3D printing process feedback optimization method and system based on visual inspection

Abstract

According to the 3D printing process feedback optimization method and system based on visual inspection, part machining image data of all stages in the 3D printing process are collected on the basis of the visual inspection technology, an image basis is provided for further detection of parts, and the 3D printing process feedback optimization method and system based on standard machining data are obtained on the basis of the image processing technology. Part processing image data is analyzed to obtain printing defect data, real-time monitoring and analysis of processed parts are achieved, adjustment parameters of initial printing process data are determined based on the incidence relation between the printing defect data and the printing process data, analysis of printing defects and deviation based on monitoring data is achieved, adjustment data are provided, and the processing precision is improved. And the adjustment parameters are input into the feedback control device to automatically control parameter adjustment in the 3D printing process, dynamic optimization control is achieved based on automatic adjustment of the printing parameters, and according to the scheme, the printing precision and quality are improved, manual intervention is reduced, and the method is suitable for precise manufacturing of complex parts.

Description

Technical Field

[0001] The present invention relates to the field of 3D printing technology, and in particular to a 3D printing process feedback optimization method and system based on visual inspection. Background Art

[0002] With the rapid development of the manufacturing industry, the demand for high-precision, complex structural parts is also growing. For example, in the fields of aerospace, automotive, medical, electronics and mold manufacturing, there are high-precision requirements for parts. However, due to the limitations of traditional manufacturing methods in certain aspects, such as complex structures, material utilization, and production cycles, there are certain limitations on the precision manufacturing of complex parts.

[0003] The core value of 3D printing of complex parts lies in breaking through the geometric limitations of traditional manufacturing and achieving the unity of "design freedom" and "manufacturing freedom". Its application has moved from prototype manufacturing to direct production, becoming a key enabling technology in high-end equipment manufacturing, precision medicine, green manufacturing and other fields.

[0004] However, in the process of 3D printing complex parts, how to combine image detection technology to accurately control production process data is a key link in achieving high-precision production based on 3D printing. Summary of the Invention

[0005] The present invention provides a 3D printing process feedback optimization method and system based on visual inspection, which are used to solve the problems raised in the background technology.

[0006] A 3D printing process feedback optimization method based on visual inspection, comprising:

[0007] S1: Based on visual inspection technology, it collects image data of parts processing at various stages of the 3D printing process;

[0008] S2: Based on the standard part image data and combined with image processing technology, the part processing image data is analyzed to obtain printing defect data;

[0009] S3: Determining adjustment parameters for the initial printing process data based on the correlation between the printing defect data and the printing process data;

[0010] S4: Inputting the adjustment parameters into a feedback control device to automatically control the adjustment of the parameters during the 3D printing process.

[0011] Preferably, in S1, based on visual inspection technology, collecting part processing image data at various stages of the 3D printing process includes:

[0012] Set up visual inspection devices at various stages of the 3D printing process;

[0013] Collect image data of parts processing at each stage based on visual inspection equipment;

[0014] Transmit the parts processing image data to the server.

[0015] Preferably, in S2, based on the standard part image data, combined with image processing technology, the part processing image data is analyzed to obtain printing defect data, including:

[0016] The part processing image data is sequentially subjected to grayscale conversion, noise reduction and contrast enhancement processing to obtain a pre-processed image;

[0017] Based on the position information of the pre-processed image, the pre-processed image is fused to obtain a comprehensive part processing image;

[0018] Perform contour and texture feature extraction on the overall part processing image to obtain contour features and texture features;

[0019] Compare the standard contour features and standard texture features of the standard part image data with the contour features and texture features respectively to obtain contour differences and texture differences;

[0020] Printing defect data is obtained based on the contour difference and the texture difference.

[0021] Preferably, after obtaining the printing defect data, the method further includes:

[0022] Firstly, the printing defect data is divided according to each stage of the 3D printing process to obtain stage defect data, and stage batch defect data of all processed parts in each stage are obtained from the stage defect data;

[0023] Obtain a single contour difference from the stage batch defect data to establish a contour difference sequence; obtain a single texture difference from the stage batch defect data to establish a texture difference sequence;

[0024] Determining a first processing deviation based on an average contour difference of all single contour differences, determining a second processing deviation based on an average texture difference of all single texture differences, and determining a processing deviation trend based on sequence trends of the contour difference sequence and the texture difference sequence;

[0025] Determine the comprehensive machining part deviation at each stage based on the first machining deviation, the second machining deviation and the machining deviation trend;

[0026] Perform a second division based on the defect data of each part in all stages during the 3D printing process to obtain the defect data of each processed part in all stages;

[0027] Based on the defect data of all stages of the part, the defect cumulative characteristics of the processed part are determined, and each extreme defect is marked to obtain the defect marking cumulative characteristics;

[0028] Based on the neural network model, the accumulated features of the defect marks are learned to determine the impact features of the differences in the previous stage on the processing of the next stage in adjacent stages. Based on the impact features of all stages, the deviations of the processed parts caused by the processing sequence that can be eliminated are determined;

[0029] Print defect data is supplemented based on the comprehensive processing part deviations at each stage and the removable deviations of the processed parts due to the processing sequence.

[0030] Preferably, the printing defect data is supplemented based on the comprehensive processing part deviations at each stage and the removable deviations of the processed parts caused by the processing sequence, including:

[0031] Add comprehensive processing part deviations and removable deviations to print defect data;

[0032] The difference between the comprehensive processing part deviation and the eliminateable deviation is taken as the part deviation to be eliminated and added to the printing defect data.

[0033] Preferably, in S3, determining adjustment parameters for the initial printing process data based on the association between the printing defect data and the printing process data includes:

[0034] Eliminating the initial contour features and initial texture features based on the print defect data and the deviation of the part to be eliminated to obtain target contour features and target texture features, and obtaining defect types corresponding to the target contour features and target texture features;

[0035] Calculating a correlation value between each defect type and each 3D printing device printing process data, and sorting the printing process data based on the correlation value to determine a correlation sequence between the defect type and the plurality of printing process data;

[0036] Acquire printing process data with a correlation value greater than a preset value from the correlation sequence as initial operation data related to the defect type;

[0037] Acquire historical operation data and historical defect data related to the initial operation data, learn the linear relationship between the historical operation data and the historical defect data based on a machine model, and construct a defect association recognition model;

[0038] Based on the defect correlation recognition model and combined with the correlation sequence, a secondary correlation analysis is performed on the printing defect data and the printing process data to obtain the target operation data related to the printing defect data, and determine the degree of difference between the target operation data and the standard operation data;

[0039] An adjustment parameter for the target operating data is determined based on the degree of difference.

[0040] Preferably, based on the defect correlation recognition model and in combination with the related sequence, a secondary correlation analysis is performed on the printing defect data and the printing process data to obtain target operation data related to the printing defect data, including:

[0041] determining an operational data type of the initial operational data associated with the defect type based on the correlation sequence;

[0042] The association relationship between the defect data corresponding to the defect type and the initial operation data is identified based on the defect association recognition model, and the target operation data related to the printing defect data is obtained based on the association relationship.

[0043] Preferably, obtaining the defect type corresponding to the target contour feature and the target texture feature includes:

[0044] Comparing the target contour features and target texture features with standard contour features and standard texture features of standard part image data to obtain difference contour features and difference texture features;

[0045] The defect type corresponding to the difference contour feature and the difference texture feature is obtained from the defect type feature library.

[0046] Preferably, in S4, inputting the adjustment parameters into a feedback control device to automatically control the adjustment of the parameters during the 3D printing process includes:

[0047] automatically inputting the adjustment parameters into a feedback control device;

[0048] The feedback control device automatically generates an adjustment strategy based on the adjustment parameters to automatically control the adjustment of the parameters during the 3D printing process.

[0049] A 3D printing process feedback optimization system based on visual inspection, comprising:

[0050] Data acquisition module, used to collect part processing image data at various stages of the 3D printing process based on visual inspection technology;

[0051] The data analysis module is used to analyze the part processing image data based on the standard part image data and combine it with image processing technology to obtain printing defect data;

[0052] a parameter determination module, configured to determine adjustment parameters for the initial printing process data based on an association between the printing defect data and the printing process data;

[0053] The parameter adjustment module is used to input the adjustment parameters into the feedback control device to automatically control the adjustment of the parameters during the 3D printing process.

[0054] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0055] Based on visual inspection technology, the image data of part processing at each stage of the 3D printing process is collected to provide an image basis for further inspection of the parts. Based on standard processing data and combined with image processing technology, the part processing image data is analyzed to obtain printing defect data, thereby realizing real-time monitoring and analysis of processed parts, and providing a basis for feedback optimization of the 3D printing process. Based on the correlation between printing defect data and printing process data, the adjustment parameters of the initial printing process data are determined, and analysis of printing defects and deviations based on monitoring data is realized, and adjustment data is provided. The adjustment parameters are input into the feedback control device to automatically control the adjustment of parameters in the 3D printing process. Based on the automatic adjustment of printing parameters, dynamic optimization control is realized. This solution improves printing accuracy and quality, reduces manual intervention, and is suitable for the precision manufacturing of complex parts.

[0056] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 Flowchart of a 3D printing process feedback optimization method based on visual inspection in an embodiment of the present invention;

[0060] Figure 2 A flowchart of obtaining printing defect data in an embodiment of the present invention;

[0061] Figure 3 This is a structural diagram of a 3D printing process feedback optimization system based on visual inspection in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0063] Example 1:

[0064] The embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection, such as Figure 1 Shown, including:

[0065] S1: Based on visual inspection technology, it collects image data of parts processing at various stages of the 3D printing process;

[0066] S2: Based on the standard part image data and combined with image processing technology, the part processing image data is analyzed to obtain printing defect data;

[0067] S3: Determining adjustment parameters for the initial printing process data based on the correlation between the printing defect data and the printing process data;

[0068] S4: Inputting the adjustment parameters into a feedback control device to automatically control the adjustment of the parameters during the 3D printing process.

[0069] In this embodiment, each stage of the 3D printing process is determined according to the structure of the complex part to be processed, and the processing level and the manufacturing process of each layer are determined.

[0070] In this embodiment, the visual detection technology is, for example, camera detection, laser scanning detection, etc.

[0071] In this embodiment, standard part image data and data such as the size and shape of the part when the part is qualified, each stage corresponds to a set of standard part image data.

[0072] In this embodiment, one stage includes a plurality of parts processing image data, which are data of various orientations.

[0073] In this embodiment, the image processing technology includes, for example, image preprocessing, image comparison and other operations.

[0074] In this embodiment, the printing defect data includes, for example, protrusions, depressions, and size deviations.

[0075] In this embodiment, the correlation between the printing defect data and the printing process data is, for example, that the size deviation is related to the printing distance in the printing process data, and the protrusions and depressions are related to the temperature and air pressure in the printing process data.

[0076] In this embodiment, the feedback control device is pre-installed in the 3D printing device to achieve automatic feedback adjustment of the 3D printing process.

[0077] The beneficial effects of the above design scheme are: based on visual inspection technology, the part processing image data at each stage of the 3D printing process is collected to provide an image basis for further inspection of the parts; based on standard processing data, combined with image processing technology, the part processing image data is analyzed to obtain printing defect data, and real-time monitoring and analysis of the processed parts are achieved, providing a basis for feedback optimization of the 3D printing process; based on the correlation between printing defect data and printing process data, the adjustment parameters of the initial printing process data are determined, and analysis of printing defects and deviations based on monitoring data is achieved, and adjustment data is provided. The adjustment parameters are input into the feedback control device to automatically control the adjustment of parameters in the 3D printing process; based on the automatic adjustment of printing parameters, dynamic optimization control is achieved. This scheme improves printing accuracy and quality, reduces manual intervention, and is suitable for the precision manufacturing of complex parts.

[0078] Example 2:

[0079] Based on Example 1, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection. In S1, based on visual inspection technology, part processing image data at various stages of the 3D printing process is collected, including:

[0080] Set up visual inspection devices at various stages of the 3D printing process;

[0081] Collect image data of parts processing at each stage based on visual inspection equipment;

[0082] Transmit the parts processing image data to the server.

[0083] In this embodiment, the time for collecting the image data of the part processing at each stage by the visual inspection device is flexibly set according to specific circumstances.

[0084] The beneficial effect of the above design scheme is: by setting up a visual inspection device at each stage of the 3D printing process, collecting the part processing image data at each stage based on the visual inspection device, and transmitting the part processing image data to the server, the collection and acquisition of the part processing image data is realized, providing an image basis for further inspection of the parts.

[0085] Example 3:

[0086] Based on Example 1, the present invention provides a 3D printing process feedback optimization method based on visual inspection, such as Figure 2 As shown, in S2, based on the standard part image data, combined with image processing technology, the part processing image data is analyzed to obtain printing defect data, including:

[0087] The part processing image data is sequentially subjected to grayscale conversion, noise reduction and contrast enhancement processing to obtain a pre-processed image;

[0088] Based on the position information of the pre-processed image, the pre-processed image is fused to obtain a comprehensive part processing image;

[0089] Perform contour and texture feature extraction on the overall part processing image to obtain contour features and texture features;

[0090] The standard contour features and standard texture features of the standard part image data are compared with the contour features and texture features respectively to obtain contour differences and texture differences, and printing defect data is obtained based on the contour differences and texture differences.

[0091] In this embodiment, each stage corresponds to a set of printing defect data.

[0092] In this embodiment, image fusion is performed on the pre-processed images to obtain a comprehensive part processing image, which enriches the data information of the part processing image and makes the obtained comprehensive part processing image have all-round features.

[0093] The beneficial effects of the above design scheme are: by extracting the contour and texture features of the comprehensive part processing image, the contour features and texture features are obtained, and the standard contour features and standard texture features of the standard part image data are compared with the contour features and texture features respectively to obtain contour differences and texture differences. Based on the contour differences and texture differences, printing defect data is obtained, and real-time monitoring and analysis of the processed parts are realized, providing a basis for feedback optimization of the 3D printing process.

[0094] Example 4:

[0095] Based on Example 1, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection, which, after obtaining printing defect data, further includes:

[0096] Firstly, the printing defect data is divided according to each stage of the 3D printing process to obtain stage defect data, and stage batch defect data of all processed parts in each stage are obtained from the stage defect data;

[0097] Obtain a single contour difference from the stage batch defect data to establish a contour difference sequence; obtain a single texture difference from the stage batch defect data to establish a texture difference sequence;

[0098] Determining a first processing deviation based on an average contour difference of all single contour differences, determining a second processing deviation based on an average texture difference of all single texture differences, and determining a processing deviation trend based on sequence trends of the contour difference sequence and the texture difference sequence;

[0099] Determine the comprehensive machining part deviation at each stage based on the first machining deviation, the second machining deviation and the machining deviation trend;

[0100] Perform a second division based on the defect data of each part in all stages during the 3D printing process to obtain the defect data of each processed part in all stages;

[0101] Based on the defect data of all stages of the part, the defect cumulative characteristics of the processed part are determined, and each extreme defect is marked to obtain the defect marking cumulative characteristics;

[0102] Based on the neural network model, the accumulated features of the defect marks are learned to determine the impact features of the differences in the previous stage on the processing of the next stage in adjacent stages. Based on the impact features of all stages, the deviations of the processed parts caused by the processing sequence that can be eliminated are determined;

[0103] Print defect data is supplemented based on the comprehensive processing part deviations at each stage and the removable deviations of the processed parts due to the processing sequence.

[0104] In this embodiment, the deviation that can be eliminated is the deviation of the current process caused by the deviation of the previous process. Adjusting the deviation of the previous process can eliminate the deviation of the current process.

[0105] In this embodiment, the first processing deviation is a deviation of size, area, etc. related to the contour, and the second processing deviation is a deviation of cracks, porosity, etc. related to the texture.

[0106] In this embodiment, the defect cumulative feature is the defect feature accumulated from defects in each stage.

[0107] In this embodiment, the processing deviation trend is the deviation direction of the equipment's processing of the part as time increases, for example, as time increases, the leftward offset increases.

[0108] In this embodiment, based on the neural network model, the defect mark cumulative features are learned to pre-establish the difference data before and after the neural network model learning, as well as the stage processing features, to obtain the law of the influence characteristics of the previous stage difference on the next stage processing.

[0109] The beneficial effects of the above design scheme are: by obtaining a single contour difference from the stage batch defect data, a contour difference sequence is established; by obtaining a single texture difference from the stage batch defect data, a texture difference sequence is established; a second division is performed according to the defect data of each part in all stages during the 3D printing process, and the full-stage defect data of each processed part is obtained; the defect characteristics are processed and analyzed from two aspects: the horizontal stage processing situation and the vertical full processing process of a processed part; finally, the printing defect data is supplemented based on the comprehensive processing part deviation of each stage and the eliminateable deviation of the processing part caused by the processing sequence, so as to realize further analysis of the printing defect data, so that the final printing defect data is accurate and intuitive, providing a basis for feedback optimization of the 3D printing process based on visual inspection.

[0110] Example 5:

[0111] Based on Example 4, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection, which supplements printing defect data based on the comprehensive processing part deviation at each stage and the removable deviation of the processed parts caused by the processing sequence, including:

[0112] Add comprehensive processing part deviations and removable deviations to print defect data;

[0113] The difference between the comprehensive processing part deviation and the eliminateable deviation is taken as the part deviation to be eliminated and added to the printing defect data.

[0114] The beneficial effect of the above design scheme is: by adding the comprehensive processing part deviation and the removable deviation to the printing defect data, taking the difference between the comprehensive processing part deviation and the removable deviation as the part deviation to be eliminated, and adding it to the printing defect data, the accuracy and intuitiveness of the final printing defect data are achieved, providing a basis for feedback optimization of the 3D printing process based on visual inspection.

[0115] Example 6:

[0116] Based on Example 1, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection. In S3, based on the correlation between the printing defect data and the printing process data, the adjustment parameters of the initial printing process data are determined, including:

[0117] Eliminating the initial contour features and initial texture features based on the print defect data and the deviation of the part to be eliminated to obtain target contour features and target texture features, and obtaining defect types corresponding to the target contour features and target texture features;

[0118] Calculating a correlation value between each defect type and each 3D printing device printing process data, and sorting the printing process data based on the correlation value to determine a correlation sequence between the defect type and the plurality of printing process data;

[0119] Acquire printing process data with a correlation value greater than a preset value from the correlation sequence as initial operation data related to the defect type;

[0120] Acquire historical operation data and historical defect data related to the initial operation data, learn the linear relationship between the historical operation data and the historical defect data based on a machine model, and construct a defect association recognition model;

[0121] Based on the defect correlation recognition model and combined with the correlation sequence, a secondary correlation analysis is performed on the printing defect data and the printing process data to obtain the target operation data related to the printing defect data, and determine the degree of difference between the target operation data and the standard operation data;

[0122] An adjustment parameter for the target operating data is determined based on the degree of difference.

[0123] In this embodiment, the correlation relationship is, for example, that when the printing temperature is too low, the porosity increases significantly.

[0124] In this embodiment, the association relationship is a one-to-one or one-to-many relationship, the initial operation data is a type of operation data that may be related, and the target operation data is a type of operation data that is indeed related, and the specific impact of the target operation data on the defect type is also determined.

[0125] In this embodiment, the adjustment parameter is, for example, adjustment of temperature, speed, distance, etc.

[0126] The beneficial effect of the above design scheme is: by analyzing and learning the correlation relationship from the two aspects of statistical analysis and machine learning analysis, the accuracy of the obtained correlation relationship is guaranteed, thereby ensuring the accuracy of the adjustment parameters of the initial printing process data, and providing a data basis for real-time adjustment of the 3D printing process.

[0127] Example 7:

[0128] Based on Example 6, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection. Based on the defect association recognition model and in combination with the related sequence, a secondary correlation analysis is performed on the printing defect data and the printing process data to obtain target operation data related to the printing defect data, including:

[0129] determining an operational data type of the initial operational data associated with the defect type based on the correlation sequence;

[0130] The association relationship between the defect data corresponding to the defect type and the initial operation data is identified based on the defect association recognition model, and the target operation data related to the printing defect data is obtained based on the association relationship.

[0131] The beneficial effects of the above design scheme are: by determining the operating data type of the initial operating data related to the defect type based on the relevant sequence, identifying the association relationship between the defect data corresponding to the defect type and the initial operating data based on the defect association recognition model, and based on the association relationship, obtaining the target operating data related to the printing defect data, realizing accurate analysis of the association relationship based on the machine model, and ensuring the accuracy of the obtained association relationship.

[0132] Example 8:

[0133] Based on Example 6, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection, which obtains defect types corresponding to target contour features and target texture features, including:

[0134] Comparing the target contour features and target texture features with standard contour features and standard texture features of standard part image data to obtain difference contour features and difference texture features;

[0135] The defect type corresponding to the difference contour feature and the difference texture feature is obtained from the defect type feature library.

[0136] The beneficial effect of the above design scheme is: by comparing the target contour features and target texture features with the standard contour features and standard texture features of the standard part image data, the difference contour features and difference texture features are obtained, and the defect type corresponding to the difference contour features and difference texture features is obtained from the defect type feature library to ensure the accuracy of the obtained defect type.

[0137] Example 9:

[0138] Based on Example 1, this embodiment of the present invention provides a 3D printing process feedback optimization method based on visual inspection. In S4, the adjustment parameters are input into a feedback control device to automatically control the adjustment of the parameters during the 3D printing process, including:

[0139] automatically inputting the adjustment parameters into a feedback control device;

[0140] The feedback control device automatically generates an adjustment strategy based on the adjustment parameters to automatically control the adjustment of the parameters during the 3D printing process.

[0141] In this embodiment, the automatically generated adjustment strategy is, for example, a step-by-step adjustment in units.

[0142] The beneficial effect of the above design scheme is: by automatically inputting the adjustment parameters into the feedback control device, the feedback control device automatically generates an adjustment strategy based on the adjustment parameters to automatically control the adjustment of parameters in the 3D printing process, thereby realizing dynamic optimization control. This scheme improves printing accuracy and quality, reduces manual intervention, and is suitable for the precision manufacturing of complex parts.

[0143] Example 10:

[0144] The embodiment of the present invention provides a 3D printing process feedback optimization system based on visual inspection, such as Figure 3 Shown, including:

[0145] Data acquisition module, used to collect part processing image data at various stages of the 3D printing process based on visual inspection technology;

[0146] The data analysis module is used to analyze the part processing image data based on the standard part image data and combine it with image processing technology to obtain printing defect data;

[0147] a parameter determination module, configured to determine adjustment parameters for the initial printing process data based on an association between the printing defect data and the printing process data;

[0148] The parameter adjustment module is used to input the adjustment parameters into the feedback control device to automatically control the adjustment of the parameters during the 3D printing process.

[0149] In this embodiment, each stage of the 3D printing process is determined according to the structure of the complex part to be processed, and the processing level and the manufacturing process of each layer are determined.

[0150] In this embodiment, the visual detection technology is, for example, camera detection, laser scanning detection, etc.

[0151] In this embodiment, the standard part image data and the data such as the size and shape of the part when the part is qualified, each stage corresponds to a set of standard part image data.

[0152] In this embodiment, one stage includes a plurality of parts processing image data, which are data of various orientations.

[0153] In this embodiment, the image processing technology includes, for example, image preprocessing, image comparison and other operations.

[0154] In this embodiment, the printing defect data includes, for example, protrusions, depressions, and size deviations.

[0155] In this embodiment, the correlation between the printing defect data and the printing process data is, for example, that the size deviation is related to the printing distance in the printing process data, and the protrusions and depressions are related to the temperature and air pressure in the printing process data.

[0156] In this embodiment, the feedback control device is pre-installed in the 3D printing device to achieve automatic feedback adjustment of the 3D printing process.

[0157] The beneficial effects of the above design scheme are: based on visual inspection technology, the part processing image data at each stage of the 3D printing process is collected to provide an image basis for further inspection of the parts; based on standard processing data, combined with image processing technology, the part processing image data is analyzed to obtain printing defect data, and real-time monitoring and analysis of the processed parts are achieved, providing a basis for feedback optimization of the 3D printing process; based on the correlation between printing defect data and printing process data, the adjustment parameters of the initial printing process data are determined, and analysis of printing defects and deviations based on monitoring data is achieved, and adjustment data is provided. The adjustment parameters are input into the feedback control device to automatically control the adjustment of parameters in the 3D printing process; based on the automatic adjustment of printing parameters, dynamic optimization control is achieved. This scheme improves printing accuracy and quality, reduces manual intervention, and is suitable for the precision manufacturing of complex parts.

[0158] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of this application document and its equivalents, the present invention is intended to include these modifications and variations.

Claims

1. A 3D printing process feedback optimization method based on visual inspection, characterized in that: include: S1: Based on visual inspection technology, it collects image data of parts processing at various stages of the 3D printing process; S2: Based on the standard part image data and combined with image processing technology, the part processing image data is analyzed to obtain printing defect data; S3: Determining adjustment parameters for the initial printing process data based on the correlation between the printing defect data and the printing process data; S4: Inputting the adjustment parameters into a feedback control device to automatically control the adjustment of the parameters during the 3D printing process.

2. The 3D printing process feedback optimization method based on visual inspection according to claim 1, characterized in that: In S1, based on visual inspection technology, image data of parts processing at various stages of the 3D printing process is collected, including: Set up visual inspection devices at various stages of the 3D printing process; Collect image data of parts processing at each stage based on visual inspection equipment; Transmit the parts processing image data to the server.

3. The 3D printing process feedback optimization method based on visual inspection according to claim 1, characterized in that: In S2, based on the standard part image data, combined with image processing technology, the part processing image data is analyzed to obtain printing defect data, including: The part processing image data is sequentially subjected to grayscale conversion, noise reduction and contrast enhancement processing to obtain a pre-processed image; Based on the position information of the pre-processed image, the pre-processed image is fused to obtain a comprehensive part processing image; Perform contour and texture feature extraction on the overall part processing image to obtain contour features and texture features; Compare the standard contour features and standard texture features of the standard part image data with the contour features and texture features respectively to obtain contour differences and texture differences; Printing defect data is obtained based on the contour difference and the texture difference.

4. The 3D printing process feedback optimization method based on visual inspection according to claim 1, characterized in that: After obtaining the print defect data, it also includes: Firstly, the printing defect data is divided according to each stage of the 3D printing process to obtain stage defect data, and stage batch defect data of all processed parts in each stage are obtained from the stage defect data; Obtain a single contour difference from the stage batch defect data to establish a contour difference sequence; obtain a single texture difference from the stage batch defect data to establish a texture difference sequence; Determining a first processing deviation based on an average contour difference of all single contour differences, determining a second processing deviation based on an average texture difference of all single texture differences, and determining a processing deviation trend based on sequence trends of the contour difference sequence and the texture difference sequence; Determine the comprehensive machining part deviation at each stage based on the first machining deviation, the second machining deviation and the machining deviation trend; Perform a second division based on the defect data of each part in all stages during the 3D printing process to obtain the defect data of each processed part in all stages; Based on the defect data of all stages of the part, the defect cumulative characteristics of the processed part are determined, and each extreme defect is marked to obtain the defect marking cumulative characteristics; Based on the neural network model, the accumulated features of the defect marks are learned to determine the impact features of the differences in the previous stage on the processing of the next stage in adjacent stages. Based on the impact features of all stages, the deviations of the processed parts caused by the processing sequence that can be eliminated are determined; Print defect data is supplemented based on the comprehensive processing part deviations at each stage and the removable deviations of the processed parts due to the processing sequence.

5. The 3D printing process feedback optimization method based on visual inspection according to claim 4, characterized in that: Print defect data is supplemented based on the comprehensive processing part deviations at each stage and the removable deviations of the processed parts caused by the processing sequence, including: Add comprehensive processing part deviations and removable deviations to print defect data; The difference between the comprehensive processing part deviation and the eliminateable deviation is taken as the part deviation to be eliminated and added to the printing defect data.

6. The 3D printing process feedback optimization method based on visual inspection according to claim 1, characterized in that: In S3, based on the correlation between the printing defect data and the printing process data, determining the adjustment parameters for the initial printing process data includes: Eliminating the initial contour features and initial texture features based on the print defect data and the deviation of the part to be eliminated to obtain target contour features and target texture features, and obtaining defect types corresponding to the target contour features and target texture features; Calculating a correlation value between each defect type and each 3D printing device printing process data, and sorting the printing process data based on the correlation value to determine a correlation sequence between the defect type and the plurality of printing process data; Acquire printing process data with a correlation value greater than a preset value from the correlation sequence as initial operation data related to the defect type; Acquire historical operation data and historical defect data related to the initial operation data, learn the linear relationship between the historical operation data and the historical defect data based on a machine model, and construct a defect association recognition model; Based on the defect correlation recognition model and combined with the related sequence, a secondary correlation analysis is performed on the printing defect data and the printing process data to obtain the target operation data related to the printing defect data, and determine the degree of difference between the target operation data and the standard operation data; An adjustment parameter for the target operating data is determined based on the degree of difference.

7. The 3D printing process feedback optimization method based on visual inspection according to claim 6, characterized in that: Based on the defect correlation recognition model and combined with the related sequence, a secondary correlation analysis is performed on the printing defect data and the printing process data to obtain the target operation data related to the printing defect data, including: determining an operational data type of the initial operational data associated with the defect type based on the correlation sequence; The association relationship between the defect data corresponding to the defect type and the initial operation data is identified based on the defect association recognition model, and the target operation data related to the printing defect data is obtained based on the association relationship.

8. The 3D printing process feedback optimization method based on visual inspection according to claim 6, characterized in that: Obtain the defect types corresponding to the target contour features and target texture features, including: Comparing the target contour features and target texture features with standard contour features and standard texture features of standard part image data to obtain difference contour features and difference texture features; The defect type corresponding to the difference contour feature and the difference texture feature is obtained from the defect type feature library.

9. The 3D printing process feedback optimization method based on visual inspection according to claim 1, characterized in that: In S4, inputting the adjustment parameters into a feedback control device to automatically control the adjustment of the parameters during the 3D printing process includes: automatically inputting the adjustment parameters into a feedback control device; The feedback control device automatically generates an adjustment strategy based on the adjustment parameters to automatically control the adjustment of the parameters during the 3D printing process.

10. A 3D printing process feedback optimization system based on visual inspection, used to implement the feedback optimization method according to claim 1, characterized in that: include: Data acquisition module, used to collect part processing image data at various stages of the 3D printing process based on visual inspection technology; The data analysis module is used to analyze the part processing image data based on standard part image data and combine image processing technology to obtain printing defect data; a parameter determination module, configured to determine adjustment parameters for the initial printing process data based on an association between the printing defect data and the printing process data; The parameter adjustment module is used to input the adjustment parameters into the feedback control device to automatically control the adjustment of the parameters during the 3D printing process.

Images