Robot post-processing method and equipment for automobile integrated die-casting parts

Abstract

The invention relates to the technical field of integrated die casting of automobile parts, in particular to a robot post-processing method for an integrated die-casting part of an automobile. Compared with the prior art, the technical scheme provided by the invention has the following beneficial effects: according to the method provided by the invention, the processing feature image of the integrated die-casting part is identified through the convolutional neural network learning model deployed in the vision measurement sensor, and mask processing is performed on the processing feature image; according to the method, on one hand, complicated manual teaching is avoided, and on the other hand, on the other hand, on the other hand, on the other hand, on the other hand, on the other hand, on the other hand, on the other hand, on the other hand, on the other hand, the working efficiency is improved; and on the other hand, the problem that a workpiece deformation track cannot be adjusted through traditional off-line programming is solved, and the accuracy and reliability of the machining track of each workpiece can be guaranteed.

Description

Technical Field

[0001] This invention relates to the field of integrated die-casting technology for automotive parts, specifically to a robotic post-processing method and equipment for integrated die-cast automotive parts. Background Technology

[0002] The large size and significant variations of integrated die-cast automotive parts present a major challenge for automated die-casting post-processing. On one hand, the front, bottom, and both sides of the product have deburring and grinding areas, resulting in numerous grinding points and a large grinding area. Traditional robotic teaching involves many manual teaching areas, which is time-consuming, labor-intensive, and results in low automation. On the other hand, die-cast parts are designed as thin-walled structures with large dimensional spans and significant deformation, potentially exceeding 5mm. Offline programming of robots based on part digital models is unsuitable. If offline programming trajectories are used, localized workpiece deformation can lead to incomplete machining or over-cutting, affecting processing quality and potentially damaging the workpiece.

[0003] Currently, the main method used for robotic post-processing of die-cast body-integrated parts is robotic deburring. Common methods include robot-manual teaching or offline programming. The main disadvantages of online robotic teaching for die-cast body-integrated parts are:

[0004] 1) The online programming teaching process is cumbersome and inefficient;

[0005] 2) The machining accuracy of the robot is entirely determined by the visual estimation of the teacher, and online programming teaching of complex paths is difficult to achieve satisfactory results;

[0006] 3) Accidents are prone to occur during the teaching process, ranging from minor damage to equipment to serious injuries to people. In addition, due to the inconsistent deformation of the integrated die-cast parts after each die-casting, the robot processing trajectory taught manually cannot be reused.

[0007] Offline programming of robots can overcome some of the shortcomings of manual teaching, but it cannot solve the deformation problem of integrated die-cast parts, and cannot guarantee that the offline programming trajectory can be applied to the post-processing of all die-cast parts. This problem will directly affect the processing quality of integrated die-cast parts by robot post-processing. Summary of the Invention

[0008] The purpose of this invention is to overcome the shortcomings of the prior art and solve the problems of programming efficiency and grinding trajectory quality of robotic automated grinding in the post-processing of automotive integrated die-cast parts. It proposes a method and equipment for robotic post-processing based on the combination of image recognition, 3D visual positioning and robot offline trajectory planning.

[0009] To achieve the above objectives, this invention provides a robotic post-processing method for integrated die-cast automotive parts, the specific steps of which are as follows:

[0010] S1. Obtain the transformation relationship between the coordinate systems of the vision measurement sensor, the industrial robot, and the end-effector grinding tool through the calibration matrix;

[0011] S2. The industrial robot adjusts the relative position of the vision sensor and the workpiece to be processed, and takes pictures of the processing area of ​​the integrated die-cast automotive parts at different positions through the vision measurement sensor to obtain the processing feature images of the corresponding areas.

[0012] S3. Label the above processing feature images to form an image dataset of part processing features, and build a convolutional neural network learning model for integrated die-casting part processing feature recognition. Train the image dataset and deploy the trained convolutional neural network learning model into the controller of the vision measurement sensor.

[0013] S4. The convolutional neural network learning model deployed in the vision measurement sensor identifies the processing feature images of the integrated die-cast parts, performs masking on the processing feature images, and extracts the features that need to be processed.

[0014] S5. Collect three-dimensional point cloud data of the surface of the integrated die-cast parts in the base coordinate system through a visual measurement sensor, and save it as a CSV or PCD format file. Process the three-dimensional point cloud data, fit the three-dimensional point cloud data with straight line, curve and surface features, and convert the fitted model into a CAD model and file.

[0015] S6. Map the relevant information of the two-dimensional image of the processing features of the integrated die-cast parts extracted by the convolutional neural network model with the CAD information of the integrated die-cast parts obtained by processing the three-dimensional point cloud data. By performing information matching between pixel points and feature points, the relevant information of the processing features of the integrated die-cast parts in the CAD model is obtained.

[0016] S7. Establish a workpiece coordinate system for robot machining on integrated die-cast automotive parts, and use the workpiece coordinate system as the reference coordinate system for robot machining;

[0017] S8. Obtain the pose information of machining features in the CAD model of integrated die-cast automotive parts in the robot coordinate system through the robot workpiece coordinate system;

[0018] S9. The machining features in the CAD model of integrated die-cast automotive parts are used to plan the robot's machining trajectory using the equidistant interpolation method;

[0019] S10. Generate a robot program script based on the robot's machining trajectory, perform offline simulation on the generated robot program, and after the offline simulation determines the machining trajectory, upload the machining trajectory to the robot controller to start the post-processing of automotive integrated die-cast parts.

[0020] Preferably, step S3 is as follows:

[0021] S31. The vision sensor acquires images of the processing feature areas on the surface of the integrated die-cast automotive parts, annotates the processing features, and establishes an image dataset of the parts' processing features;

[0022] S32. Convolutional neural network learning model for integrated die-casting parts processing feature recognition is constructed, including: input layer, convolutional layer, pooling layer and fully connected layer. The input layer is used to input image data; the convolutional layer is responsible for extracting the local features of each small part in the image to achieve preliminary feature extraction; the pooling layer is responsible for reducing the dimensionality of the feature map, reducing the features of the data, and achieving the extraction of the main features; the fully connected layer summarizes the features of each part, re-extracts the existing features of the data and outputs the results.

[0023] S33. The processing characteristics of integrated die-cast parts are trained and learned through a convolutional neural network learning model;

[0024] S34. Improve the training and testing sets of the processing feature images of integrated die-cast parts, and expand the dataset;

[0025] S35. Save the trained convolutional neural network learning model for recognizing the processing features of integrated die-cast parts;

[0026] S36. Call the trained convolutional neural network learning model for integrated die-casting parts processing feature recognition and perform relevant tests;

[0027] S37. Deploy the trained convolutional neural network learning model into the controller of the vision measurement sensor.

[0028] Preferably, step S4 is as follows:

[0029] S41. Extract the processing features of the integrated die-casting part as the region of interest. Use the pre-made processing features as a mask for the region of interest and multiply it with the image of the integrated die-casting part to be processed. The image values ​​of the processing features within the region of interest remain unchanged, while the image values ​​outside the region of interest are all 0.

[0030] S42. Use a mask to shield certain areas on the image of an integrated die-cast part so that they are not processed or not included in the calculation of processing parameters, or only the shielded area is processed or statistically analyzed.

[0031] S43. Use similarity variables or image matching methods to detect and extract structural features similar to the mask in images of integrated die-cast parts;

[0032] S44. Extract relevant data information on machining features from images of integrated die-cast parts.

[0033] The present invention also provides a computer device, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method according to any one of claims 1 to 3.

[0034] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 3.

[0035] Compared with the prior art, the technical solution proposed in this application has the following beneficial effects: The method of the present invention, by extracting two-dimensional images of the processing features of integrated die-cast parts from a visual measurement sensor and mapping and matching relevant information with the CAD model obtained from the three-dimensional point cloud, can obtain accurate trajectory information of the processing features of the workpiece. This method avoids tedious manual teaching on the one hand, and solves the problem that traditional offline programming cannot adjust the deformation trajectory of the workpiece on the other hand, thus ensuring the accuracy and reliability of the processing trajectory of each workpiece. The convolutional neural network model is used to learn the processing features in the workpiece image. On the one hand, it can solve the problem of large deformation of the workpiece processing features. On the other hand, through production, a dataset can be continuously accumulated. The model can be continuously trained and optimized on the dataset, which can further improve and optimize the robot processing trajectory. Through the positioning of the visual sensor and the workpiece coordinate system, it is ensured that the quality of the robot's post-processing is not affected by the inaccurate placement of the workpiece during the robot processing. Attached Figure Description

[0036] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0037] Figure 1 This is a flowchart illustrating the robotic post-processing method for integrated die-cast automotive parts according to the present invention.

[0038] Figure 2 This is a structural diagram of a computer device according to the present invention;

[0039] Figure 3 This is a schematic diagram of the structure of a computer-readable storage medium according to the present invention. Detailed Implementation

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described and discussed below with reference to the accompanying drawings. Obviously, what is described here is only a part of the examples of the present invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0041] It should be noted that when a component is described as "fixed to" another component, it can be directly on the other component or may have a component in between. When a component is considered "connected to" another component, it can be directly connected to the other component or may have a component in between. When a component is considered "set on" another component, it can be directly set on the other component or may have a component in between. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0043] Reference Figure 1 The hardware of the robotic post-processing system for integrated die-cast automotive parts mainly includes industrial robots, positioners, tooling fixtures, vision measurement sensors, and robot end effectors.

[0044] Industrial robots are responsible for executing the motion trajectory of integrated die-cast parts (workpieces) during post-processing. Positioners adjust the position and orientation of the integrated die-cast parts, working in conjunction with the industrial robot to achieve accessibility and flexibility in robotic processing. Fixtures hold the workpiece on the positioner, ensuring that the part's position does not shift due to excessive force during post-processing. Vision measurement sensors photograph the areas of the integrated die-cast parts that need processing, for learning the processing features. Furthermore, the vision measurement sensors generate 3D point cloud data, which is used to create a 3D geometric model of the workpiece. This model, along with the visually recognized processing features, generates the robot's motion trajectory. The robot's end effector is responsible for deburring or grinding the workpiece.

[0045] Methods for implementing robotic post-processing of integrated die-cast automotive parts:

[0046] 1) The vision measurement sensor is installed at the end of the industrial robot. First, the transformation relationship between the industrial robot and the tool coordinate system of the end-grinding tool is calibrated by the six-point calibration method. Then, the transformation relationship between the vision measurement sensor and the robot coordinate system is calibrated by the hand-eye calibration algorithm. The transformation relationship between the vision measurement sensor and the robot end-grinding tool coordinate system can be obtained through the above two calibration matrices.

[0047] 2) The industrial robot adjusts the relative position of the vision sensor and the workpiece, and takes pictures of the processing area of ​​the surface of the integrated die-cast automotive parts at different positions through the vision measurement sensor. This invention mainly targets the two typical features of the die-cast parts, namely the parting line flash and the ejector pin flash, for post-processing.

[0048] 3) The processing feature areas on the surface of integrated die-cast automotive parts acquired by the vision sensor are labeled (tagged) to form an image dataset of the parts' processing features. A convolutional neural network learning model for recognizing the processing features of integrated die-cast parts is built, trained on the dataset, and deployed to the controller of the vision measurement sensor. The specific implementation method is as follows:

[0049] ① Visual sensors acquire images of the processing feature areas on the surface of integrated die-cast automotive parts, and annotate (label) the processing features to establish an image dataset of the parts' processing features;

[0050] ② A convolutional neural network learning model for integrated die-casting parts processing feature recognition was constructed, including: an input layer, a convolutional layer, a pooling layer, and a fully connected layer. The input layer is used to input image data; the convolutional layer is responsible for extracting the local features of each small part of the image, achieving preliminary feature extraction; the pooling layer is responsible for reducing the dimensionality of the feature map, reducing the number of features in the data, and achieving the extraction of the main features; the fully connected layer summarizes the features of each part, re-extracts the existing features of the data, and outputs the results.

[0051] ③ The processing characteristics of integrated die-cast parts are trained and learned through a convolutional neural network learning model;

[0052] ④ Improve the training and testing sets of processing feature images for integrated die-cast parts, and expand the dataset;

[0053] ⑤ Save the trained convolutional neural network learning model for the integrated die-casting parts processing feature recognition;

[0054] ⑥ Call the trained convolutional neural network learning model for integrated die-casting parts processing feature recognition and conduct relevant tests;

[0055] ⑦ Deploy the trained convolutional neural network learning model into the controller of the vision measurement sensor.

[0056] 4) The convolutional neural network learning model deployed in the vision measurement sensor controller identifies the features of the area to be processed in the image of the integrated die-cast parts. The processing feature image is then masked to extract the features that need to be processed. The specific method is as follows:

[0057] ① Extract the processing features of the integrated die-cast parts as regions of interest: Use the pre-made processing features as a mask for the region of interest and multiply it with the image of the integrated die-cast parts to be processed. The image values ​​of the processing features within the region of interest remain unchanged, while the image values ​​outside the region of interest are all 0.

[0058] ② Use a mask to shield certain areas on the image of the integrated die-cast part so that they are not processed or not included in the calculation of processing parameters, or only the shielded area is processed or statistically analyzed;

[0059] ③ Use similarity variables or image matching methods to detect and extract structural features similar to the mask in images of integrated die-cast parts;

[0060] ④ Extract relevant data information on machining features from images of integrated die-cast parts;

[0061] 5) Collect 3D point cloud data of the integrated die-cast parts surface in the base coordinate system using a visual measurement sensor and save it as a CSV or PCD format file; process the 3D point cloud data by using optimized data structures and algorithms to achieve noise reduction, filtering and simplification of the 3D point cloud data; fit the 3D point cloud data to features such as lines, curves and surfaces; convert the fitted model into an STP format CAD model file.

[0062] 6) Map the relevant information of the two-dimensional image of the processing features of the integrated die-cast parts extracted by the convolutional neural network model with the CAD information of the integrated die-cast parts obtained by processing the three-dimensional point cloud data. By performing information matching between pixel points and feature points, the relevant information of the processing features of the integrated die-cast parts in the CAD model is obtained.

[0063] 7) Establish a workpiece coordinate system for robot machining on the integrated die-cast automotive parts, and use the workpiece coordinate system as the reference coordinate system for robot machining; if the workpiece position changes, the robot program that has shifted can be easily adjusted using the workpiece coordinate system.

[0064] 8) Obtain the pose information of the machining features in the CAD model of the integrated die-cast automotive parts in the robot coordinate system through the robot workpiece coordinate system;

[0065] 9) The machining features in the CAD model of integrated die-cast automotive parts are used to plan the robot's machining trajectory using the equidistant interpolation method.

[0066] 10) Generate a robot program script based on the robot's machining trajectory, and perform offline simulation on the generated robot program. After confirming the accuracy of the machining trajectory through offline simulation, upload the machining trajectory to the robot controller to realize the post-processing of automotive integrated die-cast parts.

[0067] Reference Figure 2 A device for multi-device linkage and remote control, comprising:

[0068] Memory, used to store computer programs;

[0069] The processor is used to execute computer programs to implement any of the multi-device linkage remote control methods described in Embodiments 3 and 4 above.

[0070] It is understood that various aspects of the technical solution of this application can be implemented as a system, method, or program product. Therefore, various aspects of the technical solution of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementation, which can be collectively referred to here as a "circuit", "module", or "platform".

[0071] The following reference Figure 2 The electronic device 600 implemented according to the embodiments of this example will be described in detail below. Figure 2 The electronic device 600 shown is merely an example and should not impose any limitation on the functionality and scope of use of any embodiment of the technical solution in this application.

[0072] like Figure 2 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0073] The storage unit stores program code, which can be executed by the processing unit 610, causing the processing unit 610 to perform the implementation steps described in the image stitching method area of ​​this embodiment. For example, the processing unit 610 can perform... Figure 1 The steps are shown in the figure.

[0074] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access unit (RAM) 6201 and / or cache storage unit 6202, and may further include read-only storage unit (ROM) 6203.

[0075] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each of these examples or some combination thereof may include an implementation of a network environment.

[0076] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, an image acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0077] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable user interaction with electronic device 600, and / or with any device that enables electronic device to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although... Figure 2 As not shown in the diagram, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0078] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any one of the multi-device linkage remote control methods described in the third and fourth embodiments above.

[0079] Figure 3 A schematic diagram of the structure of a computer-readable storage medium is shown according to some embodiments of this application. For example... Figure 3As shown, a program product 800 for implementing the above-described method according to an embodiment of the technical solution of this application is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. Of course, the program product generated according to this embodiment is not limited to this. In the technical solution of this application, the readable storage medium may be any tangible medium containing or storing a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0080] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] Computer-readable storage media may include data signals propagated in baseband or as a carrier wave region, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0082] Program code for executing the technical solutions of this application can be written in any combination of one or more programming languages. These programming languages ​​include object-oriented programming languages—such as Java and C++—and conventional procedural programming languages—such as C or similar languages. The program code can execute entirely on the user's computing device, locally on the user's device, as a standalone software package, locally on the user's computing device, locally on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0083] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, nor to combinations thereof. Those skilled in the art can make various changes, modifications, or combinations within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A robotic post-processing method for integrated die-cast automotive parts, characterized in that, The specific steps are as follows: S1. Obtain the transformation relationship between the coordinate systems of the vision measurement sensor, the industrial robot, and the end-effector grinding tool through the calibration matrix; S2. The industrial robot adjusts the relative position of the vision sensor and the workpiece to be processed, and takes pictures of the processing area of ​​the integrated die-cast automotive parts at different positions through the vision measurement sensor to obtain the processing feature images of the corresponding areas. S3. Label the above processing feature images to form an image dataset of part processing features, and build a convolutional neural network learning model for integrated die-casting part processing feature recognition. Train the image dataset and deploy the trained convolutional neural network learning model into the controller of the vision measurement sensor. S4. The convolutional neural network learning model deployed in the vision measurement sensor identifies the processing feature images of the integrated die-cast parts, performs masking on the processing feature images, and extracts the features that need to be processed. S5. Collect three-dimensional point cloud data of the surface of the integrated die-cast parts in the base coordinate system through a visual measurement sensor, and save it as a CSV or PCD format file. Process the three-dimensional point cloud data, fit the three-dimensional point cloud data with straight line, curve and surface features, and convert the fitted model into a CAD model and file. S6. Map the relevant information of the two-dimensional image of the processing features of the integrated die-cast parts extracted by the convolutional neural network model with the CAD information of the integrated die-cast parts obtained by processing the three-dimensional point cloud data. By performing information matching between pixel points and feature points, the relevant information of the processing features of the integrated die-cast parts in the CAD model is obtained. S7. Establish a workpiece coordinate system for robot machining on integrated die-cast automotive parts, and use the workpiece coordinate system as the reference coordinate system for robot machining; S8. Obtain the pose information of machining features in the CAD model of integrated die-cast automotive parts in the robot coordinate system through the robot workpiece coordinate system; S9. The machining features in the CAD model of integrated die-cast automotive parts are used to plan the robot's machining trajectory using the equidistant interpolation method; S10. Generate a robot program script based on the robot's machining trajectory, perform offline simulation on the generated robot program, and after the offline simulation determines the machining trajectory, upload the machining trajectory to the robot controller to start the post-processing of automotive integrated die-cast parts.

2. The robotic post-processing method for integrated die-cast automotive parts according to claim 1, characterized in that, Step S3 is as follows: S31. The vision sensor acquires images of the processing feature areas on the surface of the integrated die-cast automotive parts, annotates the processing features, and establishes an image dataset of the parts' processing features; S32. Convolutional neural network learning model for integrated die-casting parts processing feature recognition is constructed, including: input layer, convolutional layer, pooling layer and fully connected layer. The input layer is used to input image data; the convolutional layer is responsible for extracting the local features of each small part in the image to achieve preliminary feature extraction; the pooling layer is responsible for reducing the dimensionality of the feature map, reducing the features of the data, and achieving the extraction of the main features; the fully connected layer summarizes the features of each part, re-extracts the existing features of the data and outputs the results. S33. The processing characteristics of integrated die-cast parts are trained and learned through a convolutional neural network learning model; S34. Improve the training and testing sets of the processing feature images of integrated die-cast parts, and expand the dataset; S35. Save the trained convolutional neural network learning model for recognizing the processing features of integrated die-cast parts; S36. Call the trained convolutional neural network learning model for integrated die-casting parts processing feature recognition and perform relevant tests; S37. Deploy the trained convolutional neural network learning model into the controller of the vision measurement sensor.

3. The robotic post-processing method for integrated die-cast automotive parts according to claim 1, characterized in that, Step S4 is as follows: S41. Extract the processing features of the integrated die-casting part as the region of interest. Use the pre-made processing features as a mask for the region of interest and multiply it with the image of the integrated die-casting part to be processed. The image values ​​of the processing features within the region of interest remain unchanged, while the image values ​​outside the region of interest are all 0. S42. Use a mask to shield certain areas on the image of an integrated die-cast part so that they are not processed or not included in the calculation of processing parameters, or only the shielded area is processed or statistically analyzed. S43. Use similarity variables or image matching methods to detect and extract structural features similar to the mask in images of integrated die-cast parts; S44. Extract relevant data information on machining features from images of integrated die-cast parts.

4. A computer device, the computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 3.

Images