the recognition results of the parts in the three-dimensional drawing of the target sheet metal product are obtained. These recognition results of the parts contain specific information about each sheet metal part, such as position, shape, and size. Further, based on these recognition results of the parts, each part is separately extracted from the three-dimensional drawing of the target sheet metal product, and then the three-dimensional drawing of each part is unfolded into the corresponding two-dimensional drawing, and is sorted and saved according to the requirements of the DXF file format. In the present invention, the process of exporting the DXF file of a sheet metal part involves operations such as cropping, scaling, and rotating the drawing to ensure that each part can be presented in the correct proportion and position in the DXF file. At the same time, the relevant attribute information of the part, such as material type, thickness, and processing requirements, will also be retained, so that these information can be accurately understood and used in the subsequent production and processing process.

[0030] Finally, through the above steps, a series of target DXF files corresponding one by one to the parts in the three-dimensional drawing of the target sheet metal product can be obtained. These files can be directly used for the processing and manufacturing of sheet metal parts, improving production efficiency and accuracy.

[0031] The DXF file export method provided by the present invention uses a sheet metal part recognition model trained by a neural network model to identify the target sheet metal part recognition result in the 3D drawing of the target sheet metal product. Finally, the target DXF file is obtained according to the recognition result and imported into the target folder, thereby improving the export efficiency and accuracy of the sheet metal DXF file.

[0032] Based on the above embodiment, the sheet metal part recognition model is trained through the following steps: Obtain the sample sheet metal product split drawing and the sheet metal table data corresponding to the sample sheet metal product split drawing. Among them, the correspondence between the sheet metal table data and the sample sheet metal product split drawing is constructed based on the sheet metal key parameters, and the sheet metal key parameters include sheet metal coding parameters, sheet metal material parameters, and sheet metal thickness parameters; the sample sheet metal product split drawing is the 3D drawing corresponding to the sheet metal part. Based on the sheet metal key parameters marked as sheet metal parts in the sheet metal table data, mark the sheet metal part labels in the corresponding sheet metal part drawing area of the sample sheet metal product split drawing to obtain the first training sample set. According to the first training sample set, train the neural network model to obtain the sheet metal part recognition model.

[0033] In the present invention, first, a series of 3D drawings of sample sheet metal products (i.e., sample sheet metal product split drawings) need to be collected, and these drawings need to match the corresponding sheet metal table data, which contains key information related to the sheet metal parts in the drawings. In the present invention, the correspondence between the sample sheet metal product split drawing and the sheet metal table data is established through a series of key parameters, including the coding, material, and thickness of the sheet metal parts, which can be used to identify and distinguish different sheet metal parts.

[0034] Then, according to the marked sheet metal part information in the sheet metal table data, find the positions of these parts on the corresponding sample sheet metal product split drawing and label them, thereby obtaining a set of labeled training samples, that is, the first training sample set. Finally, by inputting these labeled samples into the neural network model, the neural network model can learn how to identify and label sheet metal parts according to the features in the 3D drawing. After training, the neural network model can perform part recognition on new and unseen sheet metal drawings to obtain the required sheet metal part recognition model.

[0035] Based on the above embodiment, the method further includes: Update the sheet metal part splitting recognition model according to the second training sample set to obtain an updated sheet metal part splitting recognition model, where the second training sample set is constructed based on new sheet metal product splitting drawings and the sheet metal table data corresponding to the new sheet metal product splitting drawings.

[0036] In the present invention, in order to improve or adjust the performance of the sheet metal part splitting recognition model to adapt to new sheet metal product designs, new training data (i.e., the second training sample set) needs to be used to retrain or fine-tune the model, thereby improving the recognition accuracy and increasing the model's ability to recognize new types of sheet metal parts.

[0037] Similar to the first training sample set, the second training sample set is also composed of corresponding sheet metal product splitting drawings and corresponding sheet metal table data. The difference is that these data are based on new sheet metal products, that is, products that the previous model has never seen or learned, and these new drawings and data reflect the latest changes in sheet metal design or newly added sheet metal part types.

[0038] Finally, use this second training sample set to train or fine-tune the existing sheet metal part splitting recognition model to obtain an updated model. This updated model will be able to better recognize and process new sheet metal product drawings, improving the recognition accuracy and efficiency.

[0039] Based on the above embodiments, the obtaining of the target DXF file according to the target sheet metal part splitting recognition result includes: Obtain the target sheet metal product splitting drawing corresponding to the target sheet metal part splitting recognition result, and unfold the target sheet metal product splitting drawing to obtain a design drawing DXF file, where the design drawing DXF file is the DXF file of the sheet metal two-dimensional drawing corresponding to the target sheet metal product splitting drawing; Determine whether there is a blank drawing area in the design drawing DXF file that meets the preset dimension information, where the blank drawing area is an area within the design drawing area of the design drawing DXF file where no graphic objects or annotations are drawn; If there is such a blank drawing area, generate two-dimensional code information corresponding to the design drawing DXF file according to the sheet metal coding parameters; Generate file name information corresponding to the design drawing DXF file according to the sheet metal material parameters, the sheet metal coding parameters, and the sheet metal thickness parameters; Construct the target DXF file according to the design drawing DXF file, the two-dimensional code information, and the file name information.

[0040] In the present invention, the target sheet metal product disassembly drawings corresponding to the target sheet metal disassembly part recognition results are obtained, and these target sheet metal product disassembly drawings are unfolded into two-dimensional drawings, and then these two-dimensional drawings are saved as design drawing DXF files. Further, by calculating the distance between the relevant points (i.e., a certain point corresponding to the blank drawing area in the design drawing, and a QR code is generated under the condition of meeting the preset dimension information) and the surrounding design sketch area (i.e., the design drawing area), it is compared whether the QR code dimension requirement (i.e., the preset dimension information) is met. After determining that the point meets the conditions, then using the existing QR code generation library, the encoding parameters corresponding to the current design drawing are converted into QR code information. In the present invention, the blank drawing area refers to the area in the design drawing DXF file where no graphic objects or annotations are drawn, and the present invention can judge whether there is such a blank area according to the preset dimension information.

[0041] Moreover, in the present invention, the generated QR code information can be directly embedded in the specified position (i.e., the blank drawing area) of the exported DXF file; at the same time, according to the sheet metal material parameters, sheet metal coding parameters, and sheet metal thickness parameters, the file name information corresponding to the exported design drawing DXF file is generated, which is convenient for subsequent sheet metal informatization processing traceability and management, and realizes the rapid identification and reading of drawing information.

[0042] On the basis of the above embodiments, after obtaining the target DXF file according to the target sheet metal disassembly part recognition result, the method further includes: Judging whether the target DXF file meets the preset sheet metal disassembly industrial requirements, if not, generating a corresponding abnormal data prompt message; Receiving a first input, where the first input includes a drawing modification instruction corresponding to the target DXF file constructed based on the abnormal data prompt message; In response to the first input, performing drawing design modification on the target DXF file to obtain a modified target DXF file.

[0043] In the present invention, anti-fool detection rules for sheet metal drawings are pre-constructed and analyzed in combination with the recognized sheet metal disassembly part recognition results, so as to comprehensively detect the drawing data and quickly identify abnormal data that does not conform to the rules. Once a problematic drawing is detected, the problematic drawing is singled out and placed in a specific folder for display with a special identifier, which is convenient for the user side to quickly locate and modify, so as to ensure the drawing quality and avoid losses caused by incorrect drawings.

[0044] Specifically, in the present invention, the generated target DXF file is checked according to pre-set sheet metal drawing industrial standards or specifications. These standards or specifications include aspects such as the dimensional accuracy of the drawing, the integrity of graphic objects, product design requirements, and annotation clarity, which can be obtained from the application requirements or design requirements of sheet metal products in the early stage.

[0045] When the target DXF file does not meet the pre-set sheet metal drawing industrial requirements, an abnormal data prompt message is automatically generated, including specific error descriptions, error locations, and suggested modification methods, etc., so that the user side can quickly locate the problem and handle it.

[0046] In the present invention, after receiving the abnormal data prompt message, the user side constructs drawing modification instructions according to this information. These instructions include operations such as adding, deleting, and modifying graphic objects or annotations, aiming to make the target DXF file meet the pre-set sheet metal drawing industrial requirements. Finally, after receiving the drawing modification instructions from the user side, the target DXF file is automatically modified accordingly to ensure that the modified target DXF file meets the pre-set sheet metal drawing industrial requirements.

[0047] Based on the above embodiments, the obtaining of the three-dimensional drawing of the target sheet metal product includes: Obtaining the three-dimensional drawing of the target sheet metal product through a drawing import interaction interface constructed based on WinForm.

[0048] In the present invention, a drawing import interaction interface is constructed using a WinForm window. The drawing import interaction interface is provided with a file export start button and a file selection button. After importing the three-dimensional drawing of the target sheet metal product into the interaction interface and setting the corresponding file saving path, subsequent DXF files can be quickly executed.

[0049] Figure 2 For the overall flow diagram of the DXF file export method provided by the present invention, reference can be made to Figure 2 As shown, in the present invention, first, through the drawing import interaction interface, the saving paths of the sheet metal file (used to save three-dimensional drawings and two-dimensional drawings) and the DXF file are set, and after classifying these files, based on the operation process of the user side, the three-dimensional drawings that need to be exported as sheet metal split parts this time are determined (if not selected, it is default to perform subsequent operations on all three-dimensional drawings imported this time).

[0050] Further, open each sheet metal 3D drawing in sequence, and through the unfolding operation, select the geometric surfaces that need to be exported currently. Then, through the anti-fool detection mechanism constructed by the present invention, detect the engineering sketches. If there are abnormal situations in the detection results, close the current sheet metal 3D drawing, generate corresponding prompt information, and process the next sheet metal 3D drawing; if the detection results meet the requirements, generate corresponding QR code information for this engineering sketch, and then save this engineering sketch as a DXF file. After determining that all the geometric surfaces that need to be exported in the current sheet metal 3D drawing have been exported, execute the DXF file export step in the next sheet metal 3D drawing.

[0051] The present invention can parse the internal data of the selected sheet metal 3D drawing file based on the SolidWorks secondary development interface, filter out the effective data related to sheet metal, and reorganize and arrange it according to the data organization specification of the DXF file, accurately identify and select the DXF files of the sheet metal split parts that need to be exported, and open the 2D drawings in sequence to identify the relevant annotations and custom attributes of the sheet metal split parts for anti-fool detection, greatly improving the export efficiency of the DXF file and reducing the drawing error rate.

[0052] Next, the DXF file export system provided by the present invention will be described. The DXF file export system described below can be correspondingly referred to the DXF file export method described above.

[0053] Figure 3 is a schematic structural diagram of the DXF file export system provided by the present invention. As Figure 3 shown, the present invention provides a DXF file export system, including an interaction module 301, a data processing module 302, and a file export module 303. Among them, the interaction module 301 is used to obtain the 3D drawing of the target sheet metal product; the data processing module 302 is used to input the 3D drawing of the target sheet metal product into the sheet metal split part recognition model to obtain the corresponding target sheet metal split part recognition result output by the sheet metal split part recognition model. The sheet metal split part recognition model is trained by a neural network model based on the sample sheet metal product split drawings marked with sheet metal split part labels; the file export module 303 is used to obtain the target DXF file according to the target sheet metal split part recognition result and import the target DXF file into the target folder.

[0054] The DXF file export system provided by the present invention uses a sheet metal split part recognition model trained by a neural network model to identify the target sheet metal split part recognition result in the 3D drawing of the target sheet metal product, and finally obtains the target DXF file according to the recognition result and imports it into the target folder, thereby improving the export efficiency and accuracy of the sheet metal DXF file.

[0055] The system provided by the embodiment of the present invention is used to execute the above-mentioned method embodiments. For the specific process and detailed content, please refer to the above embodiments and will not be elaborated here.

[0056] Figure 4 It is a schematic structural diagram of the electronic device provided by the present invention. As Figure 4 shown, the electronic device may include: a processor (Processor) 401, a communication interface (Communications Interface) 402, a memory (Memory) 403, and a communication bus 404. Among them, the processor 401, the communication interface 402, and the memory 403 complete mutual communication through the communication bus 404. The processor 401 can call the logical instructions in the memory 403 to execute the DXF file export method, and the method includes: obtaining a three-dimensional drawing of a target sheet metal product; inputting the three-dimensional drawing of the target sheet metal product into a sheet metal split part recognition model to obtain a target sheet metal split part recognition result corresponding to the three-dimensional drawing of the target sheet metal product output by the sheet metal split part recognition model, wherein the sheet metal split part recognition model is obtained by training a neural network model based on a sample sheet metal product split drawing marked with a sheet metal split part label; obtaining a target DXF file according to the target sheet metal split part recognition result, and importing the target DXF file into a target folder.

[0057] In addition, when the logical instructions in the above-mentioned memory 403 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0058] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the DXF file export method provided by each of the above methods. The method includes: obtaining a three-dimensional drawing of a target sheet metal product; inputting the three-dimensional drawing of the target sheet metal product into a sheet metal split part recognition model to obtain a corresponding target sheet metal split part recognition result in the three-dimensional drawing of the target sheet metal product output by the sheet metal split part recognition model. Among them, the sheet metal split part recognition model is obtained by training a neural network model based on a sample sheet metal product split drawing marked with a sheet metal split part label; according to the target sheet metal split part recognition result, obtaining a target DXF file and importing the target DXF file into a target folder.

[0059] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the DXF file export method provided by each of the above embodiments. The method includes: obtaining a three-dimensional drawing of a target sheet metal product; inputting the three-dimensional drawing of the target sheet metal product into a sheet metal split part recognition model to obtain a corresponding target sheet metal split part recognition result in the three-dimensional drawing of the target sheet metal product output by the sheet metal split part recognition model. Among them, the sheet metal split part recognition model is obtained by training a neural network model based on a sample sheet metal product split drawing marked with a sheet metal split part label; according to the target sheet metal split part recognition result, obtaining a target DXF file and importing the target DXF file into a target folder.

[0060] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0061] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for exporting DXF files, characterized in that, Including: Obtain the 3D drawing of the target sheet metal product; Input the 3D drawing of the target sheet metal product into the sheet metal split part recognition model to obtain the corresponding target sheet metal split part recognition result output by the sheet metal split part recognition model. Among them, the sheet metal split part recognition model is trained based on the sample sheet metal product split drawings marked with sheet metal split part labels for the neural network model; According to the target sheet metal split part recognition result, obtain the target DXF file and import the target DXF file into the target folder.

2. The DXF file export method according to claim 1, characterized in that, The sheet metal split part recognition model is trained through the following steps: Obtain the sample sheet metal product split drawings and the corresponding sheet metal table data of the sample sheet metal product split drawings. Among them, the correspondence between the sheet metal table data and the sample sheet metal product split drawings is constructed based on the sheet metal key parameters. The sheet metal key parameters include sheet metal coding parameters, sheet metal material parameters, and sheet metal thickness parameters; the sample sheet metal product split drawings are the 3D drawings corresponding to the sheet metal split parts; Based on the sheet metal key parameters marked as sheet metal split parts in the sheet metal table data, mark the sheet metal split part labels in the corresponding sheet metal split part drawing area of the sample sheet metal product split drawings to obtain the first training sample set; According to the first training sample set, train the neural network model to obtain the sheet metal split part recognition model.

3. The DXF file export method according to claim 2, wherein The method further includes: According to the second training sample set, update the sheet metal split part recognition model to obtain the updated sheet metal split part recognition model. Among them, the second training sample set is constructed based on the new sheet metal product split drawings and the corresponding sheet metal table data of the new sheet metal product split drawings.

4. The DXF file export method according to claim 2, wherein The obtaining the target DXF file according to the target sheet metal split part recognition result includes: Obtain the target sheet metal product split drawings corresponding to the target sheet metal split part recognition result and unfold the target sheet metal product split drawings to obtain the design drawing DXF file. Among them, the design drawing DXF file is the DXF file of the sheet metal 2D drawing corresponding to the target sheet metal product split drawings; Judge whether there is a blank drawing area that meets the preset dimension information in the design drawing DXF file. Among them, the blank drawing area is the area in the design drawing area of the design drawing DXF file where no graphic objects or annotations are drawn; If there is the blank drawing area, generate the QR code information corresponding to the design drawing DXF file according to the sheet metal coding parameters; Generate the file name information corresponding to the design drawing DXF file according to the sheet metal material parameters, the sheet metal coding parameters, and the sheet metal thickness parameters; Construct the target DXF file according to the design drawing DXF file, the QR code information, and the file name information.

5. The DXF file export method according to claim 1, characterized in that After obtaining the target DXF file according to the target sheet metal split part recognition result, the method further includes: Determine whether the target DXF file meets the industrial requirements for preset sheet metal drawing disassembly. If not, generate corresponding abnormal data prompt information; Receive a first input, where the first input includes a drawing modification instruction corresponding to the target DXF file constructed based on the abnormal data prompt information; In response to the first input, modify the drawing design of the target DXF file to obtain a modified target DXF file.

6. The DXF file export method according to claim 1, wherein The obtaining of the three-dimensional drawing of the target sheet metal product includes: Based on the drawing import interaction interface constructed by WinForm, obtain the three-dimensional drawing of the target sheet metal product.

7. A DXF file export system, characterized in that, It includes: An interaction module for obtaining the three-dimensional drawing of the target sheet metal product; A data processing module for inputting the three-dimensional drawing of the target sheet metal product into a sheet metal disassembly part recognition model to obtain a target sheet metal disassembly part recognition result corresponding to the three-dimensional drawing of the target sheet metal product output by the sheet metal disassembly part recognition model, where the sheet metal disassembly part recognition model is trained by a neural network model based on the sample sheet metal product disassembly drawings marked with sheet metal disassembly part labels; A file export module for obtaining a target DXF file according to the target sheet metal disassembly part recognition result and importing the target DXF file into a target folder.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the DXF file export method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the DXF file export method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the DXF file export method according to any one of claims 1 to 6.

Images