7 results about "Mesh generator" patented technology

The invention discloses a self-adaptive spatial transformation network for cross-medium optical distortion, and solves the problem that the existing spatial transformation network is difficult to consider both global transformation and local nonlinear optical distortion. The network is integrated in a target detection model, and the method comprises the steps that firstly, a parameter prediction network synchronously outputs affine transformation parameters and a water surface fluctuation physical parameter diagram; then, the local distortion grid generation network generates a distortion sampling grid based on the parameter diagram and a predefined water surface fluctuation physical model; meanwhile, the grid generator generates an affine sampling grid according to the affine transformation parameters; then, a grid fusion device fuses the two grids to generate a final sampling grid; and finally, the sampler samples the input image or the feature map according to the final sampling grid to obtain an output image or a feature map. Through a space transformation mechanism guided by physical prior, optical distortion caused by water surface fluctuation can be effectively relieved, and the accuracy and robustness of a target detection model in a cross-medium underwater scene are remarkably improved.

This invention discloses a neutron transport calculation system with decoupled geometric modeling and mesh generation, including a mesh generator and a CSG geometric modeling module. The module is fully embedded into the computational framework of the neutron transport procedure using the feature line method. First, a suitable type of mesh generator is selected based on the geometry of the underlying material cell. The internal structure of the mesh generator is completed by setting the meshing parameters. Subsequently, the mesh generator is set as an attribute of the material cell. The mesh generator's built-in positioning algorithm can quickly determine the fine mesh index of the ray segment endpoints; its intersection algorithm can accurately calculate the intersection distance between the ray and the fine mesh. Thus, all feature line segment information is generated. Finally, source iteration is performed until the convergence condition is met to obtain the key physical parameters. By using this invention, fine mesh generation can be achieved, which is helpful for subsequent reactor parameter acquisition. This invention can be widely applied in the field of nuclear reactor physics numerical calculation technology.

This invention provides a method and system for discretizing and reconstructing the microstructure mesh of continuous fiber composite materials, relating to the field of image processing technology. The method includes: acquiring slice images from multi-directional industrial CT scans; labeling the slice images; training an image segmentation model using a 2.5DU-Net architecture; inputting the target slice image into the trained model and outputting the image segmentation result; performing image post-processing on the image segmentation result; extracting the geometric parameters of the fiber bundles using Fourier transform and ellipse extraction algorithms, and grouping the fiber bundles into multiple unit cells; establishing a geometric model of the fiber bundle and matrix assembly using the lofting and Boolean operation functions of a geometric modeling library; meshing the geometric model of the fiber bundle and matrix assembly using the Gmsh mesh generator, generating a 3D finite element mesh file, and exporting it as an .inp format file; and obtaining the complete input file by setting a Set collection.

The invention discloses an aircraft part boundary line grid node distribution and anisotropy parameter prediction method, and relates to the field of automation and intellectualization of simulation pretreatment of computational fluid mechanics, and the method comprises the steps: determining geometric data, part semantic tags, calculation conditions and boundary lines of an aircraft CAD model; utilizing the trained multi-task graph neural network model to perform grid region type intelligent classification on the boundary line to obtain an isotropic or anisotropic classification result; then, according to a classification result, predicting a sub-network through differentiated parameters corresponding to the region types in the model, and predicting a grid control parameter set corresponding to each boundary line for each boundary line; and finally, driving a grid generator to automatically generate a high-quality surface grid based on the parameter set. According to the method, full-process intelligent decision making from semantic information to grid generation strategies and parameters is achieved, a traditional method depending on artificial experience is replaced, and the automation degree and efficiency of CFD pretreatment and the consistency of grid quality are remarkably improved.

An apparatus is provided. The apparatus includes a communications interface to receive raw data from an external source. The raw data includes a representation of an object. Furthermore, the apparatus includes a memory storage unit to store the raw data. The apparatus also includes a pre-processing engine to generate a coarse segmentation map and a joint heatmap from the raw data. The coarse segmentation map is to outline the object and the joint heatmap is to represent a point on the object. The apparatus further includes a neural network engine to receive the raw data, the coarse segmentation map, and the joint heatmap. The neural network engine is to generate a plurality of two-dimensional maps. Also, the apparatus includes a mesh creator engine to generate a three-dimensional mesh based on the plurality of two-dimensional maps.

The application discloses a method for predicting the distribution of grid nodes of boundary lines of aircraft components and anisotropy parameters, relates to the field of automation and intellectualization of pre-processing of computational fluid dynamics simulation, and determines the geometric data of an aircraft CAD model, component semantic labels, calculation working conditions and each boundary line. A trained multi-task graph neural network model is used to intelligently classify the grid region types of the boundary lines, and isotropic or anisotropic classification results are obtained. Then, according to the classification results, the corresponding differential parameter prediction sub-network in the model is used to predict the corresponding grid control parameter set for each boundary line. Finally, based on the parameter set, a grid generator is driven to automatically generate high-quality surface grids. The application realizes intelligent decision-making of the whole process from semantic information to grid generation strategy and parameters, replaces the traditional method relying on artificial experience, and significantly improves the automation degree, efficiency and grid quality consistency of CFD pre-processing.