Material thickness cutting method of automatic slicing machine

Abstract

The invention relates to the technical field of slice detection methods, and particularly discloses a material thickness cutting method of an automatic slicer, which comprises the following steps: preparing slice sample materials: acquiring three groups of slice samples treated under a condition I, a condition II and a condition III respectively; performing three-dimensional scanning on the outer contours of the three groups of slice samples to obtain three groups of slice scanning images; sequentially inputting each group of slice scanning images into a preset three-dimensional model to train and construct a three-dimensional material data model; according to the position relation of triangular mesh information of intersection of each group of slice planes output by the three-dimensional material data model, slice parameters of the corresponding group are determined; then, according to the sequence set of the combined slice parameters, carrying out self-adaptive slice processing on the multi-layer slices subjected to random superposition of different groups; if the self-adaptive slicing processing meets the requirement, continuing to carry out the next layer of slicing processing, and outputting a previous layer of slicing processing result; and if not, pausing the slicing processing of the current layer, and generating an adjustment strategy.

Description

Technical Field

[0001] The invention relates to the technical field of slicing detection methods, and in particular to a material thickness cutting method of an automatic slicing machine. Background Art

[0002] Modern automatic slicers are precision mechanical devices that are used to slice various materials into thin slices. These machines play an important role in the fields of materials science, biomedicine, and electronic manufacturing. They are able to provide high-precision and high-efficiency slice services and are suitable for slice processing of hard materials such as metals and ceramics, as well as soft materials such as food and biological tissues.

[0003] In the material thickness cutting method of the automatic slicer, it is usually involved to detect the uniformity of the slice thickness, the cutting speed, the degree of material damage, and the method of improving the automation and intelligence level of the equipment. Existing, in the automatic slicer, the grid model is used to calculate the movement trajectory of the slicer prop to realize the slice simulation and plan the slice process to ensure the accuracy and repeatability of the slice.

[0004] The material is sliced ​​by adaptively analyzing data through a grid model combined with sensors. Existing methods usually require edge selection and cutting of redundant parts for multi-layer slices, and in the actual slicing position selection process, it is necessary to make multiple judgments on the overlap between the current slicing plane and the triangular grid at the cutting position, which ultimately affects the adaptive slicing efficiency of the material, the quality of subsequent processing, the optimization of cutting speed, and reduces slicing production efficiency and material cost control. Summary of the invention

[0005] The purpose of the present invention is to provide a material thickness cutting method for an automatic slicer to solve the following technical problems: How to reduce the number of times the slice plane overlaps with the triangular mesh identification area at the resection position, and improve the slice production efficiency and material cost control.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A material thickness cutting method for an automatic slicer, the method comprising: S1. Prepare slice sample materials: obtain three groups of slice samples processed under condition one, condition two, and condition three respectively; Condition 1 is the setting of uniform slice thickness; Condition 2 is the setting of slice thickness changing with position information; Condition 3 is the setting of gradual increase / decrease of slice thickness; S2, respectively perform three-dimensional scanning on the external contours of the three groups of slice samples to obtain three groups of slice scan images, and input each group of slice scan images into a preset three-dimensional model in turn to train and construct a three-dimensional material data model; S3, analyzing the triangular mesh information of each group of slice plane intersections output by the three-dimensional material data model based on the triangular mesh coordinates, determining the positional relationship between the triangular mesh and the plane, and determining the slice parameters of the corresponding group according to the positional relationship; S4, acquiring three groups of slice samples in real time, performing random superposition of different groups to form a multi-layer slice set, and performing adaptive slice processing on the multi-layer slice according to the sequence set of combined slice parameters; And determine whether the adaptive slicing process meets the requirements: If yes, continue to process the next layer of slices and output the processing result of the previous layer of slices; If not, the current layer slice processing is suspended and an adjustment strategy is generated; S5. Obtain the contour information of each layer after slicing, input the three-dimensional material data model training output superimposed slicing direction and thickness information in sequence, and obtain the actual slicing processing result.

[0007] Preferably, the method of judging whether the adaptive slicing process meets the requirements is: Get the number of slice samples and sample group information for each slice layer, and collect the current slice adaptability coefficient according to the current slice direction: By formula Calculate the Layer slice adaptability coefficient ; in, is the total number of samples in the current layer, and ∈ ; For the Layer Slice The slice parameter of each sample changes in real time. To set the time interval under the slice parameters, is the conversion function; For the Layer Slice The slice position coefficient for each sample.

[0008] Preferably, the Layer slice adaptability coefficient The threshold interval of the preset slice adaptability coefficient To compare the sizes: like , then it is judged that the current layer slicing processing meets the requirements; like , then it is judged that the current layer slice processing does not meet the requirements and an adjustment strategy is generated.

[0009] Preferably, the adjustment strategy includes: like < , then increase the acquisition frequency of slice parameters and shorten the acquisition interval; like > , then reduce the acquisition frequency of slice parameters and extend the acquisition interval.

[0010] Preferably, the method of constructing the three-dimensional material data model in step S2 is: S21, using a three-dimensional scanning technology to perform high-precision scanning on the external contours of the three groups of slices, obtaining two-dimensional scanning images of the surfaces of the three groups of slice samples, and obtaining contour information of the two-dimensional scanning images of the surfaces of the slice samples; S22, inputting each set of two-dimensional scanned images and their contour information into a preset three-dimensional model for deep learning based on a three-dimensional reconstruction algorithm, outputting three-dimensional spatial information corresponding to each set of two-dimensional scanned images, and obtaining feature points and structures of each set of slice samples; S23, converting the extracted feature points and structures into a grid model in a three-dimensional space, training the three-dimensional model using the three-dimensional space information obtained by the grid model, adjusting the model parameters through an iterative optimization algorithm, and optimizing the three-dimensional shape and structure; S24, training to form a three-dimensional material data model based on the optimized three-dimensional spatial information, and outputting the three-dimensional shape, thickness and position information of each group of slice samples in the three-dimensional material data model.

[0011] Preferably, step S3 includes: S31, respectively obtaining the number of coordinate intersections of each set of slice planes in the triangular mesh information; S32, calculating the line equation between each intersection point based on the fixed point coordinates of the triangular mesh; S33, obtaining the coordinate value of each intersection point according to the line equation; S34. Obtain slice parameters of the group according to the number of coordinate intersections and the coordinate values.

[0012] Preferably, the slice parameters are obtained in the following manner: If the triangle mesh and Layer Slice Plane Do not intersect, set the slice parameters to ; If the triangle mesh and Layer Slice Plane There is only one intersection point, set the slice parameters to ; If the triangle mesh and Layer Slice Plane There are two intersection points: If two vertices are coplanar with another vertex, then = and = ,but ; If two vertices are not on the same plane as the other vertex, set the slice parameters to ; is the distance between two intersection points, and 0< ≤ , To preset the standard distance value between two intersection points, is the preset weight coefficient, and 0< <1; If the triangle mesh and Layer Slice Plane Overlap; set the slice parameter to 1.

[0013] Preferably, the adaptive slicing process further comprises obtaining an adaptive slice thickness , the slice thickness is determined based on the changes in the slice parameters of the layer and the cumulative slice time The angle changes with respect to the slice plane.

[0014] Beneficial effects of the present invention: (1) The present invention obtains sliced ​​sample materials under designed processing conditions, and the processing conditions set respectively are divided into three categories. Condition 1 is a setting for uniform slicing with equal thickness, condition 2 is a setting for slicing thickness varying with position information; condition 3 is a setting for gradual increase / decrease in slicing thickness; the corresponding parameters for the setting of increasing and decreasing slicing thickness are pre-set according to actual experiments; by realizing the diversified parameter selection of the cutting shape of subsequent superimposed slicing by realizing the setting of the cutting condition of the sliced ​​material, the initial sample cutting is optimized.

[0015] (2) The present invention acquires three groups of slice samples in real time and randomly superimposes different groups to form a multi-layer slice set, and performs adaptive slicing processing on the multi-layer slices according to the sequential set of combined slice parameters; and determines whether the adaptive slicing processing meets the requirements and generates an adjustment strategy. The technical adjustment of the slice parameters is timely made through the adjustment strategy, thereby reducing the number of times the overlap between the current layer slice plane and the triangular mesh recognition area at the resection position is determined, thereby improving the slicing operation efficiency.

[0016] (3) The present invention obtains randomly selected slices from three groups of slice samples after preprocessing in real time and superimposes them to form a set of multi-layer slices. After the multi-layer slice processing, the slice parameters (such as thickness, shape, position, etc.) after the adaptive slice processing are timely judged to determine whether the adaptive slice processing meets the requirements and then evaluate the characteristics of the overall slice set; the multi-layer slices are adaptively sliced ​​according to the sequential set of combined slice parameters. This processing setting ensures the diversity and unpredictability of each processing, increases the flexibility of the slice processing process and improves the slicing efficiency; thereby improving the slicing production efficiency and controlling the material cost.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 A step diagram of a material thickness cutting method of an automatic slicer of the present invention; Figure 2 A diagram showing the steps of constructing a three-dimensional material data model in step S2 of the present invention; Figure 3 This is a step diagram of the method for obtaining slice parameters in step S3 of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] See also Figure 1 As shown, the present invention is a material thickness cutting method of an automatic slicer, the method comprising: S1. Prepare slice sample materials: obtain three groups of slice samples processed under condition one, condition two, and condition three respectively; Condition 1 is the setting of uniform slice thickness; Condition 2 is the setting of slice thickness changing with position information; Condition 3 is the setting of gradual increase / decrease of slice thickness; S2, respectively perform three-dimensional scanning on the external contours of the three groups of slice samples to obtain three groups of slice scan images, and input each group of slice scan images into a preset three-dimensional model in turn to train and construct a three-dimensional material data model; S3, analyzing the triangular mesh information of each group of slice plane intersections output by the three-dimensional material data model based on the triangular mesh coordinates, determining the positional relationship between the triangular mesh and the plane, and determining the slice parameters of the corresponding group according to the positional relationship; S4, acquiring three groups of slice samples in real time, performing random superposition of different groups to form a multi-layer slice set, and performing adaptive slice processing on the multi-layer slice according to the sequence set of combined slice parameters; And determine whether the adaptive slicing process meets the requirements: If yes, continue to process the next layer of slices and output the processing result of the previous layer of slices; If not, the current layer slice processing is suspended and an adjustment strategy is generated; S5. Obtain the contour information of each layer after slicing, input the three-dimensional material data model training output superimposed slicing direction and thickness information in sequence, and obtain the actual slicing processing result.

[0022] In the above technical scheme, this embodiment designs a material thickness cutting method for an automatic slicer. First, the preparation of the sliced ​​sample material is completed. The sliced ​​sample material is obtained according to different processing conditions. The set processing conditions are divided into three categories. Condition one is to set equal thickness uniform slicing. Condition two is to set the slice thickness to change with position information. Condition three is to set the slice thickness to increase / decrease gradually. The corresponding parameters of the slice thickness increase and decrease settings are pre-set according to actual experiments. By realizing the diversified parameter selection of the cutting shape of the subsequent superimposed slices that reduces the setting of the cutting situation of the sliced ​​material, the initial sample cutting is optimized.

[0023] Secondly, the external contours of the three groups of slice samples are scanned in three dimensions respectively, and three groups of slice scan images are obtained based on the three-dimensional scanning. Each group of slice scan images is input into the preset three-dimensional model in turn to train and construct a three-dimensional material data model. The construction of the three-dimensional material data model here is based on machine learning to construct a preliminary three-dimensional model of the acquired scan image point cloud data information, and optimize the simulation according to the input conditions to obtain the three-dimensional material data model.

[0024] For details, please refer to Figure 3 As shown, as an implementation of the present invention, the specific method of constructing the three-dimensional material data model in step S2 is: S21, using a three-dimensional scanning technology to perform high-precision scanning on the external contours of the three groups of slices, obtaining two-dimensional scanning images of the surfaces of the three groups of slice samples, and obtaining contour information of the two-dimensional scanning images of the surfaces of the slice samples; S22, inputting each set of two-dimensional scanned images and their contour information into a preset three-dimensional model for deep learning based on a three-dimensional reconstruction algorithm, outputting three-dimensional spatial information corresponding to each set of two-dimensional scanned images, and obtaining feature points and structures of each set of slice samples; S23, converting the extracted feature points and structures into a grid model in a three-dimensional space, training the three-dimensional model using the three-dimensional space information obtained by the grid model, adjusting the model parameters through an iterative optimization algorithm, and optimizing the three-dimensional shape and structure; S24, training to form a three-dimensional material data model based on the optimized three-dimensional spatial information, and outputting the three-dimensional shape, thickness and position information of each group of slice samples in the three-dimensional material data model.

[0025] In the above technical scheme, in this embodiment, the contour information of the two-dimensional scanned image is first obtained, and then the machine recognition and analysis are performed according to the contour information of the two-dimensional scanned image, and the two-dimensional scanned image is converted into three-dimensional space information through software and algorithms. This usually involves the recognition, edge detection and feature extraction of image point cloud information, cleaning and preprocessing of the original data, removing noise, and unifying the format to determine the feature points and structures in the image. Then, the extracted feature points and structures are converted into a grid model in three-dimensional space. The grid model is a mathematical structure used to represent the shape of an object in three-dimensional space. It consists of a series of interconnected points (vertices), lines (edges) and faces (faces). This design takes a triangular grid as an example. Through the grid model, the interaction between the tool and the material can be simulated on the computer, the slicing path can be optimized, the material waste can be reduced, and the production efficiency can be improved; this practical design uses the three-dimensional space information obtained by the grid model to train the three-dimensional model, adjust the model parameters through the iterative optimization algorithm, and optimize the three-dimensional shape and structure. Finally, the current three-dimensional model is updated according to the optimized three-dimensional space information training to form a three-dimensional material data model, and the three-dimensional shape, thickness and position information of each group of slice samples are finally output through the updated model to complete the slicing superposition molding of the material thickness, thereby obtaining a three-dimensional entity.

[0026] Thirdly, the triangular mesh information of each group of intersecting slicing planes output by the three-dimensional material data model is analyzed based on the triangular mesh coordinates, and the coordinate information of the triangular mesh that constitutes the basis of the model is extracted from the three-dimensional material data model to form the basic structural unit of the model; the slicing parameters of the corresponding group are determined according to the positional relationship between the triangular mesh and the plane; wherein the position and direction of the slicing plane are defined, and its slicing parameters are clarified in the three-dimensional coordinate system, and the setting of this plane will be used for subsequent cutting operations; the intersection between the slicing plane and the triangular mesh is detected by an algorithm, and the intersection lines or intersection points are generated by the intersection results, and these intersection points and intersection lines will be used for the subsequent selection of slicing parameters for samples.

[0027] In addition, for the acquisition and analysis process of slice parameters: Slice parameter calculation: Calculate slice thickness, position and other parameters based on positional relationships and information about intersection points / intersection lines. For example, if the intersection of two adjacent triangle meshes generates an intersection line on a plane, the length and coordinate position of this intersection line can be used to determine an edge of a slice.

[0028] Adjust slice parameters: Based on the calculated parameters, fine-tune the thickness and position of the slices to ensure that the quality of the slices meets the requirements. For slices that are too small, eliminate them and adjust the thickness to maintain continuity.

[0029] Slicing data integration: All calculated slicing parameters are organized into an ordered data set to guide subsequent slicing operations.

[0030] Slicing implementation: Based on the integrated parameters, the actual slicing operation is performed to accurately separate the required parts from the 3D model.

[0031] For details, please refer to Figure 3 As shown, as an implementation of the present invention, the process of obtaining the slice parameters in the above step S3 includes: S31, respectively obtaining the number of coordinate intersections of each set of slice planes in the triangular mesh information; S32, calculating the line equation between each intersection point based on the fixed point coordinates of the triangular mesh; S33, obtaining the coordinate value of each intersection point according to the line equation; S34. Obtain slice parameters of the group according to the number of coordinate intersections and the coordinate values.

[0032] In the above technical scheme, this embodiment obtains the intersection of each set of slicing planes in the triangular mesh, and positions them according to the thickness setting and the starting position of the slice, obtains the positioning coordinate point of the cutting point and the connecting line between the two coordinate points, and uses them as a reference for setting the slicing parameters at the cutting point.

[0033] Specifically, as an implementation of the present invention, the slicing parameter acquisition method is: If the triangle mesh and Layer Slice Plane Do not intersect, set the slice parameters to ; If the triangle mesh and Layer Slice Plane There is only one intersection point, set the slice parameters to ; If the triangle mesh and Layer Slice Plane There are two intersection points: If two vertices are coplanar with another vertex, then = and = ,but ; If two vertices are not on the same plane as the other vertex, set the slice parameters to ; is the distance between two intersection points, and 0< ≤ , To preset the standard distance value between two intersection points, is the preset weight coefficient, and 0< <1; If the triangle mesh and Layer Slice Plane Overlap; set the slice parameter to 1.

[0034] In the above technical solution, this embodiment sets the corresponding slice parameter by analyzing the positional relationship between the triangle mesh and the slice plane of the current layer, and the size of this parameter is processed according to the positional relationship. Layer Slice Plane Do not intersect, for example, set the slice parameter to , " " indicates that no slicing is required, and for the triangle mesh and the Layer Slice Plane There is only one intersection point, set the slice parameters to This means that no slicing is required. Since the position of a point here just meets the requirement of eliminating too small slices, the current setting does not need to be processed. In addition, if the triangle mesh is Layer Slice Plane There are two intersection points, then there are two cases, for two vertices and another vertex on the same plane, then = and = ,but , indicating that no slicing is required; if two vertices are not on the same plane as another vertex, that is, the triangle mesh passes through the slicing plane of this layer, the slicing parameters are set to ; is the distance between two intersection points, and 0< ≤ , To preset the standard distance value between two intersection points, is the preset weight coefficient, and 0< <1. Finally, for the triangle mesh and the Layer Slice Plane If they overlap, the slicing plane of this layer is determined to be the slicing location of the triangular mesh; the slicing parameter is set to 1, and "1" means that the entire plane is to be completely sliced.

[0035] Fourthly, slices are further randomly selected from the three groups of slice samples obtained in real time after preprocessing to be superimposed to form a collection of multi-layer slices. This setting ensures the diversity and unpredictability of each processing, and ensures that the multi-layer slices are adaptively sliced ​​according to the sequential set of combined slice parameters, which increases the flexibility of the slice processing process and improves the slicing efficiency; after the multi-layer slice processing, the slice parameters (such as thickness, shape, position, etc.) after the adaptive slice processing are timely judged to determine whether the adaptive slice processing meets the requirements and then evaluate the characteristics of the overall slice collection. If the specific judgment result meets the requirements, the next layer of slice processing will continue, and the previous layer of slice processing results will be output; if it does not meet the requirements, the current layer of slice processing will be paused, and an adjustment strategy will be generated to automatically adjust the position, angle and other parameters of the slice tool through computer software to adapt to the characteristics of the current slice collection. This adaptive slice processing ensures the accuracy and consistency of each slice.

[0036] Among them, the process of forming the adjustment strategy: when the slicing processing does not meet the requirements, the system will analyze the reasons and generate corresponding adjustment strategies. The specific settings include changing the slicing parameters, adjusting the tool path, etc., to correct the deviation and ensure the smooth progress of subsequent processing.

[0037] As an implementation manner of the present invention, specifically, a method for determining whether the adaptive slicing processing meets the requirements is: Get the number of slice samples and sample group information for each slice layer, and collect the current slice adaptability coefficient according to the current slice direction: By formula Calculate the Layer slice adaptability coefficient ; in, is the total number of samples in the current layer, and ∈ ; For the Layer Slice The slice parameter of each sample changes in real time. To set the time interval under the slice parameters, is the conversion function; For the Layer Slice The slice position coefficient for each sample.

[0038] In the above technical solution, the rationality judgment of the adaptive slicing processing in this embodiment is a process of obtaining the size of the adaptability coefficient and performing rationality judgment, specifically through the formula Calculate the Layer slice adaptability coefficient ; According to the set processing time period The real-time change of slice parameters based on the cumulative number of samples within the set time period is calculated to determine whether the conversion efficiency meets the specified size when the current slice switches to the processing state, that is, the rationality of the current slice efficiency is determined based on the cumulative changes in slice parameters completed within the set time period.

[0039] It needs to be explained that the conversion function To obtain the data according to the test data fitting, and convert the current real-time slice parameters into data to ensure the reasonable variation range of the obtained adaptability coefficient; set the time interval under the slice parameters It is the set time length for performing slicing processing with corresponding slicing parameters in the current layer under the state of known thickness. This time length is set in advance according to the specific superposition state and will not be described in detail here.

[0040] As an embodiment of the present invention, Layer slice adaptability coefficient The threshold interval of the preset slice adaptability coefficient To compare the sizes: like , then it is judged that the current layer slicing processing meets the requirements; like , then it is judged that the current layer slice processing does not meet the requirements and an adjustment strategy is generated.

[0041] In the above technical solution, the size of the slice adaptability coefficient in this embodiment is determined by comparing the size of the preset interval, and when The slice adaptability coefficient threshold interval that belongs to the setting If it is within the normal range, it is judged that the current layer slicing processing settings meet the requirements. If it does not meet the requirements of the current layer slicing processing, it is necessary to form an adjustment strategy to change the slice parameter size or change the starting path of the slice to adjust the slice parameter size order, etc.

[0042] As an implementation mode of the present invention, the adjustment strategy includes: like < , then increase the acquisition frequency of slice parameters and shorten the acquisition interval; like > , then reduce the acquisition frequency of slice parameters and extend the acquisition interval.

[0043] As an embodiment of the present invention, in addition to determining and setting parameters for adaptive slicing processing, adaptive slicing processing also includes obtaining adaptive slicing thickness. , the slice thickness is determined based on the changes in the slice parameters of the layer and the cumulative slice time The angle changes with respect to the slice plane.

[0044] In the above technical solution, since the slice thickness of the material at different positions during the slicing process is different, it is also necessary to obtain the slice thickness and slice angle information through adaptive slicing processing. By utilizing the size of the angle between the normal vector of the triangular mesh and the cutting plane, a mathematical model for determining the adaptive slice thickness is established. By slicing with an appropriate amount of thickness, it is ensured that the efficiency of the variable slice processing meets the production requirements.

[0045] Fifth, finally obtain the contour information of each layer after slicing, input the three-dimensional material data model training output superimposed slicing direction and thickness information in turn, and obtain the actual slicing processing results.

[0046] In the above technical scheme, in the slicing process of the three-dimensional material data model, the slices are grouped under different conditions, the slice parameters set by different groups are randomly combined and layered, and the contour information of each layer of slices is obtained by cutting. The direction and thickness information of the superimposed slices are combined to output the actual processing results, which is a key link to ensure the accuracy and practicality of the model.

[0047] The specific slicing process is as follows: Slice contour information extraction: Perform detailed analysis on each slice layer, identify and record the outer boundary and internal feature contour of each slice for preprocessing, filter out unclear parts, and extract its edge contour information.

[0048] Slice direction and thickness confirmation: Determine the stacking direction and thickness of each slice layer. The overall direction should be consistent with the required model construction axis, and its thickness needs to be set according to design requirements or processing limitations to ensure accurate stacking of each layer.

[0049] Superimposed slice processing: Each layer of slices is superimposed in the specified direction and thickness to form a complete three-dimensional model, which verifies the consistency and accuracy of the model.

[0050] Actual processing result output: Output the processing result of each slice, including the slice contour map, thickness parameters, stacking direction and other information, to ensure the correctness of the verification model and the subsequent processing and manufacturing process.

[0051] Result verification and adjustment: Compare the slice processing results with the expected goals, verify the model's fit and performance, and make minor adjustments to optimize model performance.

[0052] Data analysis and reporting: Collect and analyze the processing data of each slice layer and organize it into a report form for reference for subsequent research and improvement.

[0053] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0054] The above specific embodiments of this specification are described. Other embodiments are within the scope of the attached documents. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0055] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this application, they shall all fall within the protection scope of the present invention.

Claims

1. A material thickness cutting method of an automatic slicer, characterized in that: The method comprises: S1. Prepare slice sample materials: obtain three groups of slice samples processed under condition one, condition two, and condition three respectively; The first condition is a setting in which the slice thickness is uniform; the second condition is a setting in which the slice thickness varies with the position information; the third condition is a setting in which the slice thickness gradually increases / decreases; S2, respectively perform three-dimensional scanning on the external contours of the three groups of slice samples to obtain three groups of slice scan images, and input each group of slice scan images into a preset three-dimensional model in turn to train and construct a three-dimensional material data model; S3, analyzing the triangular mesh information of each group of slice plane intersections output by the three-dimensional material data model based on the triangular mesh coordinates, determining the positional relationship between the triangular mesh and the plane, and determining the slice parameters of the corresponding group according to the positional relationship; S4, acquiring three groups of slice samples in real time, performing random superposition of different groups to form a multi-layer slice set, and performing adaptive slice processing on the multi-layer slice according to the sequence set of combined slice parameters; And determine whether the adaptive slicing process meets the requirements: If yes, continue to process the next layer of slices and output the processing result of the previous layer of slices; If not, the current layer slice processing is suspended and an adjustment strategy is generated; S5. Obtain the contour information of each layer after slicing, input the three-dimensional material data model training output superimposed slicing direction and thickness information in sequence, and obtain the actual slicing processing result.

2. The material thickness cutting method of an automatic slicer according to claim 1, characterized in that: The method for determining whether the adaptive slicing process meets the requirements is: Get the number of slice samples and sample group information for each slice layer, and collect the current slice adaptability coefficient according to the current slice direction: By formula Calculate the Layer slice adaptability coefficient ; in, is the total number of samples in the current layer, and ∈ ; For the Layer Slice The slice parameter of each sample changes in real time. To set the time interval under the slice parameters, is the conversion function; For the Layer Slice The slice position coefficient for each sample.

3. The material thickness cutting method of an automatic slicer according to claim 2, characterized in that: The first Layer slice adaptability coefficient The threshold interval of the preset slice adaptability coefficient To compare the sizes: like , then it is judged that the current layer slicing processing meets the requirements; like , then it is judged that the current layer slice processing does not meet the requirements and an adjustment strategy is generated.

4. The material thickness cutting method of an automatic slicer according to claim 3, characterized in that: The adjustment strategies include: like < , then increase the acquisition frequency of slice parameters and shorten the acquisition interval; like > , then reduce the acquisition frequency of slice parameters and extend the acquisition interval.

5. The material thickness cutting method of an automatic slicer according to claim 1, characterized in that: The method of constructing the three-dimensional material data model in step S2 is: S21, using a three-dimensional scanning technology to perform high-precision scanning on the external contours of the three groups of slices, obtaining two-dimensional scanning images of the surfaces of the three groups of slice samples, and obtaining contour information of the two-dimensional scanning images of the surfaces of the slice samples; S22, inputting each set of two-dimensional scanned images and their contour information into a preset three-dimensional model for deep learning based on a three-dimensional reconstruction algorithm, outputting three-dimensional spatial information corresponding to each set of two-dimensional scanned images, and obtaining feature points and structures of each set of slice samples; S23, converting the extracted feature points and structures into a grid model in a three-dimensional space, training the three-dimensional model using the three-dimensional space information obtained by the grid model, adjusting the model parameters through an iterative optimization algorithm, and optimizing the three-dimensional shape and structure; S24, training to form a three-dimensional material data model based on the optimized three-dimensional spatial information, and outputting the three-dimensional shape, thickness and position information of each group of slice samples in the three-dimensional material data model.

6. The material thickness cutting method of an automatic slicer according to claim 1, characterized in that: Step S3 includes: S31, respectively obtaining the number of coordinate intersections of each set of slice planes in the triangular mesh information; S32, calculating the line equation between each intersection point based on the fixed point coordinates of the triangular mesh; S33, obtaining the coordinate value of each intersection point according to the line equation; S34. Obtain slice parameters of the group according to the number of coordinate intersections and the coordinate values.

7. The material thickness cutting method of an automatic slicer according to claim 6, characterized in that: The slicing parameter acquisition method is: If the triangle mesh and Layer Slice Plane Do not intersect, set the slice parameters to ; If the triangle mesh and Layer Slice Plane There is only one intersection point, set the slice parameters to ; If the triangle mesh and Layer Slice Plane There are two intersection points: If two vertices are coplanar with another vertex, then = and = ,but ; If two vertices are not on the same plane as the other vertex, set the slice parameters to ; is the distance between two intersection points, and 0< ≤ , To preset the standard distance value between two intersection points, is the preset weight coefficient, and 0< <1; If the triangle mesh and Layer Slice Plane Overlap; set the slice parameter to 1.

8. The material thickness cutting method of an automatic slicer according to claim 1, characterized in that: The adaptive slicing process also includes obtaining an adaptive slice thickness , the slice thickness is determined according to the changes in the slice parameters of the layer and the cumulative slice time The angle changes with respect to the slice plane.

Images