基于粒子群与Markov优化的PMIGM(1,1)模型预测路基沉降方法研究
|
摘要
高速公路路基沉降的准确预测对高速公路病害预防和治理有着极其重要的指导意义。以往的路基沉降预测模型多为单一模型或简单改进模型,提出了一种基于粒子群与Markov优化的PMIGM(1,1)预测模型。首先,基于灰色理论,提出了改进的IGM(1,1)预测模型;然后,利用Markov理论对IGM(1,1)预测模型的相对残差序列进行修正,使得该模型能反映数据的波动特征,得到了MIGM(1,1)预测模型;在此基础上,采用粒子群算法对残差序列参数进行白化,建立了PMIGM(1,1)预测模型。将该预测模型应用于云南保施高速公路高填方路基,分析结果表明该模型可提高预测模型的精度。
Accurate prediction of subgrade settlement of expressways is of great significance to their disease prevention and treatment. The previous prediction models for the subgrade settlement are mostly single models or simple improved models. A PMIGM(1,1) prediction model based on the particle swarm optimization(PSO) and Markov optimization is proposed. Firstly,based on the grey theory, an improved GM(1,1) prediction model is put forward. Then, according to the theory knowledge of Markov chains, an MIGM(1, 1) model is built to correct the relative residuals of IGM(1, 1) model, which can reflect the volatility characteristics of the data. Based on the principle of PSO, an optimization of PMIGM(1, 1) model is set up, which crystallizes the parameters of grey interval. The forecasting model is applied to a high-fill subgrade of Baoshan-Shidian Expressway in Yunnan Province. The analysis results show that the proposed model can improve the accuracy of the forecasting model.
Accurate prediction of subgrade settlement of expressways is of great significance to their disease prevention and treatment. The previous prediction models for the subgrade settlement are mostly single models or simple improved models. A PMIGM(1,1) prediction model based on the particle swarm optimization(PSO) and Markov optimization is proposed. Firstly,based on the grey theory, an improved GM(1,1) prediction model is put forward. Then, according to the theory knowledge of Markov chains, an MIGM(1, 1) model is built to correct the relative residuals of IGM(1, 1) model, which can reflect the volatility characteristics of the data. Based on the principle of PSO, an optimization of PMIGM(1, 1) model is set up, which crystallizes the parameters of grey interval. The forecasting model is applied to a high-fill subgrade of Baoshan-Shidian Expressway in Yunnan Province. The analysis results show that the proposed model can improve the accuracy of the forecasting model.
引文
[1]DJONKAMLA Y,DORE G,BILODEAU J P.Development of a prediction model of permanent deformation considering the physical properties of subgrade soil[J].Canadian Journal of Civil Engineering,2016,43(11):958-967.
[2]POTTS D M.Numerical analysis:a virtual dream or practical reality(42nd Rankine Lecture)[J].Géotechnique,2003,53(6):535-573.
[3]柳治国,陈善雄,徐海滨.沉降预测的非等步长灰色时变参数模型[J].岩土力学,2004,32(12):1-4.(LIU Zhi-guo,CHEN Shan-xiong,XU Hai-bin.Unequal step lengths grey time-varying parameters model for settlement prediction[J].Rock and Soil Mechanics,2004,32(12):1-4.(in Chinese))
[4]李洪然,张阿根,叶为民.参数累积估计灰色模型及地面沉降预测[J].岩土力学,2008,29(12):3417-3421.(LI Hong-ran,ZHANG A-gen,YE Wei-min.Accumulating method GM(1,1)model and prediction of land subsidence[J].Rock and Soil Mechanics,2008,29(12):3417-3421.(in Chinese))
[5]GUO X,LIU S,WU L,et al.A multi-variable grey model with a self-memory component and its application on engineering prediction[J].Engineering Applications of Artificial Intelligence,2015,42:82-93.
[6]韩晋,杨岳,陈峰,等.基于非等时距加权灰色模型与神经网络的组合预测算法[J].应用数学和力学,2013,34(4):408-419.(HAN Jin,YANG Yue,CHEN Feng,et al.Combination forecasting algorithm based on non-equal interval weighted grey model and neural network[J].Applied Mathematics and Mechanics,2013,34(4):408-419.(in Chinese))
[2]POTTS D M.Numerical analysis:a virtual dream or practical reality(42nd Rankine Lecture)[J].Géotechnique,2003,53(6):535-573.
[3]柳治国,陈善雄,徐海滨.沉降预测的非等步长灰色时变参数模型[J].岩土力学,2004,32(12):1-4.(LIU Zhi-guo,CHEN Shan-xiong,XU Hai-bin.Unequal step lengths grey time-varying parameters model for settlement prediction[J].Rock and Soil Mechanics,2004,32(12):1-4.(in Chinese))
[4]李洪然,张阿根,叶为民.参数累积估计灰色模型及地面沉降预测[J].岩土力学,2008,29(12):3417-3421.(LI Hong-ran,ZHANG A-gen,YE Wei-min.Accumulating method GM(1,1)model and prediction of land subsidence[J].Rock and Soil Mechanics,2008,29(12):3417-3421.(in Chinese))
[5]GUO X,LIU S,WU L,et al.A multi-variable grey model with a self-memory component and its application on engineering prediction[J].Engineering Applications of Artificial Intelligence,2015,42:82-93.
[6]韩晋,杨岳,陈峰,等.基于非等时距加权灰色模型与神经网络的组合预测算法[J].应用数学和力学,2013,34(4):408-419.(HAN Jin,YANG Yue,CHEN Feng,et al.Combination forecasting algorithm based on non-equal interval weighted grey model and neural network[J].Applied Mathematics and Mechanics,2013,34(4):408-419.(in Chinese))