A method and device for processing synthetic casting model

Abstract

The present invention provides a method and apparatus for processing a composite casting model. The method comprises: obtaining at least two three-dimensional casting models to be processed; inputting the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, obtaining feature graphs at different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; performing processing based on the feature graphs at different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models; and performing splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model. The method for processing a composite casting model provided by the present invention can effectively improve the efficiency of composite casting models, thereby reducing the workload of composite casting models.

Description

Technical Field

[0001] The present invention relates to the field of casting technology, and in particular to a method and device for processing a synthetic casting model, and also to an electronic device, a non-transitory computer-readable storage medium, and a computer program product. Background Art

[0002] In recent years, with the continuous development of computer industry technology, various casting models have become increasingly widely used in the industrial field. However, there are many types of casting models, and collecting and organizing them cannot fully reflect the characteristics of the castings. Artificial modeling requires constructing structures from scratch, which is very labor-intensive. Numerical simulation technology is widely used in the casting field, but its limitations, such as cumbersome implementation and long calculation times, result in the low efficiency of synthesizing casting models. Therefore, how to design an efficient solution for synthesizing casting models has become a technical problem that needs to be solved urgently. Summary of the Invention

[0003] The present invention provides a method for processing a synthetic casting model, which is used to solve the defect that the synthetic casting model solution in the prior art has high limitations, resulting in poor efficiency of the actual synthetic casting model.

[0004] The present invention provides a method for processing a synthetic casting model, comprising:

[0005] obtaining at least two three-dimensional casting models to be processed;

[0006] Inputting the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, thereby obtaining feature maps of different network levels output by the casting prediction model and corresponding to the at least two three-dimensional casting models, respectively; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on sample three-dimensional casting models and feature prediction result labels corresponding to the sample three-dimensional casting models;

[0007] Based on the feature maps of the different network levels, processing is performed to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; based on the casting feature sub-models corresponding to the at least two three-dimensional casting models, splicing and synthesis processing is performed to obtain a new casting model.

[0008] According to a method for processing a synthetic casting model provided by the present invention, the processing based on the feature graphs of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively includes:

[0009] Screening the values ​​in the three-dimensional array corresponding to the feature maps of the different network levels to obtain target feature maps of the different network levels after the value screening process;

[0010] Connectivity detection is performed based on the target feature graphs of different network levels after the screening process to obtain models of a preset number of connected areas, and the models of the connected areas are used as the casting feature sub-models.

[0011] According to a method for processing a synthetic casting model provided by the present invention, the values ​​in the three-dimensional array corresponding to the feature maps of different network levels are screened to obtain target feature maps of different network levels after the value screening process, specifically comprising:

[0012] Performing screening processing on the feature maps of the different network layers to obtain screened feature maps;

[0013] The values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

[0014] According to a method for processing a synthetic casting model provided by the present invention, the connectivity detection is performed based on the target feature graphs of different network layers after the screening process to obtain a model of a preset number of connected areas, specifically comprising:

[0015] Performing connectivity detection based on the target feature graphs of different network levels after the screening process to obtain connectivity detection results of the target feature graphs of different network levels;

[0016] According to the sizes of the connected areas in the connectivity detection results, the connected areas are sorted in descending order to obtain a sorting result; models of a preset number of first N connected areas are obtained from the sorting results; wherein N is a positive integer greater than or equal to 2.

[0017] According to a method for processing a synthetic casting model provided by the present invention, the method of filtering the values ​​in the three-dimensional array corresponding to the feature map after the filtering process to obtain target feature maps of different network levels after the value filtering process specifically includes:

[0018] According to the quantitative characteristics of all values ​​in the three-dimensional array corresponding to the feature map after the screening process, a value threshold is determined; based on the value threshold, the values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

[0019] According to a method for processing a synthetic casting model provided by the present invention, the method comprises: performing a splicing and synthesis process based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model, specifically comprising:

[0020] Acquire size and position information of casting feature sub-models corresponding to the at least two three-dimensional casting models respectively;

[0021] Based on the size and position information of the casting feature sub-models corresponding to the at least two three-dimensional casting models, the casting feature sub-models corresponding to the at least two three-dimensional casting models are rotated, scaled and / or translated respectively, so that the casting feature sub-models corresponding to the at least two three-dimensional casting models are spliced ​​and synthesized to obtain a new casting model.

[0022] The present invention also provides a processing device for a synthetic casting model, comprising:

[0023] A casting model obtaining unit, configured to obtain at least two three-dimensional casting models to be processed;

[0024] a casting model feature extraction unit, configured to input the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtain feature graphs of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on sample three-dimensional casting models and feature prediction result labels corresponding to the sample three-dimensional casting models;

[0025] The casting model processing unit is used to perform processing based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; and to perform splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models respectively to obtain a new casting model.

[0026] According to a processing device for a synthetic casting model provided by the present invention, the casting model processing unit is specifically used for:

[0027] Screening the values ​​in the three-dimensional array corresponding to the feature maps of the different network levels to obtain target feature maps of the different network levels after the value screening process;

[0028] Connectivity detection is performed based on the target feature graphs of different network levels after the screening process to obtain models of a preset number of connected areas, and the models of the connected areas are used as the casting feature sub-models.

[0029] According to a processing device for a synthetic casting model provided by the present invention, the filtering process of the values ​​in the three-dimensional array corresponding to the feature maps of different network levels to obtain the target feature maps of different network levels after the value filtering process specifically includes:

[0030] Performing screening processing on the feature maps of the different network layers to obtain screened feature maps;

[0031] The values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

[0032] According to a processing device for a synthetic casting model provided by the present invention, the connectivity detection is performed based on the target feature graphs of different network layers after the screening process to obtain a model of a preset number of connected areas, specifically comprising:

[0033] Performing connectivity detection based on the target feature graphs of different network levels after the screening process to obtain connectivity detection results of the target feature graphs of different network levels;

[0034] According to the sizes of the connected areas in the connectivity detection results, the connected areas are sorted in descending order to obtain a sorting result; models of a preset number of first N connected areas are obtained from the sorting results; wherein N is a positive integer greater than or equal to 2.

[0035] According to a processing device for a synthetic casting model provided by the present invention, the filtering process is performed on the values ​​in the three-dimensional array corresponding to the feature graph after the filtering process to obtain target feature graphs of different network levels after the value filtering process, specifically comprising:

[0036] According to the quantitative characteristics of all values ​​in the three-dimensional array corresponding to the feature map after the screening process, a value threshold is determined; based on the value threshold, the values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

[0037] According to a processing device for a synthetic casting model provided by the present invention, the casting model processing unit is specifically used for:

[0038] Acquire size and position information of casting feature sub-models corresponding to the at least two three-dimensional casting models respectively;

[0039] Based on the size and position information of the casting feature sub-models corresponding to the at least two three-dimensional casting models, the casting feature sub-models corresponding to the at least two three-dimensional casting models are rotated, scaled and / or translated respectively, so that the casting feature sub-models corresponding to the at least two three-dimensional casting models are spliced ​​and synthesized to obtain a new casting model.

[0040] The present invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for processing a synthetic casting model as described in any one of the above items is implemented.

[0041] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processing method for synthesizing a casting model as described in any one of the above items is implemented.

[0042] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the processing method for synthesizing a casting model as described in any one of the above items is implemented.

[0043] The processing method of the synthetic casting model provided by the present invention obtains at least two three-dimensional casting models to be processed, inputs the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, obtains feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models, processes based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models, and performs splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to quickly obtain a new casting model. The method can effectively improve the efficiency of synthesizing the casting model, thereby reducing the workload of synthesizing the casting model. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 This is one of the flow diagrams of the method for processing a synthetic casting model provided by the present invention.

[0046] Figure 2 This is the second flow chart of the method for processing a synthetic casting model provided by the present invention.

[0047] Figure 3 It is a schematic diagram of a three-dimensional casting model provided by the present invention.

[0048] Figure 4 It is a schematic diagram of another three-dimensional casting model provided by the present invention.

[0049] Figure 5 It is a schematic diagram of the positions of two three-dimensional casting models provided by the present invention.

[0050] Figure 6 It is a schematic diagram of the new casting model provided by the present invention.

[0051] Figure 7 It is the feature map of the third convolutional layer channel 5 and its reference value provided by the present invention.

[0052] Figure 8 It is the feature map of the 8th convolutional layer channel 2 and its reference value provided by the present invention.

[0053] Figure 9 It is the feature map of the 8th convolutional layer channel 15 and its reference value provided by the present invention.

[0054] Figure 10 It is the casting feature sub-model of the 8th convolutional layer channel 2 and its reference value provided by the present invention.

[0055] Figure 11 It is a structural schematic diagram of the processing device for synthetic casting models provided by the present invention.

[0056] Figure 12 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0057] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0058] The following combination Figures 1-12 The present invention is described in detail with respect to a method and apparatus for processing a composite casting pattern.

[0059] The following is a detailed description of an embodiment of the method for processing a synthetic casting model according to the present invention. Figure 1 As shown, it is one of the flow diagrams of the method for processing the synthetic casting model provided by the present invention, and the specific implementation process includes the following steps:

[0060] Step 101: Obtain at least two three-dimensional casting models to be processed.

[0061] In an embodiment of the present invention, before executing this step, it is necessary to perform model training in advance to obtain a trained casting prediction model. Specifically, first obtain a sample three-dimensional casting model, and determine the feature prediction result label corresponding to the sample three-dimensional casting model, and then iteratively train the initial casting prediction model based on the sample three-dimensional casting model and the feature prediction result label corresponding to the sample three-dimensional casting model. When the loss function meets the preset conditions, the trained casting prediction model is obtained. Figure 2The sample three-dimensional casting model shown may include casting model 1, casting model 2, and casting model 3. The initial casting prediction model may be as follows Figure 2 The convolutional neural network portion shown.

[0062] It should be noted that the sample three-dimensional casting models can be selected from multiple existing typical three-dimensional casting models, and a three-dimensional array with the same side length in three directions is set. The multiple typical three-dimensional casting models are discretized in the three-dimensional space corresponding to the three-dimensional array. The position of the three-dimensional casting model and other positions in the three-dimensional array are set to different values. An initial casting prediction model (i.e., an initial convolutional neural network model) is established, using multi-level convolution operations to extract features. The three-dimensional casting model is input, and the three-dimensional casting model data is uniformly normalized during input. Specifically, supervised or unsupervised learning can be selected. Supervised learning can classify known castings into multiple categories, with labels set as the serial number of the casting category. Unsupervised learning can set the labels as the input itself. During the model training process, the initial casting prediction model is trained with the selected sample three-dimensional casting models until the loss function reaches a minimum value. After training, the casting prediction model is obtained. In actual implementation, a number of existing typical three-dimensional casting models can be selected as sample three-dimensional casting models. A three-dimensional array with side lengths b in all three directions is set. The shape of the three-dimensional casting model is discretized into a grid pattern in the three-dimensional space corresponding to the three-dimensional array and scaled so that the three-dimensional casting model can be included in the three-dimensional array. The values ​​of the corresponding positions in the three-dimensional array corresponding to the three-dimensional space occupied by the shapes of different three-dimensional casting models are set to c, and the remaining positions are set to d. Positions c and d represent the casting and mold, respectively. An initial casting prediction model is trained using the sample three-dimensional casting models until the loss function reaches a minimum value. For example, when the loss function is the Mean Squared Error (MSE) loss function, the maximum threshold of the loss function can be set to q. After training, a casting prediction model is obtained. The value ranges of the aforementioned parameters can be as follows: a ranges from 10-100, b ranges from 16-256, k ranges from 1-4, m ranges from 2-10, n ranges from 1-5, q ranges from 0.1-0.0001, and p ranges from 2-10.

[0063] For example, 10 existing typical 3D casting models can be selected. These models are rotated to obtain three upward configurations in the x, y, and z directions, resulting in 30 3D casting models. These models are then replicated once to obtain data for 60 3D casting models. The 3D casting models are converted into 3D arrays with a side length of 128. The area outside the 3D casting model is set as the casting mold, with the casting portion and the casting portion taking values ​​of 9 and 1, respectively. An initial convolutional neural network model based on U-net is established, using three encoder and decoder structures, each including two convolution operations. Both the input and output are casting models, with a validation set ratio of 0.5, and the input data is normalized. This initial convolutional neural network model is trained using existing typical 3D casting models as sample 3D casting models. Training for 80 epochs yields a loss function value of 0.0733.

[0064] In an embodiment of the present invention, the at least two three-dimensional casting models to be processed are three-dimensional casting models of different shapes. When there are two three-dimensional casting models, the three-dimensional casting models may include casting model A and casting model B. Casting model A is specifically as follows: Figure 3 As shown, the casting model B is as follows Figure 4 As shown, the relative positions of casting model A and casting model B are as follows Figure 5 In actual implementation, the three-dimensional casting models can be three-dimensional casting models of blades and three-dimensional casting models of cylinders respectively.

[0065] Step 102: Input the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtain feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on sample three-dimensional casting models and feature prediction result labels corresponding to the sample three-dimensional casting models.

[0066] In an embodiment of the present invention, the at least two three-dimensional casting models are respectively input into a preset casting prediction model for feature extraction and analysis, and for any three-dimensional casting model (i.e., casting), feature maps at different network levels and different channels are obtained.

[0067] Step 103: Processing is performed based on the feature graphs of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; splicing and synthesizing processing is performed based on the casting feature sub-models corresponding to the at least two three-dimensional casting models respectively to obtain a new casting model.

[0068] In an embodiment of the present invention, when processing based on the feature graphs of different network levels to obtain the casting feature sub-models corresponding to the at least two three-dimensional casting models, the values ​​in the three-dimensional array corresponding to the feature graphs of different network levels can be filtered to obtain the target feature graphs of different network levels after the value filtering process, and connectivity detection can be performed based on the target feature graphs of different network levels after the filtering process to obtain models of a preset number of connected areas, and the models of the connected areas can be used as the casting feature sub-models. In addition, when splicing and synthesizing the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model, the size and position information of the casting feature sub-models corresponding to the at least two three-dimensional casting models can be obtained; based on the size and position information of the casting feature sub-models corresponding to the at least two three-dimensional casting models, the casting feature sub-models corresponding to the at least two three-dimensional casting models can be rotated, scaled and / or translated so that the casting feature sub-models corresponding to the at least two three-dimensional casting models can be spliced ​​and synthesized to obtain a new casting model. Figure 2 As shown, the casting feature sub-model may include a feature model Mk1 and a feature model Mk2.

[0069] Among them, the values ​​in the three-dimensional array corresponding to the feature maps of the different network levels are screened to obtain the target feature maps of the different network levels after the value screening process. The corresponding implementation process includes: screening the feature maps of the different network levels to obtain the feature maps after the screening process; screening the values ​​in the three-dimensional array corresponding to the feature maps after the screening process to obtain the target feature maps of the different network levels after the value screening process. Specifically, in the process of screening the feature maps of the different network levels to obtain the feature maps after the screening process, the specific screening method adopted is, for example: for the feature maps of different channels of a certain level, a series of values ​​{Pi} are obtained by performing global average pooling on each feature map, and these values ​​are normalized by the softmax function to represent the weights of different channels. For the feature maps of different levels, different series of values ​​are obtained by independent calculation, and the p feature maps with the highest values ​​are selected in each series.

[0070] It should be noted that, in the process of filtering the values ​​in the three-dimensional array corresponding to the feature graph after the filtering process to obtain the target feature graphs of different network levels after the value filtering process, a value threshold can be determined based on the quantitative characteristics of all values ​​in the three-dimensional array corresponding to the feature graph after the filtering process; based on the value threshold, the values ​​in the three-dimensional array corresponding to the feature graph after the filtering process are filtered to obtain the target feature graphs of different network levels after the value filtering process. In addition, the connectivity test is performed based on the target feature graphs of different network levels after the filtering process to obtain models of a preset number of connected areas. The corresponding implementation process includes: performing connectivity test based on the target feature graphs of different network levels after the filtering process to obtain connectivity test results of the target feature graphs of different network levels; sorting the connected areas in the connectivity test results in descending order according to the size of the connected areas to obtain a sorting result; obtaining models of the first N connected areas of a preset number from the sorting result; wherein N is a positive integer greater than or equal to 2.

[0071] In determining the threshold based on the quantitative characteristics of all values ​​in the three-dimensional array corresponding to the filtered feature graph, the values ​​at different positions in the three-dimensional array of each feature graph can be arranged from smallest to largest, and the value with the most digits in the corresponding position in the array can be found. This value is set as the threshold value W1. By detecting the number of digits above and below the threshold in the casting portion of the array, the side with the most digits is selected and retained. Subsequently, the positions of the first n values ​​with the largest mutations in this sequence are found, or the values ​​of the first n positions in the array other than W1 are found. For example, the differences x1 and x2 between the digit at a certain position and the values ​​corresponding to the digits to the left and right can be compared, and the first n values ​​with the largest absolute value of the other value when one of the two is zero can be found. Any one of the n values ​​is used as the threshold value W2, and the side with the most digits is selected and retained. Then, a connectivity check is performed. If multiple connected regions exist, the models of the first N largest connected regions are retained. The models of these connected regions are the casting feature submodels of the three-dimensional casting model, namely, the {Mki} models. Furthermore, multiple casting MKi models of different shapes (i.e., casting feature submodels of the 3D casting model) are selected as submodels for synthesizing a new casting model. An algorithm ensures that these submodels are in contact with each other. For example, the coordinates (a1, a2, a3) and (b1, b2, b3) of the center points of two casting feature submodels A and B are found. The coordinates of casting feature submodel B are then translated by (a1-b1, a2-b2, 2a3) units. Casting feature submodel B is then moved up and down so that it contacts and is directly above casting feature submodel A. Finally, the submodels are assembled to form a new casting model. The threshold is set so that the local or overall features of the model are clearly visible.

[0072] In a complete embodiment of the present invention, the three-dimensional casting model of the blade and the three-dimensional casting model of the cylinder can be input into the casting prediction model for feature extraction and analysis, and the feature graphs of different network levels during prediction are output. The feature graphs of different network levels are screened. Figure 7 The feature map of the 3rd convolutional layer channel 5 of casting A (i.e., one of the 3D casting models) is shown in Figure 8 The feature map of channel 2 of the 8th convolutional layer of casting A is shown in Figure 9 The feature map of channel 15 of the 8th convolutional layer of casting A is shown in Figure 10 The figure shows the casting feature submodel for channel 2 of the 8th convolutional layer of casting A. The values ​​at different positions in the three-dimensional array of each feature map are arranged from small to large. The value with the most digits in the corresponding three-dimensional array is found and set as the threshold. The values ​​above the threshold are retained, and the same filtering method is repeated several times. For example, the final threshold for channel 2 of the 8th convolutional layer is 0.3291. Connectivity testing is then performed. If multiple connected regions exist, the models of the largest connected regions are retained. The resulting models of these connected regions are the casting feature submodels of the 3D casting model. A visualization of the feature submodel for channel 2 of the 8th convolutional layer is shown. Select two casting feature sub-models of different shapes as the sub-models of the new casting model. Find the coordinates of the center points of the two casting feature sub-models A and B (7, 7, 4), (3, 3, 7). Translate all the coordinates of the casting feature sub-model B by (4, 4, 8) units. Move the casting feature sub-model B up and down so that it contacts the casting feature sub-model A and is directly above A. Finally, splice them together to form a new casting model. Figure 4 As shown, it is based on the splicing and synthesis processing of the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model, and the new casting model can be as follows Figure 6 shown.

[0073] Embodiments of the present invention provide a method, apparatus, medium, and device for casting heat transfer simulation based on deep learning, comprising the steps of: selecting a typical three-dimensional casting model and converting it into a three-dimensional array; establishing a convolutional neural network (i.e., an initial convolutional neural network model); training the convolutional neural network using the typical three-dimensional casting model; inputting at least two three-dimensional casting models to be processed to obtain feature graphs at different network levels; screening the feature graphs in terms of network level, channel, value, and connectivity to obtain a core feature model (i.e., a casting feature sub-model); processing the casting feature sub-models and combining them to form a new casting model. This method can efficiently and quickly generate casting models. The present invention is applicable to feature extraction of existing three-dimensional casting models, can refine the basic features of the three-dimensional casting model, and reconstruct and synthesize new casting models based on these basic features, thereby enabling the generation of a large number of new casting models. This solves the problem of constructing a large number of training sets required for artificial intelligence-based simulation and can automatically generate a large number of three-dimensional casting models to meet the needs of deep learning training sets.

[0074] In summary, the processing method of the synthetic casting model provided by the present invention obtains at least two three-dimensional casting models to be processed, inputs the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, obtains feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models, processes based on the feature maps of different network levels, obtains casting feature sub-models corresponding to the at least two three-dimensional casting models, and performs splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to quickly obtain a new casting model, which can effectively improve the efficiency of synthesizing the casting model, thereby reducing the workload of synthesizing the casting model.

[0075] The following describes the processing device of the synthetic casting model provided by the present invention. The processing device of the synthetic casting model described below and the processing method of the synthetic casting model described above can be referred to each other. Figure 11 , which is a schematic diagram of the structure of the processing device for the synthetic casting model provided by the present invention. The processing device for the synthetic casting model of the present invention specifically includes the following parts:

[0076] The casting model obtaining unit 1101 is used to obtain at least two three-dimensional casting models to be processed.

[0077] The casting model feature extraction unit 1102 is used to input the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtain feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on sample three-dimensional casting models and feature prediction result labels corresponding to the sample three-dimensional casting models.

[0078] The casting model processing unit 1103 is used to perform processing based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; and to perform splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models respectively to obtain a new casting model.

[0079] According to a processing device for a synthetic casting model provided by the present invention, the casting model processing unit is specifically used for:

[0080] Screening the values ​​in the three-dimensional array corresponding to the feature maps of the different network levels to obtain target feature maps of the different network levels after the value screening process;

[0081] Connectivity detection is performed based on the target feature graphs of different network levels after the screening process to obtain models of a preset number of connected areas, and the models of the connected areas are used as the casting feature sub-models.

[0082] According to a processing device for a synthetic casting model provided by the present invention, the filtering process of the values ​​in the three-dimensional array corresponding to the feature maps of different network levels to obtain the target feature maps of different network levels after the value filtering process specifically includes:

[0083] Performing screening processing on the feature maps of the different network layers to obtain screened feature maps;

[0084] The values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

[0085] According to a processing device for a synthetic casting model provided by the present invention, the connectivity detection is performed based on the target feature graphs of different network layers after the screening process to obtain a model of a preset number of connected areas, specifically comprising:

[0086] Performing connectivity detection based on the target feature graphs of different network levels after the screening process to obtain connectivity detection results of the target feature graphs of different network levels;

[0087] According to the sizes of the connected areas in the connectivity detection results, the connected areas are sorted in descending order to obtain a sorting result; models of a preset number of first N connected areas are obtained from the sorting results; wherein N is a positive integer greater than or equal to 2.

[0088] According to a processing device for a synthetic casting model provided by the present invention, the filtering process is performed on the values ​​in the three-dimensional array corresponding to the feature graph after the filtering process to obtain target feature graphs of different network levels after the value filtering process, specifically comprising:

[0089] According to the quantitative characteristics of all values ​​in the three-dimensional array corresponding to the feature map after the screening process, a value threshold is determined; based on the value threshold, the values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

[0090] According to a processing device for a synthetic casting model provided by the present invention, the casting model processing unit is specifically used for:

[0091] Acquire size and position information of casting feature sub-models corresponding to the at least two three-dimensional casting models respectively;

[0092] Based on the size and position information of the casting feature sub-models corresponding to the at least two three-dimensional casting models, the casting feature sub-models corresponding to the at least two three-dimensional casting models are rotated, scaled and / or translated respectively, so that the casting feature sub-models corresponding to the at least two three-dimensional casting models are spliced ​​and synthesized to obtain a new casting model.

[0093] The processing device for synthesized casting models provided by the present invention obtains at least two three-dimensional casting models to be processed, inputs the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, obtains feature graphs of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models, performs processing based on the feature graphs of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models, and performs splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to quickly obtain a new casting model. The device can effectively improve the efficiency of synthesizing casting models, thereby reducing the workload of synthesizing casting models.

[0094] Figure 12 An example of a physical structure diagram of an electronic device is shown below. Figure 12As shown, the electronic device (i.e., the power grid real-time monitoring system or the power grid real-time monitoring device) may include: a processor (processor) 1201, a communication interface (Communications Interface) 1204, a memory (memory) 1202 and a communication bus 1203, wherein the processor 1201, the communication interface 1204, and the memory 1202 communicate with each other through the communication bus 1203. The processor 1201 can call the logic instructions in the memory 1202 to execute a processing method for a synthetic casting model, which includes: obtaining at least two three-dimensional casting models to be processed; inputting the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtaining feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on a sample three-dimensional casting model and a feature prediction result label corresponding to the sample three-dimensional casting model; processing is performed based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models; and splicing and synthesis processing is performed based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model.

[0095] In addition, the logical instructions in the above-mentioned memory 1202 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program code.

[0096] On the other hand, the present application also provides a computer program product, which includes a computer program, which can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the processing method of the synthetic casting model provided by the above-mentioned methods, the method including: obtaining at least two three-dimensional casting models to be processed; inputting the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtaining feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on a sample three-dimensional casting model and the feature prediction result label corresponding to the sample three-dimensional casting model; processing is performed based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models; splicing and synthesis processing is performed based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model.

[0097] On the other hand, the present application also provides a computer-readable storage medium, which includes a stored program, wherein when the program is run, the processing method of the synthetic casting model provided by the above-mentioned methods is executed, and the method includes: obtaining at least two three-dimensional casting models to be processed; inputting the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtaining feature maps of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on a sample three-dimensional casting model and the feature prediction result label corresponding to the sample three-dimensional casting model; processing is performed based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models; and splicing and synthesis processing is performed based on the casting feature sub-models corresponding to the at least two three-dimensional casting models to obtain a new casting model.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0099] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing a synthetic casting model, characterized in that: include: obtaining at least two three-dimensional casting models to be processed; Inputting the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, thereby obtaining feature maps of different network levels output by the casting prediction model and corresponding to the at least two three-dimensional casting models, respectively; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on sample three-dimensional casting models and feature prediction result labels corresponding to the sample three-dimensional casting models; Based on the feature maps of different network levels, processing is performed to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; based on the casting feature sub-models corresponding to the at least two three-dimensional casting models, splicing and synthesis processing is performed to obtain a new casting model.

2. The method for processing a synthetic casting pattern according to claim 1, wherein: The processing based on the feature graphs of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models specifically includes: Screening the values ​​in the three-dimensional array corresponding to the feature maps of the different network levels to obtain target feature maps of the different network levels after the value screening process; Connectivity detection is performed based on the target feature graphs of different network levels after the screening process to obtain models of a preset number of connected areas, and the models of the connected areas are used as the casting feature sub-models.

3. The method for processing a synthetic casting pattern according to claim 2, wherein: The filtering process of the values ​​in the three-dimensional array corresponding to the feature maps of the different network levels to obtain the target feature maps of the different network levels after the value filtering process specifically includes: Performing screening processing on the feature maps of the different network layers to obtain screened feature maps; The values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network layers after the value screening process.

4. The method for processing a synthetic casting pattern according to claim 2, wherein: The connectivity detection is performed based on the target feature graphs of different network layers after the screening process to obtain a model of a preset number of connected areas, specifically including: Performing connectivity detection based on the target feature graphs of different network levels after the screening process to obtain connectivity detection results of the target feature graphs of different network levels; According to the sizes of the connected areas in the connectivity detection results, the connected areas are sorted in descending order to obtain a sorting result; models of a preset number of first N connected areas are obtained from the sorting results; wherein N is a positive integer greater than or equal to 2.

5. The method for processing a synthetic casting pattern according to claim 3, wherein: The filtering process is performed on the values ​​in the three-dimensional array corresponding to the feature map after the filtering process to obtain target feature maps of different network layers after the value filtering process, specifically comprising: According to the quantitative characteristics of all values ​​in the three-dimensional array corresponding to the feature map after the screening process, a value threshold is determined; based on the value threshold, the values ​​in the three-dimensional array corresponding to the feature map after the screening process are screened to obtain target feature maps of different network levels after the value screening process.

6. The method for processing a synthetic casting pattern according to claim 1, wherein: The step of performing a splicing and synthesis process based on the casting feature sub-models respectively corresponding to the at least two three-dimensional casting models to obtain a new casting model specifically includes: Acquire size and position information of casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; Based on the size and position information of the casting feature sub-models corresponding to the at least two three-dimensional casting models, the casting feature sub-models corresponding to the at least two three-dimensional casting models are rotated, scaled and / or translated respectively, so that the casting feature sub-models corresponding to the at least two three-dimensional casting models are spliced ​​and synthesized to obtain a new casting model.

7. A processing device for a synthetic casting pattern, characterized in that: include: A casting model obtaining unit, configured to obtain at least two three-dimensional casting models to be processed; a casting model feature extraction unit, configured to input the at least two three-dimensional casting models into a preset casting prediction model for feature extraction and analysis, and obtain feature graphs of different network levels output by the casting prediction model corresponding to the at least two three-dimensional casting models; wherein the casting prediction model is a convolutional neural network model obtained by iterative training based on sample three-dimensional casting models and feature prediction result labels corresponding to the sample three-dimensional casting models; The casting model processing unit is used to perform processing based on the feature maps of different network levels to obtain casting feature sub-models corresponding to the at least two three-dimensional casting models respectively; and to perform splicing and synthesis processing based on the casting feature sub-models corresponding to the at least two three-dimensional casting models respectively to obtain a new casting model.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method for processing a synthetic casting model according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing a synthetic casting model according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for processing a synthetic casting model according to any one of claims 1 to 6 is implemented.

Images