A Method and System for Optimizing Pressing Parameters Based on Online Defect Detection of Silicon Carbide Preform

Abstract

This invention discloses a method and system for optimizing pressing parameters based on online defect detection in silicon carbide billets, relating to the field of silicon carbide billet defect detection technology. The method includes: performing tomographic scanning of the silicon carbide billet to be sintered to obtain a three-dimensional density distribution map; measuring the surface morphology to obtain a high-precision three-dimensional geometric model of the billet; correcting geometric distortion to obtain a spatial model of the billet's fusion defects; performing fine-grained defect detection to obtain multiple spatial distribution characteristics of defects; outputting multiple single-dimensional pressing correction parameters; performing spatial multivariate coupling processing to output global pressing coupling parameters; and performing batch pressing of the silicon carbide billets to be sintered. This invention solves the technical problems of low precision in silicon carbide billet defect detection, lack of specificity in pressing parameter optimization, and large quality fluctuations in batch-pressed billets in existing technologies. It achieves online defect detection and pressing parameter optimization of silicon carbide billets, improving pressing quality and consistency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of silicon carbide green body defect detection, and particularly relates to a pressing parameter optimization method and system based on silicon carbide green body defect online detection. BACKGROUND

[0002] In the prior art, green body defect detection is mostly performed by a single method and a rough process, and it is difficult to simultaneously capture internal density unevenness, porosity and other hidden defects and external geometric distortion, and it is also difficult to realize accurate positioning and quantitative analysis of defects. At the same time, the correction of the pressing process has long relied on the experience of operators, and when defects occur in the green body, the parameters such as pressure and pressure holding time are mostly adjusted according to subjective experience, and there is a lack of systematic research on the correlation between defect distribution characteristics and pressing parameters. This detection and correction mode makes the defect correction lack of pertinence, and it is difficult to effectively eliminate existing defects, and new defects may be generated due to insufficient parameter adaptability, ultimately resulting in large quality fluctuations and poor consistency of the green body in batch production, and it is difficult to meet the stringent requirements of the field of semiconductor equipment and the like for high-purity and high-density silicon carbide parts.

[0003] In the prior art, the defect detection of the silicon carbide green body has low precision, the pressing parameter optimization lacks pertinence, and the quality of the batch-pressed green body fluctuates greatly. SUMMARY

[0004] The present application provides a pressing parameter optimization method and system based on silicon carbide green body defect online detection, which is used to solve the technical problems of low defect detection precision, lack of pertinence in pressing parameter optimization and large quality fluctuations of batch-pressed green bodies in the prior art.

[0005] In view of the above problems, the present application provides a pressing parameter optimization method and system based on silicon carbide green body defect online detection.

[0006] In a first aspect of the present application, a pressing parameter optimization method based on silicon carbide green body defect online detection is provided, and the method comprises:

[0007] The three-dimensional density distribution diagram of the sintering silicon carbide blank is obtained by tomography of the sintering silicon carbide blank through an industrial CT device; the high-precision three-dimensional geometric model of the sintering silicon carbide blank is obtained by surface topography measurement of the sintering silicon carbide blank through a 3D optical scanning device; the sintering silicon carbide blank fusion defect space model is obtained by performing geometric distortion correction after spatial alignment and fusion of the three-dimensional density distribution diagram of the sintering silicon carbide blank and the high-precision three-dimensional geometric model of the sintering silicon carbide blank; the sintering silicon carbide blank fusion defect space model is subjected to fine-grained defect detection, and a plurality of defect space distribution characteristics corresponding to a plurality of defect types are obtained; the plurality of defect space distribution characteristics are subjected to pressing associated defect inversion, and a plurality of single-dimensional pressing correction parameters are output; the plurality of single-dimensional pressing correction parameters are subjected to spatial multivariate coupling processing based on the spatial attributes of the sintering silicon carbide blank, and a global pressing coupling parameter is output; and the sintering silicon carbide blank is subjected to batch pressing by using the global pressing coupling parameter.

[0008] In a second aspect of the present application, a pressing parameter optimization system based on online detection of sintering silicon carbide blank defects is provided, and the system comprises:

[0009] A distribution diagram acquisition module is configured to obtain a three-dimensional density distribution diagram of a sintering silicon carbide blank by tomography of the sintering silicon carbide blank through an industrial CT device; a geometric model acquisition module is configured to obtain a high-precision three-dimensional geometric model of the sintering silicon carbide blank by surface topography measurement of the sintering silicon carbide blank through a 3D optical scanning device; a space model acquisition module is configured to obtain a sintering silicon carbide blank fusion defect space model by performing geometric distortion correction after spatial alignment and fusion of the three-dimensional density distribution diagram of the sintering silicon carbide blank and the high-precision three-dimensional geometric model of the sintering silicon carbide blank; a defect detection module is configured to perform fine-grained defect detection on the sintering silicon carbide blank fusion defect space model, and obtain a plurality of defect space distribution characteristics corresponding to a plurality of defect types; a correction parameter output module is configured to perform pressing associated defect inversion according to the plurality of defect space distribution characteristics, and output a plurality of single-dimensional pressing correction parameters; a coupling parameter output module is configured to perform spatial multivariate coupling processing of the plurality of single-dimensional pressing correction parameters based on the spatial attributes of the sintering silicon carbide blank, and output a global pressing coupling parameter; and a batch pressing module is configured to perform batch pressing of the sintering silicon carbide blank by using the global pressing coupling parameter.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] The three-dimensional density distribution diagram of the sintering silicon carbide blank is obtained by tomography of the sintering silicon carbide blank to be sintered through an industrial CT device; the surface topography of the sintering silicon carbide blank is measured through a 3D optical scanning device to obtain a high-precision three-dimensional geometric model of the sintering silicon carbide blank; after fusing the three-dimensional density distribution diagram of the sintering silicon carbide blank and the high-precision three-dimensional geometric model of the sintering silicon carbide blank, geometric distortion correction is performed to obtain a sintering silicon carbide blank fusion defect space model; fine-grained defect detection is performed to obtain a plurality of defect space distribution characteristics corresponding to a plurality of defect types; pressing associated defect inversion is performed to output a plurality of single-dimensional pressing correction parameters; spatial multivariate coupling processing of the plurality of single-dimensional pressing correction parameters is performed to output a global pressing coupling parameter; and the global pressing coupling parameter is used for batch pressing of the sintering silicon carbide blank to be sintered. The technical effect of realizing online detection of sintering silicon carbide blank defects and optimizing pressing parameters is achieved, and the pressing quality and consistency are improved. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 The pressing parameter optimization method based on online detection of sintering silicon carbide blank defects provided by the embodiments of the present application is shown in the flowchart.

[0014] Figure 2 The structure schematic diagram of the pressing parameter optimization system based on online detection of sintering silicon carbide blank defects provided by the embodiments of the present application is shown.

[0015] Marked legend: distribution diagram acquisition module 10, geometric model acquisition module 20, space model acquisition module 30, defect detection module 40, correction parameter output module 50, coupling parameter output module 60, batch pressing module 70. DETAILED DESCRIPTION

[0016] The present application provides a pressing parameter optimization method and system based on online detection of sintering silicon carbide blank defects, which is used to solve the technical problems of low detection accuracy of sintering silicon carbide blank defects, lack of pertinence of pressing parameter optimization and large quality fluctuation of batch pressed sintering silicon carbide blanks in the prior art.

[0017] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0018] As shown in Embodiment I, Figure 1 The present application provides a pressing parameter optimization method based on online detection of silicon carbide blank defects, and the method comprises the following steps:

[0019] Step S100: tomography of the sintering silicon carbide blank is performed by an industrial CT device to obtain a three-dimensional density distribution map of the blank.

[0020] Specifically, the industrial CT device is controlled to perform comprehensive tomography of the sintering silicon carbide blank. The industrial CT ray can penetrate the blank and can generate different attenuation signals according to the density difference of the material in different regions of the blank. The density data of each depth section of the blank from the surface to the interior is collected. Then, the three-dimensional reconstruction technology is used to integrate and reconstruct the multiple groups of continuous section density data obtained by scanning, and finally a three-dimensional density distribution map of the blank is generated, which can accurately reflect the overall density distribution of the interior of the sintering silicon carbide blank. The distribution map will serve as the key internal information basis for subsequent spatial alignment and fusion of the blank high-precision three-dimensional geometric model and construction of the blank fusion defect space model, and provide core data support for subsequent fine-grained defect detection in the density dimension of the blank interior.

[0021] Step S200: surface topography measurement of the sintering silicon carbide blank is performed by a 3D optical scanning device to obtain a blank high-precision three-dimensional geometric model.

[0022] Specifically, the 3D optical scanning device, such as a structured light scanning device or a laser scanning device, is used to perform full-surface coverage scanning of the sintering silicon carbide blank. The principle of reflection / diffuse reflection of the optical signal emitted by the device with the surface of the blank is used to collect the coordinate data of the million or even ten million feature points on the surface of the blank, and the original point cloud data containing the surface profile, texture and size details of the blank are formed. Then, the original point cloud data is preprocessed by removing abnormal points caused by environmental interference in the scanning process through a denoising algorithm, such as statistical filtering and radius filtering. Then, the point cloud registration and splicing technology is used to integrate the local point cloud data obtained by scanning the blank at different angles into a complete global point cloud model. Finally, based on the complete point cloud data after processing, a three-dimensional gridding and model reconstruction algorithm, such as the Poisson surface reconstruction algorithm, is used to construct a blank high-precision three-dimensional geometric model which is highly consistent with the actual external geometric shape of the blank and meets the requirements of subsequent spatial registration and geometric verification in size accuracy.

[0023] Step S300: After the space alignment fusion of the blank three-dimensional density distribution map and the blank high-precision three-dimensional geometric model, geometric distortion correction is performed to obtain a blank fusion defect space model.

[0024] Specifically, the first natural feature point distribution and the second natural feature point distribution are identified in the blank three-dimensional density distribution map and the blank high-precision three-dimensional geometric model, respectively. The iterative closest point algorithm is used to register the two sets of natural feature point distributions and construct a space transformation matrix. The two models are mapped to a unified coordinate system according to the matrix to complete space registration, and a preliminary registration model is obtained. Then, the preliminary registration model is segmented into multiple grid-level spatial pixel points according to a preset grid scale. The position and shape distortion of each grid-level spatial pixel point are corrected based on the optical geometric true value corresponding to the blank high-precision three-dimensional geometric model, and multiple corrected spatial pixel points are generated. Finally, all the corrected spatial pixel points are re-integrated by a reverse recombination algorithm to restore and output the blank fusion defect space model that combines the internal density information and the external geometric information of the blank.

[0025] Step S400: Perform fine-grained defect detection on the blank fusion defect space model to obtain multiple defect space distribution characteristics corresponding to multiple defect types.

[0026] Specifically, according to the multiple defect size distribution sets corresponding to the multiple defect types, the multi-scale defect characteristics are analyzed and output. Then, based on the multi-scale defect characteristics, the blank fusion defect space model is subjected to multi-scale space segmentation to generate a series of scale analysis models. Next, multiple defect original image sets and multiple defect shape identification sets of multiple defect types are called in a network to be used as training data for multi-directional parameter optimization of the basic defect detection model, multiple single-task defect detection modules are constructed, and these modules are connected in a logically isolated manner to form a multi-defect parallel detection network. The series of scale analysis models are input into the network one by one for defect parallel reasoning and detection, and a series of scale intermediate results are output. Then, the series of scale intermediate results are decomposed according to defect types to obtain multiple series of multi-scale pixel-level defects. According to the multi-scale defect characteristics, multi-scale defect confidence values are set, multiple defect probability maps are generated for the spatially aligned multiple series of multi-scale pixel-level defects, and weighted probability fusion is performed based on multi-scale defect confidence value mapping to output multiple initial defect space distributions. Finally, based on the blank high-precision three-dimensional geometric model, geometric distortion verification is performed on the multiple initial defect space distributions, and finally multiple defect space distribution characteristics corresponding to multiple defect types are output, providing accurate defect information basis for subsequent pressing associated defect inversion.

[0027] Step S500: Perform pressing associated defect inversion according to the multiple defect space distribution characteristics to output multiple single-dimensional pressing correction parameters.

[0028] Specifically, for each defect spatial distribution feature, a corresponding defect feature vector is quantitatively extracted, which needs to cover key information such as defect type, defect volume, defect density, defect spatial orientation, and defect structure position distribution. For example, a first defect feature vector containing the above dimensions is extracted from the first defect spatial distribution feature. Then, the extracted defect feature vector is input into a pre-constructed defect pressing correlation rule library for matching. The rule library is formed by first performing process simulation repair to record a plurality of sample defect vectors corresponding to a plurality of sample pressing correction parameters, then performing feature space enhancement on the sample data, and finally constructing the causal correlation of sample defect vectors and sample pressing correction parameters through a decision tree. Through matching, single-dimensional pressing correction parameters corresponding to each defect feature vector are output, including but not limited to pressing pressure gradient adjustment amount, holding time correction amount, and demolding rate optimization value. Finally, a plurality of single-dimensional pressing correction parameters are obtained, providing a basis for subsequent spatial multivariate coupling processing.

[0029] Step S600: Spatial multivariate coupling processing of the plurality of single-dimensional pressing correction parameters based on the dough space attribute, outputting a global pressing coupling parameter.

[0030] Specifically, based on the dough space attribute, key spatial features such as the shape, size, and material distribution of different regions of the dough are covered to construct a process sensitivity field model that can reflect the sensitivity of different spatial positions of the dough to changes in pressing process parameters. Subsequently, with dough density optimization and density distribution uniformization as the core multi-objective, the output multiple single-dimensional pressing correction parameters such as pressing pressure gradient adjustment amount, holding time correction amount, and demolding rate optimization value are mapped into the constructed process sensitivity field model. Through spatial multivariate coupling optimization algorithm, the mutual influence and adaptation relationship of each single-dimensional pressing correction parameter in different dough spatial regions is coordinated, and possible conflicts between parameters are eliminated, finally outputting a global pressing coupling parameter that can meet the process requirements of each spatial region of the dough and satisfy the multi-objective optimization requirements, providing unified and precise process parameter guidance for subsequent batch pressing of the sintered silicon carbide dough.

[0031] Step S700: Batch pressing of the sintered silicon carbide dough using the global pressing coupling parameter.

[0032] Specifically, the output global pressing coupling parameters are transmitted to the batch pressing equipment control system of the sintered silicon carbide green body to be sintered, and then the pressing equipment automatically adjusts the core process indicators in the pressing process according to the global pressing coupling parameters, including but not limited to the pressing pressure gradient, the pressure holding time, the demolding rate and the like corresponding to the parameters, and finally, the standard batch pressing operation is carried out on the sintered silicon carbide green body according to the adjusted process parameters, so as to ensure that the batch production green body can avoid the defect types detected in the early stage, reduce the overall defect rate, and at the same time ensure that the key quality indicators such as the green body density and the geometric shape meet the production requirements, so as to realize efficient and high-quality batch production based on online defect detection and parameter optimization.

[0033] In one possible implementation, step S300 further includes:

[0034] Step S310: mapping the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model to a unified coordinate system to perform spatial registration, to obtain a preliminary registration model.

[0035] Step S320: after the preliminary registration model is segmented into a plurality of grid-level spatial pixel points according to a preset grid scale, distortion correction is performed on the plurality of grid-level spatial pixel points based on optical geometric true values, to obtain a plurality of corrected spatial pixel points.

[0036] Step S330: reverse recombining the plurality of corrected spatial pixel points to restore and output the green body fusion defect space model.

[0037] Specifically, first, the first natural feature point distribution is identified in the green body three-dimensional density distribution map, and these feature points are usually selected from regions with obvious density mutations, such as internal pore edges and density anomaly boundaries, to ensure that they have clear spatial recognition; at the same time, the second natural feature point distribution is identified in the green body high-precision three-dimensional geometric model, and positions with significant geometric shapes are preferentially selected, such as surface protrusion vertices, process hole edges and corner intersection points, to ensure that the two types of feature points can form corresponding associations. Then, the iterative closest point algorithm is used to perform registration calculation on the first natural feature point distribution and the second natural feature point distribution: the closest point pairs in the two types of feature point sets are found through continuous iteration, the spatial error between the point pairs is calculated, the spatial pose of the green body three-dimensional density distribution map is adjusted, and the adjustment is continued until the overall error is reduced to below a preset threshold, and in this process, a spatial transformation matrix that can realize the spatial conversion of the two types of data is constructed. Finally, according to the spatial transformation matrix, all spatial coordinates of the green body three-dimensional density distribution map are mapped to a unified coordinate system with the green body high-precision three-dimensional geometric model as the reference, so that the two are accurately aligned in spatial position, while the density data of the green body three-dimensional density distribution map and the geometric shape data of the green body high-precision three-dimensional geometric model are retained, and finally a preliminary registration model is formed by fusion, laying a foundation for spatial consistency for subsequent geometric distortion correction.

[0038] According to the actual size of the silicon carbide green body to be sintered and the defect detection accuracy requirement, a preset grid scale is determined, which needs to consider the detection accuracy and data processing efficiency to ensure that both the details of the small defects can be captured and the data volume is not too large and the processing time is not too long due to too fine grid. Then, the obtained preliminary registration model is discretely segmented in three-dimensional space with the preset grid scale as the segmentation standard, and the continuous preliminary registration model is uniformly divided into a large number of non-overlapping grid-level spatial pixel points, each pixel point corresponds to a unique spatial coordinate and the green body density data at the position, forming a discretized pixel point set. Next, the optical geometric true value verified by 3D optical scanning in the high-precision three-dimensional geometric model of the green body is called, which includes the accurate geometric coordinates of the surface and internal key structures of the green body, such as surface contour points, internal process hole center coordinates, etc. These coordinates have been calibrated through multiple scans and have very high accuracy. Then, for each grid-level spatial pixel point, its current spatial coordinate is extracted and compared with the standard coordinate at the corresponding position in the optical geometric true value, and the deviation value in the X, Y and Z coordinate axis directions, i.e. distortion error, is calculated. According to the calculated distortion error, a polynomial fitting correction algorithm is used to correct the coordinates of each grid-level spatial pixel point: by constructing an error fitting function, the deviation value is converted into a coordinate correction amount, the original coordinates of the pixel point are adjusted, and the position deviation caused by industrial CT scanning distortion, spatial registration deviation and other factors is eliminated. Finally, after the distortion correction of all grid-level spatial pixel points is completed, a plurality of corrected spatial pixel points with accurate position and high matching of coordinates and optical geometric true value are formed.

[0039] The core basis of reverse recombination is to set a unified coordinate system as a spatial framework to ensure the coordinate consistency of all corrected spatial pixel points in the recombination process. Then, the obtained multiple corrected spatial pixel points, each containing accurate spatial coordinates and the density data of the corresponding position of the blank, are sorted in a three-dimensional grid according to the spatial coordinates of the pixel points to ensure that each pixel point can be returned to the original spatial position corresponding relationship before the preliminary registration model is segmented. Next, the three-dimensional space interpolation and voxel reconstruction algorithm is used to continuously process the discrete corrected spatial pixel points: by calculating the density gradient between adjacent pixel points, the density information in the gap between the pixel points is supplemented, and the model fault caused by discrete segmentation is eliminated; at the same time, based on the coordinate position of the pixel points, a continuous three-dimensional voxel structure is constructed, so that the reconstructed model can not only completely retain the external geometric shape of the blank and be consistent with the high-precision three-dimensional geometric model of the blank, but also accurately present the internal density distribution difference. In the recombination process, the geometric integrity and density data accuracy of the model need to be checked in real time, and the key dimensions of the reconstructed model, such as length, diameter, and the corresponding dimensions of the high-precision three-dimensional geometric model of the blank, are compared to ensure that the error is within the allowable range; at the same time, the density values of the internal key areas are randomly checked to verify whether they are consistent with the original data of the three-dimensional density distribution map of the blank. Finally, after the reverse recombination of all corrected spatial pixel points is completed, the blank fusion defect space model with accurate geometric shape and real internal density distribution is output, which can be directly used for subsequent fine-grained defect detection and provides complete and accurate three-dimensional data support for identifying internal pores, surface cracks and other defects of the blank.

[0040] In one possible implementation manner, the step S310 further includes:

[0041] Step S311: Identifying a first natural feature point distribution and a second natural feature point distribution from the three-dimensional density distribution map of the blank and the high-precision three-dimensional geometric model of the blank, respectively.

[0042] Step S312: Registering the first natural feature point distribution and the second natural feature point distribution by using an iterative closest point algorithm to construct a spatial transformation matrix.

[0043] Step S313: Mapping the three-dimensional density distribution map of the blank and the high-precision three-dimensional geometric model of the blank to a unified coordinate system to perform spatial registration according to the spatial transformation matrix, and obtaining the preliminary registration model.

[0044] Specifically, for the green body three-dimensional density distribution map, a density gradient threshold segmentation algorithm combined with a feature point extraction algorithm is used to identify the first natural feature point distribution: by setting a reasonable density gradient threshold, regions with sudden changes in internal density of the green body are screened out, such as the junction of internal pores and dense regions, the edge of local density abnormal blocks, etc., and then corner detection and contour sampling are performed on these regions to extract points with spatial uniqueness as the first natural feature points, and finally a first natural feature point distribution containing multiple such points is formed, ensuring that each point can accurately reflect the key position of the internal density structure of the green body. At the same time, for the high-precision three-dimensional geometric model of the green body, an edge detection algorithm and a geometric feature recognition algorithm are used to identify the second natural feature point distribution: first, the contour lines of the green body surface are extracted through edge detection, such as the edges of the green body, the circumferential edges of the process holes, etc., and then geometrically significant points are selected on the contour lines, such as the vertexes of the edges, the centers of the process holes, the highest points of the surface protrusions, etc., which can clearly represent the key positions of the external geometric structure of the green body, and finally the second natural feature point distribution is integrated to form a potential corresponding relationship between the two types of natural feature points in the spatial position, laying a foundation for subsequent spatial registration.

[0045] The identified first natural feature point distribution and second natural feature point distribution are imported into the calculation module of the iterative closest point algorithm, the spatial correspondence relationship of the two sets of feature points is initialized, the Euclidean distance is taken as the measurement standard, the second natural feature point closest in distance is matched for each first natural feature point, and an initial point pair set is formed. Then, based on the initial point pair set, a preliminary spatial transformation matrix is calculated through the singular value decomposition algorithm, which contains parameters of translation, rotation and scaling in three dimensions, and can realize the spatial mapping of the first natural feature point distribution to the second natural feature point distribution. Subsequently, the preliminary spatial transformation matrix is used to perform coordinate transformation on all first natural feature points to obtain the transformed first natural feature point distribution, and the distance error of each transformed point and the corresponding second natural feature point is recalculated, and the abnormal point pairs with error exceeding the preset threshold, such as 0.01 mm, are screened out and removed, and a new nearest point pair set is updated. The iterative process of calculating the spatial transformation matrix, transforming the feature points, updating the point pairs, and calculating the error is repeatedly executed until the overall error change of two consecutive iterations is less than the set convergence threshold, at which time the algorithm converges and outputs the final spatial transformation matrix. The matrix can accurately describe the spatial conversion relationship between the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model, and provide key parameter support for subsequent spatial registration of the two in a unified coordinate system.

[0046] A reference of the unified coordinate system is determined, usually taking the original coordinate system of the high-precision three-dimensional geometric model of the blank as the reference coordinate system. Due to the high precision of 3D optical scanning, the coordinate system can provide reliable position reference for spatial registration. Then, the constructed spatial transformation matrix is called, which contains translation, rotation and scaling parameters, and the spatial conversion of the three-dimensional density distribution map of the blank and the reference coordinate system can be realized. Next, all the spatial coordinate data of the three-dimensional density distribution map of the blank are input into the coordinate transformation module, and the coordinate conversion operation is performed according to the spatial transformation matrix. The density distribution data originally in the industrial CT scanning coordinate system is accurately mapped into the unified coordinate system taking the high-precision three-dimensional geometric model of the blank as the reference, so that the internal density distribution information of the blank and the external geometric shape information form a corresponding relationship in the spatial position. In this process, the density value data of the three-dimensional density distribution map of the blank and the geometric contour data of the high-precision three-dimensional geometric model of the blank need to be synchronously preserved to ensure that the data fusion is realized in the unified coordinate system rather than data loss. Finally, the mapped three-dimensional density distribution map of the blank and the high-precision three-dimensional geometric model of the blank are spatially aligned and verified. By comparing the coordinate deviation of the key feature points, it is confirmed that the registration accuracy meets the preset requirements, such as the deviation being less than 0.02 mm. After the verification is passed, the preliminary registration model with the internal density distribution and the external accurate geometric shape of the blank can be output.

[0047] In one possible implementation manner, the step S400 further includes:

[0048] Step S410: analyzing and outputting multi-scale defect characteristics according to the plurality of defect size distribution sets of the plurality of defect types.

[0049] Step S420: performing multi-scale spatial segmentation on the blank fusion defect spatial model by using the multi-scale defect characteristics to generate a series of scale analysis models.

[0050] Step S430: inputting the series of scale analysis models into a multi-defect parallel detection network to perform defect parallel inference detection and output a series of scale intermediate results.

[0051] Step S440: after the probability fusion of the series of scale intermediate results, performing geometric distortion verification based on the high-precision three-dimensional geometric model of the blank to output a plurality of defect spatial distribution characteristics corresponding to the plurality of defect types.

[0052] Specifically, various defect types commonly found in the production of sintered silicon carbide blanks are identified, such as internal porosity, surface cracks, local density abnormalities, etc. For each defect type, a corresponding set of defect size distributions is obtained, which includes key size data such as length, width, depth, volume, and cross-sectional dimensions of the corresponding defects under different production batches and different pressing conditions. Subsequently, statistical analysis is performed on the defect size distribution sets of each defect type. By analyzing the distribution frequency, size variation, and typical morphological characteristics of defects in different size intervals, multi-scale defect characteristics that can distinguish size differences between different defect types and adapt to subsequent multi-scale detection needs are extracted and output. For example, micron-level size features are extracted for small pores, and millimeter-level extension size features are extracted for surface cracks, providing accurate scale division basis for multi-scale spatial segmentation of the blank fusion defect space model in subsequent steps.

[0053] The output multi-scale defect characteristics, including size intervals and morphological feature parameters of different defect types, are converted into scale constraints for the neural network. Meanwhile, the blank fusion defect space model is preprocessed into three-dimensional voxel data that conforms to the network input format, which covers the internal density information and external geometric information of the blank. Then, an improved 3D U-Net multi-scale neural network is started. The network encoder part extracts multi-scale features from the voxel data using different size convolution kernels, such as 1x1x1, 3x3x3, and 5x5x5. Small size convolution kernels focus on local features of small defects such as micron-level pores, while large size convolution kernels capture global distribution features of defects such as millimeter-level cracks and centimeter-level density abnormalities. Each encoding layer outputs a feature map corresponding to the multi-scale defect characteristics. Subsequently, the network decoder part fuses the feature maps of different encoding layers through skip connections and performs hierarchical semantic segmentation on the feature maps based on the scale constraints. The segmentation is divided into three dimensions: macro, which adapts to centimeter-level density abnormalities; meso, which adapts to millimeter-level cracks; and micro, which adapts to micron-level pores. Each dimension generates a scale sub-model. Finally, the scale sub-models in each dimension are calibrated and verified for completeness to ensure that each sub-model accurately covers the defect detection needs of the corresponding scale, and an ordered series of scale analysis models is formed.

[0054] For various defect types of silicon carbide blanks, such as internal porosity, surface cracks, and local density anomalies, single-task defect detection sub-models based on CNN are constructed for each defect type. The original defect image set and defect morphology identification set are used as training data, ResNet50 is used as the basic backbone network, network parameters are initialized through transfer learning, and spatial attention modules are introduced to strengthen defect region feature extraction. Through the Adam optimizer and cross-entropy loss function, each sub-model is iteratively trained to accurately adapt to the detection task of a single defect type, forming multiple special detection sub-models. Then, a multi-defect parallel detection network is constructed by connecting these sub-models in parallel. Each sub-model receives data independently and the inference process does not interfere with each other. The network has a built-in data distribution module that can distribute each scale sub-model in the series scale analysis model to the corresponding defect scale sub-model. For example, micron-level sub-models are distributed to CNN sub-models for detecting internal porosity, and millimeter-level sub-models are distributed to CNN sub-models for detecting surface cracks. Then, a parallel inference process is started, and each CNN sub-model performs feature extraction on the received scale sub-model. The convolution layer and the pooling layer are used to extract defect texture, contour features, and feature mapping. The fully connected layer is used to convert features into defect probability distribution, and the single-scale detection result containing defect position coordinates, defect confidence, and defect morphology parameters is output. Finally, the network data integration module arranges all single-scale detection results output by the sub-models in order of scale to form a series of scale intermediate results covering all sub-model detection data of the series scale analysis model.

[0055] According to the determined multiple defect types, the series of scale intermediate results are classified and decomposed by defect type to obtain multiple series of multi-scale pixel-level defect data corresponding to each defect type. Then, referring to the multi-scale defect characteristics, appropriate multi-scale defect confidence values are set for pixel-level defects of different scales, such as high confidence values for large-scale defects due to prominent features and low confidence values for small-scale defects. Spatial alignment is performed on multi-scale pixel-level defect data of the same defect type to ensure that the pixel coordinates of the same defect region at different scales match, and defect probability maps corresponding to each scale are generated. Then, a weighted coefficient matrix is constructed according to the multi-scale defect confidence values to perform weighted probability fusion on the multiple defect probability maps after spatial alignment, eliminating the deviation of detection results at different scales, and outputting the initial defect spatial distribution of each defect type. Finally, the high-precision three-dimensional geometric model of the blank is taken as the reference to extract the optical geometric true value from the model, and the position, shape, and size of each initial defect spatial distribution are checked for geometric distortion. The spatial offset error caused by segmentation or detection is corrected, and finally multiple defect spatial distribution features corresponding to multiple defect types and accurate spatial information are output.

[0056] In one possible implementation, step S430 further includes:

[0057] Step S431: calling a plurality of defect original image sets and a plurality of defect morphology identification sets of the plurality of defect types through networking.

[0058] Step S432: taking the plurality of defect original image sets and the plurality of defect morphology identification sets as training data, performing multi-directional parameter adjustment optimization of a basic defect detection model, and constructing a plurality of single-task defect detection modules.

[0059] Step S433: connecting the plurality of single-task defect detection modules in parallel in a logical isolation manner to construct the multi-defect parallel detection network.

[0060] Step S434: inputting a plurality of single-scale pixel-level models in a first scale analysis model into the multi-defect parallel detection network one by one, performing defect parallel inference detection, outputting a plurality of single-scale pixel-level defects, and constructing a first scale intermediate result.

[0061] Step S435: analogously inputting the series of scale analysis models into the multi-defect parallel detection network, performing defect parallel inference detection, and outputting the series of scale intermediate results.

[0062] Specifically, a plurality of defect original image sets and a plurality of defect morphology identification sets corresponding to a plurality of defect types of a silicon carbide blank, such as internal porosity, surface cracks, local density abnormalities, etc., are called through networking, wherein the defect original image set contains high-definition three-dimensional image data of various defects under different production conditions, and the defect morphology identification set labels the category, boundary, size and morphology characteristic parameters of the corresponding defect, providing complete sample data support for subsequent model training.

[0063] The multiple defect original image sets corresponding to multiple defect types obtained by the networked call contain high-definition three-dimensional image data of various defects of the silicon carbide billet under different working conditions and multiple defect morphology identification sets containing information such as defect category, boundary, size, and morphological feature parameters. The multiple defect original image sets are preprocessed, including image denoising, pixel-level annotation calibration, data enhancement such as rotation, scaling, and mirror processing, and are divided into a training set and a verification set in a preset 8:2 ratio as training data for a basic CNN defect detection model. Then, a basic CNN model is configured for each defect type, ResNet50 is selected as the backbone network, a spatial attention module is introduced to strengthen defect region feature extraction, the training set data of a single defect type is used to initialize and train the corresponding CNN model, and multi-directional parameter adjustment optimization is carried out. The convolution kernel size is adjusted, such as setting a 3x3x3 convolution kernel for micron-level pores and a 5x5x5 convolution kernel for millimeter-level cracks to adapt to the defect scale, the learning rate is optimized, the cosine annealing strategy is adopted to gradually reduce the gradient from 0.001 to 0.0001 to improve the convergence stability of the model, and the iteration number is adjusted. The loss function value of the verification set no longer decreases as the termination condition, and 100-200 rounds are usually set to ensure sufficient training. Finally, the performance of each CNN model after parameter adjustment is verified by the verification set data, and the model with a defect recognition accuracy of ≥95% and a false detection rate of ≤3% is selected. Each performance meeting the CNN model is used as a special detection tool for the corresponding defect type, and multiple single-task defect detection modules corresponding to multiple defect types are constructed.

[0064] The multiple single-task defect detection modules are constructed, each module corresponds to a defect type of the silicon carbide billet, such as an internal pore detection module, a surface crack detection module, and a local density anomaly detection module, and has an independent data processing boundary. Each module is configured with a dedicated input interface, a data cache unit, and an output channel to ensure that the modules do not occupy resources during data reception, inference calculation, and result output. Then, a parallel framework is built using a logical isolation architecture, and the scheduling controller is used to realize the cooperative scheduling of the single-task defect detection modules. The scheduling controller can automatically distribute model data to the single-task module corresponding to the detection scale according to the input scale analysis model type, such as a model suitable for micron-level defects and a model suitable for millimeter-level defects. At the same time, the logical isolation protocol is used to block invalid data interaction between modules to avoid detection deviation caused by data confusion. Finally, a result temporary storage and integration unit is integrated into the framework, and the detection results output by each single-task defect detection module can be stored in the unit in real time and do not overlap with each other, forming a multiple defect parallel detection network with multiple defect parallel detection capability, independent operation of each module, and cooperative work.

[0065] The properties of the first scale analysis model are determined, the model being a sub-model corresponding to a specific defect scale in the generated series of scale analysis models, and the model including a plurality of single-scale pixel-level models divided according to a preset grid, each single-scale pixel-level model including local density information and geometric characteristics of a blank at the scale; then, a scheduling mechanism of the multi-defect parallel detection network is started, and the plurality of single-scale pixel-level models in the first scale analysis model are sequentially input into the network; the network scheduling controller automatically activates a single-task defect detection module corresponding to a defect detection task according to the scale properties of the single-scale pixel-level model, for example, activates an internal pore detection module for a micrometer-level model, while keeping other modules in a ready state to avoid resource occupation; each activated single-task defect detection module performs parallel inference detection on the input single-scale pixel-level model, extracts pixel-level defect features through the convolution layer and the pooling layer of the CNN network, focuses on the suspected defect area by combining the attention mechanism, and outputs a set of single-scale pixel-level defect data including defect position coordinates, defect confidence, and defect morphology parameters; after all single-scale pixel-level models in the first scale analysis model are detected, the output multiple sets of single-scale pixel-level defect data are sorted, de-duplicated, and verified according to the input order to ensure data integrity and consistency, and finally a first scale intermediate result covering the full range of detection results of the first scale analysis model is formed.

[0066] Batch detection is performed on all remaining scale analysis models in the series of scale analysis models, the scale hierarchy of the series of scale analysis models and the corresponding defect detection requirements are sorted out, and the number of single-scale pixel-level models, scale properties, and adaptive single-task defect detection modules included in each non-first scale analysis model are determined; then, the plurality of single-scale pixel-level models in each scale analysis model are sequentially input into the multi-defect parallel detection network in order from fine to coarse or from coarse to fine, and the network scheduling controller automatically activates the matching single-task defect detection module according to the scale properties of the current input model; each activated module synchronously performs defect parallel inference detection on the single-scale pixel-level model, and outputs single-scale pixel-level defect data including defect position, confidence, and morphology parameters; after all single-scale pixel-level models of each scale analysis model are detected, the intermediate results of the corresponding scales are respectively integrated; finally, the first scale intermediate result and the subsequent scale intermediate results are sorted according to the scale order to ensure that the detection data of all scales completely covers the detection range of the series of scale analysis models, and finally the series of scale intermediate results including full-scale defect detection information are output.

[0067] In one possible implementation, step S440 further includes:

[0068] Step S441: decomposing the series of scale intermediate results according to the plurality of defect types to obtain a plurality of series of multi-scale pixel-level defects.

[0069] Step S442: Set a multi-scale defect confidence value according to the multi-scale defect characteristics.

[0070] Step S443: After spatially aligning the multiple series of multi-scale pixel-level defects, a weighted probability fusion of the multiple defect probability maps is performed according to the multi-scale defect confidence value mapping, and multiple initial defect spatial distributions are output.

[0071] Step S444: Geometric distortion verification of the multiple initial defect spatial distributions is performed based on the green body high-precision three-dimensional geometric model, and multiple defect spatial distribution characteristics are output.

[0072] Specifically, a plurality of defect types to be detected in the production of the sintered silicon carbide green body, such as internal porosity, surface cracks, local density abnormalities, etc., are determined, and each defect type is taken as an independent classification dimension. Then, for the output series of scale intermediate results, defect detection data covering different scale analysis models are resolved according to the core screening basis of "defect type", and all scale detection data related to a single defect type are extracted one by one from the series of scale intermediate results, for example, for the defect type of "internal porosity", the corresponding pixel-level detection data in different scale analysis models such as micrometer level and sub-millimeter level are extracted, including defect pixel position, suspected probability, and local morphology parameters, and for surface cracks, pixel-level detection data in millimeter-level and centimeter-level scale analysis models are extracted. Finally, a data set corresponding to each defect type is formed, i.e., each data set only contains the detection performance of a single defect type at the multi-scale pixel level, thereby obtaining a plurality of series of multi-scale pixel-level defects consistent with the number of defect types, ensuring that subsequent centralized processing can be carried out for multi-scale data of a single defect type.

[0073] The multi-scale defect characteristic of the output is analyzed, which includes the internal pores, surface cracks, local density abnormalities and other key features of various defect types of the silicon carbide blank at different scales. The key features include the micron-level size range of the internal pores, the millimeter-level extension range of the surface cracks, the large-scale defect with more obvious features and easy to be accurately identified, the small-scale defect with weak features and difficult to be identified, and the historical detection accuracy data. Then, based on the multi-scale defect characteristics, a multi-scale defect confidence value is set for each defect type at different detection scales. For the millimeter-level surface cracks with obvious features and high historical detection accuracy, the linear extension feature is clear, the detection accuracy is more than 95%, and a high confidence value of 0.9-0.95 is set. For the micron-level small pores with weak features and relatively low historical detection accuracy, the volume is small and easy to be confused with the background interference, the detection accuracy is about 80%-85%, and a relatively low but meets the detection accuracy requirement confidence value of 0.7-0.8 is set. Finally, a multi-scale defect confidence value system corresponding to the defect type-detection scale is formed.

[0074] The global coordinate system of the blank fusion defect space model is taken as a unified reference for the spatial alignment operation of the obtained multiple series of multi-scale pixel-level defects. Through the coordinate calibration algorithm, the pixel-level defect data of the same defect type at different scales is mapped to the same spatial coordinate system, ensuring the accurate matching of the pixel positions of the corresponding defect regions at different scales and avoiding spatial misalignment caused by scale segmentation differences. After completing the spatial alignment, the multi-scale pixel-level defect data of each defect type is converted into a visual defect probability map, in which the value of each pixel represents the probability of the existence of the corresponding defect at that position, so as to intuitively present the spatial distribution possibility of the defects at different scales. Then, the set multi-scale defect confidence value is called to construct a weighted coefficient mapping relationship corresponding to the defect probability map scale, i.e. a high confidence value corresponds to a higher weighted coefficient, and a low confidence value corresponds to an adaptive low weighted coefficient. Then, according to the mapping relationship, the weighted probability fusion calculation is performed on the multiple defect probability maps of the same defect type, the deviation and redundancy of the detection results at different scales are eliminated through weighted summation, the weight of the detection results at high confidence scales is strengthened, and the effective information in the detection results at low confidence scales is reasonably retained. Finally, the threshold screening and morphological regularization are performed on the fused probability data to eliminate the suspected interference points with a probability lower than the set threshold, and the boundary and morphology of the defects are clarified, so as to output an initial defect spatial distribution for each defect type that can integrate multi-scale detection information, clearly presenting the preliminary spatial position, range and morphological characteristics of the defects in the blank.

[0075] The green body high-precision three-dimensional geometric model obtained by the 3D optical scanning device is called, which contains the accurate surface profile coordinates, internal structure size and geometric topological relationship of the sintered silicon carbide green body to be sintered, and can be used as a reference basis for geometric distortion checking. Then, the output multiple initial defect spatial distributions are compared with the green body high-precision three-dimensional geometric model in space, and the initial defect spatial distribution is completely aligned with the global coordinate system of the geometric model through coordinate matching algorithm. Then, the geometric distortion checking is carried out: on the one hand, the position rationality of the initial defect spatial distribution is checked, and whether the defect falls within the actual geometric structure range of the green body is judged, and the abnormal defect data exceeding the green body boundary is removed; on the other hand, the shape and size consistency of the defect is checked, and the length, width, depth and other parameters of the initial defect are compared with the physical size of the corresponding area in the green body high-precision three-dimensional geometric model, and the defect size distortion caused by multi-scale segmentation or detection deviation is corrected, such as the crack size exceeding the local structure thickness of the green body is corrected to the value conforming to the actual structure. At the same time, for the position offset problem that may exist in the initial defect spatial distribution, the feature mark points in the geometric model, such as the specific protrusions on the surface of the green body and the internal process holes, are taken as the reference, and the defect coordinates are fine-tuned and calibrated. After all the initial defect spatial distributions complete the above checking, the defect position, shape, size and other information after checking are integrated to form multiple defect spatial distribution characteristics that can accurately reflect the real distribution state of the defects in the green body, and each characteristic corresponds to a defect type.

[0076] In one possible implementation manner, the step S500 further includes:

[0077] Step S510: quantitatively extracting a first defect feature vector from the first defect spatial distribution characteristic, wherein the first defect feature vector includes a first defect type, a first defect volume, a first defect density, a first defect spatial orientation, and a first defect structure position distribution.

[0078] Step S520: using the first defect feature vector in the defect pressing correlation rule library to match and output a first single-dimensional pressing correction parameter, wherein the first single-dimensional pressing correction parameter includes but is not limited to a pressing pressure gradient adjustment amount, a pressure holding time correction amount, and a demolding speed optimization value.

[0079] Specifically, for the first defect type, a defect classification model based on deep learning, such as an improved ResNet model, is used to identify visual features such as defect morphology and gray scale distribution in the first defect spatial distribution feature, and match them with a preset defect type library containing labels such as internal pores and surface cracks, to automatically label and output the first defect type; for the first defect volume, a three-dimensional space integration algorithm is used to convert the discrete pixel point coordinates of the defect region in the first defect spatial distribution feature into a continuous space grid, and by calculating the product of the number of grid cells occupied by the defect and the volume of a single grid cell, the accurate defect volume value is obtained; for the first defect density extraction, the blank three-dimensional space is divided into several equal-volume sub-regions by a region division algorithm, the number of first defects in each sub-region is counted, and then the number of defects per unit volume is calculated based on the sub-region volume, which is the first defect density; for the first defect spatial orientation, a principal component analysis algorithm is used to reduce the dimension of the three-dimensional coordinate points of the defect region, extract the long axis and short axis direction vectors of the defect, and by calculating the angle between the vectors and the high-precision three-dimensional geometric model coordinate system (X, Y, Z axes) of the blank, the first defect spatial orientation parameter is determined and output; for the first defect structure position distribution, the three-dimensional coordinates of the defect are aligned with the structure coordinates of the high-precision three-dimensional geometric model of the blank through coordinate mapping technology, and combined with the preset partitioning data of the blank structure, such as edge zone, center zone, and process hole peripheral zone, the structure region where the defect is located is determined and the position distribution information is output. Finally, the quantification results of the above five dimensions are integrated according to the preset data format to form a complete first defect feature vector.

[0080] A pre-constructed defect suppression association rule library is called, which is formed by using a decision tree algorithm to establish the causal association between the sample defect vector and the corresponding sample suppression correction parameter obtained by process simulation repair, and is enhanced in the feature space. The library stores the corresponding rules of different defect feature vectors and suppression correction parameters. Then, the first defect feature vector obtained, including the first defect type, volume, density, spatial orientation and structure position distribution, is input into the matching system of the rule library, and a feature comparison algorithm is used to select the most suitable association rule from the rule library for each dimension parameter of the first defect feature vector. If there is a complete matching rule, the suppression correction parameter corresponding to the rule is directly extracted; if there is no complete matching item, the parameter fusion is performed on multiple rules with the highest similarity by weighted similarity calculation. Finally, the first single-dimensional suppression correction parameter matched with the first defect feature vector is output, which at least includes the suppression pressure gradient adjustment amount, such as adjusting the local area suppression pressure gradient from 1.2 MPa / mm to 1.5 MPa / mm for internal pore defects, the pressure holding time correction amount, such as extending the pressure holding time by 15 seconds to enhance the compactness of the green body and the demolding rate optimization value, such as reducing the demolding rate from 8 mm / s to 5 mm / s to reduce defects. These parameters can be directly used for single-dimensional adjustment of the subsequent pressing process to improve or eliminate the corresponding defects.

[0081] In one possible implementation manner, the step S510 further includes:

[0082] Step S511: Record a plurality of sample suppression correction parameters of a plurality of sample defect vectors by performing process simulation repair.

[0083] Step S512: Perform feature space enhancement on the plurality of sample defect vectors and the plurality of sample suppression correction parameters to obtain a sample defect vector set and a sample suppression correction set.

[0084] Step S513: Build the causal association of the sample defect vector set and the sample suppression correction set by a decision tree to construct the defect suppression association rule library.

[0085] Specifically, a simulation platform is built to adapt to the pressing process of silicon carbide blanks. This platform needs to simulate the core process parameters such as pressing pressure, holding time, demolding rate in actual production, and can digitally simulate the generation and repair process of blank defects. Then, in the simulation platform, multiple typical defect types of silicon carbide blank samples are preset, such as internal porosity, surface cracks, and local density abnormalities. For each defect type, multiple sample defect vectors containing different defect parameters such as defect volume, defect density, defect spatial orientation, and defect structure position distribution are generated to ensure that the samples cover different defect shapes and severity. Then, for each sample defect vector, the "defect-containing blank" is simulated and repaired: first, set the initial pressing parameters for simulation pressing, and observe the retention of the defect; then gradually adjust the pressing pressure gradient, holding time, demolding rate and other parameters, and after each adjustment, re-simulate and evaluate the improvement effect of the defect until the defect size or number is reduced to the preset qualified standard. Finally, record the pressing parameter combination corresponding to the successful repair of each sample defect, and form multiple sample pressing correction parameters corresponding to multiple sample defect vectors, providing basic data support for subsequent construction of defect pressing correlation rule base.

[0086] For the recorded multiple sample defect vectors, a combination of data augmentation and feature enhancement is used for processing: by adding a small random disturbance such as a ±5% parameter fluctuation in each defect feature dimension such as defect volume, density, spatial orientation, a large number of derived vectors similar to but not identical to the original sample defect vector features are generated, while supplementing defect vector samples under different working conditions such as different initial pressing temperatures and raw material particle sizes, enriching the coverage of defect features; the feature parameters of each sample defect vector are normalized to convert different dimension parameters to the [0, 1] interval, eliminating the influence of dimension difference on subsequent modeling. Then, for multiple sample pressing correction parameters, combined with the reasonable fluctuation range of process parameters in actual production, linear interpolation and boundary expansion method is used to supplement data, inserting multiple intermediate parameter values uniformly within the existing parameter interval, while reasonably extending the boundary values of the parameters, such as extending the holding time from the existing 20-60 seconds to 15-70 seconds, to ensure the continuity and integrity of the parameter distribution; then the correction parameters are standardized to convert the parameter values to standardized data with a mean of 0 and a standard deviation of 1, improving the stability of subsequent model training. Finally, all the processed sample defect vectors are arranged in a unified format to form a sample defect vector set with regular structure and rich features; at the same time, the corresponding sample pressing correction parameters are arranged and archived to form a sample pressing correction set corresponding to the sample defect vector set.

[0087] A C4.5 decision tree algorithm suitable for feature correlation modeling is selected, and the obtained sample defect vector set is taken as the model input feature, which includes defect type, defect volume, defect density, defect spatial orientation, defect structure position distribution and other dimensions. Meanwhile, the sample pressing correction set is taken as the model output label, which includes pressing pressure gradient adjustment, holding pressure time correction and demolding speed optimization value and other parameters, so as to clearly define the modeling goal of defect feature-pressing parameter. Then, the input features are discretized, and continuous features such as defect volume and defect density are divided into multiple discrete categories according to reasonable intervals, so as to facilitate the branch node splitting of the decision tree; then the decision tree training is started, and the algorithm automatically calculates the information gain ratio of each input feature, and preferentially selects the feature with the maximum information gain ratio as the root node or intermediate node, divides the sample data into different subsets according to the feature value, and gradually constructs the branch structure, such as first taking the defect type as the primary splitting feature to divide the sample into internal pores, surface cracks and other subsets, and then further splitting each subset according to the defect volume as the secondary feature, until the output label, that is, the pressing correction parameter, tends to be consistent or reaches the preset tree depth threshold. During the training process, the pruning parameters of the decision tree are adjusted through cross-validation to avoid overfitting of the model and ensure that the correlation rules have good generalization ability. After the decision tree model is trained, the path from the root node to the leaf node in the tree is extracted, the feature judgment conditions on the path constitute the "cause", and the pressing correction parameters corresponding to the leaf node constitute the "effect". These cause-effect correlations are arranged as structured rules, for example, if the defect type is internal pores and the volume is less than 5 cubic millimeters, the pressing pressure gradient adjustment is positive 0.3 megapascal per millimeter, and the holding pressure time correction is positive 10 seconds. Finally, the effectiveness of all rules is verified, the rules with conflicts are removed, the rules in the edge scenario are supplemented, and then the rules are classified and archived according to the defect type and parameter category, forming a defect pressing correlation rule library that can be directly used for subsequent defect inversion matching.

[0088] In one possible implementation manner, the step S600 further includes:

[0089] Step S610: constructing a process sensitivity field model based on the green body spatial attributes.

[0090] Step S620: mapping the plurality of single-dimensional pressing correction parameters to the process sensitivity field model for spatial coupling optimization with density optimization and distribution uniformization as multiple objectives, and outputting the global pressing coupling parameters.

[0091] Specifically, the core components of the green compact space attributes are determined, including the three-dimensional dimensions (length, width, and height) of the green compact, the particle distribution density of the raw materials in different areas, and the structural differences between the surface and the interior, such as edge fillets, internal process channels, and other key parameters. These parameters are obtained by integrating the data from the early industrial CT scanning and 3D optical scanning. Subsequently, a process sensitivity field model is constructed by combining finite element analysis and process simulation: the green compact space is divided into multiple discrete spatial units. For each unit, the influence of different pressing parameters, such as pressure and holding time, on the density distribution of the unit is simulated, and the sensitivity coefficients of each unit to the pressing parameters are quantified. These sensitivity coefficients are then arranged in a matrix according to the spatial unit positions to form a process sensitivity field model that includes sensitivity information indexed by spatial coordinates.

[0092] First, a multi-objective optimization function is set, with the overall density of the green compact reaching a pre-set optimal threshold, such as 95% of the theoretical density, as the density optimization goal, and the standard deviation of the density values of each spatial unit being less than a pre-set range, such as ±2%, as the distribution uniformization goal. A double-objective optimization function is constructed and the weight coefficients are determined, which can be adjusted according to the actual production requirements for density and uniformity. Then, the output multiple single-dimensional pressing correction parameters, such as the pressing pressure gradient adjustment amount and the holding time correction amount, are taken as input variables and mapped into the constructed process sensitivity field model. Through a multivariate coupling algorithm, such as the non-dominated sorting genetic algorithm, the input variables are iteratively optimized: in each iteration, the density simulation values of each unit of the green compact under different parameter combinations are calculated according to the process sensitivity field model, and the fitness is calculated by substituting the values into the multi-objective optimization function. The parameter combination that takes into account both density optimization and distribution uniformity is selected. After multiple iterations until the optimization result converges, i.e., the fitness changes less than a pre-set threshold for two consecutive iterations, the global pressing coupling parameters that meet the double-objective requirements are finally output. These parameters can realize the overall optimization of the green compact pressing process and ensure the quality consistency of the batch-pressed green compacts.

[0093] In the second embodiment, based on the same inventive concept as the pressing parameter optimization method based on online detection of silicon carbide green compact defects in the preceding embodiments, as shown in Figure 2 The present application provides a pressing parameter optimization system based on online detection of silicon carbide green compact defects. The system and method embodiments in the present application are based on the same inventive concept. The system comprises:

[0094] The distribution map acquisition module 10 is used to perform tomographic scanning of the to-be-sintered silicon carbide green compact by an industrial CT device to obtain a three-dimensional density distribution map of the green compact.

[0095] The geometric model acquisition module 20 is used to perform surface topography measurement on the to-be-sintered silicon carbide green compact by a 3D optical scanning device to obtain a high-precision three-dimensional geometric model of the green compact.

[0096] The space model obtaining module 30 is configured to obtain a green body fusion defect space model by performing geometric distortion correction after aligning and fusing the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model.

[0097] The defect detection module 40 is configured to perform fine-grained defect detection on the green body fusion defect space model to obtain a plurality of defect space distribution characteristics corresponding to a plurality of defect types.

[0098] The correction parameter output module 50 is configured to perform pressing associated defect inversion according to the plurality of defect space distribution characteristics to output a plurality of single-dimensional pressing correction parameters.

[0099] The coupling parameter output module 60 is configured to perform spatial multi-variable coupling processing on the plurality of single-dimensional pressing correction parameters based on green body space attributes to output global pressing coupling parameters.

[0100] The batch pressing module 70 is configured to perform batch pressing of the sintering silicon carbide green body by using the global pressing coupling parameters.

[0101] Further, the system is further configured to implement the following functions:

[0102] According to a plurality of defect size distribution sets of the plurality of defect types, a plurality of multi-scale defect characteristics are analyzed and output; the plurality of multi-scale defect characteristics are used to perform multi-scale space segmentation on the green body fusion defect space model to generate a series of scale analysis models; the series of scale analysis models are input into a multi-defect parallel detection network to perform defect parallel inference detection and output a series of scale intermediate results; after probability fusion of the series of scale intermediate results that are spatially aligned, geometric distortion verification is performed based on the green body high-precision three-dimensional geometric model to output a plurality of defect space distribution characteristics corresponding to the plurality of defect types.

[0103] Further, the system is further configured to implement the following functions:

[0104] The plurality of defect original image sets and the plurality of defect morphology identification sets of the plurality of defect types are called in a network; the plurality of defect original image sets and the plurality of defect morphology identification sets are used as training data to perform multi-directional parameter optimization of a basic defect detection model, a plurality of single-task defect detection modules are constructed; the plurality of single-task defect detection modules are connected in parallel in a logical isolation manner to construct the multi-defect parallel detection network; a plurality of single-scale pixel-level models in a first scale analysis model are input into the multi-defect parallel detection network one by one to perform defect parallel inference detection, output a plurality of single-scale pixel-level defects to constitute a first scale intermediate result; by analogy, the series of scale analysis models are input into the multi-defect parallel detection network to perform defect parallel inference detection and output the series of scale intermediate results.

[0105] Further, the system is also used to implement the following functions:

[0106] According to the plurality of defect types, the series of multi-scale pixel-level defects are obtained by decomposing the series of intermediate results of the multi-scale; according to the multi-scale defect characteristics, the multi-scale defect confidence values are set; after the plurality of defect probability maps are obtained by spatially aligning the plurality of series of multi-scale pixel-level defects, the weighted probability fusion of the plurality of defect probability maps is performed according to the multi-scale defect confidence value mapping, and the plurality of initial defect spatial distributions are output; based on the green body high-precision three-dimensional geometric model, the geometric distortion of the plurality of initial defect spatial distributions is checked, and the plurality of defect spatial distribution characteristics are output.

[0107] Further, the system is also used to implement the following functions:

[0108] The first defect feature vector is extracted from the first defect spatial distribution characteristic quantity, wherein the first defect feature vector includes the first defect type, the first defect volume, the first defect density, the first defect spatial orientation, and the first defect structure position distribution; the first single-dimensional pressing correction parameter is matched and output by using the first defect feature vector in the defect pressing correlation rule library, wherein the first single-dimensional pressing correction parameter includes but is not limited to the pressing pressure gradient adjustment amount, the pressure holding time correction amount, and the demolding speed optimization value.

[0109] Further, the system is also used to implement the following functions:

[0110] By executing the process simulation repair, the plurality of sample defect vectors and the plurality of sample pressing correction parameters are recorded; the feature space of the plurality of sample defect vectors and the plurality of sample pressing correction parameters is enhanced to obtain a sample defect vector set and a sample pressing correction set; the causal relationship between the sample defect vector set and the sample pressing correction set is constructed by decision tree to construct the defect pressing correlation rule library.

[0111] Further, the system is also used to implement the following functions:

[0112] The green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model are mapped to a unified coordinate system to perform spatial registration to obtain a preliminary registration model; after the preliminary registration model is segmented into a plurality of grid-level spatial pixel points according to a preset grid scale, the plurality of grid-level spatial pixel points are corrected based on optical geometric true values to obtain a plurality of corrected spatial pixel points; the plurality of corrected spatial pixel points are inversely recombined to restore and output the green body fusion defect spatial model.

[0113] Further, the system is also used to implement the following functions:

[0114] The first natural feature point distribution and the second natural feature point distribution are respectively identified according to the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model; the first natural feature point distribution and the second natural feature point distribution are registered by using an iterative closest point algorithm to construct a spatial transformation matrix; and the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model are mapped to a unified coordinate system to perform spatial registration according to the spatial transformation matrix, so as to obtain the preliminary registration model.

[0115] Further, the system is also used to realize the following functions:

[0116] A process sensitivity field model is constructed based on the green body spatial attributes; density optimization and distribution uniformization are taken as multiple targets, the multiple single-dimensional pressing correction parameters are mapped to the process sensitivity field model for spatial coupling optimization, and the global pressing coupling parameters are output.

[0117] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above-mentioned embodiments of the present application are described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0118] The above-mentioned is only the preferred embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

[0119] The present specification and drawings are only exemplary descriptions of the present application, and should be considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalents, the present application intends to include these modifications and changes.

Claims

1. A method for optimizing pressing parameters based on online detection of defects in silicon carbide green bodies, characterized in that, The method comprises: Carrying out tomography of the sintering silicon carbide blank to be sintered by an industrial CT device to obtain a blank three-dimensional density distribution map; Carrying out surface topography measurement of the sintering silicon carbide blank to be sintered by a 3D optical scanning device to obtain a blank high-precision three-dimensional geometric model; After aligning and fusing the blank three-dimensional density distribution map and the blank high-precision three-dimensional geometric model in space, carrying out geometric distortion correction to obtain a blank fused defect space model; Performing fine-grained defect detection on the blank fused defect space model to obtain a plurality of defect space distribution characteristics corresponding to a plurality of defect types; Performing pressing correlation defect inversion according to the plurality of defect space distribution characteristics to output a plurality of single-dimensional pressing correction parameters; Based on the spatial attributes of the blank, performing spatial multivariate coupling processing on the plurality of single-dimensional pressing correction parameters to output a global pressing coupling parameter; Using the global pressing coupling parameter to perform batch pressing of the sintering silicon carbide blank to be sintered; Performing fine-grained defect detection on the blank fused defect space model to obtain a plurality of defect space distribution characteristics corresponding to a plurality of defect types, the method comprising: According to a plurality of defect size distribution sets of the plurality of defect types, analyzing and outputting multi-scale defect characteristics; Using the multi-scale defect characteristics, performing multi-scale spatial segmentation on the blank fused defect space model to generate a series of scale analysis models; Inputting the series of scale analysis models into a multi-defect parallel detection network to perform defect parallel reasoning detection and output a series of scale intermediate results; After probability fusion of the series of scale intermediate results aligned in space, performing geometric distortion verification based on the blank high-precision three-dimensional geometric model to output a plurality of defect space distribution characteristics corresponding to the plurality of defect types.

2. The method for optimization of pressing parameters based on online detection of defects in silicon carbide green bodies as claimed in claim 1 wherein, Inputting the series of scale analysis models into a multi-defect parallel detection network to perform defect parallel reasoning detection and output a series of scale intermediate results, the method comprising: Network calling a plurality of defect original image sets and a plurality of defect morphology identification sets of the plurality of defect types; Using the plurality of defect original image sets and the plurality of defect morphology identification sets as training data, performing multi-directional parameter optimization of a basic defect detection model to construct a plurality of single-task defect detection modules; Parallelly connecting the plurality of single-task defect detection modules in a logical isolation manner to construct the multi-defect parallel detection network; Inputting a plurality of single-scale pixel-level models in a first scale analysis model into the multi-defect parallel detection network one by one to perform defect parallel reasoning detection and output a plurality of single-scale pixel-level defects to constitute a first scale intermediate result, the scale analysis model comprising a plurality of single-scale pixel-level models generated by scale segmentation, and each single-scale pixel-level model comprising local blank characteristics of the scale; By analogy, inputting the series of scale analysis models into the multi-defect parallel detection network to perform defect parallel reasoning detection and output the series of scale intermediate results.

3. The method of claim 1, wherein the pressing parameters are optimized based on the on-line detection of the silicon carbide green body defects. After probability fusion of the series of scale intermediate results aligned in space, performing geometric distortion verification based on the blank high-precision three-dimensional geometric model to output a plurality of defect space distribution characteristics corresponding to the plurality of defect types, the method comprising: According to the plurality of defect types, the series of multi-scale pixel-level defects are obtained by decomposing the series of intermediate results of the multi-scale; According to the multi-scale defect characteristics, a multi-scale defect confidence value is set; After spatially aligning the plurality of series of multi-scale pixel-level defects to obtain a plurality of defect probability maps, a weighted probability fusion of the plurality of defect probability maps is performed according to the multi-scale defect confidence value mapping, and a plurality of initial defect spatial distributions are output; Based on the green body high-precision three-dimensional geometric model, a geometric distortion check of the plurality of initial defect spatial distributions is performed, and a plurality of defect spatial distribution characteristics are output.

4. The method for optimization of pressing parameters based on online detection of defects in silicon carbide green bodies as claimed in claim 1 wherein, According to the plurality of defect spatial distribution characteristics, a pressing associated defect inversion is performed, and a plurality of single-dimensional pressing correction parameters are output, the method comprising: quantitative extraction of a first defect feature vector from a first defect spatial distribution characteristic, wherein the first defect feature vector includes a first defect type, a first defect volume, a first defect density, a first defect spatial orientation, and a first defect structure position distribution. Defect spatial distribution characteristics refer to the distribution information of each defect type in the green body three-dimensional space after multi-scale defect detection. Using the first defect feature vector in the defect pressing associated rule library, a first single-dimensional pressing correction parameter is matched and output, wherein the first single-dimensional pressing correction parameter includes but is not limited to a pressing pressure gradient adjustment amount, a holding pressure time correction amount, and a demolding rate optimization value.

5. The method for optimization of pressing parameters based on online detection of defects in silicon carbide green bodies as claimed in claim 4 wherein, The method further comprises: By performing process simulation repair, a plurality of sample defect vectors and a plurality of sample pressing correction parameters are recorded; Feature space enhancement is performed on the plurality of sample defect vectors and the plurality of sample pressing correction parameters to obtain a sample defect vector set and a sample pressing correction set; The causal relationship between the sample defect vector set and the sample pressing correction set is constructed through a decision tree to construct the defect pressing associated rule library.

6. The method of pressing parameter optimization based on online detection of silicon carbide green body defects according to claim 1, wherein, After spatially aligning and fusing the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model, geometric distortion correction is performed to obtain a green body fusion defect spatial model, the method comprising: Mapping the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model to a unified coordinate system to perform spatial registration to obtain a preliminary registration model; After segmenting the preliminary registration model into a plurality of grid-level spatial pixel points according to a preset grid scale, distortion correction of the plurality of grid-level spatial pixel points is performed based on optical geometric true values to obtain a plurality of corrected spatial pixel points; The plurality of corrected spatial pixel points are inversely recombined to restore and output the green body fusion defect spatial model.

7. The method for optimization of pressing parameters based on online detection of defects in silicon carbide green bodies as claimed in claim 6 wherein, The method further comprises: The green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model respectively identify a first natural feature point distribution and a second natural feature point distribution; The first natural feature point distribution and the second natural feature point distribution are registered using an iterative closest point algorithm to construct a spatial transformation matrix; According to the spatial transformation matrix, the green body three-dimensional density distribution map and the green body high-precision three-dimensional geometric model are mapped to a unified coordinate system to perform spatial registration to obtain the preliminary registration model.

8. The method of pressing parameter optimization based on online detection of silicon carbide green body defects according to claim 1, wherein, The system is used for implementing the pressing parameter optimization method based on the online detection of the silicon carbide blank defects according to any one of claims 1-8, and the system comprises: a distribution map acquisition module, configured to perform tomography on the to-be-sintered silicon carbide blank by an industrial CT device to obtain a blank three-dimensional density distribution map; a geometric model acquisition module, configured to perform surface topography measurement on the to-be-sintered silicon carbide blank by a 3D optical scanning device to obtain a blank high-precision three-dimensional geometric model; 9. A system for optimizing pressing parameters based on online detection of defects in silicon carbide green bodies, characterized in that, a spatial model acquisition module, configured to perform geometric distortion correction after aligning and fusing the blank three-dimensional density distribution map and the blank high-precision three-dimensional geometric model in space to obtain a blank fused defect spatial model; a defect detection module, configured to perform fine-grained defect detection on the blank fused defect spatial model to obtain a plurality of defect spatial distribution characteristics corresponding to a plurality of defect types; a correction parameter output module, configured to perform pressing associated defect inversion according to the plurality of defect spatial distribution characteristics to output a plurality of single-dimensional pressing correction parameters; a coupling parameter output module, configured to perform spatial multivariate coupling processing of the plurality of single-dimensional pressing correction parameters based on blank spatial attributes to output a global pressing coupling parameter; a batch pressing module, configured to perform batch pressing on the to-be-sintered silicon carbide blank by using the global pressing coupling parameter. The system is used for implementing the pressing parameter optimization method based on the online detection of the silicon carbide blank defects according to any one of claims 1-8, and the system comprises: a distribution map acquisition module, configured to perform tomography on the to-be-sintered silicon carbide blank by an industrial CT device to obtain a blank three-dimensional density distribution map; a geometric model acquisition module, configured to perform surface topography measurement on the to-be-sintered silicon carbide blank by a 3D optical scanning device to obtain a blank high-precision three-dimensional geometric model; a spatial model acquisition module, configured to perform geometric distortion correction after aligning and fusing the blank three-dimensional density distribution map and the blank high-precision three-dimensional geometric model in space to obtain a blank fused defect spatial model; a defect detection module, configured to perform fine-grained defect detection on the blank fused defect spatial model to obtain a plurality of defect spatial distribution characteristics corresponding to a plurality of defect types; a correction parameter output module, configured to perform pressing associated defect inversion according to the plurality of defect spatial distribution characteristics to output a plurality of single-dimensional pressing correction parameters; a coupling parameter output module, configured to perform spatial multivariate coupling processing of the plurality of single-dimensional pressing correction parameters based on blank spatial attributes to output a global pressing coupling parameter; a batch pressing module, configured to perform batch pressing on the to-be-sintered silicon carbide blank by using the global pressing coupling parameter.

Images