隧道洞室地基稳定性双阶段多策略粒子群BP网络模型研究
|
摘要
影响隧道洞室地基稳定性的因素众多,这些因素与隧道洞室地基稳定性之间存在着复杂的非线性关系,并且常规的方法很难描述这种复杂的关系。文章提出了一种双阶段多策略粒子群算法(DMPSO)优化的BP神经网络隧道洞室地基稳定性评价模型。粒子群算法具有全局优化能力强、搜索效率高等特点,算法改进后使这些特点更加突出。BP算法有很强的非线性映射能力、泛化能力,但也有收敛速度慢,容易陷入局部最优等缺陷。采用双阶段多策略粒子群算法(DMPSO)搜索BP模型的权值和阈值,弥补了BP模型的缺陷,提高了其预测的准确度。文章以重庆小什字车站洞室地基为例,证明了双阶段多策略粒子群算法优化的BP神经网络模型(DMPSO-BP)的可行性,并且该模型比模糊神经网络和粒子群优化的BP神经网络(PSO-BP)模型有更好的预测精度。
Many factors affect the stability of a tunnel cavern foundation;there is a complex nonlinear relationship between these factors and the tunnel cavern foundation stability,and conventional methods have difficulty describing this complex relationship.Therefore,a dual-stage multi-strategy particle swarm optimization(DMPSO)BP neural network model is proposed for evaluating the stability of tunnel cavern foundations.The particle swarm algorithm is characterized by a strong capability for global optimization and a high search efficiency,with these characteristics being more prominent after improvement of the algorithm.The BP algorithm has a strong capacity for nonlinear mapping and generalization,with the disadvantages of slow convergence and local optimization.By using the dual-stage multi-strategy particle swarm optimization(DMPSO)to determine the weights and thresholds of the BP neural network,the shortcomings of the BP neural network are solved and the prediction accuracy is improved.Using the Chongqing Xiaoshizi station cavern foundation as an example,the feasibility of the dual-stage multi-strategy particle swarm optimization BP neural network model(DMPSO-BP)is verified,with the prediction accuracy of the proposed model being better than that of the fuzzy neural network model and particle swarm optimization BP neural network(PSO-BP)model.
Many factors affect the stability of a tunnel cavern foundation;there is a complex nonlinear relationship between these factors and the tunnel cavern foundation stability,and conventional methods have difficulty describing this complex relationship.Therefore,a dual-stage multi-strategy particle swarm optimization(DMPSO)BP neural network model is proposed for evaluating the stability of tunnel cavern foundations.The particle swarm algorithm is characterized by a strong capability for global optimization and a high search efficiency,with these characteristics being more prominent after improvement of the algorithm.The BP algorithm has a strong capacity for nonlinear mapping and generalization,with the disadvantages of slow convergence and local optimization.By using the dual-stage multi-strategy particle swarm optimization(DMPSO)to determine the weights and thresholds of the BP neural network,the shortcomings of the BP neural network are solved and the prediction accuracy is improved.Using the Chongqing Xiaoshizi station cavern foundation as an example,the feasibility of the dual-stage multi-strategy particle swarm optimization BP neural network model(DMPSO-BP)is verified,with the prediction accuracy of the proposed model being better than that of the fuzzy neural network model and particle swarm optimization BP neural network(PSO-BP)model.
引文
[1]胡军,李俊杰,康飞.隧道洞室地基稳定性进化支持向量机识别[J].辽宁工程技术大学学报,2007,26(5):703-705.HU Jun,LI Junjie,KANG Fei.Stability Recognition of Tunnel Cavern Foundation Based on Support Vector Machines with Genetic Algorithms[J].Journal of Liaoning Technical University,2007,26(5):703-705.
[2]KENNEDY J,EBERHART R C.Particle Swarm Optimization[C]//Proc IEEE International Conference on Neural Networks,USA:IEEE Press,1995,1942-1948.
[3]SHI Y,EBERHART R C.Parameter Selection in Particle Swarm Optimization[C]//Proc 7th Annual Conference on Evolutionary Programming,Washington DC:IEEE Press,1998,591-600.
[4]陈伟,丁秋林.可扩展数据清理软件平台的研究[J].电子科技大学学报,2006,35(1):100-103.CHEN Wei,DING Qiulin.Study on the Extensible Data Cleaning Software Platform[J].Journal of UEST of China,2006,35(1):100-103.
[5]李明,张勇,张军权,等.改进PSO-SVM在说话人识别中的应用[J].电子科技大学学报,2007,36(6):1345-1349.LI Ming,ZHANG Yong,ZHANG Junquan,et al.Application of Improved PSO-SVM Approach in Speaker Recognition[J].Journal of UEST of China,2007,36(6):1345-1349.
[6]那日苏,李强,乌力吉.基于仿生学改进的粒子群算法[J].计算机工程与应用,2014,50(6):61-63.NA Risu,LI Qiang,WU Liji.Particle Swarm Optimization Based on Bionics[J].Computer Engineering and Applications,2014,50(6):61-63.
[7]李丽,牛奔.粒子群优化算法[M].北京:冶金工业出版社,2009:27-33.LI Li,NIU Ben.Particle Swarm Optimization[M].Beijing:Metallurgical Industry Press,2009:27-33.
[8]李国勇.智能预测控制及其MATLAB实现[M].北京:电子工业出版社,2010:75-105.LI Guoyong.Intelligent Prediction Control and Its MATLAB Implementation[M].Beijing:Publishing House of Electronics Industry,2010:75-105.
[9]张永兴,王桂林,胡居义.岩石洞室地基稳定性分析方法与实践[M].北京:科学出版社,2005.ZHANG Yongxing,WANG Guilin,HU Juyi.Analysis Method of Rock Cavern Foundation Stability and Its Practice[M].Beijing:Science Press,2005.
[10]颜七笙,王士同.基于PSO-SVR的岩质边坡稳定性评价模型[J].计算机工程与应用,2011,47(16):235-238.YAN Qisheng,WANG Shitong.Stability Evaluation Model of Rock Mass Slope Based on PSO-SVR[J].Computer Engineering and Applications,2011,47(16):235-238.
[11]HASSOUN M.Fundamentals of Artificial Neural Networks[M].Cambridge:The MIT Press,1995.
[12]李翔,崔吉峰,熊军,等.克隆选择粒子群优化BP神经网络电力需求预测[J].湖南大学学报,2008,35(6):41-45.LI Xiang,CUI Jifeng,XIONG Jun,et al.Power Demand Forecasting Based on BP Neural Network Optimized by Clonal Selection Particle Swarm[J].Journal of Hunan University,2008,35(6):41-45.
[13]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.ZHANG Naiyao,YAN Pingfan.Neural Network and Fuzzy Control[M].Beijing:Tsinghua University Press,1998.
[2]KENNEDY J,EBERHART R C.Particle Swarm Optimization[C]//Proc IEEE International Conference on Neural Networks,USA:IEEE Press,1995,1942-1948.
[3]SHI Y,EBERHART R C.Parameter Selection in Particle Swarm Optimization[C]//Proc 7th Annual Conference on Evolutionary Programming,Washington DC:IEEE Press,1998,591-600.
[4]陈伟,丁秋林.可扩展数据清理软件平台的研究[J].电子科技大学学报,2006,35(1):100-103.CHEN Wei,DING Qiulin.Study on the Extensible Data Cleaning Software Platform[J].Journal of UEST of China,2006,35(1):100-103.
[5]李明,张勇,张军权,等.改进PSO-SVM在说话人识别中的应用[J].电子科技大学学报,2007,36(6):1345-1349.LI Ming,ZHANG Yong,ZHANG Junquan,et al.Application of Improved PSO-SVM Approach in Speaker Recognition[J].Journal of UEST of China,2007,36(6):1345-1349.
[6]那日苏,李强,乌力吉.基于仿生学改进的粒子群算法[J].计算机工程与应用,2014,50(6):61-63.NA Risu,LI Qiang,WU Liji.Particle Swarm Optimization Based on Bionics[J].Computer Engineering and Applications,2014,50(6):61-63.
[7]李丽,牛奔.粒子群优化算法[M].北京:冶金工业出版社,2009:27-33.LI Li,NIU Ben.Particle Swarm Optimization[M].Beijing:Metallurgical Industry Press,2009:27-33.
[8]李国勇.智能预测控制及其MATLAB实现[M].北京:电子工业出版社,2010:75-105.LI Guoyong.Intelligent Prediction Control and Its MATLAB Implementation[M].Beijing:Publishing House of Electronics Industry,2010:75-105.
[9]张永兴,王桂林,胡居义.岩石洞室地基稳定性分析方法与实践[M].北京:科学出版社,2005.ZHANG Yongxing,WANG Guilin,HU Juyi.Analysis Method of Rock Cavern Foundation Stability and Its Practice[M].Beijing:Science Press,2005.
[10]颜七笙,王士同.基于PSO-SVR的岩质边坡稳定性评价模型[J].计算机工程与应用,2011,47(16):235-238.YAN Qisheng,WANG Shitong.Stability Evaluation Model of Rock Mass Slope Based on PSO-SVR[J].Computer Engineering and Applications,2011,47(16):235-238.
[11]HASSOUN M.Fundamentals of Artificial Neural Networks[M].Cambridge:The MIT Press,1995.
[12]李翔,崔吉峰,熊军,等.克隆选择粒子群优化BP神经网络电力需求预测[J].湖南大学学报,2008,35(6):41-45.LI Xiang,CUI Jifeng,XIONG Jun,et al.Power Demand Forecasting Based on BP Neural Network Optimized by Clonal Selection Particle Swarm[J].Journal of Hunan University,2008,35(6):41-45.
[13]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.ZHANG Naiyao,YAN Pingfan.Neural Network and Fuzzy Control[M].Beijing:Tsinghua University Press,1998.