9 results about "Complex polygon" patented technology

The invention discloses a polygonal and quadrilateral mesh automatic subdivision method based on deep reinforcement learning, relates to the field of computational geometry and mesh generation, and constructs an automatic subdivision framework fusing geometric priori knowledge and a data driving strategy. According to the method, nine basic topology filling templates covering triangles to hexagons are predefined as discrete action spaces, and continuous geometric segmentation is converted into a sequence decision problem; learning a mapping relation between the polygon state characteristics and the optimal template selection strategy by using a deep Q network, and balancing exploration and utilization through a dynamic epsilon-greedy mechanism; and in combination with a vertex number priority scheduling strategy and a multi-dimensional quality award function, guiding an intelligent agent to adaptively generate a high-quality quadrilateral grid. According to the method, full-automatic and high-robustness subdivision of the complex polygon area is achieved, the grid orthogonality and the length-width ratio quality are remarkably improved, manual intervention is avoided, and the method is suitable for engineering scenes such as finite element analysis.

The application discloses a line-shaped slope map spot extraction method and system with a width less than or equal to 1 grid and a storage medium, and relates to the field of land resource management. Firstly, spot points are generated in a slope classification map to obtain all boundary node coordinate information of a polygon, all coordinate point combinations are calculated according to the coordinate information, all points are compared with existing nodes, then rectangular spots with a side length of two grid widths or more are found and marked in the spot area, the above process is repeated until all spots are traversed, finally, spots with qualified rectangles are removed, and the remaining spots are line-shaped slope map spots with a width less than or equal to 1 grid. The application does not need to rely on complex polygon geometry width calculation, avoids large errors and low efficiency problems of manual visual interpretation, provides a reliable basis for subsequent merging of spots according to the average allocation principle, guarantees the quality of slope classification map results, and supports the scientificity and accuracy of natural resource management decision-making.

The invention provides a geometric topology perception photoetching hot spot detection method based on graph contrast learning. For an input layout sample, a model predicts a category label of the input layout sample, specifically, firstly, hierarchical geometry-topology perception graph representation is constructed through a new multi-level graph representation construction and feature coding method, and multi-scale spatial dependence is captured to distinguish a hot spot mode and a non-hot spot mode; then, node embedding is optimized by adopting a graph contrast learning method, and feature separability is enhanced; and finally, introducing a graphical complex detection mechanism, and carrying out refined judgment on the predicted hot spots. Complex polygon units are modeled into graph nodes, the local geometric attributes and the global topology interaction relation are jointly coded, the structural integrity of the layout is kept, and the recognition capacity of the model for complex shapes and tiny differences is effectively improved.

The application discloses a kind of polygon quadrilateral grid automatic subdivision methods based on deep reinforcement learning, it is related to the field of computational geometry and grid generation, the application constructs a kind of automatic subdivision framework of fusion geometry priori knowledge and data-driven strategy.The method predefines 9 kinds of basic topological filling templates covering triangle to hexagon as discrete action space, converts continuous geometry segmentation into sequence decision problem;The mapping relationship between polygon state characteristics and optimal template selection strategy is learned using deep Q network, and exploration and utilization are balanced through dynamic epsilon-greedy mechanism;Combining vertex number priority scheduling strategy and multidimensional quality reward function, guide agent to adaptively generate high-quality quadrilateral grid.The application realizes the full-automatic, high robustness subdivision of complex polygon region, significantly improves the grid orthogonality and aspect ratio quality, avoids manual intervention, and is suitable for finite element analysis and other engineering scenarios.

The invention discloses a polygon interpolation-based antenna housing electrical performance interval analysis method, which comprises the following steps of: generating an antenna housing error parameter set, an actual angle combination and a sampling angle combination, and calculating a real polygon interval and a sampling polygon interval of a transmission coefficient; carrying out vertex resampling on the sampling polygon interval to obtain a resampling polygon interval with uniformly distributed vertexes; then, predicting an interpolation polygon interval of any point according to all the resampling polygon intervals by adopting a conformal interpolation method; respectively calculating far-field complex polygon intervals based on the real polygon interval and the interpolation polygon interval, and comparing the two electrical performance index change intervals; and iteratively adjusting the number of the resampled vertexes until the electrical performance index meets a preset requirement. According to the method, the change area of the transmission coefficient is accurately represented by the polygons, the predicted interpolation polygon interval is closer to reality through the shape-preserving interpolation method, and the accuracy and reliability of prediction of the electrical performance interval of the antenna housing are remarkably improved.

The invention provides a polygon labeling method and device based on contour feature recognition. The method comprises the steps of automatic acquisition of a user coordinate system, acquisition and preprocessing of contour data, generation of a peripheral main label and supplementary labeling of a local recess. The method comprises the following steps: acquiring contour vertex data of a complex polygon, determining a user coordinate system, generating a peripheral main label based on an axial bounding box, and judging and generating a local concave supplementary label through concave edge characteristics, so as to finally form a complete continuous size label chain which is reasonable in layout and conforms to engineering drawing specifications. Compared with traditional manual labeling and an existing labeling tool, the processing efficiency and the drawing quality are greatly improved.

The invention relates to a rectangular splitting method and system for a polygonal contour of a structural platform, and the method comprises the steps: obtaining a platform contour, and processing a bevel edge according to a main structure direction; generating a dense point set through vertex projection, and generating a large number of candidate rectangles; screening out rectangles which are completely located in the contour and have the compliant size by combining column grid size constraints (minimum and maximum column distances) input by structural design; and finally, finding out conformance rectangular combinations which can completely cover the original contour, are equal in area and are not overlapped by adopting an optimization search algorithm. According to the method, various feasible rectangular division schemes can be automatically and efficiently generated, and each scheme corresponds to a potential column grid and primary and secondary beam arrangement pattern to be selected by a designer, so that the design efficiency and quality of a structural platform are greatly improved. Complex polygons containing concave parts and holes can be processed, and the applicability is wide.

This invention discloses a method for generating arc additive manufacturing trajectories for complex mold cavities. The method involves layering and slicing the arc additive manufacturing target model to obtain polygonal data of the additive cavity cross-section; dividing the maximum envelope rectangle into m rows and n columns horizontally and vertically to obtain the background mesh of the maximum envelope rectangle; calculating the level set function value of the background mesh nodes using a signed distance function, where the level set function value is positive when the background mesh node is inside the cross-sectional polygon, and negative otherwise; and calculating the maximum value ψ of this function. max and in [0,ψ max The process involves dividing the material into equal parts with a spacing equal to the fill spacing L, resulting in a sequence of equal parts. Each element in this sequence is then traversed to obtain the corresponding horizontal set function contour line. This contour line represents the additive trajectory of the complex cross-section, offset by a certain distance. This invention avoids complex polygon operations such as polygon intersection, difference, and union, greatly simplifying the process of generating equidistant additive trajectories for complex cross-sectional contours and improving the efficiency of additive trajectory generation in arc additive manufacturing.

The invention provides an unmanned aerial vehicle flight path planning method and device, and the method comprises the steps: obtaining the boundary data of a target region, and constructing a target polygon based on the boundary data; based on a scanning line algorithm, scanning the target polygon, and based on the number of intersection points of scanning lines and the target polygon, generating segmentation lines; based on the segmentation lines, decomposing the target polygon into a plurality of convex polygons, and determining a communication sequence of the convex polygons; and based on the communication sequence, combining the plurality of convex polygons into a communication coverage area, and determining an inspection track of the target area in the communication coverage area. The method can automatically adapt to areas with complex geometric features such as multiple concave points and internal holes, realizes automatic conversion from irregular areas to ordered tracks, effectively solves the problems of insufficient coverage or serious overlapping of paths crossing boundaries in complex polygonal area coverage, and improves the coverage efficiency. And the routing inspection coverage rate of the unmanned aerial vehicle for routing inspection of a complex area is improved.