刘翠芝;吴桐;杨恒赞;

• 1:东北大学资源与土木工程学院
• 2:南洋理工大学电机与电子工程学院

摘要(Abstract)：

针对非线性趋势模型参数求解问题,该文提出一种全新通用算法:外点最速下降算法。该算法依据约束最优化方法理论,使用外点法和最速下降法,将参数求解问题转化为有约束非线性规划问题。以沉降预测为例,通过对3种典型非线性趋势模型的试算,说明使用该算法所得参数建立模型预测精度普遍较高;同时选用预测平均绝对误差作为衡量精度指标,在此算法下,能在事先计算出此数值,从而可大致估计预测精度;之后分情况给出获得精度较高参数的公式,并通过分析,进一步优化选点方法。

关键词(KeyWords)： 非线性趋势模型;参数求解;约束最优化问题;沉降预测;精度控制

Abstract:

Keywords:

基金项目(Foundation):

作者(Authors): 刘翠芝;吴桐;杨恒赞;

DOI: 10.16251/j.cnki.1009-2307.2019.01.004

参考文献(References)：

• [1]BOX M J.The occurrence of replications in optimal designs of experiments to estimate parameters in nonlinear models[J].Journal of the Royal Statistical Society,1968,30(2):290-302.
• [2]BEALE E M L.Confidence regions in nonlinear estimation[J].Journal of the Royal Statistical Society,1960,22(1):41-88.
• [3]BATES D M,WATTS D G.Nonlinear regression analysis and its applications[J].Technometrics,1988,32(2):219-220.
• [4]BATES D M,WATTS D G.Relative curvature measures of non-linearity[J].Journal of the Royal Statistical Society,1980,42(1):1-25.
• [5]XU P L.Testing the hypotheses of non-estimable functions in free net adjustment models[J].Manuscripta Geodaetica,1995,20:73-81.
• [6]TEUNISSEN P J G.KNICKMEYER E H.Non-liner and least-squares[J].CISM Journal ACSGC,1988,42(4):321-330.
• [7]TEUNISSEN P J G.Non-liner least squares[J].Manuscripta Geodaetica,1990,1(5):137-150.
• [8]TEUNISSEN P J G.First and second moment of nonlinear least squares estimators[J].Bulletin Géodésique,191089,63(3):253-262.
• [9]TEUNISSEN P J G.The nonlinear 2D symmetric Helmert transformation:anexact nonlinear least squares solution[J].Bulletin Géodésique,1988,62(1):1-16.
• [10]BLAHA G.Non-iterative approach to nonlinear leastsquares adjustment[J].Manuscripta Geodaetica,1994,19:199-212.
• [11]DERMANIS A,SANSO F.Nonlinear estimation problems for nonlinear models[J].Manuscripta Geodaetica,1995,20(2):110-122
• [12]王新洲.非线性模型参数估计的直接解法[J].武汉大学学报(信息科学版),1999,24(1):64-67.(WANGXinzhou.A direct solution method of parameter estimation of nonlinear model[J].Geomatics and Information Science of Wuhan University,1999,24(1):64-67.
• [13]陶本藻.关于测量中非线性模型的估计问题[J].测绘通报,1998(2):6-8.(TAO Benzao.The estimation of nonlinear models in measurement[J].Bulletin of Surveying and Mapping,1998(2):6-8.)
• [14]韦博成.近代非线性回归分析[M].南京:东南大学出版社,1989.(WEI Bocheng.Modern nonlinear regression analysis[M].Nanjing:Southeast University Press,1989.)
• [15]李朝奎,黄力民,曾卓乔,等.基于Monte-Carlo方法的强非线性函数的方差估计[J].中国有色金属学报,2000,10(4):613-617.(LI Chaokui,HUANG Limin,ZENG Zhuoqiao et al.Variance estimation of intensive nonlinear functions based on Monte-Carlo method[J].The Chinese Journal of Nonferrous Metals,2000,10(4):613-617.)
• [16]刘大杰,黄加纳.非线性最小二乘平差的迭代算法[J].武测科技,1987(4):25-31.(LIU Dajie,HUANG Jiana.An iterative algorithm for nonlinear least squares adjustment[J].Geomatics and Information Science of Wuhan University,1987(4):25-31.)
• [17]陶华学,李桂苓.现代变形监测布网方案的非线性多目标优化算法[J].山东矿业学院学报(自然科学版),1999,18(1):1-3.(TAO Huaxue,LI Guiling.Optionization for the layout alternatives of deformation monitoring net[J]Journal of Shandong Mining Institute of Mining Technology(Natural Science),1999,18(1):1-3.)
• [18]白亿同.非线性最小二乘平差迭代解法的收敛性[J].武汉测绘科技大学学报,1991,16(2):92-95.(BAIYitong.Convergence of iterative solution for nonlinear least squares adjustment[J].Journal of Wuhan Technical University of Surveying and Mapping,1991,16(2):92-95.)
• [19]白亿同.从黎曼流形的观点看非线性最小二乘平差[J].武汉测绘科技大学学报,1991,16(4):78-84.(BAIYitong.Nonlinear least squares adjustment from the viewpoint of Riemann manifold[J].Journal of Wuhan Technical University of Surveying and Mapping,1991,16(4):78-84.)
• [20]李朝奎,黄力民,黄建柏.基于非线性误差模型的参数估计[J].测绘工程,2000,9(3):19-22.(LI Chaokui,HUANG Limin,HUANG Jianbai.Parameters estimation based on nonlinear error models[J].Engineering of Surveying and Mapping,2000,9(3):19-22.)
• [21]李朝奎.非线性模型空间测量数据处理理论及其应用[M].北京:化学工业出版社,2013.(LI Chaokui.Theory and application of data processing in space of nonlinear models[M].Beijing:Chemical Industry Press,2013.)
• [22]张俊,独知行,杜宁,等非线性模型的补偿最小二乘估计[J].大地测量与地球动力学,2015,35(1):122-125.(ZHANG Jun,DU Zhixing,DU Ning,et al.Penalized least square estimator for non-linear models[J].Journal of Geodesy and Geodynamics,2005,35(1):122-125.)
• [23]薛嘉庆.最优化原理与方法[M].沈阳:东北大学出版社,2004.(XUE Jiaqing.Theory and method of optimization[M].Shenyang:Northeast University Press,2004.)
• [24]赵睿,王江荣,袁维红,等.基于指数函数的非线性模型在路基沉降预测分析中的应用[J].工程质量,2016,34(4):89-91.(ZHAO Rui,WANG Jiangrong,Yuan Weihong,et al.The application of nonlinear model based on exponential function to the prediction and analysis of subgrade settlement[J].Construction Quality,2016,34(4):89-91.)
• [25]熊春宝,李法超.指数曲线模型预测基坑周边地面沉降[J].测绘与空间地理信息,2011,34(4):4-6.(XIONGChunbao,LI Fachao.The exponential curve method model for predicting foundation settlement in the base pit vicinity[J].Geomatics&Spatial Information Technology,2011,34(4):4-6.)