A method and system for detecting model islands in slice data management

Abstract

This invention discloses a method and system for detecting isolated models in slice data management. The method includes: acquiring slice data corresponding to 3D model data used for 3D printing; identifying at least two potentially suspended suspicious slice layers in the slice data based on a suspension prediction model; identifying multiple isolated components in the 3D model data based on component matching rules and all the suspicious slice layers; and determining the degree of isolated risk corresponding to any isolated component based on the component parameters of the isolated components and an association risk analysis algorithm. Therefore, this invention can achieve accurate isolated risk assessment based on slice layer association and component characteristics, improving the accuracy of suspended component detection and printing stability during 3D printing, and reducing the risk of printing failure due to isolated components.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for detecting model islands in slice data management. Background Technology

[0002] With the widespread application of 3D printing technology in high-precision manufacturing, enterprises and users are increasingly emphasizing the improvement of printing stability and success rate through optimized slice data analysis. Existing technologies typically acquire slice data from 3D models, employ simple geometric analysis or fixed threshold methods to detect potentially suspended slice layers, and adjust printing parameters based on standard component inspection rules to reduce the risk of printing failure. However, existing solutions lack dynamic prediction of slice layer suspendability and correlation analysis of isolated components, making it difficult to accurately identify high-risk isolated components and assess their risk level. This easily leads to printing defects or failures, limiting the stability and quality of the 3D printing process. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a model island detection method and system for slice data management, which can realize accurate island risk assessment based on slice layer correlation and component characteristics, improve the accuracy of suspended component detection and printing stability in 3D printing process, and reduce the risk of printing failure caused by island components.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a method for detecting isolated models in slice data management, the method comprising:

[0005] Obtain the slice data corresponding to the 3D model data used for 3D printing;

[0006] Based on the dangling prediction model, at least two potentially dangling suspicious slice layers in the slice data are identified;

[0007] Based on the component matching rules, multiple isolated components in the 3D model data are determined according to all the suspected slice layers;

[0008] Based on the component parameters of the isolated components, and using an association risk analysis algorithm, the degree of islanding risk corresponding to any of the isolated components is determined.

[0009] As an optional implementation, in the first aspect of the invention, determining at least two potentially suspended suspicious slice layers in the slice data based on the dangling prediction model includes:

[0010] For any two slice layers in the slice data whose interval is less than a preset interval threshold, the closed contours of the patterns corresponding to the two slice layers are determined based on the closed contour recognition algorithm.

[0011] Based on the closed contours of the patterns corresponding to the two slice layers, calculate the possible parameters of association between the two slice layers.

[0012] Based on the associated possible parameters, at least two potentially suspended suspicious slice layers are selected from all the slice layers.

[0013] As an optional implementation, in the first aspect of the invention, calculating the possible correlation parameters between the two slice layers based on the pattern closure contours corresponding to the two slice layers respectively includes:

[0014] Calculate the contour similarity between the closed contours of the patterns corresponding to the two slice layers respectively;

[0015] Calculate the area of ​​the overlapping portion of the closed outline of the pattern corresponding to the two slice layers respectively;

[0016] Based on the contour continuity prediction model, the continuity probability of the closed contours of the patterns corresponding to the two slice layers is predicted; the contour continuity prediction model is trained by a training dataset that includes multiple training continuous contour data and corresponding continuity annotations.

[0017] The product of the contour similarity, the area, and the continuity probability is calculated to obtain the possible parameters of association between the two slice layers.

[0018] As an optional implementation, in the first aspect of the invention, the step of filtering out at least two potentially suspended suspicious slice layers from all the slice layers based on the associated possible parameters includes:

[0019] For each slice layer, calculate the weighted average of the possible correlation parameters between the slice layer and all other slice layers to obtain the coherence parameters corresponding to the slice layer;

[0020] From all the slice layers, slice layers whose coherence parameter is less than a preset first parameter threshold are selected to obtain at least two potentially suspended suspicious slice layers.

[0021] As an optional implementation, in the first aspect of the invention, when calculating the coherence parameters, the weighted calculation weight corresponding to each of the associated possible parameters is inversely proportional to the layer interval between the corresponding two slice layers.

[0022] As an optional implementation, in the first aspect of the invention, determining multiple isolated components in the 3D model data based on component matching rules and according to all the suspected slice layers includes:

[0023] Determine the data component corresponding to each of the suspected slice layers in the three-dimensional model data;

[0024] For each of the data components, determine the total number of all the suspected slice layers corresponding to that data component;

[0025] Calculate the reciprocal of the average value of the coherence parameters of all the suspected slice layers corresponding to the data component;

[0026] Calculate the product of the total quantity and the reciprocal to obtain the suspicious parameters corresponding to the data component;

[0027] From all the data components, components with suspicious parameters greater than a preset second parameter threshold are selected to obtain multiple isolated components in the three-dimensional model data.

[0028] As an optional implementation, in the first aspect of the present invention, the component parameters include at least one of component volume, component surface area, component shape, component minimum bounding box volume, component type, and component purpose.

[0029] As an optional implementation, in the first aspect of the present invention, determining the islanding risk level corresponding to any one of the islanded components based on the component parameters of the islanded components and using an association risk analysis algorithm includes:

[0030] For any two isolated island components, calculate the parameter similarity between the component parameters of the two isolated island components;

[0031] Calculate the positional distance between the positions of the two isolated island components;

[0032] The product of the parameter similarity and the location distance is calculated to obtain the association risk between the two isolated components;

[0033] For each of the islanded components, calculate the average risk of the associated risk between that islanded component and all other islanded components;

[0034] The component parameters of the isolated component are input into the trained risk prediction model to obtain the corresponding predicted risk of the isolated component; the risk prediction model is trained using a training dataset that includes multiple training component parameters and corresponding printed risk labels.

[0035] The islanding risk level corresponding to the islanding component is obtained by multiplying the average risk and the predicted risk.

[0036] A second aspect of this invention discloses a model island detection system for slice data management, the system comprising:

[0037] The acquisition module is used to acquire slice data corresponding to the 3D model data used for 3D printing;

[0038] The first determining module is used to determine at least two potentially suspended suspicious slice layers in the slice data based on the suspending prediction model.

[0039] The second determining module is used to determine multiple isolated components in the 3D model data based on component matching rules and all the suspected slice layers;

[0040] The analysis module is used to determine the degree of island risk corresponding to any of the island components based on the component parameters of the island components and an association risk analysis algorithm.

[0041] As an optional implementation, in a second aspect of the invention, the first determining module determines at least two potentially suspended suspicious slice layers in the slice data based on a dangling prediction model, including:

[0042] For any two slice layers in the slice data whose interval is less than a preset interval threshold, the closed contours of the patterns corresponding to the two slice layers are determined based on the closed contour recognition algorithm.

[0043] Based on the closed contours of the patterns corresponding to the two slice layers, calculate the possible parameters of association between the two slice layers.

[0044] Based on the associated possible parameters, at least two potentially suspended suspicious slice layers are selected from all the slice layers.

[0045] As an optional implementation, in a second aspect of the invention, the specific method by which the first determining module calculates the possible correlation parameters between the two slice layers based on the pattern closure contours corresponding to the two slice layers includes:

[0046] Calculate the contour similarity between the closed contours of the patterns corresponding to the two slice layers respectively;

[0047] Calculate the area of ​​the overlapping portion of the closed outline of the pattern corresponding to the two slice layers respectively;

[0048] Based on the contour continuity prediction model, the continuity probability of the closed contours of the patterns corresponding to the two slice layers is predicted; the contour continuity prediction model is trained by a training dataset that includes multiple training continuous contour data and corresponding continuity annotations.

[0049] The product of the contour similarity, the area, and the continuity probability is calculated to obtain the possible parameters of association between the two slice layers.

[0050] As an optional implementation, in a second aspect of the invention, the specific method by which the first determining module filters out at least two potentially suspended suspicious slice layers from all the slice layers based on the associated possible parameters includes:

[0051] For each slice layer, calculate the weighted average of the possible correlation parameters between the slice layer and all other slice layers to obtain the coherence parameters corresponding to the slice layer;

[0052] From all the slice layers, slice layers whose coherence parameter is less than a preset first parameter threshold are selected to obtain at least two potentially suspended suspicious slice layers.

[0053] As an optional implementation, in a second aspect of the invention, when calculating the coherence parameters, the weighted calculation weight corresponding to each of the associated possible parameters is inversely proportional to the layer interval between the corresponding two slice layers.

[0054] As an optional implementation, in a second aspect of the invention, the second determining module determines the specific method by which it determines multiple isolated components in the 3D model data based on component matching rules and according to all the suspected slice layers, including:

[0055] Determine the data component corresponding to each of the suspected slice layers in the three-dimensional model data;

[0056] For each of the data components, determine the total number of all the suspected slice layers corresponding to that data component;

[0057] Calculate the reciprocal of the average value of the coherence parameters of all the suspected slice layers corresponding to the data component;

[0058] Calculate the product of the total quantity and the reciprocal to obtain the suspicious parameters corresponding to the data component;

[0059] From all the data components, components with suspicious parameters greater than a preset second parameter threshold are selected to obtain multiple isolated components in the three-dimensional model data.

[0060] As an optional implementation, in a second aspect of the invention, the component parameters include at least one of component volume, component surface area, component shape, component minimum bounding box volume, component type, and component purpose.

[0061] As an optional implementation, in a second aspect of the invention, the analysis module determines the degree of islanding risk corresponding to any of the islanded components based on the component parameters of the islanded components and an association risk analysis algorithm, including:

[0062] For any two isolated island components, calculate the parameter similarity between the component parameters of the two isolated island components;

[0063] Calculate the positional distance between the positions of the two isolated island components;

[0064] The product of the parameter similarity and the location distance is calculated to obtain the association risk between the two isolated components;

[0065] For each of the islanded components, calculate the average risk of the associated risk between that islanded component and all other islanded components;

[0066] The component parameters of the isolated component are input into the trained risk prediction model to obtain the corresponding predicted risk of the isolated component; the risk prediction model is trained using a training dataset that includes multiple training component parameters and corresponding printed risk labels.

[0067] The islanding risk level corresponding to the islanding component is obtained by multiplying the average risk and the predicted risk.

[0068] A third aspect of this invention discloses another model island detection system for slice data management, the system comprising:

[0069] Memory containing executable program code;

[0070] A processor coupled to the memory;

[0071] The processor calls the executable program code stored in the memory to execute some or all of the steps in the model island detection method for slice data management disclosed in the first aspect of the present invention.

[0072] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the model island detection method for slice data management disclosed in the first aspect of the present invention.

[0073] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0074] This invention acquires slice data of 3D printed three-dimensional models and identifies potentially suspended suspicious slice layers based on a suspended prediction model. It uses component matching rules to determine isolated components and combines component parameters and correlation risk analysis algorithms to assess the degree of isolated component risk. This enables accurate isolated component risk assessment based on slice layer correlation and component characteristics, improving the accuracy of suspended component detection and printing stability during 3D printing, and reducing the risk of printing failure caused by isolated components. Attached Figure Description

[0075] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0076] Figure 1 This is a flowchart illustrating a model island detection method for slice data management disclosed in an embodiment of the present invention.

[0077] Figure 2 This is a schematic diagram of a model island detection system for slice data management disclosed in an embodiment of the present invention.

[0078] Figure 3 This is a schematic diagram of another model island detection system for slice data management disclosed in an embodiment of the present invention. Detailed Implementation

[0079] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0080] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0081] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0082] This invention discloses a model island detection method and system for slice data management. It acquires slice data from 3D printed 3D models and identifies potentially suspended slice layers based on a suspension prediction model. It then uses component matching rules to determine isolated components and combines component parameters and a correlation risk analysis algorithm to assess the degree of island risk. This enables accurate island risk assessment based on slice layer correlation and component characteristics, improving the accuracy of suspended component detection and printing stability during 3D printing, and reducing the risk of printing failures due to isolated components. Detailed explanations follow.

[0083] Example 1

[0084] Please see Figure 1 , Figure 1 This is a flowchart illustrating a model island detection method for slice data management disclosed in an embodiment of the present invention. Figure 1 The described model island detection method for slice data management can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). Figure 1 As shown, the model island detection method for slice data management may include the following operations:

[0085] 101. Obtain the slice data corresponding to the 3D model data used for 3D printing.

[0086] Optionally, the 3D model data can be an STL file, an OBJ file, or a CAD design file; this invention does not impose any limitations.

[0087] Optionally, the process of acquiring the slice data can be implemented based on slicing software, cloud processing, or local computing, and this invention does not limit it.

[0088] 102. Based on the dangling prediction model, identify at least two potentially dangling suspicious slice layers in the slice data.

[0089] 103. Based on the component matching rules, identify multiple isolated components in the 3D model data according to all suspicious slice layers.

[0090] 104. Based on the component parameters of the isolated components, determine the degree of island risk corresponding to any isolated component using the correlation risk analysis algorithm.

[0091] Optionally, the component parameters may include component volume, surface area, or geometric complexity, which is not limited in this invention.

[0092] Optionally, the association risk analysis algorithm can be a statistical analysis algorithm, a machine learning algorithm, or a graph network analysis algorithm; this invention does not limit the algorithm.

[0093] Optionally, the degree of risk of the isolated island can be a risk score, risk level, or risk probability; this invention does not limit this.

[0094] As can be seen, the above-described embodiments of the invention acquire slice data of 3D printed three-dimensional model data and identify potentially suspended suspicious slice layers based on the suspension prediction model. They then use component matching rules to determine isolated components and combine component parameters and correlation risk analysis algorithms to assess the degree of isolated risk. This enables accurate isolated risk assessment based on slice layer correlation and component characteristics, improves the accuracy of suspended component detection and printing stability during 3D printing, and reduces the risk of printing failure caused by isolated components.

[0095] As an optional embodiment, the step described above, identifying at least two potentially suspended suspicious slice layers in the slice data based on the dangling prediction model, includes:

[0096] For any two slices in the slice data whose interval is less than a preset interval threshold, the closed contours of the patterns corresponding to the two slices are determined based on the closed contour recognition algorithm.

[0097] Based on the closed contours of the patterns corresponding to the two slice layers, calculate the possible parameters of association between the two slice layers.

[0098] Based on the associated possible parameters, at least two potentially suspended suspicious slice layers are selected from all slice layers.

[0099] Optionally, the interval threshold can be a fixed number of layers, a dynamic number of layers, or a number of layers adjusted based on model accuracy; this invention does not impose any limitations.

[0100] Optionally, the closed contour recognition algorithm can be an edge detection algorithm, a contour tracking algorithm, or a deep learning segmentation algorithm; this invention does not limit the algorithm.

[0101] Optionally, the closed outline of the pattern can be a two-dimensional outline, a three-dimensional projected outline, or a simplified outline; the present invention does not limit this.

[0102] Optionally, the associated parameter may be a similarity score, association strength, or probability value; this invention does not limit this.

[0103] Optionally, the calculation process of the associated possible parameters can be based on geometric analysis, feature matching or statistical methods, and the present invention does not limit it.

[0104] As can be seen, through the above optional embodiments, by determining the closed contour of any two slice layer patterns with a layer number interval of less than a threshold based on the closed contour recognition algorithm, calculating the contour similarity, overlapping area and continuity probability to obtain the associated possible parameters, and screening slice layers with continuity parameters less than the threshold as suspicious slice layers, accurate identification of suspended slice layers based on contour features and continuity analysis is achieved, improving the accuracy of 3D printing suspension risk assessment and reducing the risk of printing defects.

[0105] As an optional embodiment, the step described above, calculating the possible association parameters between the two slice layers based on the pattern closure contours corresponding to the two slice layers respectively, includes:

[0106] Calculate the contour similarity between the closed contours of the patterns corresponding to the two slice layers respectively;

[0107] Calculate the area of ​​the overlapping portion of the closed outline of the pattern corresponding to the two slice layers respectively;

[0108] Based on the contour continuity prediction model, the continuity probability of the closed contours of the patterns corresponding to the two slice layers is predicted; optionally, the contour continuity prediction model is trained by a training dataset that includes multiple training continuous contour data and corresponding continuity annotations.

[0109] The possible parameters of the association between the two slice layers are obtained by calculating the product of contour similarity, area, and continuity probability.

[0110] Optionally, the contour similarity can be Hausdorff distance, cosine similarity, or shape matching degree, and the present invention does not limit it.

[0111] Optionally, the calculation of contour similarity can be based on contour point comparison, feature vector analysis, or image processing algorithms, and this invention does not limit it.

[0112] Optionally, the area can be a pixel area, a geometric area, or a standardized area; this invention does not impose any limitations on this.

[0113] Optionally, the calculation of the area can be based on contour overlay, region integration, or Boolean operations, and this invention does not limit the scope of the calculation.

[0114] Optionally, the contour continuous prediction model can be a convolutional neural network, a recurrent neural network, or a probabilistic model; this invention does not impose any limitations.

[0115] Optionally, the continuity probability can be a probability value, confidence score, or continuity level; this invention does not limit this.

[0116] Optionally, the training dataset may include historical contour data, simulated data, or labeled data, and this invention does not impose any limitations.

[0117] As can be seen, through the above optional embodiments, by calculating the contour similarity, overlapping area and continuity probability based on the contour continuity prediction model of the closed contours of two slice layers, and combining the product of the three as the correlation probability parameter, accurate slice layer correlation assessment based on multi-dimensional contour features can be achieved, thereby improving the accuracy and reliability of 3D printing suspended slice layer screening and reducing the risk of printing failure due to misjudgment of suspension.

[0118] As an optional embodiment, the step described above, which involves filtering out at least two potentially suspended suspicious slice layers from all slice layers based on possible association parameters, includes:

[0119] For each slice layer, calculate the weighted average of the possible parameters of the association between the slice layer and all other slice layers to obtain the coherence parameters corresponding to the slice layer.

[0120] From all slice layers, slice layers with a coherence parameter less than a preset first parameter threshold are selected to obtain at least two potentially suspended suspicious slice layers.

[0121] Optionally, the first parameter threshold can be a fixed threshold, a dynamic threshold, or a threshold adjusted based on model accuracy; this invention does not impose any limitations.

[0122] As can be seen, through the above optional embodiments, by calculating the weighted summation average of the possible parameters associated with each slice layer and other slice layers to obtain the coherence parameter, slice layers with coherence parameters less than a threshold are selected as potentially suspended slice layers, thereby achieving accurate screening of suspended slice layers based on inter-layer correlation and interval weighting, improving the accuracy and efficiency of 3D printing suspension risk detection, and reducing the risk of printed structural defects.

[0123] As an optional embodiment, in the above steps, when calculating the coherence parameters, the weighted calculation weight corresponding to each associated possible parameter is inversely proportional to the layer interval between the corresponding two slice layers.

[0124] As can be seen, the above optional embodiments limit the weight settings when calculating coherent parameters, so as to introduce weights related to the layer interval to obtain more accurate parameter calculation results, assist in realizing accurate island risk assessment based on slice layer correlation and component characteristics, improve the accuracy of suspended component detection and printing stability during 3D printing, and reduce the risk of printing failure caused by island components.

[0125] As an optional embodiment, the step described above, determining multiple isolated components in the 3D model data based on component matching rules and all suspicious slice layers, includes:

[0126] Determine the corresponding data component in the 3D model data for each suspicious slice layer;

[0127] For each data component, determine the total number of all suspicious slice layers corresponding to that data component;

[0128] Calculate the reciprocal of the average value of the coherence parameters of all suspicious slice layers corresponding to this data component;

[0129] Calculate the product of the total quantity and its reciprocal to obtain the suspicious parameters corresponding to the data component;

[0130] Components with suspicious parameters greater than a preset second parameter threshold are selected from all data components to obtain multiple isolated components in the 3D model data.

[0131] Optionally, the second parameter threshold can be a fixed threshold, a dynamic threshold, or a threshold adjusted based on the printing task; this invention does not impose any limitations.

[0132] As can be seen, through the above optional embodiments, by identifying the data components of suspicious slice layers in the 3D model data, calculating the product of the number of slice layers corresponding to the component and the reciprocal of the average value of the coherence parameter as the suspicious parameter, and screening components with suspicious parameters exceeding the threshold as island components, accurate island component identification based on slice layer distribution and coherence analysis is achieved, thereby improving the accuracy of 3D printing model stability assessment and reducing the risk of printing failure caused by island components.

[0133] As an optional embodiment, the component parameters in the above steps include at least one of component volume, component surface area, component shape, component minimum bounding box volume, component type, and component purpose.

[0134] As can be seen, the above optional embodiments limit the content of component parameters to comprehensively characterize component features, assist in achieving accurate island risk assessment based on slice layer correlation and component features, improve the accuracy of suspended component detection and printing stability during 3D printing, and reduce the risk of printing failure caused by island components.

[0135] As an optional embodiment, the step described above, determining the islanding risk level corresponding to any islanded component based on the component parameters of the islanded component and using an association risk analysis algorithm, includes:

[0136] For any two isolated components, calculate the parameter similarity between the component parameters of the two isolated components;

[0137] Calculate the positional distance between the two isolated island components;

[0138] The product of parameter similarity and location distance is calculated to obtain the association risk between the two isolated components;

[0139] For each isolated component, calculate the average risk of the associated risk between that isolated component and all other isolated components;

[0140] The component parameters of the isolated component are input into the trained risk prediction model to obtain the corresponding predicted risk of the isolated component; optionally, the risk prediction model is trained using a training dataset that includes multiple training component parameters and corresponding printed risk labels.

[0141] The islanding risk level corresponding to the islanded component is obtained by multiplying the average risk and the predicted risk.

[0142] Optionally, the similarity parameter can be cosine similarity, Euclidean distance, or Jaccard coefficient; this invention does not impose any limitation on it.

[0143] Optionally, the component parameters may also include component size, shape features, or material properties, which are not limited in this invention.

[0144] Optionally, the calculation of the similarity of this parameter can be based on feature comparison, geometric analysis or statistical methods, and this invention does not limit it.

[0145] Optionally, the position of the component can be three-dimensional coordinates, centroid position, or boundary point coordinates; this invention does not impose any limitations.

[0146] Optionally, the risk prediction model can be a regression model, a classification model, or a neural network model; this invention does not impose any limitations.

[0147] Optionally, the predicted risk can be a risk probability, risk level, or risk score; this invention does not limit this.

[0148] Optionally, the training dataset may include historical component data, simulation data, or experimental data, and this invention does not impose any limitations.

[0149] As can be seen, through the above optional embodiments, the product of the similarity of component parameters and the positional distance between isolated components is calculated as the associated risk. The degree of isolated risk is calculated by combining the average risk of the component with all other isolated components and the predicted risk output by the risk prediction model. This achieves accurate isolated risk assessment based on component association and risk prediction, improves the reliability and printing quality of the 3D printing process, and reduces the risk of printing defects caused by isolated components.

[0150] Example 2

[0151] Please see Figure 2 , Figure 2 This is a schematic diagram of a model island detection system for slice data management disclosed in an embodiment of the present invention. Figure 2The described model island detection system for slice data management can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 2 As shown, the model island detection system for slice data management may include:

[0152] The acquisition module 201 is used to acquire slice data corresponding to the three-dimensional model data used for 3D printing.

[0153] The first determination module 202 is used to determine at least two potentially suspended suspicious slice layers in the slice data based on the suspended prediction model.

[0154] The second determination module 203 is used to determine multiple isolated components in the 3D model data based on component matching rules and all suspicious slice layers.

[0155] Analysis module 204 is used to determine the degree of island risk corresponding to any island component based on the component parameters of the island component and the correlation risk analysis algorithm.

[0156] As can be seen, the above-described embodiments of the invention acquire slice data of 3D printed three-dimensional model data and identify potentially suspended suspicious slice layers based on the suspension prediction model. They then use component matching rules to determine isolated components and combine component parameters and correlation risk analysis algorithms to assess the degree of isolated risk. This enables accurate isolated risk assessment based on slice layer correlation and component characteristics, improves the accuracy of suspended component detection and printing stability during 3D printing, and reduces the risk of printing failure caused by isolated components.

[0157] As an optional embodiment, the first determining module determines, based on the dangling prediction model, at least two potentially dangling suspicious slice layers in the slice data in a specific manner, including:

[0158] For any two slices in the slice data whose interval is less than a preset interval threshold, the closed contours of the patterns corresponding to the two slices are determined based on the closed contour recognition algorithm.

[0159] Based on the closed contours of the patterns corresponding to the two slice layers, calculate the possible parameters of association between the two slice layers.

[0160] Based on the associated possible parameters, at least two potentially suspended suspicious slice layers are selected from all slice layers.

[0161] As can be seen, through the above optional embodiments, by determining the closed contour of any two slice layer patterns with a layer number interval of less than a threshold based on the closed contour recognition algorithm, calculating the contour similarity, overlapping area and continuity probability to obtain the associated possible parameters, and screening slice layers with continuity parameters less than the threshold as suspicious slice layers, accurate identification of suspended slice layers based on contour features and continuity analysis is achieved, improving the accuracy of 3D printing suspension risk assessment and reducing the risk of printing defects.

[0162] As an optional embodiment, the first determining module calculates the specific method of the possible correlation parameters between the two slice layers based on the closed contours of the patterns corresponding to the two slice layers, including:

[0163] Calculate the contour similarity between the closed contours of the patterns corresponding to the two slice layers respectively;

[0164] Calculate the area of ​​the overlapping portion of the closed outline of the pattern corresponding to the two slice layers respectively;

[0165] Based on the contour continuity prediction model, the continuity probability of the closed contours of the patterns corresponding to the two slice layers is predicted; optionally, the contour continuity prediction model is trained by a training dataset that includes multiple training continuous contour data and corresponding continuity annotations.

[0166] The possible parameters of the association between the two slice layers are obtained by calculating the product of contour similarity, area, and continuity probability.

[0167] As can be seen, through the above optional embodiments, by calculating the contour similarity, overlapping area and continuity probability based on the contour continuity prediction model of the closed contours of two slice layers, and combining the product of the three as the correlation probability parameter, accurate slice layer correlation assessment based on multi-dimensional contour features can be achieved, thereby improving the accuracy and reliability of 3D printing suspended slice layer screening and reducing the risk of printing failure due to misjudgment of suspension.

[0168] As an optional embodiment, the specific method by which the first determining module filters out at least two potentially suspended suspicious slice layers from all slice layers based on associated possible parameters includes:

[0169] For each slice layer, calculate the weighted average of the possible parameters of the association between the slice layer and all other slice layers to obtain the coherence parameters corresponding to the slice layer.

[0170] From all slice layers, slice layers with a coherence parameter less than a preset first parameter threshold are selected to obtain at least two potentially suspended suspicious slice layers.

[0171] As can be seen, through the above optional embodiments, by calculating the weighted summation average of the possible parameters associated with each slice layer and other slice layers to obtain the coherence parameter, slice layers with coherence parameters less than a threshold are selected as potentially suspended slice layers, thereby achieving accurate screening of suspended slice layers based on inter-layer correlation and interval weighting, improving the accuracy and efficiency of 3D printing suspension risk detection, and reducing the risk of printed structural defects.

[0172] As an optional embodiment, when calculating coherence parameters, the weighted calculation weight corresponding to each associated possible parameter is inversely proportional to the layer interval between the corresponding two slice layers.

[0173] As can be seen, the above optional embodiments limit the weight settings when calculating coherent parameters, so as to introduce weights related to the layer interval to obtain more accurate parameter calculation results, assist in realizing accurate island risk assessment based on slice layer correlation and component characteristics, improve the accuracy of suspended component detection and printing stability during 3D printing, and reduce the risk of printing failure caused by island components.

[0174] As an optional embodiment, the second determining module determines the specific method by which it identifies multiple isolated components in the 3D model data based on component matching rules and all suspicious slice layers, including:

[0175] Determine the corresponding data component in the 3D model data for each suspicious slice layer;

[0176] For each data component, determine the total number of all suspicious slice layers corresponding to that data component;

[0177] Calculate the reciprocal of the average value of the coherence parameters of all suspicious slice layers corresponding to this data component;

[0178] Calculate the product of the total quantity and its reciprocal to obtain the suspicious parameters corresponding to the data component;

[0179] Components with suspicious parameters greater than a preset second parameter threshold are selected from all data components to obtain multiple isolated components in the 3D model data.

[0180] As can be seen, through the above optional embodiments, by identifying the data components of suspicious slice layers in the 3D model data, calculating the product of the number of slice layers corresponding to the component and the reciprocal of the average value of the coherence parameter as the suspicious parameter, and screening components with suspicious parameters exceeding the threshold as island components, accurate island component identification based on slice layer distribution and coherence analysis is achieved, thereby improving the accuracy of 3D printing model stability assessment and reducing the risk of printing failure caused by island components.

[0181] As an optional embodiment, the component parameters include at least one of the following: component volume, component surface area, component shape, component minimum bounding box volume, component type, and component purpose.

[0182] As can be seen, the above optional embodiments limit the content of component parameters to comprehensively characterize component features, assist in achieving accurate island risk assessment based on slice layer correlation and component features, improve the accuracy of suspended component detection and printing stability during 3D printing, and reduce the risk of printing failure caused by island components.

[0183] As an optional embodiment, the analysis module determines the specific method for the degree of islanding risk corresponding to any islanding component based on the component parameters of the islanding component and an association risk analysis algorithm, including:

[0184] For any two isolated components, calculate the parameter similarity between the component parameters of the two isolated components;

[0185] Calculate the positional distance between the two isolated island components;

[0186] The product of parameter similarity and location distance is calculated to obtain the association risk between the two isolated components;

[0187] For each isolated component, calculate the average risk of the associated risk between that isolated component and all other isolated components;

[0188] The component parameters of the isolated component are input into the trained risk prediction model to obtain the corresponding predicted risk of the isolated component; optionally, the risk prediction model is trained using a training dataset that includes multiple training component parameters and corresponding printed risk labels.

[0189] The islanding risk level corresponding to the islanded component is obtained by multiplying the average risk and the predicted risk.

[0190] As can be seen, through the above optional embodiments, the product of the similarity of component parameters and the positional distance between isolated components is calculated as the associated risk. The degree of isolated risk is calculated by combining the average risk of the component with all other isolated components and the predicted risk output by the risk prediction model. This achieves accurate isolated risk assessment based on component association and risk prediction, improves the reliability and printing quality of the 3D printing process, and reduces the risk of printing defects caused by isolated components.

[0191] Example 3

[0192] Please see Figure 3 , Figure 3 This is another model island detection system for slice data management disclosed in the embodiments of the present invention. Figure 3 The described model island detection system for slice data management is applied in data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 3 As shown, the model island detection system for slice data management may include:

[0193] Memory 301 storing executable program code;

[0194] Processor 302 coupled to memory 301;

[0195] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the model island detection method for slice data management described in Embodiment 1.

[0196] Example 4

[0197] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the model island detection method for slice data management described in Embodiment 1.

[0198] Example 5

[0199] This 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 perform the steps of the model island detection method for slice data management described in Embodiment 1.

[0200] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0201] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0202] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0203] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0204] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0205] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0206] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0207] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0208] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0209] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0210] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0211] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0212] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0213] Finally, it should be noted that the model island detection method and system for slice data management disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting isolated models in slice data management, characterized in that, The method includes: Obtain the slice data corresponding to the 3D model data used for 3D printing; Based on the dangling prediction model, at least two potentially dangling suspicious slice layers in the slice data are identified; Based on the component matching rules, multiple isolated components in the 3D model data are determined according to all the suspected slice layers; Based on the component parameters of the isolated components, and using an association risk analysis algorithm, the degree of islanding risk corresponding to any of the isolated components is determined, including: For any two isolated island components, calculate the parameter similarity between the component parameters of the two isolated island components; Calculate the positional distance between the positions of the two isolated island components; The product of the parameter similarity and the location distance is calculated to obtain the association risk between the two isolated components; For each of the islanded components, calculate the average risk of the associated risk between that islanded component and all other islanded components; The component parameters of the isolated component are input into the trained risk prediction model to obtain the corresponding predicted risk of the isolated component; the risk prediction model is trained using a training dataset that includes multiple training component parameters and corresponding printed risk labels. The islanding risk level corresponding to the islanding component is obtained by multiplying the average risk and the predicted risk.

2. The model island detection method for slice data management according to claim 1, characterized in that, The method of identifying at least two potentially suspended suspicious slice layers in the slice data based on the dangling prediction model includes: For any two slice layers in the slice data whose interval is less than a preset interval threshold, the closed contours of the patterns corresponding to the two slice layers are determined based on the closed contour recognition algorithm. Based on the closed contours of the patterns corresponding to the two slice layers, calculate the possible parameters of association between the two slice layers. Based on the associated possible parameters, at least two potentially suspended suspicious slice layers are selected from all the slice layers.

3. The model island detection method for slice data management according to claim 2, characterized in that, The step of calculating the possible correlation parameters between the two slice layers based on the closed contours of the patterns corresponding to the two slice layers includes: Calculate the contour similarity between the closed contours of the patterns corresponding to the two slice layers respectively; Calculate the area of ​​the overlapping portion of the closed outline of the pattern corresponding to the two slice layers respectively; Based on the contour continuity prediction model, the continuity probability of the closed contours of the patterns corresponding to the two slice layers is predicted; the contour continuity prediction model is trained by a training dataset that includes multiple training continuous contour data and corresponding continuity annotations. The product of the contour similarity, the area, and the continuity probability is calculated to obtain the possible parameters of association between the two slice layers.

4. The model island detection method for slice data management according to claim 2, characterized in that, The step of filtering out at least two potentially suspended suspicious slice layers from all the slice layers based on the associated possible parameters includes: For each slice layer, calculate the weighted average of the possible correlation parameters between the slice layer and all other slice layers to obtain the coherence parameters corresponding to the slice layer; From all the slice layers, slice layers whose coherence parameter is less than a preset first parameter threshold are selected to obtain at least two potentially suspended suspicious slice layers.

5. The model island detection method for slice data management according to claim 4, characterized in that, When calculating the coherence parameters, the weighted calculation weight corresponding to each of the associated possible parameters is inversely proportional to the layer interval between the two corresponding slice layers.

6. The model island detection method for slice data management according to claim 4, characterized in that, The method of determining multiple isolated components in the 3D model data based on component matching rules, according to all the suspected slice layers, includes: Determine the data component corresponding to each of the suspected slice layers in the three-dimensional model data; For each of the data components, determine the total number of all the suspected slice layers corresponding to that data component; Calculate the reciprocal of the average value of the coherence parameters of all the suspected slice layers corresponding to the data component; Calculate the product of the total quantity and the reciprocal to obtain the suspicious parameters corresponding to the data component; From all the data components, components with suspicious parameters greater than a preset second parameter threshold are selected to obtain multiple isolated components in the three-dimensional model data.

7. The model island detection method for slice data management according to claim 1, characterized in that, The component parameters include at least one of the following: component volume, component surface area, component shape, component minimum bounding box volume, component type, and component purpose.

8. A model island detection system for slice data management, characterized in that, The system is used to perform the model island detection method for slice data management as described in any one of claims 1-7, the system comprising: The acquisition module is used to acquire slice data corresponding to the 3D model data used for 3D printing; The first determining module is used to determine at least two potentially suspended suspicious slice layers in the slice data based on the suspending prediction model. The second determining module is used to determine multiple isolated components in the three-dimensional model data based on component matching rules and according to all the suspicious slice layers; The analysis module is used to determine the degree of island risk corresponding to any of the island components based on the component parameters of the island components and an association risk analysis algorithm.

9. A model island detection system for slice data management, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the model island detection method for slice data management as described in any one of claims 1-7.

Images