强玲娟,常安定,陈玉雪
QIANG Lingjuan, CHANG Anding, CHEN Yuxue

• 1:长安大学理学院，陕西 西安 710064

摘要(Abstract)：

传统方法求解优化问题时，一般都是依据最小二乘原理来确定目标函数。鉴于这种方法没有考虑到原始测量数据的误差对计算结果及精度带来的影响。为此，提出机器学习算法改进传统的目标函数，同时结合双评价粒子群算法来求解水文地质参数。结果表明，该算法具有良好的收敛性和稳定性，求解效率高，简单易实现。
When solving optimization problem, the traditional method determines the objective function on the basis of the least squares principle without considering the influence of the error of the original measurement data on the results and the accuracy of calculation. Therefore machine learning algorithm is proposed in this paper to improve the general objective function and to solve the hydrogeological parameters in combination with particle swarm optimization of double evaluation. The result shows that machine learning algorithm has good convergence and stability as well as high solution efficiency, is simple and easy to realize.

关键词(KeyWords)： 机器学习;双评价粒子群;水文地质参数
machine learning;particle swarm of double evaluation;hydrogeological parameters

Abstract:

Keywords:

基金项目(Foundation): 陕西省科技计划项目（2015JM1022）

作者(Author): 强玲娟,常安定,陈玉雪
QIANG Lingjuan, CHANG Anding, CHEN Yuxue

DOI: 10.3969/j.issn.1001-1986.2017.03.016

参考文献(References)：

• [1] ZHAO Qian,MENG Deyu,LU Jiang,et al. Self-paced learning for matrix factorization[C]//Proceeding of the Twenty-Ninth AAAI Conference on Artifical Intelligence,USA,2015.
  [2] 何清,李宁. 大数据下的机器学习算法综述[J]. 模式识别与人工智能,2014,27(4):327-336. HE Qing,LI Ning. A survey of machine learning algorithms for big data[J]. Pattern Recognition and Artificial Intellgence,2014, 27(4):327-336.
  [3] JOENUX. 机器学习中的范数规则化[Z/OL].[2015-12-30]. http://blog.csdn.net/zouxy09.
  [4] 郭东屏. 地下水动力学[M]. 西安:陕西科学技术出版社, 1994:230-238.
  [5] 张娟娟,郭建青. 基于改进模拟退火算法反演水文地质参数[J]. 中国农村水利水电,2005(9):5-8. ZHANG Juanjuan, GUO Jianqing. Identification of hydrogeological parameters based on modified simulation annealing algorithm[J]. China Rural Water and Hydropower,2005(9):5-8.
  [6] 张媛媛,高兴宝. 双评价粒子群算法[J]. 陕西科技大学学报, 2012,30(1):93-96. ZHANG Yuanyuan,GAO Xingbao. Particle swarm optimization with double evaluation[J]. Journal of Shaanxi University of Science & Technology,2012,30(1):93-96.
  [7] 刘逸,寇卫东. 粒子群优化算法的改进与应用研究[D]. 西安:西安电子科技大学,2012.
  [8] 王菲,刘元会,郭建青. 双评价粒子群确定非线性流含水层参数[J]. 中国农村水利水电,2013(12):19-26. WANG Fei,LIU Yuanhui,GUO Jianqing. Determination of aquifer parameters in nonlinear flow by double evaluation of particle swarm optimization algorithm[J]. China Rural Water and Hydropower,2013(12):19-26.
  [9] 艾宁宁. 基于混合智能算法求解随机期望值模型和机会约束规划[D]. 西安:长安大学,2012.
  [10] 郭建青,郑力,雷玉平,等. 分析直线隔水边界附近抽水试验数据的新方法[J]. 工程勘察,2006(1):26-29. GUO Jianqing,ZHENG Li,LEI Yuping,et al. Linear regression method to identify aquifer parameters and the position of impervious boundary by using the data from pumping tests[J]. Geotechnical Investigation & Surveying,2006(1):26-29.
  [11] 郭建青,李彦. 粒子群优化算法在确定河流水质参数中的应用[J]. 水利水电科技进展,2007,27(6):1-5. GUO Jianqing,LI Yan. Application of particle swarm optimi zation algorithm in determination of the river water quality parameters[J]. Advances in Science and Technology of Water Resources,2007,27(6):1-5.
  [12] 张全兴,常安定. 利用差分进化算法反求含水层参数[J]. 煤田地质与勘探,2008,36(5):54-57. ZAHNG Quanxing,CAHNG Anding. Estimation of hydrogeological parameters using differential evolution algorithm[J]. Coal Geology & Exploration,2008,36(5):54-57.

文章评论(Comment)：