Abstract：With the rapid development of computer graphics, industrial design, natural science and other fields, the demand for high-quality scientific computing methods is increased. These scientific computing methods are inseparable from high-quality grid generation algorithms. For the commonly used orthogonal grid generation algorithms, whether they can reduce the computational amount and whether the manual intervention can be reduced are still the main challenges faced by them. Aiming at these challenges, for the single-connected target region, an automatic generation algorithm of orthogonal grid was proposed based on Long Short-Term Memory network (LSTM), one of the recurrent neural networks and Schwarz-Christoffel conformal mapping (SC mapping). Firstly, the basic conditions of the Gridgen-c tool based on SC mapping were used to transform the grid generation problem into an integer programming problem with linear constraints. Next, a classifier, which is capable of calculating the probability of the corner type of each vertex of the target polygonal region, was obtained by using the pre-processed GADM dataset and LSTM training. This classifier was able to greatly reduce the time complexity of integer programming problem, making the problem be solved quickly and automatically. Finally, the simple graphics areas, animated graphics areas and geographical boundary areas were taken as examples to conduct a grid generation experiment. Results show that for simple graphic areas, the proposed algorithm can reach the optimal solution on all examples. For animated graphic areas and geographical boundary areas with complex boundaries, the example grid results show that the proposed algorithm can make the calculation amount in these target areas reduced by 88.42% and 91.16% respectively, and can automatically generate better orthogonal grid.
[1] ERICKSON B A,DUNHAM E M,KHOSRAVIFAR A. A finite difference method for off-fault plasticity throughout the earthquake cycle[J]. Journal of the Mechanics and Physics of Solids,2017, 109:50-77. [2] LI J,LIU F,FENG L,et al. A novel finite volume method for the Riesz space distributed-order diffusion equation[J]. Computers and Mathematics with Applications,2017,74(4):772-783. [3] MU L,WANG X,YE X. A weak Galerkin finite element method for the Stokes equations[J]. Advances in Computational Mathematics,2016,42(1):155-174. [4] OWIPS. Grid clipart map grid[EB/OL].[2019-12-04]. https://owips.com/grid-clipart/grid-clipart-map-grid. [5] MathWorks. mesh[EB/OL].[2019-12-04]. https://www.mathworks.com/help/matlab/ref/mesh.html. [6] Wikipedia. Surface triangulation[EB/OL].[2019-12-04]. https://en.wikipedia.org/wiki/Surface_triangulation. [7] BOISSONNAT J D,DYER R,GHOSH A. Delaunay triangulation of manifolds[J]. Foundations of Computational Mathematics, 2018,18(2):399-431. [8] MISTANI P,GUITTET A,BOCHKOV D,et al. The island dynamics model on parallel quadtree grids[J]. Journal of Computational Physics,2018,361:150-166. [9] FERGUSON B G,CRISWICK L G,LO K W. Locating far-field impulsive sound sources in air by triangulation[J]. The Journal of the Acoustical Society of America,2002,111(1):104-116. [10] LIU G,JIANG S,ZHAO W,et al. Modular reluctance network simulation of a linear permanent-magnet vernier machine using new mesh generation methods[J]. IEEE Transactions on Industrial Electronics,2017,64(7):5323-5332. [11] 胡恩球, 张新访, 向文, 等. 有限元网格生成方法发展综述[J]. 计算机辅助设计与图形学学报,1997,9(4):378-383.(HU E Q,ZHANG X F,XIANG W,et al. A review of mesh generation methods for finite element computation[J]. Journal of ComputerAided Design and Computer Graphics,1997,9(4):378-383.) [12] 郭晓霞, 刘建生. 一种有限元网格自动生成方法[J]. 太原重型机械学院学报,2000,21(1):1-5.(GUO X X,LIU J S. An automatic mesh generator for finite element simulation[J]. Journal of Taiyuan Heavy Machinery Institute,2000,21(1):1-5. [13] 宋策, 刘玉玲. 近似正交的曲线网格生成技术研究[J]. 水资源与水工程学报,2012,23(3):68-70. (SONG C,LIU Y L. Research on generation technique of orthogonal curvilinear grid[J]. Journal of Water Resources and Water Engineering,2012,23(3):68-70.) [14] HANSON J,YANG Y,PALIWAL K,et al. Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks[J]. Bioinformatics, 2017, 33(5):685-692. [15] RAMAKRISHNAN K,ZARKO D,HANIC A,et al. Improved method for field analysis of surface permanent magnet machines using Schwarz-Christoffel transformation[J]. IET Electric Power Applications,2017,11(6):1067-1075. [16] MARTA-ALMEIDA M,LESSA G C,AGUIAR A L,et al. Realistic modelling of shelf-estuary regions[J]. Ocean Dynamics,2019, 69(11/12):1311-1331. [17] YANG C,YANG X,XIAO X. Data-driven projection method in fluid simulation[J]. Computer Animation and Virtual Worlds, 2016,27(3/4):415-424. [18] TIM N,ZORITA E,HÜNICKE B. Decadal variability and trends of the Benguela upwelling system as simulated in a high-resolution ocean simulation[J]. Ocean Science,2015,11(3):483-502. [19] 刘明明, 崔春风, 童小娇, 等. 混合整数非线性规划的算法软件及最新进展[J]. 中国科学:数学,2016,46(1):1-20.(LIU M M,CUI C F,TONG X J,et al. Algorithms,softwares and recent developments of mixed integer nonlinear programming[J]. SCIENTIA SINICA Mathematica,2016,46(1):1-20.) [20] GADM. GADM maps and data[EB/OL].[2019-12-04]. https://www.gadm.org/. [21] DENG J,DONG W,SOCHER R,et al. ImageNet:a large-scale hierarchical image database[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2009:248-255. [22] LIN T Y,MAIRE M,BELONGIE S,et al. Microsoft COCO:common objects in context[C]//Proceedings of the 2014 European Conference on Computer Vision,LNCS 8693. Cham:Springer, 2014:740-755. [23] HUANG G,SUN Y,LIU Z,et al. Deep networks with stochastic depth[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9908. Cham:Springer,2016:646-661. [24] XU S,WANG B,LIU J. On the use of Schwarz-Christoffel conformal mappings to the grid generation for global ocean models[J]. Geoscientific Model Development,2015,8:3471-3485. [25] SAKOV P. Gridgen-c[EB/OL].[2019-12-04]. https://github.com/sakov/gridgen-c. [26] HETLAND R. Pygridgen[EB/OL].[2019-12-04]. https://github.com/hetland/pygridgen. [27] Sea-mat. Seagrid[EB/OL].[2019-12-04]. https://github.com/sea-mat/seagrid. [28] DRISCOLL T A. Schwarz-Christoffel toolbox user's guide[EB/OL].[2019-12-04]. https://http://www.math.udel.edu/~driscoll/SC/guide.pdf. [29] LARRYYIN. Retanguler[EB/OL].[2019-12-04]. https://github.com/larryyin/rectangular. [30] DELTARES. Delftares[EB/OL].[2019-12-04]. https://oss.deltares.nl. [31] LIU X,MA J,XU S,et al. On the generation of coastline-following grids for ocean models-trade-off between orthogonality and alignment to coastlines[J]. Ocean Dynamics,2017,67(8):1095-1104.
2020, Vol. 40 
