摘要
针对传统建模主观性造成的精度影响以及预测数据的噪声干扰,提出了基于提升小波的系统优化GM(1,1)模型.该模型可有效剔除监测信息的噪声分量,减小预测误差,同时根据最小二乘原理提出了以GM(1,1)的一次累加生成建模序列所有分量的拟合误差平方和最小为约束条件,建立了优化GM(1,1)预测模型的最优初始值.对某大坝位移监测信息进行了计算,相对传统GM(1,1)模型而言,优化GM(1,1)模型可明显提高预测精度.
Considering the accuracy bias of subjective modeling and noise interfere, a systematical optimization model GM （1,1） is proposed in this paper. And such model could effectively delete the noisy part of monitoring data to decrease prediction error. At the same time, the constraint conditions of minimum fitting error sum of squares of each variable during once accumulation is raised to build and optimize a prediction model with optimal initial values based on the principle of Least Squares. Moreover, the new GM （1,1） model is established by improving the background value and gray value with consideration of systematical opti- mization. Finally, by comparing with classic GM （1,1） model in predicting the displacements, the new one gives relatively desired consequences through numerical calculation.
出处
《江西水利科技》
2013年第3期210-214,共5页
Jiangxi Hydraulic Science & Technology
关键词
提升小波
系统优化
GM（1
1）模型
大坝位移
Iifting wavelet
Systematical optimization
GM （1,1） model
Displacements of dam
