首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于粒子群优化的理论变异函数拟合方法研究
引用本文:马海,王延江,胡睿,魏茂安.基于粒子群优化的理论变异函数拟合方法研究[J].地球物理学进展,2009,24(3):1075-1080.
作者姓名:马海  王延江  胡睿  魏茂安
作者单位:1. 中国石油大学信息与控制工程学院,东营,257061
2. 中国石化胜利石油管理局钻井工艺研究院,东营,257017
基金项目:中国石油化工股份有限公司重点科技攻关项目 
摘    要:变异函数是地统计学中区域化变量空间结构分析和空间局部插值的主要分析工具.理论变异函数模型的获取是地质统计学中的基础性工作,它是了解区域化变量的变异特征、进一步对地质统计学计算的必要环节.针对现有的理论变异函数的拟合方法,如人工拟合法、线性规划拟合法、加权多项式拟合法、目标规划拟合法等的不足之处,充分利用粒子群优化算法在求解非线性优化问题时具有的全局寻优的特点,提出基于粒子群优化的理论变异函数拟合方法.在实例应用中,分别利用粒子群优化算法和加权多项式拟合方法进行理论变异函数拟合,交叉验证结果表明粒子群优化算法预测精度较高,具有较强的稳健性.

关 键 词:理论变异函数  粒子群优化  加权多项式拟舍  参数估计  稳健性
收稿时间:2008-10-12
修稿时间:2008-12-22

A novel method for matching theoretical variogram based on particle swarm optimization
MA Hai,WANG Yan-jiang,HU Rui,WEI Mao-an.A novel method for matching theoretical variogram based on particle swarm optimization[J].Progress in Geophysics,2009,24(3):1075-1080.
Authors:MA Hai  WANG Yan-jiang  HU Rui  WEI Mao-an
Institution:(1.CollegeofInformationandControlEngineering,ChinaUniversityofPetroleum,Dongying257061,China;2.DrillingTechnologyResearchInstitute,SinopecShengliPetroleumAdministrationBureau,Dongying257017,China)
Abstract:Variogram is the main analysis tool of regionalized variable spatial structure and spatial local interpolation in geostatistics. In particular, theoretical variogram model is essential in geostatistics, which is the key issue in investigating the variability of regionalized variable and further geostatistics computing. Concerning the disadvantages of conventional methods that match theoretical variogram such as man-made matching method, linear programming method, weighted polynomial matching and goal programming method, a novel method for matching theoretical variogram based on particle swarm optimization was presented allowing for the characteristic of global optimization of particle swarm optimization algorithm. The experimental results show that the proposed method has higher prediction precision and stronger robustness than weighted polynomial matching based approach.
Keywords:theoretical variogram  particle swarm optimization  weighted polynomial matching  parameter estimation  robustness
本文献已被 万方数据 等数据库收录!
点击此处可从《地球物理学进展》浏览原始摘要信息
点击此处可从《地球物理学进展》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号