Determination of the acceleration factor in groundwater simulation process through BP algorithm

doi:10.7523/j.issn.2095-6134.2011.1.008

Abstract

Abstract:

In applying the successive over-relaxation iteration method to solve large-scale linear equations,one often has difficulties in determining the acceleration factor.Through training and learning using BP neural network and comparative analyses, we obtained a good model,which could be used for fast determination of the acceleration factor.We used it in the Luancheng hydrology experimental base in Shijiazhuang,and the results show that BP artificial neural network has been successfully used in solving the difficult problem, determination of the acceleration factor in the groundwater numerical simulation process.

Key words: groundwater numerical simulation, acceleration factor, successive over-relaxation iteration method, neural network

CLC Number:

P641

MA Rong, LIU Ji-Chao, SHI Jian-Sheng, WANG Hu. Determination of the acceleration factor in groundwater simulation process through BP algorithm[J]. , 2011, 28(1): 51-56.

References

[1] 薛禹群,谢春红.地下水数值模拟
[M].北京:科学出版社,2007.

[2] 戈卢布 G H,范洛恩 C F.矩阵计算
[M].袁亚湘译.北京:科学出版社,2001.

[3] Zeng M L.Weighting-relaxation Relative Method
[J].Journal of Putian University,2008,15(2):30-33(in Chinese). 曾闵丽.加权-对称超松弛迭代法
[J].莆田学院学报,2008,15(2):30-33.

[4] Maleknejad K,Safdari H.Parallel algorithm for solving linear systems arising from PDE and integral equation
[J].Applied Mathematics and Computation,2004,15(2):443- 453.

[5] Wang S R.Successive over relaxation iteration method to find the solution of sparsity linear equation system
[J].Journal of Shenyang Normal University: Natural Science,2006,24(4):408- 410(in Chinese). 王诗然.稀疏线性方程组求解的逐次超松弛迭代法
[J].沈阳师范大学学报:自然科学版,2006,24(4):408- 410.

[6] 马东升.数值计算方法
[M].北京:机械工业出版社,2002.

[7] Hu F,Yu F X.The selection method of the Relaxation factor ω in successive over-relaxation Iteration algorithm
[J]. Journal of Qinghai Normal University: Natural Science, 2006(1):43- 46(in Chinese). 胡枫,于福溪.超松弛迭代法中松弛因子的选取方法
[J].青海师范大学学报:自然科学版,2006(1):43- 46.

[8] 焦李成.神经网络系统理论
[M].西安:西安电子科技大学出版社,1990.

[9] Anurag More,Deo M C.Forecasting wind with neural network
[J].Marine Structure,2003(16):35- 49.

[10] 董长虹.神经网络与应用
[M].北京:国防工业出版社,2005.

[11] Chi Z F,Yan Z Z,Huang B.Water quality evaluation model based on genetic algorithm and BP algorithm
[J].Journal of Chongqing University of Science and Technology: Natural Sciences Edition,2009,11(1):122-124(in Chinese). 蚩志锋,闫珍珠,黄彪.基于遗传算法与BP算法的水质评价模型
[J].重庆科技学院学报:自然科学版,2009,11(1):122-124.

[12] Neuman S P,Witherspoon P A.Applicability of current theories of flow in leaky aquifers
[J].Water Resource. Research,1969,5:817- 829.

[13] 孙讷正.地下水流的数学模型和数值方法
[M].北京:地质出版社,1981.

[14] Wu Q,Chen P P,Dong D L, et al.Hazard assessment system for ground fissure based on coupling of ANN and GIS: a case study of ground fissures in Yuci City, Shanxi Province
[J].Seismology and Geology,2002,24(2):249-257(in Chinese). 武强,陈珮珮,董东林,等.基于GIS与ANN耦合技术的地裂缝灾情非线性模拟预测系统:以山西榆次地裂缝灾害为例
[J].地震地质,2002,24(2):249-257.

[15] Wang H X,Wu M F.An accelerated overrelaxation iterative linear system with strictly diagonally dominant matrix
[J].Journal of WuYi University: Natural Science Edition,2004,18(2):23-26(in Chinese). 汪宏喜,吴明芬.具有严格对角占优矩阵的线性系统的加速超松弛迭代法
[J].五邑大学学报:自然科学版,2004,18(2):23-26.

[16] Lin Y K,Cai G Q.Probabilistic structural dynamics:advanced theory and applications
[M].1995.

[17] Woj Tkicwice S F,Bergmanla.High fidelity numerical solutions of the Fokker-Planck equation //Shiraishi,Shinozuki and Wen.Structural Safety and Reliability,1998:933-940.

[18] Xue Y Q.Present situation and prospect of groundwater numerical simulation in China
[J].Geological Journal of China Universities,2010,16(1):1-6(in Chinese). 薛禹群.中国地下水数值模拟的现状与展望
[J].高校地质学报,2010,16(1):1-6.