Thin-walled parts processing method, device, electronic equipment and storage medium

Abstract

The present invention discloses a method, device, electronic equipment and storage medium for processing thin-walled parts, and relates to the technical field of parts processing. The method comprises: performing rough processing and rough milling on a target thin-walled part to obtain a semi-finished part; obtaining image information of the semi-finished part; determining current size information of the semi-finished part based on the image information; obtaining target size information of the target thin-walled part; determining finishing data information of the semi-finished part based on the current size information and the target size information; and performing finish milling on the semi-finished part based on the finish data information to obtain a finished part. The present invention solves the technical problem of low processing precision of thin-walled parts in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of parts processing, and in particular to a processing method, device, electronic equipment and storage medium for thin-walled parts. Background Art

[0002] In the field of parts processing, thin-walled parts are widely used in various equipment due to their compact structure, light weight, and special performance. However, thin-walled parts have low rigidity and weak strength. During processing, they are difficult to clamp. The vibration and cutting heat generated during cutting can easily cause thin-walled parts to deform. This affects the dimensional accuracy and shape precision of the workpiece, which is also the difficulty in processing thin-walled parts.

[0003] Existing methods utilize specialized vacuum suction cups to clamp thin-walled parts for mass production. However, thermal expansion can cause the part to arch between two solid rods or between the suction cup holes, affecting part precision. Therefore, real-time monitoring of part status is necessary during thin-walled part processing.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, electronic equipment, and storage medium for processing thin-walled parts, so as to at least solve the technical problem of low processing precision of thin-walled parts in the prior art.

[0006] According to one aspect of an embodiment of the present invention, a method for processing thin-walled parts is provided, comprising: performing rough processing and rough milling on a target thin-walled part to obtain a semi-finished part; obtaining image information of the semi-finished part; determining current size information of the semi-finished part based on the image information; obtaining target size information of the target thin-walled part; determining finishing data information of the semi-finished part based on the current size information and the target size information; and performing finish milling on the semi-finished part based on the finish data information to obtain a finished part.

[0007] Furthermore, based on the image information, the current size information of the semi-finished part is determined, including: preprocessing the image information to obtain preprocessed image information; based on the preprocessed image information, determining the current size information; wherein the preprocessing includes at least one of the following: Gaussian filtering, gradient, non-maximum suppression and double threshold processing.

[0008] Furthermore, based on the preprocessed image information, the current size information is determined, including: performing edge recognition processing on the preprocessed image information based on a preset target neural network to obtain an edge recognition processing result; and determining the current size information based on the edge recognition processing result.

[0009] Furthermore, based on a preset target neural network, edge recognition processing is performed on the pre-processed image information. Before obtaining the edge recognition processing result, it includes: obtaining a sample image and an initial neural network, wherein the initial neural network includes at least one of the following: an initial image encoding module and an initial image decoding module; processing the sample image based on the initial neural network to obtain an initial processed image; determining a deviation value between the initial processed image and the sample image, and performing a first preset processing on the initial neural network based on the deviation value to generate a first-stage neural network, wherein the first-stage neural network includes at least a first image encoding module; obtaining a preset image decoding module, and generating a second-stage neural network based on the preset image decoding module and the first image encoding module; obtaining image label information corresponding to the sample image, and constructing an objective function based on the sample image and the image label information; performing a second preset processing on the second-stage neural network based on the objective function to generate a preset target neural network.

[0010] Furthermore, the target thin-walled part is subjected to rough processing and rough milling to obtain a semi-finished part, including the following steps: rough processing the target thin-walled part; placing the rough-processed target thin-walled part on a vacuum suction cup, and rough milling the target thin-walled part to obtain a semi-finished part.

[0011] Furthermore, based on the finishing data information, the semi-finished parts are finish-milled, including: obtaining sensor information of the target device; generating target action instructions based on the finishing data information and the sensor information, and the target action instructions are used to control the target device to finish-mill the semi-finished parts.

[0012] According to another aspect of an embodiment of the present invention, a processing device for thin-walled parts is also provided, including: a first processing module, the first processing module is used to perform rough processing and rough milling on the target thin-walled part to obtain a semi-finished part; a first acquisition module, the first acquisition module is used to obtain image information of the semi-finished part; a first determination module, the first determination module is used to determine the current size information of the semi-finished part based on the image information; a second acquisition module, the second acquisition module is used to obtain the target size information of the target thin-walled part; a second determination module, the second determination module is used to determine the finishing data information of the semi-finished part based on the current size information and the target size information; and a second processing module, the second processing module is used to perform finish milling on the semi-finished part based on the finish data information to obtain a finished part.

[0013] According to another aspect of an embodiment of the present invention, an electronic device is provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention when running.

[0014] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0017] According to another aspect of the embodiments of the present invention, a computer program is provided. When the computer program is executed by a processor, the methods in various embodiments of the present invention are implemented.

[0018] In an embodiment of the present invention, after rough processing and rough milling are performed on the target thin-walled part to obtain a semi-finished part, the current size of the semi-finished part is determined through a real-time image of the semi-finished part, and the fine processing data is determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the processing accuracy of the part, and thus solving the technical problem of low processing accuracy of thin-walled parts in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1 It is a flow chart of a method for processing thin-walled parts according to the prior art;

[0021] Figure 2 is a schematic structural diagram of a thin-walled parts processing device according to an embodiment of the present invention;

[0022] Figure 3 yes Figure 2 Cross-sectional view at AA in the middle;

[0023] Figure 4 The present invention is a structural diagram of a thin-walled parts processing device according to the prior art.

[0024] The above drawings include the following reference numerals:

[0025] 10. Vacuum suction cup;

[0026] 20. Sensor;

[0027] 41. First processing module;

[0028] 42. First acquisition module;

[0029] 43. First determination module;

[0030] 44. Second acquisition module;

[0031] 45. Second determination module;

[0032] 46. ​​The second processing module. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] According to an embodiment of the present invention, an embodiment of a method for processing thin-walled parts is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] Figure 1 is a method according to an embodiment of the present invention, such as Figure 1 As shown, the method includes the following steps:

[0037] Step S100 , performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part.

[0038] In step S100, excess material on the part is removed by rough machining and rough milling to quickly form the basic shape of the part in order to improve machining efficiency.

[0039] Step S200: Acquire image information of the semi-finished part.

[0040] In step S200 , a high-precision imaging device (such as an industrial camera or a laser scanner) is used to acquire images of the semi-finished part so that these images can be used for subsequent dimensional measurement and analysis.

[0041] Step S300: determining the current size information of the semi-finished part based on the image information.

[0042] In S300 , the current size information of the semi-finished part includes but is not limited to key dimensions such as length, width, height, and aperture.

[0043] Step S400: obtaining target size information of a target thin-walled part.

[0044] In step S400, the target size information of the target thin-walled part will be used as a basis for subsequent finishing.

[0045] Step S500: Determine finishing data information of the semi-finished part based on the current size information and the target size information.

[0046] In step S500, the area and amount of processing required for further processing are calculated based on the current size information and target size information obtained in steps S300 and S400 to ensure that the processed parts can meet the design requirements.

[0047] Step S600: Based on the finishing data information, the semi-finished part is finish-milled to obtain the finished part.

[0048] In step S600, the semi-finished part is further processed using fine milling equipment and tools based on the finishing data calculated in step S500, removing excess material to achieve the required dimensional accuracy and surface quality. After fine milling, the part's dimensions meet the design requirements, but before it can be completed, it may require further post-processing, such as deburring, cleaning, and inspection, to ensure part quality.

[0049] Through the above steps, after the target thin-walled part is rough-machined and roughly milled to obtain a semi-finished part, the current size of the semi-finished part can be determined through the real-time image of the semi-finished part, and the finishing data can be determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the processing accuracy of the part, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0050] In this embodiment, the status of the semi-finished parts can be monitored during the fine processing process, and fine processing can be performed according to the status of the parts, thereby improving the stability of the thin-walled parts during processing, ensuring the accuracy of the processed thin-walled parts, and achieving better results in subsequent use. In addition, the downtime adjustment time caused by unstable processing is reduced, so that the overall processing efficiency is improved and the waste of raw materials and the cost of reworking scrap are reduced.

[0051] As an optional embodiment, determining the current size information of the semi-finished part based on the image information includes:

[0052] Step S310 , preprocessing the image information to obtain preprocessed image information, wherein the preprocessing includes at least one of the following: Gaussian filtering, gradient processing, non-maximum suppression, and double threshold processing.

[0053] In step S310, the image information may be three-dimensional image information, and the three-dimensional image is input into the model to implement preprocessing of the three-dimensional image. In a specific embodiment of the present application, the preprocessing includes Gaussian filtering, gradient processing, non-maximum suppression, and double threshold processing performed in sequence to extract useful features such as edges and contours from the three-dimensional image to provide input data for subsequent image analysis or machine learning models.

[0054] Step S320, determining current size information based on the pre-processed image information;

[0055] Through the above steps, the image information is preprocessed so that the current size information obtained subsequently is more accurate, thereby improving the processing accuracy of the target thin-walled parts.

[0056] Furthermore, based on the pre-processed image information, current size information is determined, including:

[0057] Step S321 : Based on a preset target neural network, edge recognition processing is performed on the pre-processed image information to obtain an edge recognition processing result.

[0058] In step S321, the pre-processed image is fed into a pre-set neural network, which outputs information about the locations of edges in the image. The output of the neural network is typically an edge map that highlights the edges in the image. This result can be used to determine the size of the image.

[0059] Step S322: Determine the current size information based on the edge recognition processing result.

[0060] In step S322, after edge recognition results are obtained, these edges need to be analyzed to determine the dimensions of objects or features in the image (including finding continuous edge segments and measuring their lengths). Determining dimensional information involves geometric analysis, such as using line, curve, or shape recognition algorithms to measure the width, height, depth, and so on of an object. In some cases, it may be necessary to calibrate the measurement results with reference to known dimensional standards or ratios. After determining the dimensional information, calibration and verification steps are required to ensure the accuracy of the measurement results. Finally, the determined dimensional information is output, which can be in the form of numerical data, charts, or annotations superimposed on the original image.

[0061] Through the above steps, the current size information of the semi-finished part is determined more accurately, so as to facilitate the subsequent processing of the semi-finished part.

[0062] Furthermore, based on the preset target neural network, edge recognition processing is performed on the pre-processed image information, and before obtaining the edge recognition processing result, the method includes:

[0063] Step S311: Acquire a sample image and an initial neural network, wherein the initial neural network includes at least one of the following: an initial image encoding module and an initial image decoding module.

[0064] In step S311, the initial neural network can be any neural network model architecture that can perform edge recognition, such as an image reconstruction model or an image restoration model. In a specific embodiment of the present application, the initial neural network includes an image encoding module and an image decoding module. The image encoding module may include multiple convolutional layers and multiple pooling layers, and the multiple convolutional layers and the multiple pooling layers may be distributed alternately, such as the first convolutional layer (such as convolution kernel size: 9x9, number of channels: 3, corresponding to the three channels R, G, and B of the image), the first pooling layer (such as pooling size: 3x3), the second convolutional layer (such as convolution kernel size: 9x9, number of channels: 144), the second pooling layer (such as pooling size: 3x3), etc. The image decoding module includes multiple upsampling layers and multiple convolutional layers, and the multiple upsampling layers and the multiple convolutional layers can be arranged alternately, such as the first upsampling layer (e.g., upsampling size: 2x2), the first convolutional layer (e.g., convolution kernel size: 3x3, number of channels: 288), the second upsampling layer (e.g., upsampling size: 2x2), the second convolutional layer (e.g., convolution kernel size: 3x3, number of channels: 144), etc. The output of the pooling layer of the image encoding module is connected to the input of the upsampling layer of the image decoding module.

[0065] Step S312: Process the sample image based on the initial neural network to obtain an initial processed image.

[0066] Step S312 is performed so that the initial neural network can be optimized based on the deviation value between the initial processed image and the sample image.

[0067] Step S313, determining the deviation value between the initial processed image and the sample image, and performing a first preset processing on the initial neural network based on the deviation value to generate a first stage neural network, which includes at least a first image encoding module.

[0068] In step S313, unsupervised network optimization processing is performed on the initial neural network based on the deviation value to generate a first-stage neural network.

[0069] Step S314: Obtain a preset image decoding module, and generate a second-stage neural network based on the preset image decoding module and the first image encoding module.

[0070] In step S314, the preset image decoding module and the first image encoding module are combined to construct a second-stage neural network. The preset image decoding module includes multiple upsampling layers and multiple convolutional layers, and the multiple upsampling layers and the multiple convolutional layers can be arranged alternately. In the preset image decoding module, an output layer is connected after the last convolutional layer, and the output layer can include a convolution kernel and an activation function such as a sigmoid. In this way, the output layer can generate an edge probability value (such as a probability value of 0-1) for each pixel in the corresponding image. Then, the pixels whose edge probability values ​​exceed the preset probability value can be regarded as the edges of the corresponding thin-walled parts. The specific value of the preset probability value can be configured according to actual needs, for example, 0.6, 0.7, etc.

[0071] Step S315 : Obtain image label information corresponding to the sample image, and construct an objective function based on the sample image and the image label information.

[0072] In step S315 , image label information corresponding to the sample image is obtained; the image label information indicates the edge points of the thin-walled part, and an objective function (loss function), such as mean square error, is constructed based on the sample image and the image label information corresponding to the sample image.

[0073] Step S316: Perform a second preset processing on the second stage neural network based on the objective function to generate a preset target neural network.

[0074] In step S316, the second-stage neural network is subjected to supervised network optimization processing based on the objective function to generate a preset target neural network so as to obtain the current size information of the semi-finished part by marginalizing the image information through the preset target neural network.

[0075] Through the above steps, a trained preset target neural network is obtained to improve the dimensional accuracy of the semi-finished parts during the edge processing and improve the processing accuracy.

[0076] Furthermore, rough machining and rough milling are performed on the target thin-walled part to obtain a semi-finished part, including the following steps:

[0077] Step S010: performing rough machining on the target thin-walled part.

[0078] In step S010, the target thin-walled part is rough-machined to bring its shape closer to the final design. The main purpose of this step is to remove excess material and prepare for subsequent processing. Rough machining includes but is not limited to milling operations.

[0079] In step S020 , the rough-machined target thin-walled part is placed on a vacuum chuck, and rough milling is performed on the target thin-walled part to obtain a semi-finished part.

[0080] In step S020, the thin-walled part to be machined is placed on a vacuum suction cup to protect it from damage during subsequent machining and improve machining accuracy. The vacuum cup absorbs vibrations, reduces noise during machining, and improves part stability. Next, the thin-walled part undergoes rough milling, bringing the target thin-walled part's shape closer to the final design. The primary purpose of rough milling is to remove as much material as possible to prepare for subsequent finishing.

[0081] Furthermore, based on the finishing data information, the semi-finished part is finished by finishing milling, including:

[0082] Step S610: Acquire sensor information of the target device.

[0083] In step S620, the sensor information of the target device may be fed back in real time.

[0084] Step S620: generating a target motion instruction based on the finishing data information and the sensor information, wherein the target motion instruction is used to control the target device to perform finish milling on the semi-finished part.

[0085] In step S620, the fine milling process is performed on the thin-walled part according to the data information to be fine-milled. The fine milling process includes a movable milling mechanism and a carrier for the thin-walled part. The carrier's bottom contacts an adjustment bolt to enable up and down movement. The carrier is also provided with transverse and longitudinal slots for lateral and longitudinal movement. The carrier's movable arrangement allows the milling mechanism to more closely fit the thin-walled part on the carrier during machining. The movable milling mechanism is equipped with a fan-shaped piezoelectric ceramic and a vibrator. The vibrator has two rows of fan-shaped slots and a milling cutter head at its bottom. The fan-shaped piezoelectric ceramic installed in the upper row of fan-shaped slots induces bending vibration, while the fan-shaped piezoelectric ceramic installed in the lower row of fan-shaped slots induces longitudinal vibration. The longitudinal and bending vibrations combine to generate elliptical ultrasonic vibrations on the surface of the milling cutter head, milling the thin-walled part. Ultrasonic elliptical vibration machining is a type of intermittent milling process that effectively reduces the temperature rise of the thin-walled part and the cutter head, ensuring machining quality and producing high-precision thin-walled parts.

[0086] Combine Figures 2 to 3 As shown, a plurality of sensors 20 are provided on the vacuum suction cup 10, and the sensors 20 are distributed in a dot matrix. During the fine milling process, high-precision sensors are used in conjunction with the vacuum suction cup 10 to collect signals. The signal frequency is generated by the signal acquisition board, and the signal frequency is communicated with the HMI interactive screen through the RS232 protocol to form a vertical displacement curve of the semi-finished part. Different switching signals are output according to the vibration amplitude of the curve to communicate with the numerical control system NC, thereby realizing precise control of the milling process.

[0087] Through the above steps, the status of semi-finished parts can be monitored, and fine processing can be performed according to the status of the parts, thereby improving the stability of thin-walled parts during processing, ensuring the accuracy of the processed thin-walled parts, and achieving better results in subsequent use. In addition, the downtime adjustment time caused by unstable processing is reduced, thereby improving the overall processing efficiency and reducing the waste of raw materials and the cost of reworking scrap.

[0088] Combine Figure 4 As shown, according to an embodiment of the present invention, an embodiment of a processing device for thin-walled parts is provided. It should be noted that the device can be used to execute the processing methods of thin-walled parts in the above embodiments.

[0089] Specifically, the processing device for thin-walled parts includes: a first processing module 41, a first acquisition module 42, a first determination module 43, a second acquisition module 44, a second determination module 45 and a second processing module 46. The first processing module 41 is used to perform rough processing and rough milling on the target thin-walled part to obtain a semi-finished part; the first acquisition module 42 is used to obtain image information of the semi-finished part; the first determination module 43 is used to determine the current size information of the semi-finished part based on the image information; the second acquisition module 44 is used to obtain the target size information of the target thin-walled part; the second determination module 45 is used to determine the finishing data information of the semi-finished part based on the current size information and the target size information; the second processing module 46 is used to perform finish milling on the semi-finished part based on the finish data information to obtain a finished part.

[0090] By adopting this processing device, after rough processing and rough milling of the target thin-walled part to obtain the semi-finished part, the current size of the semi-finished part is determined through the real-time image of the semi-finished part, and the finishing data is determined based on the current size and the target size of the target thin-walled part, thereby realizing fine processing of the target thin-walled part, improving the processing accuracy of the part, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0091] The present application also provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein when the program is running, the method of each embodiment of the present invention is executed. The method comprises the following steps:

[0092] Step S100 , performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part.

[0093] Step S200: Acquire image information of the semi-finished part.

[0094] Step S300: determining the current size information of the semi-finished part based on the image information.

[0095] Step S400: obtaining target size information of a target thin-walled part.

[0096] Step S500: Determine finishing data information of the semi-finished part based on the current size information and the target size information.

[0097] Step S600: Based on the finishing data information, the semi-finished part is finish-milled to obtain the finished part.

[0098] Through the above steps, after the target thin-walled part is rough-machined and rough-milled to obtain a semi-finished part, the current size of the semi-finished part is determined through a real-time image of the semi-finished part, and the finishing data is determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the part processing accuracy, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0099] The embodiments of the present application further provide a computer-readable storage medium, which includes a stored executable program. When the executable program is executed, the device containing the computer-readable storage medium is controlled to execute the methods of various embodiments of the present invention. The method includes the following steps:

[0100] Step S100 , performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part.

[0101] Step S200: Acquire image information of the semi-finished part.

[0102] Step S300: determining the current size information of the semi-finished part based on the image information.

[0103] Step S400: obtaining target size information of a target thin-walled part.

[0104] Step S500: Determine finishing data information of the semi-finished part based on the current size information and the target size information.

[0105] Step S600: Based on the finishing data information, the semi-finished part is finish-milled to obtain the finished part.

[0106] Through the above steps, after the target thin-walled part is rough-machined and rough-milled to obtain a semi-finished part, the current size of the semi-finished part is determined through a real-time image of the semi-finished part, and the finishing data is determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the part processing accuracy, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0107] The embodiments of the present application further provide a computer program product, including a computer program, which, when executed by a processor, implements the methods of various embodiments of the present invention. The method includes the following steps:

[0108] Step S100 , performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part.

[0109] Step S200: Acquire image information of the semi-finished part.

[0110] Step S300: determining the current size information of the semi-finished part based on the image information.

[0111] Step S400: obtaining target size information of a target thin-walled part.

[0112] Step S500: Determine finishing data information of the semi-finished part based on the current size information and the target size information.

[0113] Step S600: Based on the finishing data information, the semi-finished part is finish-milled to obtain the finished part.

[0114] Through the above steps, after the target thin-walled part is rough-machined and rough-milled to obtain a semi-finished part, the current size of the semi-finished part is determined through a real-time image of the semi-finished part, and the finishing data is determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the part processing accuracy, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0115] The present application also provides a computer program product including a non-volatile computer-readable storage medium for storing a computer program. When the computer program is executed by a processor, the method according to various embodiments of the present invention is implemented. The method includes the following steps:

[0116] Step S100 , performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part.

[0117] Step S200: Acquire image information of the semi-finished part.

[0118] Step S300: determining the current size information of the semi-finished part based on the image information.

[0119] Step S400: obtaining target size information of a target thin-walled part.

[0120] Step S500: Determine finishing data information of the semi-finished part based on the current size information and the target size information.

[0121] Step S600: Based on the finishing data information, the semi-finished part is finish-milled to obtain the finished part.

[0122] Through the above steps, after the target thin-walled part is rough-machined and rough-milled to obtain a semi-finished part, the current size of the semi-finished part is determined through a real-time image of the semi-finished part, and the finishing data is determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the part processing accuracy, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0123] The embodiments of the present application further provide a computer program that, when executed by a processor, implements the methods described in the various embodiments of the present invention. The method comprises the following steps:

[0124] Step S100 , performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part.

[0125] Step S200: Acquire image information of the semi-finished part.

[0126] Step S300: determining the current size information of the semi-finished part based on the image information.

[0127] Step S400: obtaining target size information of a target thin-walled part.

[0128] Step S500: Determine finishing data information of the semi-finished part based on the current size information and the target size information.

[0129] Step S600: Based on the finishing data information, the semi-finished part is finish-milled to obtain the finished part.

[0130] Through the above steps, after the target thin-walled part is rough-machined and rough-milled to obtain a semi-finished part, the current size of the semi-finished part is determined through a real-time image of the semi-finished part, and the finishing data is determined based on the current size and the target size of the target thin-walled part, thereby achieving fine processing of the target thin-walled part, improving the part processing accuracy, and thus solving the technical problem of low processing accuracy of thin-walled parts in the existing technology.

[0131] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0133] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0134] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0135] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0136] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for processing thin-walled parts, characterized in that: include: Step S1, performing rough machining and rough milling on the target thin-walled part to obtain a semi-finished part; Step S2, obtaining image information of the semi-finished part; Step S3: determining the current size information of the semi-finished part based on the image information; Step S3 further includes: Step S31: preprocessing the image information to obtain preprocessed image information, wherein the preprocessing includes at least one of the following: Gaussian filtering, gradient processing, non-maximum suppression, and double threshold processing; Step S32: determining the current size information based on the pre-processed image information; Step S32 further includes: Step S321: performing edge recognition processing on the pre-processed image information based on a preset target neural network to obtain an edge recognition processing result; Step S322: determining the current size information based on the edge recognition processing result; Step S4, obtaining target size information of the target thin-walled part; Step S5: determining finishing data information of the semi-finished part based on the current size information and the target size information; Step S6: Based on the finishing data information, the semi-finished part is fine-milled to obtain a finished part; Before executing step S321, the method further includes: Acquiring a sample image and an initial neural network, wherein the initial neural network includes at least one of the following: an initial image encoding module and an initial image decoding module, wherein the initial image encoding module includes a plurality of convolutional layers and a plurality of pooling layers, and the plurality of convolutional layers and the plurality of pooling layers are alternately arranged, and the initial image decoding module includes a plurality of upsampling layers and a plurality of convolutional layers, and the plurality of upsampling layers and the plurality of convolutional layers are alternately arranged; Processing the sample image based on the initial neural network to obtain an initial processed image; Determining a deviation value between the initial processed image and the sample image, and performing a first preset processing on the initial neural network based on the deviation value to generate a first-stage neural network, wherein the first-stage neural network includes at least a first image encoding module; Obtaining a preset image decoding module, and generating a second-stage neural network based on the preset image decoding module and the first image encoding module; Obtaining image label information corresponding to the sample image, and constructing an objective function based on the sample image and the image label information; The second-stage neural network is subjected to a second preset processing based on the objective function to generate a preset target neural network.

2. The method according to claim 1, characterized in that The target thin-walled part is subjected to rough machining and rough milling to obtain the semi-finished part, comprising the following steps: Rough machining of target thin-walled parts; The target thin-walled part after rough machining is placed on a vacuum suction cup, and the target thin-walled part is subjected to rough milling to obtain the semi-finished part.

3. The method according to claim 1, characterized in that Based on the finishing data information, finishing milling the semi-finished part includes: Get sensor information of the target device; Based on the finishing data information and the sensor information, a target action instruction is generated, and the target action instruction is used to control the target device to perform finish milling on the semi-finished part.

4. A processing device for thin-walled parts, characterized in that: The processing device is processed by the method according to any one of claims 1 to 3, comprising: A first processing module, wherein the first processing module is used to perform rough processing and rough milling on the target thin-walled part to obtain a semi-finished part; A first acquisition module, the first acquisition module is used to acquire image information of the semi-finished part; a first determining module, configured to determine current size information of the semi-finished part based on the image information; a second acquisition module, the second acquisition module being used to acquire target size information of the target thin-walled part; a second determining module, configured to determine finishing data information of the semi-finished part based on the current size information and the target size information; The second processing module is used to perform fine milling on the semi-finished part based on the fine processing data information to obtain a finished part.

5. An electronic device, characterized in that: include: a memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 3 when running.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 3.

7. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 3.

Images