3D printing success rate prediction method and system based on slice processing analysis

Abstract

The application discloses a 3D printing success rate prediction method and system based on slice processing analysis, and the method comprises the following steps: obtaining three-dimensional model data to be printed; based on a slice processing algorithm, slice processing is performed on the three-dimensional model data to obtain a plurality of slice data; for any two adjacent slice data, the data similarity between the two slice data is calculated; according to the data similarity corresponding to all the slice data, the printing success rate corresponding to the three-dimensional model data is analyzed. It can be seen that the application can realize accurate printing success rate evaluation based on slice similarity analysis, improve the reliability and printing quality of the 3D printing task, and reduce the printing failure risk caused by abnormal slice data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a 3D printing success rate prediction method and system based on slice processing analysis. Background Art

[0002] With the widespread application of 3D printing technology in the field of high-precision manufacturing, companies and users are paying more and more attention to improving the accuracy and reliability of printing task planning by optimizing slice data analysis. Existing technologies usually obtain 3D model data and use standard slice processing algorithms to generate slice data, and analyze printing feasibility based on simple geometric checks or fixed evaluation rules to support printing task planning. Existing solutions lack dynamic analysis of the similarity of adjacent slice data and in-depth prediction of timing characteristics, making it difficult to accurately evaluate the printing success rate. Commonly used static analysis methods cannot adapt to complex model structures, resulting in insufficient prediction accuracy. Printing failures are easily caused by abnormal slice data, which limits the reliability and efficiency of 3D printing tasks. It can be seen that the existing technology has defects that need to be addressed urgently. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a 3D printing success rate prediction method and system based on slice processing analysis, which can realize accurate printing success rate evaluation based on slice similarity analysis, improve the reliability and printing quality of 3D printing tasks, and reduce the risk of printing failure due to abnormal slice data.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a 3D printing success rate prediction method based on slice processing analysis, the method comprising:

[0005] Obtaining three-dimensional model data to be printed;

[0006] Based on a slicing processing algorithm, slicing the three-dimensional model data to obtain a plurality of slice data;

[0007] For any two adjacent slice data, calculating the data similarity between the two slice data;

[0008] The printing success rate corresponding to the three-dimensional model data is analyzed according to the data similarities corresponding to all the slice data.

[0009] As an optional embodiment, in the first aspect of the present invention, the slicing process of the three-dimensional model data to obtain a plurality of slice data based on a slicing process algorithm includes:

[0010] Establishing a three-dimensional coordinate system with the geometric center point of the bottom surface of the three-dimensional model data as the origin;

[0011] Processing the three-dimensional model data in sections using the X-axis and Y-axis of the three-dimensional coordinate system to obtain a section graph;

[0012] Calculating vertical continuity parameters of the cross-sectional figure;

[0013] calculating a slice spacing proportional to the vertical coherence parameter;

[0014] According to the slice spacing, the three-dimensional model data is sliced ​​in the Z coordinate axis direction of the three-dimensional coordinate system to obtain a plurality of slice data.

[0015] As an optional embodiment, in the first aspect of the present invention, the calculating the vertical continuity parameter of the cross-sectional graph includes:

[0016] Based on a preset line segment division rule, determining a plurality of line segments corresponding to the cross-sectional figure;

[0017] For each line segment of the cross-sectional figure, calculating the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system;

[0018] Filter out the line segments whose parallelism is greater than a preset threshold value to obtain a plurality of vertical line segments;

[0019] The weighted sum average of the curvatures corresponding to all the vertical line segments is calculated to obtain the vertical continuity parameter of the cross-sectional figure; wherein the weighted calculation weight corresponding to each curvature is proportional to the parallelism corresponding to the corresponding vertical line segment.

[0020] As an optional embodiment, in the first aspect of the present invention, calculating the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system includes:

[0021] The line segment is processed based on an approximate fitting algorithm to obtain a plurality of interconnected straight line segment parts;

[0022] Calculating the angle difference between each of the straight line segments and the Z coordinate axis direction of the three-dimensional coordinate system;

[0023] The average value of all the angle differences is calculated to obtain the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system.

[0024] As an optional implementation, in the first aspect of the present invention, the calculating the data similarity between the two slice data includes:

[0025] Determining the slice graphic outer contours and printing material characteristics of the two slice data;

[0026] Calculating the graphic similarity between the outer contours of the slice graphics of the two slice data;

[0027] Calculating material conversion time corresponding to the printing material features of the two slice data according to historical printing records of the corresponding printing device;

[0028] The weighted average value of the graphic similarity and the material transformation time is calculated to obtain the data similarity between the two slice data.

[0029] As an optional embodiment, in the first aspect of the present invention, calculating the material conversion time corresponding to the printing material features of the two slice data based on the historical printing records of the corresponding printing device includes:

[0030] Filtering out a plurality of target printing records including the printing material features of the two slice data from historical printing records of the corresponding printing device;

[0031] The inverse of the average value of the printing times in all the target printing records is calculated to obtain the material conversion time corresponding to the printing material characteristics of the two slice data.

[0032] As an optional embodiment, in the first aspect of the present invention, analyzing the printing success rate corresponding to the three-dimensional model data based on the data similarity corresponding to all the slice data includes:

[0033] For each slice data, calculating the average value of the data similarity between the slice data and two adjacent slice data, to obtain the printing continuity corresponding to the slice data;

[0034] Sorting the printing coherence corresponding to all the slice data based on the order of the corresponding slice layers to obtain a coherence sequence;

[0035] The coherence sequence is input into a trained LSTM neural network to obtain the printing success rate corresponding to the three-dimensional model data; the LSTM neural network is trained by a training data set including a plurality of training slice data coherence sequences and corresponding printing success rate annotations.

[0036] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0037] Determining whether the printing success rate is greater than a first success rate threshold;

[0038] If yes, no further step is required;

[0039] If not, segmenting the coherent sequence based on a preset segmentation interval to obtain a plurality of partial sequences;

[0040] Inputting each of the partial sequences into the LSTM neural network to obtain a corresponding sequence printing success rate;

[0041] Screen out all partial sequences whose printing success rates of the sequences are less than a second success rate threshold to obtain fault sequences;

[0042] The slice data corresponding to the fault sequence is determined as a possible fault slice and pushed to the user terminal for display.

[0043] A second aspect of an embodiment of the present invention discloses a 3D printing success rate prediction system based on slice processing analysis, the system comprising:

[0044] An acquisition module, used to acquire the three-dimensional model data to be printed;

[0045] A processing module, configured to slice the three-dimensional model data to obtain a plurality of slice data based on a slice processing algorithm;

[0046] A calculation module, configured to calculate the data similarity between any two adjacent slice data;

[0047] An analysis module is used to analyze the printing success rate corresponding to the three-dimensional model data according to the data similarity corresponding to all the slice data.

[0048] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the processing module slices the three-dimensional model data to obtain a plurality of slice data based on a slice processing algorithm includes:

[0049] Establishing a three-dimensional coordinate system with the geometric center point of the bottom surface of the three-dimensional model data as the origin;

[0050] Processing the three-dimensional model data in sections using the X-axis and Y-axis of the three-dimensional coordinate system to obtain a section graph;

[0051] Calculating vertical continuity parameters of the cross-sectional figure;

[0052] calculating a slice spacing proportional to the vertical coherence parameter;

[0053] According to the slice spacing, the three-dimensional model data is sliced ​​in the Z coordinate axis direction of the three-dimensional coordinate system to obtain a plurality of slice data.

[0054] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the processing module calculates the vertical continuity parameter of the cross-sectional graph includes:

[0055] Based on a preset line segment division rule, determining a plurality of line segments corresponding to the cross-sectional figure;

[0056] For each line segment of the cross-sectional figure, calculating the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system;

[0057] Filter out the line segments whose parallelism is greater than a preset threshold value to obtain a plurality of vertical line segments;

[0058] The weighted sum average of the curvatures corresponding to all the vertical line segments is calculated to obtain the vertical continuity parameter of the cross-sectional figure; wherein the weighted calculation weight corresponding to each curvature is proportional to the parallelism corresponding to the corresponding vertical line segment.

[0059] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the processing module calculates the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system includes:

[0060] The line segment is processed based on an approximate fitting algorithm to obtain a plurality of interconnected straight line segment parts;

[0061] Calculating the angle difference between each of the straight line segments and the Z coordinate axis direction of the three-dimensional coordinate system;

[0062] The average value of all the angle differences is calculated to obtain the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system.

[0063] As an optional implementation, in the second aspect of the present invention, the specific manner in which the calculation module calculates the data similarity between the two slice data includes:

[0064] Determining the slice graphic outer contours and printing material characteristics of the two slice data;

[0065] Calculating the graphic similarity between the outer contours of the slice graphics of the two slice data;

[0066] Calculating material conversion time corresponding to the printing material features of the two slice data according to historical printing records of the corresponding printing device;

[0067] The weighted average value of the graphic similarity and the material transformation time is calculated to obtain the data similarity between the two slice data.

[0068] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the calculation module calculates the material conversion time corresponding to the printing material features of the two slice data based on the historical printing records of the corresponding printing device includes:

[0069] Filtering out a plurality of target printing records including the printing material features of the two slice data from historical printing records of the corresponding printing device;

[0070] The inverse of the average value of the printing times in all the target printing records is calculated to obtain the material conversion time corresponding to the printing material characteristics of the two slice data.

[0071] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the printing success rate corresponding to the three-dimensional model data based on the data similarity corresponding to all the slice data includes:

[0072] For each slice data, calculating the average value of the data similarity between the slice data and two adjacent slice data, to obtain the printing continuity corresponding to the slice data;

[0073] Sorting the printing coherence corresponding to all the slice data based on the order of the corresponding slice layers to obtain a coherence sequence;

[0074] The coherence sequence is input into a trained LSTM neural network to obtain the printing success rate corresponding to the three-dimensional model data; the LSTM neural network is trained by a training data set including a plurality of training slice data coherence sequences and corresponding printing success rate annotations.

[0075] As an optional embodiment, in the second aspect of the present invention, the system is further configured to perform the following steps:

[0076] Determining whether the printing success rate is greater than a first success rate threshold;

[0077] If yes, no further step is required;

[0078] If not, segmenting the coherent sequence based on a preset segmentation interval to obtain a plurality of partial sequences;

[0079] Inputting each of the partial sequences into the LSTM neural network to obtain a corresponding sequence printing success rate;

[0080] Screen out all partial sequences whose printing success rates of the sequences are less than a second success rate threshold to obtain fault sequences;

[0081] The slice data corresponding to the fault sequence is determined as a possible fault slice and pushed to the user terminal for display.

[0082] A third aspect of the present invention discloses another 3D printing success rate prediction system based on slice processing analysis, the system comprising:

[0083] a memory storing executable program code;

[0084] a processor coupled to the memory;

[0085] The processor calls the executable program code stored in the memory to execute part or all of the steps in the 3D printing success rate prediction method based on slicing processing analysis disclosed in the first aspect of the present invention.

[0086] A fourth aspect of the present invention discloses a computer storage medium storing computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the 3D printing success rate prediction method based on slice processing analysis disclosed in the first aspect of the present invention.

[0087] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0088] The present invention obtains three-dimensional model data and generates slice data based on a slice processing algorithm, calculates the data similarity between adjacent slice data and analyzes the printing success rate, thereby realizing accurate printing success rate evaluation based on slice similarity analysis, improving the reliability and printing quality of 3D printing tasks, and reducing the risk of printing failure due to abnormal slice data. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0090] Figure 1 It is a flow chart of a method for predicting 3D printing success rate based on slice processing analysis disclosed in an embodiment of the present invention.

[0091] Figure 2 It is a structural schematic diagram of a 3D printing success rate prediction system based on slice processing analysis disclosed in an embodiment of the present invention.

[0092] Figure 3 It is a structural diagram of another 3D printing success rate prediction system based on slice processing analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0093] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0094] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0095] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0096] This invention discloses a 3D printing success rate prediction method and system based on slice processing analysis. By acquiring three-dimensional model data and generating slice data based on a slice processing algorithm, the system calculates the data similarity between adjacent slice data and analyzes the printing success rate. This method enables accurate printing success rate assessment based on slice similarity analysis, improves the reliability and print quality of 3D printing tasks, and reduces the risk of printing failure due to abnormal slice data. These are described in detail below.

[0097] Example 1

[0098] See also Figure 1 , Figure 1 This is a flow chart of a 3D printing success rate prediction method based on slice processing analysis disclosed in an embodiment of the present invention. Figure 1 The described 3D printing success rate prediction method based on slice processing analysis can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the 3D printing success rate prediction method based on slice processing analysis may include the following operations:

[0099] 101. Obtain three-dimensional model data to be printed.

[0100] Optionally, the three-dimensional model data may be an STL file, an OBJ file, an AMF file or a CAD design file, which is not limited in the present invention.

[0101] Optionally, the acquisition process can be implemented based on file upload, cloud storage, design software output or real-time generation, which is not limited by the present invention.

[0102] 102. Based on a slicing processing algorithm, the three-dimensional model data is sliced ​​to obtain a plurality of slice data.

[0103] Optionally, the slicing processing algorithm may be a uniform slicing algorithm, an adaptive slicing algorithm, or an optimized slicing algorithm, which is not limited in the present invention.

[0104] Optionally, the slice data may include slice outline, layer height information, filling path or material distribution, which is not limited in the present invention.

[0105] Optionally, the slicing process may be optimized in combination with the performance of the printing device, the complexity of the model, or the printing accuracy requirements, which is not limited in the present invention.

[0106] 103. For any two adjacent slice data, calculate the data similarity between the two slice data.

[0107] Optionally, the data similarity may be geometric similarity, material consistency, or a comprehensive similarity score, which is not limited in the present invention.

[0108] Optionally, the data similarity calculation process may be implemented based on feature comparison, vector analysis, or statistical methods, which is not limited in the present invention.

[0109] 104. Analyze the printing success rate of the three-dimensional model data according to the data similarity corresponding to all the slice data.

[0110] Optionally, the analysis process may be implemented based on a neural network model, statistical analysis, or rule-based reasoning, which is not limited in the present invention.

[0111] Optionally, the printing success rate may be a probability value, a success level, a risk score, or a confidence level, which is not limited in the present invention.

[0112] It can be seen that the above-mentioned embodiment of the invention obtains three-dimensional model data and generates slice data based on a slice processing algorithm, calculates the data similarity between adjacent slice data and analyzes the printing success rate, thereby realizing accurate printing success rate evaluation based on slice similarity analysis, improving the reliability and printing quality of 3D printing tasks, and reducing the risk of printing failure due to abnormal slice data.

[0113] As an optional embodiment, in the above step, slicing the three-dimensional model data based on a slicing processing algorithm to obtain a plurality of slice data includes:

[0114] Establish a three-dimensional coordinate system with the geometric center point of the bottom surface of the three-dimensional model data as the origin;

[0115] Using the X-axis and Y-axis of the three-dimensional coordinate system, the three-dimensional model data is cross-sectioned to obtain a cross-sectional graph;

[0116] Calculate vertical continuity parameters of cross-section figures;

[0117] Calculate the slice spacing proportional to the vertical coherence parameter;

[0118] According to the slice spacing, the three-dimensional model data is sliced ​​in the Z coordinate axis direction of the three-dimensional coordinate system to obtain a plurality of slice data.

[0119] Optionally, the geometric center point may be determined based on centroid calculation, boundary point averaging, or geometric analysis, which is not limited in the present invention.

[0120] Optionally, the vertical coherence parameter may be a coherence score, a geometric consistency index, or a curvature distribution parameter, which is not limited in the present invention.

[0121] Optionally, the calculation process of the vertical coherence parameter may be implemented based on geometric analysis, feature extraction or statistical methods, which is not limited in the present invention.

[0122] Optionally, the calculation of the vertical continuity parameter may be optimized in combination with the model structure, printing direction or material properties, which is not limited in the present invention.

[0123] It can be seen that through the above optional embodiments, a coordinate system is established with the geometric center point of the bottom surface of the three-dimensional model as the origin, and the slice spacing is determined based on the vertical continuity parameters of the cross-sectional figure to generate slice data. Therefore, on the basis of accurate printing success rate evaluation, the generation accuracy of slice data is improved through coordinate system analysis and continuity optimization, providing a high-quality data foundation for subsequent similarity analysis and reducing the risk of printing errors caused by improper slicing.

[0124] As an optional embodiment, in the above step, calculating the vertical continuity parameter of the cross-sectional graph includes:

[0125] Based on a preset line segment division rule, a plurality of line segments corresponding to the cross-sectional figure are determined;

[0126] For each line segment of the cross-sectional figure, calculate the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system;

[0127] Filter out line segments whose parallelism is greater than a preset threshold value to obtain multiple vertical line segments;

[0128] The weighted sum average of the curvatures corresponding to all vertical line segments is calculated to obtain the vertical continuity parameter of the profile; wherein the weighted calculation weight corresponding to each curvature is proportional to the degree of parallelism corresponding to the corresponding vertical line segment.

[0129] Optionally, the line segment division rule may be an equidistant division rule, a feature point division rule, or a curvature division rule, which is not limited in the present invention.

[0130] Optionally, the line segment may be a straight line segment, a curved line segment, or a mixed line segment, which is not limited in the present invention.

[0131] Optionally, the degree of parallelism may be an angle deviation, a vector angle, or a projection similarity, which is not limited in the present invention.

[0132] Optionally, the calculation process of the degree of parallelism may be implemented based on vector analysis, geometric calculation or trigonometric function, which is not limited in the present invention.

[0133] Optionally, the curvature may be a local curvature, an average curvature or a maximum curvature, which is not limited in the present invention.

[0134] It can be seen that through the above optional embodiments, by identifying the profile graphic segments based on the line segment division rules and screening the vertical line segments with high parallelism, the curvature weighted average is calculated as the vertical continuity parameter. Therefore, on the basis of precise slicing processing, the accuracy of the profile continuity parameter is improved through line segment analysis and weighted curvature evaluation, which provides a reliable basis for the optimization of slice spacing and reduces the risk of printing defects caused by errors in model structure analysis.

[0135] As an optional embodiment, in the above step, calculating the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system includes:

[0136] The line segment is processed based on an approximate fitting algorithm to obtain a plurality of interconnected straight line segment parts;

[0137] Calculate the angle difference between each straight line segment and the Z coordinate axis direction of the three-dimensional coordinate system;

[0138] The average of all angle differences is calculated to obtain the degree of parallelism between the line segment and the Z coordinate axis of the three-dimensional coordinate system.

[0139] Optionally, the approximate fitting algorithm may be a least squares method, a spline fitting algorithm, or a polynomial fitting algorithm, which is not limited in the present invention.

[0140] Optionally, the angle difference value may be an absolute angle difference, a normalized angle difference, or a weighted angle difference, which is not limited in the present invention.

[0141] Optionally, the calculation process of the angle difference may be implemented based on vector angle, geometric projection or trigonometric function, which is not limited in the present invention.

[0142] It can be seen that through the above optional embodiments, by processing the line segments based on the approximate fitting algorithm to generate straight line segment parts and calculating the average value of the angle difference with the Z-axis direction as the degree of parallelism, the accuracy of the parallelism of the line segments is improved through fitting and angle analysis on the basis of precise continuity parameter calculation, providing a more accurate basis for vertical continuity evaluation and reducing the risk of slicing errors caused by line segment analysis deviations.

[0143] As an optional embodiment, in the above step, calculating the data similarity between the two slice data includes:

[0144] Determine the slice graphic outer contours and printing material characteristics of the two slice data;

[0145] Calculating the graphic similarity between the outer contours of the slice graphics of the two slice data;

[0146] Calculating material conversion time corresponding to the printing material features of the two slice data according to historical printing records of the corresponding printing device;

[0147] The weighted average of the graphic similarity and the material transformation time is calculated to obtain the data similarity between the two slice data.

[0148] The material conversion time is used to represent the difficulty of converting the printing material characteristics of the two slice data, and can be specifically defined as the inverse of the historical average time.

[0149] Optionally, the printing material characteristics may include material type, material density, viscosity or thermal properties, which is not limited in the present invention.

[0150] Optionally, the graphic similarity may be Hausdorff distance, cosine similarity, shape matching, or contour overlap, which is not limited in the present invention.

[0151] It can be seen that through the above optional embodiments, by determining the outer contour of the slice data and the printing material characteristics, the weighted average of the graphic similarity and the material transformation time is calculated as the data similarity, thereby improving the accuracy of the slice data similarity through contour and material feature analysis on the basis of accurate printing success rate evaluation, providing a reliable basis for printing continuity evaluation, and reducing the risk of printing failure due to material transformation or contour differences.

[0152] As an optional embodiment, in the above step, calculating the material conversion time corresponding to the printing material features of the two slice data according to the historical printing records of the corresponding printing device includes:

[0153] Filtering out a plurality of target printing records including the printing material features of the two slice data from historical printing records of the corresponding printing device;

[0154] The inverse of the average value of the printing time in all target printing records is calculated to obtain the material conversion time corresponding to the printing material characteristics of the two slice data.

[0155] It can be seen that through the above optional embodiments, by screening the target printing records containing the characteristics of the slicing data printing materials and calculating the inverse of the average printing time as the material conversion time, the accuracy of the material conversion time evaluation is improved through historical record analysis on the basis of accurate data similarity calculation, providing precise support for the slicing data similarity calculation, and reducing the risk of printing efficiency caused by misjudgment of material conversion time.

[0156] As an optional embodiment, in the above step, analyzing the printing success rate corresponding to the three-dimensional model data according to the data similarity corresponding to all the slice data includes:

[0157] For each slice data, calculate the average value of the data similarity between the slice data and two adjacent slice data to obtain the printing continuity corresponding to the slice data;

[0158] Based on the order of the corresponding slice layers, the printing continuity corresponding to all slice data is sorted to obtain a continuity sequence;

[0159] The coherence sequence is input into a trained LSTM neural network to obtain the printing success rate corresponding to the three-dimensional model data; the LSTM neural network is trained using a training data set including a plurality of coherence sequences of training slice data and corresponding printing success rate annotations.

[0160] Optionally, the sorting may be ascending sorting, descending sorting, or weight-based sorting, which is not limited in the present invention.

[0161] Optionally, the LSTM neural network can be a single-layer LSTM, a multi-layer LSTM, a bidirectional LSTM, or an attention mechanism LSTM, which is not limited in the present invention.

[0162] Optionally, the training data set may include a historical continuity sequence, a simulation sequence, or annotated data, which is not limited in the present invention.

[0163] It can be seen that through the above optional embodiments, the printing continuity is obtained by calculating the average similarity between the slice data and the adjacent slice data and sorting them to generate a continuity sequence. The printing success rate is analyzed based on the sequence. Therefore, on the basis of accurate printing success rate evaluation, the accuracy and consistency of the evaluation are improved through continuity sequence analysis, which provides a reliable basis for 3D printing task optimization and reduces the risk of printing defects caused by slicing incoherence.

[0164] As an optional embodiment, in the above steps, the method further includes:

[0165] Determining whether the printing success rate is greater than a first success rate threshold;

[0166] If yes, no further step is required;

[0167] If not, the coherent sequence is segmented based on a preset segmentation interval to obtain multiple partial sequences;

[0168] Input each part of the sequence into the LSTM neural network to obtain the corresponding sequence printing success rate;

[0169] Screen out all sequences whose printing success rates are less than a second success rate threshold to obtain fault sequences;

[0170] The slice data corresponding to the fault sequence is determined as a possible fault slice and pushed to the user terminal for display.

[0171] Optionally, the first success rate threshold or the second success rate threshold may be a fixed threshold, a dynamic threshold, or a threshold adjusted based on the complexity of the printing task, which is not limited in the present invention.

[0172] Optionally, the segmentation interval may be a fixed interval, a dynamic interval, or an interval adjusted based on sequence characteristics, which is not limited in the present invention.

[0173] Optionally, the push process of the possible faulty slice can be implemented based on user interface notification, message queue or real-time communication, which is not limited by the present invention.

[0174] Optionally, the display process of the possible fault slice can be presented in the form of a graphical interface, a text report or a warning prompt, which is not limited in the present invention.

[0175] It can be seen that through the above optional embodiments, by judging whether the printing success rate exceeds the threshold and segmenting the low success rate continuity sequence, the slice data corresponding to the fault sequence is identified and pushed to the user terminal. Therefore, on the basis of accurate printing success rate evaluation, the fault sequence identification and user feedback are used to optimize the pertinence and interactivity of fault slice detection, thereby improving the reliability of the printing process and user experience, and reducing the risk of printing failure caused by potential fault slices.

[0176] Example 2

[0177] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a 3D printing success rate prediction system based on slice processing analysis disclosed in an embodiment of the present invention. Figure 2 The 3D printing success rate prediction system based on slice processing analysis can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the 3D printing success rate prediction system based on slice processing analysis may include:

[0178] The acquisition module 201 is used to acquire the three-dimensional model data to be printed.

[0179] The processing module 202 is configured to perform slicing processing on the three-dimensional model data based on a slicing processing algorithm to obtain a plurality of slice data.

[0180] The calculation module 203 is configured to calculate the data similarity between any two adjacent slice data.

[0181] The analysis module 204 is configured to analyze the printing success rate corresponding to the three-dimensional model data based on the data similarities corresponding to all the slice data.

[0182] It can be seen that the above-mentioned embodiment of the invention obtains three-dimensional model data and generates slice data based on a slice processing algorithm, calculates the data similarity between adjacent slice data and analyzes the printing success rate, thereby realizing accurate printing success rate evaluation based on slice similarity analysis, improving the reliability and printing quality of 3D printing tasks, and reducing the risk of printing failure due to abnormal slice data.

[0183] As an optional embodiment, the specific manner in which the processing module slices the three-dimensional model data to obtain a plurality of slice data based on a slice processing algorithm includes:

[0184] Establish a three-dimensional coordinate system with the geometric center point of the bottom surface of the three-dimensional model data as the origin;

[0185] Using the X-axis and Y-axis of the three-dimensional coordinate system, the three-dimensional model data is cross-sectioned to obtain a cross-sectional graph;

[0186] Calculate vertical continuity parameters of cross-section figures;

[0187] Calculate the slice spacing proportional to the vertical coherence parameter;

[0188] According to the slice spacing, the three-dimensional model data is sliced ​​in the Z coordinate axis direction of the three-dimensional coordinate system to obtain a plurality of slice data.

[0189] It can be seen that through the above optional embodiments, a coordinate system is established with the geometric center point of the bottom surface of the three-dimensional model as the origin, and the slice spacing is determined based on the vertical continuity parameters of the cross-sectional figure to generate slice data. Therefore, on the basis of accurate printing success rate evaluation, the generation accuracy of slice data is improved through coordinate system analysis and continuity optimization, providing a high-quality data foundation for subsequent similarity analysis and reducing the risk of printing errors caused by improper slicing.

[0190] As an optional embodiment, the specific method in which the processing module calculates the vertical continuity parameter of the cross-sectional graph includes:

[0191] Based on a preset line segment division rule, a plurality of line segments corresponding to the cross-sectional figure are determined;

[0192] For each line segment of the cross-sectional figure, calculate the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system;

[0193] Filter out line segments whose parallelism is greater than a preset threshold value to obtain multiple vertical line segments;

[0194] The weighted sum average of the curvatures corresponding to all vertical line segments is calculated to obtain the vertical continuity parameter of the profile; wherein the weighted calculation weight corresponding to each curvature is proportional to the degree of parallelism corresponding to the corresponding vertical line segment.

[0195] It can be seen that through the above optional embodiments, by identifying the profile graphic segments based on the line segment division rules and screening the vertical line segments with high parallelism, the curvature weighted average is calculated as the vertical continuity parameter. Therefore, on the basis of precise slicing processing, the accuracy of the profile continuity parameter is improved through line segment analysis and weighted curvature evaluation, which provides a reliable basis for the optimization of slice spacing and reduces the risk of printing defects caused by errors in model structure analysis.

[0196] As an optional embodiment, the specific manner in which the processing module calculates the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system includes:

[0197] The line segment is processed based on an approximate fitting algorithm to obtain a plurality of interconnected straight line segment parts;

[0198] Calculate the angle difference between each straight line segment and the Z coordinate axis direction of the three-dimensional coordinate system;

[0199] The average of all angle differences is calculated to obtain the degree of parallelism between the line segment and the Z coordinate axis of the three-dimensional coordinate system.

[0200] It can be seen that through the above optional embodiments, by processing the line segments based on the approximate fitting algorithm to generate straight line segment parts and calculating the average value of the angle difference with the Z-axis direction as the degree of parallelism, the accuracy of the parallelism of the line segments is improved through fitting and angle analysis on the basis of precise continuity parameter calculation, providing a more accurate basis for vertical continuity evaluation and reducing the risk of slicing errors caused by line segment analysis deviations.

[0201] As an optional embodiment, the specific manner in which the calculation module calculates the data similarity between the two slice data includes:

[0202] Determine the slice graphic outer contours and printing material characteristics of the two slice data;

[0203] Calculating the graphic similarity between the outer contours of the slice graphics of the two slice data;

[0204] Calculating material conversion time corresponding to the printing material features of the two slice data according to historical printing records of the corresponding printing device;

[0205] The weighted average of the graphic similarity and the material transformation time is calculated to obtain the data similarity between the two slice data.

[0206] It can be seen that through the above optional embodiments, by determining the outer contour of the slice data and the printing material characteristics, the weighted average of the graphic similarity and the material transformation time is calculated as the data similarity, thereby improving the accuracy of the slice data similarity through contour and material feature analysis on the basis of accurate printing success rate evaluation, providing a reliable basis for printing continuity evaluation, and reducing the risk of printing failure due to material transformation or contour differences.

[0207] As an optional embodiment, the specific method of calculating the material conversion time corresponding to the printing material characteristics of the two slice data according to the historical printing records of the corresponding printing device includes:

[0208] Filtering out a plurality of target printing records including the printing material features of the two slice data from historical printing records of the corresponding printing device;

[0209] The inverse of the average value of the printing time in all target printing records is calculated to obtain the material conversion time corresponding to the printing material characteristics of the two slice data.

[0210] It can be seen that through the above optional embodiments, by screening the target printing records containing the characteristics of the slicing data printing materials and calculating the inverse of the average printing time as the material conversion time, the accuracy of the material conversion time evaluation is improved through historical record analysis on the basis of accurate data similarity calculation, providing precise support for the slicing data similarity calculation, and reducing the risk of printing efficiency caused by misjudgment of material conversion time.

[0211] As an optional embodiment, the specific method of analyzing the printing success rate corresponding to the three-dimensional model data by the analysis module according to the data similarity corresponding to all the slice data includes:

[0212] For each slice data, calculate the average value of the data similarity between the slice data and two adjacent slice data to obtain the printing continuity corresponding to the slice data;

[0213] Based on the order of the corresponding slice layers, the printing continuity corresponding to all slice data is sorted to obtain a continuity sequence;

[0214] The coherence sequence is input into a trained LSTM neural network to obtain the printing success rate corresponding to the three-dimensional model data; the LSTM neural network is trained using a training data set including a plurality of coherence sequences of training slice data and corresponding printing success rate annotations.

[0215] It can be seen that through the above optional embodiments, the printing continuity is obtained by calculating the average similarity between the slice data and the adjacent slice data and sorting them to generate a continuity sequence. The printing success rate is analyzed based on the sequence. Therefore, on the basis of accurate printing success rate evaluation, the accuracy and consistency of the evaluation are improved through continuity sequence analysis, which provides a reliable basis for 3D printing task optimization and reduces the risk of printing defects caused by slicing incoherence.

[0216] As an optional embodiment, the system is further configured to perform the following steps:

[0217] Determining whether the printing success rate is greater than a first success rate threshold;

[0218] If yes, no further step is required;

[0219] If not, the coherent sequence is segmented based on a preset segmentation interval to obtain multiple partial sequences;

[0220] Input each part of the sequence into the LSTM neural network to obtain the corresponding sequence printing success rate;

[0221] Screen out all sequences whose printing success rates are less than a second success rate threshold to obtain fault sequences;

[0222] The slice data corresponding to the fault sequence is determined as a possible fault slice and pushed to the user terminal for display.

[0223] It can be seen that through the above optional embodiments, by judging whether the printing success rate exceeds the threshold and segmenting the low success rate continuity sequence, the slice data corresponding to the fault sequence is identified and pushed to the user terminal. Therefore, on the basis of accurate printing success rate evaluation, the fault sequence identification and user feedback are used to optimize the pertinence and interactivity of fault slice detection, thereby improving the reliability of the printing process and user experience, and reducing the risk of printing failure caused by potential fault slices.

[0224] Example 3

[0225] See also Figure 3 , Figure 3 This is another 3D printing success rate prediction system based on slice processing analysis disclosed in an embodiment of the present invention. Figure 3 The described 3D printing success rate prediction system based on slice processing analysis is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the 3D printing success rate prediction system based on slice processing analysis may include:

[0226] A memory 301 storing executable program code;

[0227] a processor 302 coupled to the memory 301;

[0228] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the 3D printing success rate prediction method based on slicing processing analysis described in the first embodiment.

[0229] Example 4

[0230] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the 3D printing success rate prediction method based on slicing processing analysis described in the first embodiment.

[0231] Example 5

[0232] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the 3D printing success rate prediction method based on slicing processing analysis described in Example 1.

[0233] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0234] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0235] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0236] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0237] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0238] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0239] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0240] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0241] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0242] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0243] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0244] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0245] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0246] Finally, it should be noted that the 3D printing success rate prediction method and system based on slice processing analysis disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A 3D printing success rate prediction method based on slice processing analysis, characterized in that: The method comprises: Obtaining three-dimensional model data to be printed; Based on a slicing processing algorithm, slicing the three-dimensional model data to obtain a plurality of slice data; For any two adjacent slice data, calculating the data similarity between the two slice data includes: Determining the slice graphic outer contours and printing material characteristics of the two slice data; Calculating the graphic similarity between the outer contours of the slice graphics of the two slice data; According to the historical printing records of the corresponding printing device, a plurality of target printing records including the printing material features of the two slice data are screened out from the historical printing records of the corresponding printing device; Calculating the reciprocal of the average of the printing times in all the target printing records to obtain the material conversion time corresponding to the printing material characteristics of the two slice data; Calculating a weighted average of the graphic similarity and the material transformation time to obtain the data similarity between the two slice data; Analyzing the printing success rate corresponding to the three-dimensional model data according to the data similarity corresponding to all the slice data includes: For each slice data, calculating the average value of the data similarity between the slice data and two adjacent slice data, to obtain the printing continuity corresponding to the slice data; Sorting the printing coherence corresponding to all the slice data based on the order of the corresponding slice layers to obtain a coherence sequence; Inputting the coherence sequence into a trained LSTM neural network to obtain a printing success rate corresponding to the three-dimensional model data; the LSTM neural network is trained using a training data set including a plurality of coherence sequences of training slice data and corresponding printing success rate annotations; the method further includes: Determining whether the printing success rate is greater than a first success rate threshold; If yes, no further step is required; If not, segmenting the coherent sequence based on a preset segmentation interval to obtain a plurality of partial sequences; Inputting each of the partial sequences into the LSTM neural network to obtain a corresponding sequence printing success rate; Screen out all partial sequences whose printing success rates of the sequences are less than a second success rate threshold to obtain fault sequences; The slice data corresponding to the fault sequence is determined as a possible fault slice and pushed to the user terminal for display.

2. The 3D printing success rate prediction method based on slice processing analysis according to claim 1 is characterized in that: The slicing process is performed on the three-dimensional model data based on a slicing process algorithm to obtain a plurality of slice data, including: Establishing a three-dimensional coordinate system with the geometric center point of the bottom surface of the three-dimensional model data as the origin; Processing the three-dimensional model data in sections using the X-axis and Y-axis of the three-dimensional coordinate system to obtain a section graph; Calculating vertical continuity parameters of the cross-sectional figure; calculating a slice spacing proportional to the vertical coherence parameter; According to the slice spacing, the three-dimensional model data is sliced ​​in the Z coordinate axis direction of the three-dimensional coordinate system to obtain a plurality of slice data.

3. The 3D printing success rate prediction method based on slice processing analysis according to claim 2, characterized in that: The calculating of the vertical continuity parameter of the cross-sectional graph includes: Based on a preset line segment division rule, determining a plurality of line segments corresponding to the cross-sectional figure; For each line segment of the cross-sectional figure, calculating the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system; Filter out the line segments whose parallelism is greater than a preset threshold value to obtain a plurality of vertical line segments; The weighted sum average of the curvatures corresponding to all the vertical line segments is calculated to obtain the vertical continuity parameter of the cross-sectional figure; wherein the weighted calculation weight corresponding to each curvature is proportional to the parallelism corresponding to the corresponding vertical line segment.

4. The 3D printing success rate prediction method based on slice processing analysis according to claim 3 is characterized in that: Calculating the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system includes: The line segment is processed based on an approximate fitting algorithm to obtain a plurality of interconnected straight line segment parts; Calculating the angle difference between each of the straight line segments and the Z coordinate axis direction of the three-dimensional coordinate system; The average value of all the angle differences is calculated to obtain the degree of parallelism between the line segment and the Z coordinate axis direction of the three-dimensional coordinate system.

5. A 3D printing success rate prediction system based on slice processing analysis, characterized in that: The system comprises: An acquisition module, used to acquire the three-dimensional model data to be printed; A processing module, configured to slice the three-dimensional model data to obtain a plurality of slice data based on a slice processing algorithm; A calculation module, configured to calculate the data similarity between any two adjacent slice data; An analysis module is used to analyze the printing success rate corresponding to the three-dimensional model data based on the data similarity corresponding to all the slice data; the system is used to execute the 3D printing success rate prediction method based on slice processing analysis as described in any one of claims 1 to 4.

6. A 3D printing success rate prediction system based on slice processing analysis, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the 3D printing success rate prediction method based on slicing processing analysis according to any one of claims 1 to 4.

Images