A 3D printing path planning method and system based on structural stress simulation

Abstract

The present invention discloses a 3D printing path planning method and system based on structural stress simulation, and relates to the field of 3D printing technology. The method comprises: performing regional division on each structural feature in a preset structural feature set, and performing stress distribution simulation; performing printing strategy simulation on each structural feature in the preset structural feature set according to the regional division results and stress distribution simulation results of each structural feature in the preset structural feature set, so as to establish a printing mapping relationship between characteristic stress distribution and printing strategy; wherein the printing strategy comprises a 3D printing path; according to the regional division results of the part to be printed and the stress simulation results of the part to be printed, based on the printing mapping relationship between characteristic stress distribution and printing strategy, the target printing strategy is automatically called to print the part to be printed. The present application realizes the printing effect of taking into account each feature of the part to be printed when performing 3D printing.

Description

Technical Field

[0001] The present application relates to the field of 3D printing technology, and in particular to a 3D printing path planning method and system based on structural stress simulation. Background Art

[0002] At present, the molding strategy of the 3D printing process is single. The same strategy is used in the printing process of the same part, and the printing strategy cannot be divided according to different regional features, resulting in stress concentration and large deformation of local features of the part. There are the following defects: the same process parameters cannot take into account the printing effects of various features.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a 3D printing path planning method and system based on structural stress simulation to solve the above technical problems.

[0005] The present application provides a 3D printing path planning method based on structural stress simulation, comprising:

[0006] Divide each structural feature in the preset structural feature set into regions and perform stress distribution simulation;

[0007] According to the regional division results and stress distribution simulation results of each structural feature in the preset structural feature set, a printing strategy simulation is performed on each structural feature in the preset structural feature set to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy; wherein the printing strategy includes a 3D printing path;

[0008] Obtain the structural features of the parts to be printed;

[0009] According to the structural features of the part to be printed, the part to be printed is divided into regions to obtain a region division result of the part to be printed;

[0010] Simulating the stress of the part to be printed to obtain a stress simulation result of the part to be printed;

[0011] According to the area division result of the part to be printed and the stress simulation result of the part to be printed, based on the printing mapping relationship between the characteristic stress distribution and the printing strategy, the target printing strategy is automatically called to print the part to be printed.

[0012] Furthermore, the preset structural feature set includes the following structural features: angle, circle, plane, hole structure, lattice structure and hollow structure; the regional division of each structural feature in the preset structural feature set and the stress distribution simulation include:

[0013] Performing regional division on each structural feature in the preset structural feature set to obtain a sub-region corresponding to each structural feature;

[0014] The stress distribution information of the sub-regions corresponding to the various structural features in three stress directions is extracted.

[0015] Further, the stress distribution information includes a first component in a first stress direction, a second component in a second stress direction, and a third component in a third stress direction; the printing strategy also includes a printing direction, a layer thickness, a filling density, and a support structure; the printing strategy simulation is performed on each structural feature in the preset structural feature set according to the regional division result of each structural feature in the preset structural feature set and the stress distribution simulation result to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy, including:

[0016] Normalizing stress distribution information of sub-regions corresponding to each structural feature in the preset structural feature set in three stress directions;

[0017] A printing strategy recommendation model is constructed and trained based on the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein the printing strategy recommendation model is used to recommend printing strategies according to the structural features of the parts.

[0018] Furthermore, the printing strategy recommendation model is constructed and trained according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions, including:

[0019] The printing strategy recommendation model is constructed according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein,

[0020] ;

[0021] in, A printing strategy recommendation model is constructed; is the number of the input layer node; is the number of the hidden layer nodes; n is the number of input layer nodes; h is the number of hidden layer nodes; k is a positive integer less than the number of output nodes; f() represents the hidden layer activation function; Represents input data, Represents the connection weight between the input layer and the hidden layer; Represents the connection weight between the hidden layer and the output layer; Represents the initialization hidden layer threshold;

[0022] According to the classification of the structural features, the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions is divided into N stress distribution sets according to the number of categories N;

[0023] The data in the N stress distribution sets are input into the constructed printing strategy recommendation model, and the constructed printing strategy recommendation model is supervised and trained according to the loss function; wherein the data in the N stress distribution sets have corresponding weight coefficients; each layer of the network included in the printing strategy recommendation model adopts a three-dimensional convolution kernel, and the convolution kernels are shared between neighbors.

[0024] Further,

[0025] ;

[0026] in, Indicates The weight coefficients of the data in the stress distribution set; is a nonlinear function; Indicates A set of stress distributions; Indicates The confidence level of a set of stress distributions; , All are adjustment factors; is the sum of the confidences of N stress distribution sets; N is the number of the stress distribution sets.

[0027] Furthermore, the loss function The expression is as follows:

[0028] ;

[0029] Wherein, N is the number of the stress distribution sets; Indicates that during training, the first The probability of the data in a set of stress distributions; The total number of training times for the printing strategy recommendation model; represents the expected output of the printing strategy recommendation model; Indicates passing The weight matrix output by the printing strategy recommendation model after training; Indicates passing The score of the printing strategy recommended by the printing strategy recommendation model after training.

[0030] Further, receiving an instance of a mapping relationship between a characteristic stress distribution and a printing strategy sent by a preset object;

[0031] Based on the mapping relationship instance between the characteristic stress distribution and the printing strategy, the printing mapping relationship between the characteristic stress distribution and the printing strategy is updated.

[0032] The present application provides a 3D printing path planning system based on structural stress simulation, including a region division and stress simulation unit, a printing mapping relationship establishment unit, a to-be-printed part region division result determination unit, a to-be-printed part stress simulation result determination unit, and a target printing strategy calling unit; wherein,

[0033] The region division and stress simulation unit is used to divide each structural feature in the preset structural feature set into regions and perform stress distribution simulation;

[0034] The printing mapping relationship establishing unit is used to perform printing strategy simulation on each structural feature in the preset structural feature set according to the regional division result and stress distribution simulation result of each structural feature in the preset structural feature set, so as to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy; wherein the printing strategy includes a 3D printing path;

[0035] The unit for determining the area division result of the part to be printed is used to obtain the structural characteristics of the part to be printed; divide the part to be printed into areas according to the structural characteristics of the part to be printed, and obtain the area division result of the part to be printed;

[0036] The stress simulation result determination unit of the part to be printed is used to simulate the stress of the part to be printed to obtain the stress simulation result of the part to be printed;

[0037] The target printing strategy calling unit is used to automatically call the target printing strategy to print the part to be printed based on the printing mapping relationship between the characteristic stress distribution and the printing strategy according to the area division result of the part to be printed and the stress simulation result of the part to be printed.

[0038] Furthermore, the preset structural feature set includes the following structural features: angle, circle, plane, hole structure, lattice structure and hollow structure; the regional division of each structural feature in the preset structural feature set and the stress distribution simulation include:

[0039] Performing regional division on each structural feature in the preset structural feature set to obtain a sub-region corresponding to each structural feature;

[0040] The stress distribution information of the sub-regions corresponding to the various structural features in three stress directions is extracted.

[0041] Further, the stress distribution information includes a first component in a first stress direction, a second component in a second stress direction, and a third component in a third stress direction; the printing strategy also includes a printing direction, a layer thickness, a filling density, and a support structure; the printing strategy simulation is performed on each structural feature in the preset structural feature set according to the regional division result of each structural feature in the preset structural feature set and the stress distribution simulation result to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy, including:

[0042] Normalizing stress distribution information of sub-regions corresponding to each structural feature in the preset structural feature set in three stress directions;

[0043] A printing strategy recommendation model is constructed and trained based on the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein the printing strategy recommendation model is used to recommend strategies according to the structural features of the parts.

[0044] Based on the embodiment provided by the present application, each structural feature in the preset structural feature set is divided into regions, and stress distribution simulation is performed; according to the regional division results and stress distribution simulation results of each structural feature in the preset structural feature set, a printing strategy simulation is performed on each structural feature in the preset structural feature set to establish a printing mapping relationship between characteristic stress distribution and printing strategy; wherein the printing strategy includes a 3D printing path; the structural features of the part to be printed are obtained; according to the structural features of the part to be printed, the part to be printed is divided into regions to obtain the regional division results of the part to be printed; the stress simulation of the part to be printed is simulated to obtain the stress simulation results of the part to be printed; according to the regional division results and stress simulation results of the part to be printed, based on the printing mapping relationship between characteristic stress distribution and printing strategy, the target printing strategy is automatically called to print the part to be printed. Thus, the printing effect of taking into account each feature of the part to be printed when performing 3D printing is achieved. Specifically, it has the following beneficial effects: Improve printing quality and efficiency: By dividing the preset structural features into regions and simulating the stress distribution, the mechanical behavior of different regions during the printing process can be understood more accurately, thereby optimizing the printing path and parameters and improving the printing quality and efficiency; Enhance structural strength and durability: Stress distribution simulation helps to identify potential stress concentration areas. By adjusting the printing strategy, such as changing the filling mode or adding support structures, the structural strength and durability of the final product can be enhanced; Realize customized printing: Establish a mapping relationship between characteristic stress distribution and printing strategy, allowing the most appropriate printing strategy to be automatically called according to the specific characteristics of different parts to achieve customized printing; Reduce material waste: Through precise regional division and stress simulation, only Use enough material in the required areas to reduce overall material consumption and lower costs; Improve the conversion speed from design to production: Automated printing strategy calls reduce the preparation time from design to printing and speed up the product development cycle; Optimize the printing path: By considering the structural characteristics and stress distribution of the parts, the 3D printing path can be optimized to reduce printing time and improve the stability of the printing process; Improve the predictability of the printing process: Through simulation, the printing effect and possible problems of the parts can be predicted before actual printing, so that measures can be taken in advance to reduce the risk of printing failure; Support the printing of complex parts: For parts with complex internal structures or external shapes, this method can ensure that all features can get the appropriate printing strategy to achieve successful printing of complex parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 is a flowchart of an optional 3D printing path planning method based on structural stress simulation according to an embodiment of the present application;

[0047] Figure 2 It is a structural diagram of an optional 3D printing path planning system based on structural stress simulation according to an embodiment of the present application.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0050] Alternatively, if Figure 1 As shown, the present application provides a 3D printing path planning method based on structural stress simulation, comprising:

[0051] S101, dividing each structural feature in the preset structural feature set into regions and performing stress distribution simulation;

[0052] S102, performing printing strategy simulation on each structural feature in the preset structural feature set according to the regional division result and stress distribution simulation result of each structural feature in the preset structural feature set, so as to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy; wherein the printing strategy includes a 3D printing path;

[0053] S103, obtaining structural features of the part to be printed;

[0054] S104, dividing the part to be printed into regions according to the structural features of the part to be printed, and obtaining a region division result of the part to be printed;

[0055] S105, simulating the stress of the part to be printed to obtain the stress simulation result of the part to be printed;

[0056] S106, according to the area division result of the part to be printed and the stress simulation result of the part to be printed, based on the printing mapping relationship between the characteristic stress distribution and the printing strategy, automatically calling the target printing strategy to print the part to be printed.

[0057] Based on the embodiment provided by the present application, each structural feature in the preset structural feature set is divided into regions, and stress distribution simulation is performed; according to the regional division results and stress distribution simulation results of each structural feature in the preset structural feature set, a printing strategy simulation is performed on each structural feature in the preset structural feature set to establish a printing mapping relationship between characteristic stress distribution and printing strategy; wherein the printing strategy includes a 3D printing path; the structural features of the part to be printed are obtained; according to the structural features of the part to be printed, the part to be printed is divided into regions to obtain the regional division results of the part to be printed; the stress simulation of the part to be printed is simulated to obtain the stress simulation results of the part to be printed; according to the regional division results and stress simulation results of the part to be printed, based on the printing mapping relationship between characteristic stress distribution and printing strategy, the target printing strategy is automatically called to print the part to be printed. Thus, the printing effect of taking into account each feature of the part to be printed when performing 3D printing is achieved.

[0058] Specifically, it has the following beneficial effects:

[0059] Improve printing quality and efficiency: By dividing the preset structural features into regions and simulating the stress distribution, the mechanical behavior of different regions during the printing process can be understood more accurately, thereby optimizing the printing path and parameters and improving the printing quality and efficiency;

[0060] Enhance structural strength and durability: Stress distribution simulation helps identify potential stress concentration areas. By adjusting the printing strategy, such as changing the filling pattern or adding support structures, the structural strength and durability of the final product can be enhanced.

[0061] Realize customized printing: Establish the mapping relationship between characteristic stress distribution and printing strategy, allowing the most appropriate printing strategy to be automatically called according to the specific characteristics of different parts to realize customized printing;

[0062] Reduce material waste: Through accurate area division and stress simulation, sufficient material can be used only in the required areas, reducing overall material consumption and reducing costs;

[0063] Improve the conversion speed from design to production: Automated printing strategy calls reduce the preparation time from design to printing and speed up the product development cycle;

[0064] Optimizing the printing path: By considering the structural characteristics and stress distribution of the part, the 3D printing path can be optimized to reduce the printing time and improve the stability of the printing process;

[0065] Improve the predictability of the printing process: Through simulation, the printing effect and possible problems of parts can be predicted before actual printing, so that measures can be taken in advance to reduce the risk of printing failure;

[0066] Support for printing of complex parts: For parts with complex internal structures or external shapes, this method can ensure that all features can receive appropriate printing strategies, enabling successful printing of complex parts.

[0067] Furthermore, the preset structural feature set includes the following structural features: angle, circle, plane, hole structure, lattice structure and hollow structure; each structural feature in the preset structural feature set is divided into regions, and stress distribution simulation is performed, including:

[0068] Performing regional division on each structural feature in the preset structural feature set to obtain a sub-region corresponding to each structural feature;

[0069] The stress distribution information of the sub-regions corresponding to each structural feature in three stress directions is extracted.

[0070] Further, the stress distribution information includes a first component in a first stress direction, a second component in a second stress direction, and a third component in a third stress direction; the printing strategy also includes a printing direction, a layer thickness, a filling density, and a support structure; and according to the regional division results of each structural feature in the preset structural feature set and the stress distribution simulation results, a printing strategy simulation is performed on each structural feature in the preset structural feature set to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy, including:

[0071] Normalizing stress distribution information of sub-regions corresponding to each structural feature in the preset structural feature set in three stress directions;

[0072] A printing strategy recommendation model is constructed and trained based on the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein the printing strategy recommendation model is used to recommend printing strategies according to the structural features of the parts.

[0073] Furthermore, according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions, a printing strategy recommendation model is constructed and trained, including:

[0074] According to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions, a printing strategy recommendation model is constructed; wherein,

[0075] ;

[0076] in, Recommend models for the constructed printing strategy; is the number of the input layer node; is the number of the hidden layer nodes; n is the number of input layer nodes; h is the number of hidden layer nodes; k is a positive integer less than the number of output nodes; f() represents the hidden layer activation function; Represents input data, Represents the connection weight between the input layer and the hidden layer; Represents the connection weight between the hidden layer and the output layer; Represents the initialization hidden layer threshold;

[0077] According to the classification of the structural features, the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions is divided into N stress distribution sets according to the number of categories N;

[0078] The data in the N stress distribution sets are input into the constructed printing strategy recommendation model, and the constructed printing strategy recommendation model is supervised and trained according to the loss function; wherein the data in the N stress distribution sets have corresponding weight coefficients; each layer of the network included in the printing strategy recommendation model adopts a three-dimensional convolution kernel, and the convolution kernels are shared between neighbors.

[0079] Further,

[0080] ;

[0081] in, Indicates The weight coefficients of the data in the stress distribution set; is a nonlinear function; Indicates A set of stress distributions; Indicates The confidence level of a set of stress distributions; , All are adjustment factors; is the sum of the confidences of N stress distribution sets; N is the number of stress distribution sets.

[0082] Furthermore, the loss function The expression is as follows:

[0083] ;

[0084] Where N is the number of stress distribution sets; Indicates that during training, the first The probability of the data in a set of stress distributions; The total number of training times for the printing strategy recommendation model; represents the expected output of the printing strategy recommendation model; Indicates passing After training, print the weight matrix output by the strategy recommendation model; Indicates passing After training, the scores of the printing strategies recommended by the printing strategy recommendation model.

[0085] Further, receiving an instance of a mapping relationship between a characteristic stress distribution and a printing strategy sent by a preset object;

[0086] Based on the mapping relationship instance between the characteristic stress distribution and the printing strategy, the printing mapping relationship between the characteristic stress distribution and the printing strategy is updated.

[0087] In some embodiments of the present application, the printing strategies that can be selected for the following structural features are as follows: sharp corners: scanning path planning is performed according to the contour, and the energy density is reduced during printing to reduce stress concentration; thin walls: single contour printing strategy, large path spacing, low power, high scanning speed, reducing energy and reducing stress concentration; large entities: large layer thickness printing strategy, using large layer thickness, high power and low scanning speed.

[0088] Alternatively, if Figure 2 As shown, the present application provides a 3D printing path planning system based on structural stress simulation, including a region division and stress simulation unit 201, a printing mapping relationship establishment unit 202, a to-be-printed part region division result determination unit 203, a to-be-printed part stress simulation result determination unit 204, and a target printing strategy calling unit 205; wherein,

[0089] The region division and stress simulation unit 201 is used to divide each structural feature in the preset structural feature set into regions and perform stress distribution simulation;

[0090] A printing mapping relationship establishing unit 202 is used to perform printing strategy simulation on each structural feature in the preset structural feature set according to the regional division result and stress distribution simulation result of each structural feature in the preset structural feature set, so as to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy; wherein the printing strategy includes a 3D printing path;

[0091] The unit 203 for determining the region division result of the part to be printed is used to obtain the structural characteristics of the part to be printed; divide the part to be printed into regions according to the structural characteristics of the part to be printed, and obtain the region division result of the part to be printed;

[0092] The stress simulation result determination unit 204 of the part to be printed is used to simulate the stress of the part to be printed and obtain the stress simulation result of the part to be printed;

[0093] The target printing strategy calling unit 205 is used to automatically call the target printing strategy to print the part to be printed based on the region division result of the part to be printed and the stress simulation result of the part to be printed, based on the printing mapping relationship between the characteristic stress distribution and the printing strategy.

[0094] Furthermore, the preset structural feature set includes the following structural features: angle, circle, plane, hole structure, lattice structure and hollow structure; each structural feature in the preset structural feature set is divided into regions, and stress distribution simulation is performed, including:

[0095] Performing regional division on each structural feature in the preset structural feature set to obtain a sub-region corresponding to each structural feature;

[0096] The stress distribution information of the sub-regions corresponding to each structural feature in three stress directions is extracted.

[0097] Further, the stress distribution information includes a first component in a first stress direction, a second component in a second stress direction, and a third component in a third stress direction; the printing strategy also includes a printing direction, a layer thickness, a filling density, and a support structure; and according to the regional division results of each structural feature in the preset structural feature set and the stress distribution simulation results, a printing strategy simulation is performed on each structural feature in the preset structural feature set to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy, including:

[0098] Normalizing stress distribution information of sub-regions corresponding to each structural feature in the preset structural feature set in three stress directions;

[0099] A printing strategy recommendation model is constructed and trained based on the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein the printing strategy recommendation model is used to recommend strategies according to the structural features of the parts.

[0100] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A 3D printing path planning method based on structural stress simulation, characterized in that: include: Divide each structural feature in the preset structural feature set into regions and perform stress distribution simulation; According to the regional division results and stress distribution simulation results of each structural feature in the preset structural feature set, a printing strategy simulation is performed on each structural feature in the preset structural feature set to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy; wherein the printing strategy includes a 3D printing path; Obtain the structural features of the parts to be printed; According to the structural features of the part to be printed, the part to be printed is divided into regions to obtain a region division result of the part to be printed; Simulating the stress of the part to be printed to obtain a stress simulation result of the part to be printed; According to the area division result of the part to be printed and the stress simulation result of the part to be printed, based on the printing mapping relationship between the characteristic stress distribution and the printing strategy, the target printing strategy is automatically called to print the part to be printed; The preset structural feature set includes the following structural features: angle, circle, plane, hole structure, lattice structure and hollow structure; the region division of each structural feature in the preset structural feature set and the stress distribution simulation include: Performing regional division on each structural feature in the preset structural feature set to obtain a sub-region corresponding to each structural feature; Extracting stress distribution information of sub-regions corresponding to each structural feature in three stress directions; The stress distribution information includes a first component in a first stress direction, a second component in a second stress direction, and a third component in a third stress direction; the printing strategy also includes a printing direction, a layer thickness, a filling density, and a support structure; and the printing strategy simulation is performed on each structural feature in the preset structural feature set according to the regional division result of each structural feature in the preset structural feature set and the stress distribution simulation result to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy, including: Normalizing stress distribution information of sub-regions corresponding to each structural feature in the preset structural feature set in three stress directions; According to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions, a printing strategy recommendation model is constructed and trained; wherein the printing strategy recommendation model is used to recommend printing strategies according to the structural features of the parts; The method of constructing and training a printing strategy recommendation model according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions includes: The printing strategy recommendation model is constructed according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein, ； in, A printing strategy recommendation model is constructed; is the number of the input layer node; is the number of the hidden layer nodes; n is the number of input layer nodes; h is the number of hidden layer nodes; k is a positive integer less than the number of output nodes; f() represents the hidden layer activation function; Represents input data, Represents the connection weight between the input layer and the hidden layer; Represents the connection weight between the hidden layer and the output layer; Represents the initialization hidden layer threshold; According to the classification of the structural features, the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions is divided into N stress distribution sets according to the number of categories N; The data in the N stress distribution sets are input into the constructed printing strategy recommendation model, and the constructed printing strategy recommendation model is supervised and trained according to the loss function; wherein the data in the N stress distribution sets have corresponding weight coefficients; each layer of the network included in the printing strategy recommendation model adopts a three-dimensional convolution kernel, and the convolution kernels are shared between neighbors.

2. The 3D printing path planning method based on structural stress simulation according to claim 1, characterized in that: ； in, Indicates The weight coefficients of the data in the stress distribution set; is a nonlinear function; Indicates A set of stress distributions; Indicates The confidence level of a set of stress distributions; , All are adjustment factors; is the sum of the confidences of N stress distribution sets; N is the number of the stress distribution sets.

3. The 3D printing path planning method based on structural stress simulation according to claim 1, characterized in that: Loss Function The expression is as follows: ； Wherein, N is the number of the stress distribution sets; Indicates that during training, the first The probability of the data in a set of stress distributions; The total number of training times for the printing strategy recommendation model; represents the expected output of the printing strategy recommendation model; Indicates passing The weight matrix output by the printing strategy recommendation model after training; Indicates passing The score of the printing strategy recommended by the printing strategy recommendation model after training.

4. The 3D printing path planning method based on structural stress simulation according to claim 1, characterized in that: Receiving a mapping relationship instance between a characteristic stress distribution and a printing strategy sent by a preset object; Based on the mapping relationship instance between the characteristic stress distribution and the printing strategy, the printing mapping relationship between the characteristic stress distribution and the printing strategy is updated.

5. A 3D printing path planning system based on structural stress simulation, characterized in that: It includes a region division and stress simulation unit, a printing mapping relationship establishment unit, a to-be-printed part region division result determination unit, a to-be-printed part stress simulation result determination unit, and a target printing strategy calling unit; wherein, The region division and stress simulation unit is used to divide each structural feature in the preset structural feature set into regions and perform stress distribution simulation; The printing mapping relationship establishing unit is used to perform printing strategy simulation on each structural feature in the preset structural feature set according to the regional division result and stress distribution simulation result of each structural feature in the preset structural feature set, so as to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy; wherein the printing strategy includes a 3D printing path; The unit for determining the area division result of the part to be printed is used to obtain the structural characteristics of the part to be printed; divide the part to be printed into areas according to the structural characteristics of the part to be printed, and obtain the area division result of the part to be printed; The stress simulation result determination unit of the part to be printed is used to simulate the stress of the part to be printed to obtain the stress simulation result of the part to be printed; The target printing strategy calling unit is used to automatically call the target printing strategy to print the part to be printed based on the printing mapping relationship between the characteristic stress distribution and the printing strategy according to the area division result of the part to be printed and the stress simulation result of the part to be printed; The preset structural feature set includes the following structural features: angle, circle, plane, hole structure, lattice structure and hollow structure; the region division of each structural feature in the preset structural feature set and the stress distribution simulation include: Performing regional division on each structural feature in the preset structural feature set to obtain a sub-region corresponding to each structural feature; Extracting stress distribution information of sub-regions corresponding to each structural feature in three stress directions; The stress distribution information includes a first component in a first stress direction, a second component in a second stress direction, and a third component in a third stress direction; the printing strategy also includes a printing direction, a layer thickness, a filling density, and a support structure; and the printing strategy simulation is performed on each structural feature in the preset structural feature set according to the regional division result of each structural feature in the preset structural feature set and the stress distribution simulation result to establish a printing mapping relationship between the characteristic stress distribution and the printing strategy, including: Normalizing stress distribution information of sub-regions corresponding to each structural feature in the preset structural feature set in three stress directions; According to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions, a printing strategy recommendation model is constructed and trained; wherein the printing strategy recommendation model is used to recommend printing strategies according to the structural features of the parts; The method of constructing and training a printing strategy recommendation model according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions includes: The printing strategy recommendation model is constructed according to the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions; wherein, ； in, A printing strategy recommendation model is constructed; is the number of the input layer node; is the number of the hidden layer nodes; n is the number of input layer nodes; h is the number of hidden layer nodes; k is a positive integer less than the number of output nodes; f() represents the hidden layer activation function; Represents input data, Represents the connection weight between the input layer and the hidden layer; Represents the connection weight between the hidden layer and the output layer; Represents the initialization hidden layer threshold; According to the classification of the structural features, the stress distribution information of the sub-regions corresponding to each structural feature in the preset structural feature set after normalization in three stress directions is divided into N stress distribution sets according to the number of categories N; The data in the N stress distribution sets are input into the constructed printing strategy recommendation model, and the constructed printing strategy recommendation model is supervised and trained according to the loss function; wherein the data in the N stress distribution sets have corresponding weight coefficients; each layer of the network included in the printing strategy recommendation model adopts a three-dimensional convolution kernel, and the convolution kernels are shared between neighbors.

Images