Electric arc additive manufacturing path planning method, device and equipment and storage medium

Abstract

The invention discloses a path planning method, device and equipment for electric arc additive manufacturing and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring grid information of a gridded to-be-processed object and a multi-layer path curve of the object; on the basis of the grid information of the object and the multi-layer path curve, obtaining path feature information of each grid surface of the object; wherein the path feature information comprises a first path curvature vector and a first grid surface normal vector of a central point of a grid surface, and a second path curvature vector and a second grid surface normal vector of a path point corresponding to the central point; inputting the path feature information of each grid surface into a preset collapse compensation prediction model to obtain a compensation ratio of each grid surface; and planning a target printing path of the object by utilizing a preset path compensation strategy based on the compensation ratio of each grid surface and the multi-layer path curve of the object.

Description

Technical Field

[0001] The present application relates to the field of computer technology, specifically to technical fields such as arc additive manufacturing and 3D printing technology, and in particular to a path planning method, device, equipment and storage medium for arc additive manufacturing. Background Art

[0002] Arc additive manufacturing is an emerging manufacturing technology. Generally, during the arc additive manufacturing process, path collapse often occurs due to the influence of factors such as thermal stress and gravity, which seriously affects the quality and precision of manufactured products.

[0003] At present, arc additive manufacturing solutions in related technologies mainly rely on experience and trial and error to deal with the problem of path collapse and deformation. However, the processing efficiency of the solutions in related technologies is low and it is difficult to ensure accuracy. Summary of the invention

[0004] The present application provides a path planning method, device, equipment and storage medium for arc additive manufacturing, and the technical solution is as follows:

[0005] In a first aspect, a path planning method for arc additive manufacturing is provided, the method comprising:

[0006] Acquire grid information of a gridded object to be processed and a multi-layer path curve of the object;

[0007] Based on the mesh information of the object and the multi-layer path curve, path feature information of each mesh surface of the object is obtained; wherein the path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point;

[0008] Inputting the path characteristic information of each mesh surface into a preset collapse compensation prediction model to obtain a compensation ratio of each mesh surface;

[0009] Based on the compensation ratio of each grid surface and the multi-layer path curve of the object, a target printing path of the object is planned using a preset path compensation strategy.

[0010] In a possible implementation, obtaining the path feature information of each mesh surface of the object based on the mesh information of the object and the multi-layer path curve includes:

[0011] Based on the mesh information of the object and the multi-layer path curve, performing feature extraction processing on the object;

[0012] Based on the result of the feature extraction process, path feature information of each mesh surface of the object is obtained.

[0013] In a possible implementation, the performing feature extraction processing on the object based on the mesh information of the object and the multi-layer path curve includes:

[0014] Based on the mesh information of the object and the multi-layer path curve, determine the center point of each mesh surface and the path point located on the second path curve of the previous layer of the first path curve corresponding to the center point and the distance between the center point and the path point meets the preset distance condition;

[0015] A first path curvature vector and a first mesh surface normal vector of a center point of each mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point are extracted to obtain a result of the feature extraction process.

[0016] In a possible implementation, the preset path compensation strategy includes a plurality of path compensation sub-strategies, and the target printing path of the object is planned by using the preset path compensation strategy based on the compensation ratio of each mesh surface and the multi-layer path curve, including:

[0017] Based on the compensation ratio of each mesh surface, a plurality of mesh surfaces are merged to determine at least one compensation printing area of ​​the object;

[0018] Based on the preset path compensation strategy and the compensation ratio of each compensation printing area, obtaining a path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area;

[0019] Based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve, a target printing path of the object is planned.

[0020] In a possible implementation, planning the target printing path of the object based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve includes:

[0021] Determine a compensation printing path curve for each compensation printing area based on a path compensation sub-strategy corresponding to a compensation ratio of each compensation printing area;

[0022] Based on the compensation printing path curve of each compensation printing area, updating the multi-layer path curve;

[0023] Based on the result of the updating process, a target printing path of the object is obtained.

[0024] In a second aspect, a model training method is provided, the method comprising:

[0025] Acquire grid information of a gridded sample object, a multi-layer path curve of the sample object, and a compensation ratio of the sample object;

[0026] Based on the mesh information of the sample object and the multi-layer path curve, sample path feature information of each mesh surface of the sample object is obtained; wherein the sample path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point;

[0027] Inputting the sample path feature information of each mesh surface into the collapse compensation prediction model to be trained to obtain a compensation ratio of each mesh surface;

[0028] Based on the sample path feature information of each mesh surface, the compensation ratio of the sample object and the compensation ratio of each mesh surface, the collapse compensation prediction model to be trained is updated and trained to obtain a trained collapse compensation prediction model, wherein the trained collapse compensation prediction model is used to execute the aspects and methods of any possible implementation methods as described above.

[0029] In a third aspect, a path planning device for arc additive manufacturing is provided, the device comprising:

[0030] A first acquisition unit, used to acquire grid information of a gridded object to be processed and a multi-layer path curve of the object;

[0031] A first obtaining unit is used to obtain path feature information of each mesh surface of the object based on the mesh information of the object and the multi-layer path curve; wherein the path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point;

[0032] A first prediction unit, configured to input the path feature information of each mesh surface into a preset collapse compensation prediction model to obtain a compensation ratio of each mesh surface;

[0033] The first planning unit is used to plan a target printing path of the object based on the compensation ratio of each grid surface and the multi-layer path curve of the object by using a preset path compensation strategy.

[0034] In a fourth aspect, a model training device is provided, the device comprising:

[0035] A second acquisition unit, configured to acquire grid information of a gridded sample object, a multi-layer path curve of the sample object, and a compensation ratio of the sample object;

[0036] A second obtaining unit is used to obtain sample path feature information of each mesh surface of the sample object based on the mesh information of the sample object and the multi-layer path curve; wherein the sample path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point;

[0037] A second prediction unit, used for inputting the sample path feature information of each mesh surface into the collapse compensation prediction model to be trained to obtain a compensation ratio of each mesh surface;

[0038] The first training unit is used to update the training process of the collapse compensation prediction model to be trained based on the sample path feature information of each mesh surface, the compensation ratio of the sample object and the compensation ratio of each mesh surface, so as to obtain a trained collapse compensation prediction model, wherein the trained collapse compensation prediction model is used to execute the method of the aspects and any possible implementation methods as described above.

[0039] In a fifth aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method of the above-mentioned aspects and any possible implementation manner.

[0040] In a sixth aspect, an electronic device is provided, including:

[0041] at least one processor; and

[0042] a memory communicatively connected to the at least one processor; wherein,

[0043] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.

[0044] The beneficial effects of the technical solution provided by this application include at least:

[0045] It can be seen from the above technical solution that, on the one hand, the embodiment of the present application can obtain the grid information of the gridded object to be processed and the multi-layer path curve of the object, and obtain the path feature information of each grid surface of the object based on the grid information of the object and the multi-layer path curve; wherein the path feature information includes a first path curvature vector and a first grid surface normal vector of the center point of the grid surface, and a second path curvature vector and a second grid surface normal vector of the path point corresponding to the center point, and the path feature information of each grid surface is input into a preset collapse compensation prediction model to obtain a compensation ratio of each grid surface, and based on the compensation ratio of each grid surface and the multi-layer path curve of the object, a preset path compensation strategy is used to plan the target printing path of the object to be processed. Since the preset collapse compensation prediction model can be used to process the path feature information of each grid surface of the object to be processed to obtain the compensation ratio of each grid surface, and then according to the compensation ratio of each grid surface, a target printing path with a compensated path is directly planned, which can ensure the efficiency of automatic compensation manufacturing in the additive forming process, and can also effectively ensure the continuity of the additive forming process and the reliability of the printed object.

[0046] It can be seen from the above technical solution that, on the other hand, the embodiment of the present application can obtain the grid information of the gridded sample object, the multi-layer path curve of the sample object and the compensation ratio of the sample object, and then obtain the sample path feature information of each grid surface of the sample object based on the grid information of the sample object and the multi-layer path curve; wherein the sample path feature information includes a first path curvature vector and a first grid surface normal vector of the center point of the grid surface, and a second path curvature vector and a second grid surface normal vector of the path point corresponding to the center point; the sample path feature information of each grid surface is input into the collapse compensation prediction model to be trained to obtain the compensation ratio of each grid surface; based on the sample path feature information of each grid surface, the compensation ratio of each grid surface and the compensation ratio of the sample object, the collapse compensation prediction model to be trained is updated and trained to obtain a trained collapse compensation prediction model; since the collapse compensation prediction model for determining the compensation ratio of the target printing path can be trained based on the sample path feature information corresponding to each grid surface of the sample object, the accuracy of the learning information and output information of the model is improved, thereby improving the learning performance and reliability of the trained collapse compensation prediction model.

[0047] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 It is a flow chart of a path planning method for arc additive manufacturing provided by an embodiment of the present application;

[0050] Figure 2 is a flowchart of a model training method provided by another embodiment of the present application;

[0051] Figure 3 is a schematic diagram of a path planning method for arc additive manufacturing provided by another embodiment of the present application;

[0052] Figure 4 is a schematic diagram of an application scenario of a path planning method for arc additive manufacturing provided by another embodiment of the present application;

[0053] Figure 5 is a structural block diagram of a path planning device for arc additive manufacturing provided by another embodiment of the present application;

[0054] Figure 6 is a structural block diagram of a model training device provided in another embodiment of the present application;

[0055] Figure 7 It is a block diagram of an electronic device used to implement the path planning method and model training method of arc additive manufacturing in the embodiment of the present disclosure. DETAILED DESCRIPTION

[0056] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0057] Obviously, the described embodiments are only part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0058] It should be noted that the terminal devices involved in the embodiments of the present application may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.

[0059] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0060] Please refer to Figure 1 , which shows a schematic flow chart of a path planning method for arc additive manufacturing provided by an embodiment of the present application. The path planning method for arc additive manufacturing may specifically include:

[0061] Step 101: Obtain grid information of a gridded object to be processed and a multi-layer path curve of the object.

[0062] Step 102: Based on the mesh information of the object and the multi-layer path curve, obtain path feature information of each mesh surface of the object; wherein the path feature information includes a first path curvature vector and a first mesh surface normal vector of the center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of the path point corresponding to the center point.

[0063] Step 103: Input the path feature information of each mesh surface into a preset collapse compensation prediction model to obtain a compensation ratio of each mesh surface.

[0064] Step 104 : Based on the compensation ratio of each mesh surface and the multi-layer path curve of the object, a target printing path of the object is planned using a preset path compensation strategy.

[0065] It should be noted that the object to be processed may include a part manufactured by electric arc additive manufacturing, that is, a 3D printed part. The multi-layer path curve of the object may be obtained by performing a layered path planning process on the 3D printed model of the object.

[0066] It should be noted that the preset collapse compensation prediction model may be a prediction model based on a neural network.

[0067] It should be noted that part or all of the execution subject of steps 101 to 104 may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in an information processing platform on the network side, etc. This embodiment does not specifically limit this.

[0068] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0069] In this way, the path feature information of each mesh surface of the object to be processed can be processed by utilizing the preset collapse compensation prediction model to obtain the compensation ratio of each mesh surface, and then the target printing path with the compensation path can be directly planned according to the compensation ratio of each mesh surface. This can ensure the efficiency of automatic compensation manufacturing in the additive forming process while effectively ensuring the continuity of the additive forming process and the reliability of the printed object.

[0070] Optionally, in a possible implementation of the present embodiment, in step 102, feature extraction processing can be performed on the object based on the mesh information of the object and the multi-layer path curve, and then path feature information of each mesh surface of the object can be obtained based on the result of the feature extraction processing.

[0071] In an implementation, the center point and its corresponding path point may form a position point pair. The path feature information of each mesh surface may include feature information of the position point pair of each mesh surface.

[0072] In a specific implementation process of this implementation method, first, based on the mesh information of the object and the multi-layer path curve, the center point of each mesh surface and the path point located on the second path curve of the previous layer of the first path curve corresponding to the center point and whose distance from the center point meets the preset distance condition can be determined. Secondly, the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface, as well as the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point are extracted to obtain the result of the feature extraction process.

[0073] In this implementation, the preset distance condition may be that the distance between the path point and the center point is the minimum.

[0074] Here, the path point corresponding to the center point may be a point on the second path curve of the previous layer of the first path curve corresponding to the center point, with the smallest distance from the center point. The center point and the path point corresponding to it may be on the same grid surface or on different grid surfaces.

[0075] In this implementation, the first path curve corresponding to the center point may be a path curve where the center point is located, or may be a path curve with the smallest distance from the center point. The path curve may be a curve in a multi-layer path curve.

[0076] In this implementation, the first path curvature vector and the first mesh surface normal vector may be feature information of the center point. The second path curvature vector and the second mesh surface normal vector may be feature information of the path point. The path feature information of each mesh surface may include feature information of the center point of each mesh surface and feature information of the path point corresponding to the center point.

[0077] Exemplarily, for any mesh surface, the path feature information of the mesh surface may include a first path curvature vector and a first mesh surface normal vector of the center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of the path point corresponding to the center point.

[0078] In this way, the path feature information of each mesh surface of the object can be accurately extracted according to the mesh information and multi-layer path curves of the object, so that the path feature information can be used to predict a more reliable compensation ratio of the printing path later.

[0079] Optionally, in a possible implementation of the present embodiment, the preset path compensation strategy may include multiple path compensation sub-strategies. In step 104, the multiple grid surfaces may be merged based on the compensation ratio of each grid surface to determine at least one compensation printing area of ​​the object. Then, based on the preset path compensation strategy and the compensation ratio of each compensation printing area, the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area may be obtained, the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve may be obtained to plan the target printing path of the object.

[0080] In a specific implementation process of this implementation, first, mesh surfaces with the same compensation ratio may be merged to obtain at least one compensation printing area of ​​the object. The compensation ratios of the mesh surfaces in the compensation printing area may be the same.

[0081] It is understandable that other merging processing methods may be used to obtain multiple compensation printing areas of the object, which is not specifically limited here.

[0082] In this implementation, the preset path compensation strategy can be determined based on the connectivity of the compensation printing path curves of adjacent different compensation printing areas. In this way, it can be ensured that the compensation printing path curves in the horizontal direction can be aligned, optimizing the printing path, thereby further improving the reliability and printing efficiency of the printing path.

[0083] Here, the preset path compensation strategy may further include a preset compensation ratio and a path compensation sub-strategy corresponding to the preset compensation ratio. There may be multiple preset compensation ratios.

[0084] For example, a preset compensation ratio is 0.15, and its corresponding path compensation sub-strategy can be based on the multi-layer path curve of the object, first compensating one layer every ten layers, then compensating one layer every five layers, and so on. Another preset compensation ratio is 0.2, and its corresponding path compensation sub-strategy can be based on the multi-layer path curve of the object, compensating one layer every five layers.

[0085] In another specific implementation process of the implementation method, first, the compensation ratio of each compensation printing area is matched with each preset compensation ratio in the preset path compensation strategy to obtain the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area.

[0086] Exemplarily, the compensation ratio of a compensation printing area is 0.15, which matches the preset compensation ratio of 0.15. Its corresponding path compensation sub-strategy can be based on the multi-layer path curve of the object, first compensate one layer every ten layers, then compensate one layer every five layers, and execute this strategy cyclically until all the compensation printing path curves of the compensation printing area are obtained. The compensation ratio of a compensation printing area is 0.2, which matches the preset compensation ratio of 0.2. Its corresponding path compensation sub-strategy can be based on the multi-layer path curve of the object, compensate one layer every five layers, and execute this strategy cyclically until all the compensation printing path curves of the compensation printing area are obtained.

[0087] It can be understood that the path compensation sub-strategy can be to determine the compensation printing path curve according to the printing direction, that is, the compensation printing path curve can be determined from bottom to top based on the original multi-layer path curve.

[0088] In another specific implementation process of the implementation method, first, based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area, a compensation printing path curve of each compensation printing area can be determined. Secondly, based on the compensation printing path curve of each compensation printing area, the multi-layer path curve can be updated. Thirdly, based on the result of the update process, the target printing path of the object can be obtained.

[0089] One situation of the specific implementation process is that, first, based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve in each compensation printing area, the positional relationship between the compensation printing path curve in each compensation printing area and the multi-layer path curve in each compensation printing area can be determined. Secondly, based on the positional relationship and the compensation printing path curve, the multi-layer path curve in each compensation printing area is updated. Thirdly, based on the updated multi-layer path curve, the target printing path of the object is obtained.

[0090] In another specific implementation process of the implementation method, first, based on the compensation ratio of each grid surface, multiple grid surfaces are merged, and at least one compensation printing area and at least one non-compensation printing area of ​​the object can be obtained. The target printing path of the object can be obtained based on the updated multi-layer path curve of each compensation printing area and the multi-layer path curve of the non-compensation printing area.

[0091] It can be understood that, here, the compensation ratio of the non-compensated printing area can be 0.

[0092] In addition, the compensation ratio can also be used to characterize possible path collapse in multi-layer path curves.

[0093] In this way, the target printing path with the compensation path can be directly obtained through the path compensation sub-strategy and multi-layer path curve corresponding to the compensation ratio of each compensation printing area, without the need to perform separate detection of other compensation paths, thereby improving the efficiency of path planning and further providing the reliability of the target printing path.

[0094] It should be noted that the specific implementation process provided in this implementation can be combined with the various specific implementation processes provided in the aforementioned implementation to implement the arc additive manufacturing path planning method of this embodiment. For a detailed description, please refer to the relevant content in the aforementioned implementation, which will not be repeated here.

[0095] Figure 2 is a flow chart of a model training method provided by another embodiment of the present application, such as Figure 2 The model training method can be implemented as follows:

[0096] Step 201: Obtain grid information of a gridded sample object, a multi-layer path curve of the sample object, and a compensation ratio of the sample object.

[0097] Step 202: Based on the mesh information of the sample object and the multi-layer path curve, obtain sample path feature information of each mesh surface of the sample object; wherein the sample path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point.

[0098] Step 203: Input the sample path feature information of each mesh surface into the collapse compensation prediction model to be trained to obtain the compensation ratio of each mesh surface.

[0099] Step 204: Based on the sample path feature information of each mesh surface, the compensation ratio of the sample object and the compensation ratio of each mesh surface, the training collapse compensation prediction model is updated to obtain a trained collapse compensation prediction model.

[0100] It should be noted that part or all of the execution subject of steps 201 to 204 may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in a model training platform on the network side, etc. This embodiment does not specifically limit this.

[0101] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0102] In this way, a collapse compensation prediction model for determining the compensation ratio of the target printing path can be trained based on the sample path feature information corresponding to each grid surface of the sample object, thereby improving the accuracy of the model's learning information and output information, thereby improving the learning performance and reliability of the trained collapse compensation prediction model.

[0103] Optionally, in a possible implementation of this embodiment, the collapse compensation prediction model may be a prediction model based on a neural network.

[0104] In this implementation, the collapse compensation prediction model may be a neural network model of a 4*n*n*1 structure. The collapse compensation prediction model may include an input layer, a first intermediate layer, a second intermediate layer, and an output layer.

[0105] Optionally, in a possible implementation of this embodiment, the sample path feature information may be used as input data for training the collapse compensation prediction model to be trained. The compensation ratio of the sample object may be sample verification data for training. The compensation ratio of the sample object may be determined based on the historical target printing path of the sample object.

[0106] Here, the grid information of the sample object may be sample grid information, the multi-layer path curve of the sample object may be a sample multi-layer path curve, and the compensation ratio of the sample object may be a sample compensation ratio, that is, training sample verification data.

[0107] It is understandable that the trained collapse compensation prediction model can be used to execute the path planning method of arc additive manufacturing in the aforementioned embodiment. Specifically, the grid information of the gridded object to be processed and the multi-layer path curve of the object can be obtained, and the path feature information of each grid surface of the object can be obtained based on the grid information of the object and the multi-layer path curve; wherein the path feature information includes the first path curvature vector and the first grid surface normal vector of the center point of the grid surface, and the second path curvature vector and the second grid surface normal vector of the path point corresponding to the center point, and the path feature information of each grid surface is input into the preset collapse compensation prediction model to obtain the compensation ratio of each grid surface, and based on the compensation ratio of each grid surface and the multi-layer path curve of the object, the target printing path of the object is planned using the preset path compensation strategy.

[0108] In order to better understand the method of the embodiment of the present application, the method of the embodiment of the present application is described below with reference to the accompanying drawings and specific application scenarios.

[0109] Figure 3 is a flow chart of a path planning method for arc additive manufacturing provided by another embodiment of the present application, such as Figure 3 In this embodiment, the arc additive manufacturing path planning method may include:

[0110] Step 301: Obtain sample grid information, sample compensation ratio, and sample multi-layer path curve of a gridded sample object.

[0111] In this embodiment, sample grid information, sample compensation ratio and sample multi-layer path curve of the gridded sample object can be obtained based on the historical target printing path. The historical target printing path can be historical sample data of the sample object.

[0112] Step 302: Based on the sample mesh information and the sample multi-layer path curve, extract the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface of the sample object, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point.

[0113] In this embodiment, the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point can be used as sample path feature information.

[0114] Exemplarily, the first mesh surface normal vector N1 and the first path curvature vector V1 of the center point P1, the second mesh surface normal vector N2 and the second path curvature vector V2 of the path point P2 corresponding to the center point P1. Each vector can be three-dimensional, and the sample path feature information input to the collapse compensation prediction model to be trained can be a 12-dimensional tensor.

[0115] Step 303: input the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface of the sample object, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point into the collapse compensation prediction model to be trained to obtain the compensation ratio of each mesh surface.

[0116] Step 304: based on the sample compensation ratio, the compensation ratio of each mesh surface, the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point, the collapse compensation prediction model to be trained is updated and trained to obtain a trained collapse compensation prediction model.

[0117] In this embodiment, the collapse compensation prediction model may be a neural network model of a 4*n*n*1 structure. The collapse compensation prediction model may include an input layer, a first intermediate layer, a second intermediate layer and an output layer.

[0118] Here, we can use the extracted path features and corresponding path collapse features to train the neural network model based on the characteristics of arc additive manufacturing, and continuously optimize the model parameters to obtain a trained collapse compensation prediction model. Based on the nonlinear fitting ability of the neural network, we can better handle the relationship between complex process parameters and path collapse, thereby improving the accuracy of the prediction results.

[0119] Step 305: Obtain the grid information and multi-layer path curves of the gridded object to be processed.

[0120] In this embodiment, firstly, the 3D model information of the object to be processed can be horizontally sliced ​​along the height direction of the object to be processed according to a preset thickness. Secondly, based on the result of the slicing process, a multi-layer path curve of the object to be processed can be obtained, and the thickness of each layer of the path curve can be 2 mm.

[0121] Preferably, the preset thickness may be determined according to the printing material and the shape of the object.

[0122] Furthermore, the results of the slicing process may be sorted according to the branch shapes of the object to obtain a final multi-layer path curve of the object to be processed.

[0123] Step 306: Based on the mesh information and multi-layer path curves of the object, obtain the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface of the object, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point.

[0124] Step 307: input the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface of the object, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point into a preset collapse compensation prediction model, and output a compensation ratio for each mesh surface.

[0125] In this embodiment, the compensation ratio may be used to characterize a path collapse situation that may exist in a multi-layer path curve.

[0126] Here, the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface of the object, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point may constitute the path feature information of the object.

[0127] Step 308: Based on the compensation ratio of each mesh surface and the multi-layer path curve, a target printing path of the object is planned using a preset path compensation strategy.

[0128] In this embodiment, at this point, the target printing path can be used to directly print the object without the need for separate compensation printing processing.

[0129] In this embodiment, the preset path compensation strategy may include multiple path compensation sub-strategies. Specifically, first, based on the compensation ratio of each grid surface, multiple grid surfaces are merged to determine at least one compensation printing area of ​​the object. Secondly, based on the preset path compensation strategy and the compensation ratio of each compensation printing area, a path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area is obtained. Thirdly, based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area, a compensation printing path curve of each compensation printing area is determined. Thirdly, based on the compensation printing path curve of each compensation printing area, the multi-layer path curve is updated. Thirdly, based on the result of the update process, the target printing path of the object is obtained. Finally, the object to be processed can be printed according to the target printing path.

[0130] In this embodiment, Figure 4 is a schematic diagram of an application scenario of a path planning method for arc additive manufacturing provided by another embodiment of the present application, such as Figure 4 As shown. In this application scenario, first, the input data of the collapse compensation prediction model can be the path feature information of the extracted mesh surface. The path feature information can include feature information of multiple position point pairs. N1 and V1 can represent the first mesh surface normal vector and the first path curvature vector of the center point, and N2 and V2 can represent the second mesh surface normal vector and the second path curvature vector of the path point corresponding to the center point. The collapse compensation prediction model can be a neural network model with a 4*n*n*1 structure. X1 and X2 can represent 3-dimensional tensors respectively. The collapse compensation prediction model can be trained based on historical data. Historical data, that is, sample data, can be a gridded historical target printing path with compensation printing path information. Based on the historical target printing path, sample grid information, sample multi-layer path curve and sample compensation ratio can be obtained. As Figure 4 As shown, the red line segments in the historical data may represent the compensated printing path curve, and the other black line segments may represent the normal printing path curve, i.e., the multi-layer path curve. The output data of the collapse compensation prediction model may be the path compensation ratio of each mesh surface, i.e., the compensation ratio. Secondly, according to the path compensation ratio of each mesh surface, the preset path compensation strategy is used to obtain the target printing path with the compensated printing path curve for printing the object.

[0131] Here, the preset path compensation strategy may be a path compensation strategy based on a compensation ratio, such as Figure 4As shown, in the path compensation strategy based on the compensation ratio, the preset compensation ratio can be 0.05, 0.10, 0.15, 0.20, 0.25, 0.30, 0.35, and 0.40. If the preset compensation ratio can be 0.05, the path compensation sub-strategy can be to compensate one layer of path curve, that is, the red path curve, every 11 layers of multi-layer path curves, that is, the black original path curve. If the preset compensation ratio can be 0.10, the path compensation sub-strategy can be to compensate one layer of path curve every ten layers of original path curves. If the preset compensation ratio can be 0.15, the path compensation sub-strategy can be to first compensate one layer of path curve once with ten layers of original path curves, and then compensate one layer once with five layers, and so on. If the preset compensation ratio can be 0.20, the path compensation sub-strategy can be to compensate one layer of path curve every five layers of original path curves. If the preset compensation ratio can be 0.25, the path compensation sub-strategy can be to first perform three intervals of five layers of original path curves, compensate one layer of path curve, and then perform one interval of two layers to compensate one layer, and then cycle. If the preset compensation ratio can be 0.30, the path compensation sub-strategy can be to first perform one interval of five layers of original path curves, compensate one layer of path curve, and then perform one interval of two layers to compensate one layer, and then perform one interval of three layers to compensate one layer, and then cycle. If the preset compensation ratio can be 0.35, the path compensation sub-strategy can be to first perform one interval of five layers of original path curves, compensate one layer of path curve, and then perform one interval of two layers to compensate one layer, and then perform one interval of three layers to compensate one layer, and then cycle. If the preset compensation ratio can be 0.40, the path compensation sub-strategy can be to first perform one interval of two layers of original path curves, compensate one layer of path curve, and then perform one interval of three layers to compensate one layer, and then cycle.

[0132] Based on the technical solution of this embodiment, the possible path collapse can be predicted by using a trained collapse compensation prediction model, and a corresponding compensation path can be generated according to a preset path compensation strategy. Then, based on the compensation path and multi-layer path curves, a more reliable target printing path of the object can be obtained.

[0133] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0134] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] Figure 5 FIG. 1 shows a structural block diagram of a path planning device for arc additive manufacturing provided by an embodiment of the present application. Figure 5 As shown. The path planning device 500 for arc additive manufacturing of this embodiment may include a first acquisition unit 501, a first acquisition unit 502, a first prediction unit 503, and a first planning unit 504. The first acquisition unit 501 is used to acquire the grid information of the gridded object to be processed and the multi-layer path curve of the object; the first acquisition unit 502 is used to obtain the path feature information of each grid surface of the object based on the grid information of the object and the multi-layer path curve; wherein the path feature information includes the first path curvature vector and the first grid surface normal vector of the center point of the grid surface, and the second path curvature vector and the second grid surface normal vector of the path point corresponding to the center point; the first prediction unit 503 is used to input the path feature information of each grid surface into a preset collapse compensation prediction model to obtain the compensation ratio of each grid surface; the first planning unit 504 is used to plan the target printing path of the object based on the compensation ratio of each grid surface and the multi-layer path curve of the object using a preset path compensation strategy.

[0136] It should be noted that part or all of the arc additive manufacturing path planning device of this embodiment may be an application located in a local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in an application located in a local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in an information processing platform on the network side, etc. This embodiment does not specifically limit this.

[0137] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0138] Optionally, in a possible implementation of this embodiment, the first acquisition unit 502 can be used to perform feature extraction processing on the object based on the mesh information of the object and the multi-layer path curve; and based on the result of the feature extraction processing, obtain the path feature information of each mesh surface of the object.

[0139] Optionally, in a possible implementation of the present embodiment, the first obtaining unit 502 may be used to determine, based on the mesh information of the object and the multi-layer path curve, the center point of each mesh surface and the path point located on the second path curve of the previous layer of the first path curve corresponding to the center point and whose distance from the center point satisfies a preset distance condition; extract the first path curvature vector and the first mesh surface normal vector of the center point of each mesh surface, and the second path curvature vector and the second mesh surface normal vector of the path point corresponding to the center point, so as to obtain the result of the feature extraction processing.

[0140] Optionally, in a possible implementation of the present embodiment, the preset path compensation strategy includes multiple path compensation sub-strategies, and the first planning unit 504 can be used to merge multiple grid surfaces based on the compensation ratio of each grid surface to determine at least one compensation printing area of ​​the object; based on the preset path compensation strategy and the compensation ratio of each compensation printing area, obtain the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area; based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve, plan the target printing path of the object.

[0141] Optionally, in a possible implementation of the present embodiment, the first planning unit 504 may be used to determine a compensation printing path curve for each compensation printing area based on a path compensation sub-strategy corresponding to a compensation ratio of each compensation printing area; update the multi-layer path curve based on the compensation printing path curve of each compensation printing area; and obtain a target printing path for the object based on a result of the update process.

[0142] In this embodiment, the grid information of the gridded object to be processed and the multi-layer path curve of the object can be obtained by the first acquisition unit, and then the first acquisition unit obtains the path feature information of each grid surface of the object based on the grid information of the object and the multi-layer path curve; wherein the path feature information includes a first path curvature vector and a first grid surface normal vector of the center point of the grid surface, and a second path curvature vector and a second grid surface normal vector of the path point corresponding to the center point; the first prediction unit inputs the path feature information of each grid surface into a preset collapse compensation prediction model to obtain a compensation ratio of each grid surface; the first planning unit plans the target printing path of the object based on the compensation ratio of each grid surface and the multi-layer path curve of the object using a preset path compensation strategy; since the preset collapse compensation prediction model can be used to process the path feature information of each grid surface of the object to be processed to obtain the compensation ratio of each grid surface, and then according to the compensation ratio of each grid surface, a target printing path with a compensation path is directly planned, which can ensure the efficiency of automatic compensation manufacturing in the additive forming process while effectively ensuring the continuity of the additive forming process and the reliability of the printed object.

[0143] Figure 6 A structural block diagram of a model training device provided by an embodiment of the present application is shown. Figure 6 The model training device 600 of this embodiment may include a second acquisition unit 601 , a second obtaining unit 602 , a second prediction unit 603 , and a first training unit 604 . Among them, the second acquisition unit 601 is used to obtain the grid information of the gridded sample object, the multi-layer path curve of the sample object and the compensation ratio of the sample object, and the multi-layer path curve of the sample object includes a compensation printing path curve; the second acquisition unit 602 is used to obtain the sample path feature information of each grid surface of the sample object based on the grid information of the sample object and the multi-layer path curve; wherein the sample path feature information includes the first path curvature vector and the first grid surface normal vector of the center point of the grid surface, and the second path curvature vector and the second grid surface normal vector of the path point corresponding to the center point; the second prediction unit 603 is used to input the sample path feature information of each grid surface into the collapse compensation prediction model to be trained to obtain the compensation ratio of each grid surface; the first training unit 604 is used to update the collapse compensation prediction model to be trained based on the sample path feature information of each grid surface, the compensation ratio of the sample object and the compensation ratio of each grid surface to obtain a trained collapse compensation prediction model.

[0144] It should be noted that part or all of the model training device of this embodiment may be an application located in the local terminal, or may also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or may also be a processing engine located in a network-side server, or may also be a distributed system located on the network side, for example, a processing engine or distributed system in a model training platform on the network side, etc. This embodiment does not specifically limit this.

[0145] It is understandable that the application may be a local program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.

[0146] Optionally, in a possible implementation of this embodiment, the collapse compensation prediction model may be a neural network model of a 4*n*n*1 structure. The collapse compensation prediction model may include an input layer, a first intermediate layer, a second intermediate layer and an output layer.

[0147] Optionally, in a possible implementation of this embodiment, the sample path feature information may be used as input data for training the collapse compensation prediction model to be trained. The compensation ratio of the sample object may be sample verification data for training. The compensation ratio of the sample object may be determined based on the historical target printing path of the sample object.

[0148] In this embodiment, the grid information of the gridded sample object, the multi-layer path curve of the sample object and the compensation ratio of the sample object can be obtained by the second acquisition unit, and the multi-layer path curve of the sample object includes a compensation printing path curve, and then the second acquisition unit can obtain the sample path feature information of each grid surface of the sample object based on the grid information of the sample object and the multi-layer path curve; wherein the sample path feature information includes a first path curvature vector and a first grid surface normal vector of a center point of the grid surface, and a second path curvature vector and a second grid surface normal vector of a path point corresponding to the center point, and the second prediction unit converts the sample path feature information of each grid surface into a first path curvature vector and a second grid surface normal vector of a path point corresponding to the center point. This path feature information is input into the collapse compensation prediction model to be trained to obtain the compensation ratio of each grid surface, so that the first training unit can update the training process of the collapse compensation prediction model to be trained based on the sample path feature information of each grid surface, the compensation ratio of the sample object and the compensation ratio of each grid surface to obtain the trained collapse compensation prediction model. Since the collapse compensation prediction model for determining the compensation ratio of the target printing path can be trained based on the sample path feature information corresponding to each grid surface of the sample object, the accuracy of the learning information and output information of the model is improved, thereby improving the learning performance and reliability of the trained collapse compensation prediction model.

[0149] In the technical solution of this application, the user personal information involved, such as the collection, storage, use, processing, transmission, provision and disclosure of user images and attribute data, etc., complies with the provisions of relevant laws and regulations and does not violate public order and good morals.

[0150] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0151] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0152] like Figure 7As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0153] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0154] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the path planning method and the model training method for arc additive manufacturing. For example, in some embodiments, the path planning method and the model training method for arc additive manufacturing may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the path planning method and the model training method for arc additive manufacturing described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the path planning method and model training method for arc additive manufacturing in any other appropriate manner (for example, by means of firmware).

[0155] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0157] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0159] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0160] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0161] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0162] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A path planning method for arc additive manufacturing, characterized in that: The method comprises: Acquire grid information of a gridded object to be processed and a multi-layer path curve of the object; Based on the mesh information of the object and the multi-layer path curve, path feature information of each mesh surface of the object is obtained; wherein the path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point; Inputting the path characteristic information of each mesh surface into a preset collapse compensation prediction model to obtain a compensation ratio of each mesh surface; Based on the compensation ratio of each grid surface and the multi-layer path curve of the object, a target printing path of the object is planned using a preset path compensation strategy.

2. The method according to claim 1, characterized in that The obtaining, based on the mesh information of the object and the multi-layer path curve, path feature information of each mesh surface of the object comprises: Based on the mesh information of the object and the multi-layer path curve, performing feature extraction processing on the object; Based on the result of the feature extraction process, path feature information of each mesh surface of the object is obtained.

3. The method according to claim 2, characterized in that The performing feature extraction processing on the object based on the mesh information of the object and the multi-layer path curve comprises: Based on the mesh information of the object and the multi-layer path curve, determine the center point of each mesh surface and the path point located on the second path curve of the previous layer of the first path curve corresponding to the center point and the distance between the center point and the path point meets the preset distance condition; A first path curvature vector and a first mesh surface normal vector of a center point of each mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point are extracted to obtain a result of the feature extraction process.

4. The method according to claim 1, characterized in that: The preset path compensation strategy includes a plurality of path compensation sub-strategies, and the target printing path of the object is planned by using the preset path compensation strategy based on the compensation ratio of each mesh surface and the multi-layer path curve, including: Based on the compensation ratio of each mesh surface, a plurality of mesh surfaces are merged to determine at least one compensation printing area of ​​the object; Based on the preset path compensation strategy and the compensation ratio of each compensation printing area, obtaining a path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area; Based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve, a target printing path of the object is planned.

5. The method according to claim 4, characterized in that The planning of the target printing path of the object based on the path compensation sub-strategy corresponding to the compensation ratio of each compensation printing area and the multi-layer path curve includes: Determine a compensation printing path curve for each compensation printing area based on a path compensation sub-strategy corresponding to a compensation ratio of each compensation printing area; Based on the compensation printing path curve of each compensation printing area, updating the multi-layer path curve; Based on the result of the updating process, a target printing path of the object is obtained.

6. A method for model training, characterized in that: The method comprises: Acquire grid information of a gridded sample object, a multi-layer path curve of the sample object, and a compensation ratio of the sample object; Based on the mesh information of the sample object and the multi-layer path curve, sample path feature information of each mesh surface of the sample object is obtained; wherein the sample path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point; Inputting the sample path feature information of each mesh surface into the collapse compensation prediction model to be trained to obtain a compensation ratio of each mesh surface; Based on the sample path feature information of each mesh surface, the compensation ratio of the sample object and the compensation ratio of each mesh surface, the collapse compensation prediction model to be trained is updated and trained to obtain a trained collapse compensation prediction model, wherein the trained collapse compensation prediction model is used to execute the method as described in any one of claims 1 to 5.

7. A path planning device for arc additive manufacturing, characterized in that: The device comprises: A first acquisition unit, used to acquire grid information of a gridded object to be processed and a multi-layer path curve of the object; A first obtaining unit is used to obtain path feature information of each mesh surface of the object based on the mesh information of the object and the multi-layer path curve; wherein the path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point; A first prediction unit, configured to input the path feature information of each mesh surface into a preset collapse compensation prediction model to obtain a compensation ratio of each mesh surface; The first planning unit is used to plan a target printing path of the object based on the compensation ratio of each grid surface and the multi-layer path curve of the object by using a preset path compensation strategy.

8. A device for model training, characterized in that: The device comprises: A second acquisition unit, configured to acquire grid information of a gridded sample object, a multi-layer path curve of the sample object, and a compensation ratio of the sample object; A second obtaining unit is used to obtain sample path feature information of each mesh surface of the sample object based on the mesh information of the sample object and the multi-layer path curve; wherein the sample path feature information includes a first path curvature vector and a first mesh surface normal vector of a center point of the mesh surface, and a second path curvature vector and a second mesh surface normal vector of a path point corresponding to the center point; A second prediction unit, used for inputting the sample path feature information of each mesh surface into the collapse compensation prediction model to be trained to obtain a compensation ratio of each mesh surface; The first training unit is used to update the training of the collapse compensation prediction model to be trained based on the sample path feature information of each mesh surface, the compensation ratio of the sample object and the compensation ratio of each mesh surface to obtain a trained collapse compensation prediction model, wherein the trained collapse compensation prediction model is used to execute the method as described in any one of claims 1 to 5.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

Images