基于遗传神经网络的锚杆极限承载力预测的研究
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
针对BP人工神经网络具有易陷入局部极小等缺陷,提出了将遗传算法与神经网络结合,同时优化网络结构的权值与阈值的思想,建立了基于遗传算法的锚杆极限承载力预测的遗传神经网络模型。该模型以低应变动测的5个变量作为输入变量来对锚杆极限承载力进行预测,并与BP神经网络预测结果进行比较。数值算例表明,遗传神经网络在锚杆极限承载力预测中具有较高的计算效率和识别精度。
Due to some defects of BP neural network,the power size and the threshold value of the network structure are optimized by combining genetic algorithm with neural network.The estimation model of bolt bearing capacity is accordingly built based on the improved optimization algorithm.In this model,five low strain variables from dynamic testing are used to estimate the bolt bearing capacity.The calculated results are compared with those of BP neural network.The presented example shows that the genetic neural network is of both higher computing efficiency and higher identification accuracy in estimating the bolt bearing capacity.
引文
[1]程良奎.岩土锚固的现状与发展[J].土木工程学报,2001,34(3):7~13.Cheng L iangku i.Present status and developm ent of ground anchor-ages.Ch ina C ivil Engineering Journal,2001,34(3):7~13.
    [2]程良奎,张作楣,杨志银.岩土加固实用技术[M].北京:地震出版社,1994.Cheng L iangku i,Zhang Zuom ei,Yang Zh iyin.Applied technologyof land reinforcem ent.Beijing:The Earthquake Press,1994.
    [3]许明,张永兴,阴可.锚杆极限承载力的人工神经网络预测[J].岩石力学与工程学报,2002,21(5):755~758.Xu M ing,Zhang Yongxing,Y in Ke.Pred iction of lim it bearing ca-pacity of bolt using artificial neural networks.Ch inese Journal ofRock M echan ics and Engineering,2002,21(5):755~758.
    [4]雷林源.桩基动力学[M].北京:冶金工业出版社,2000.Lei L inyuan.P ile foundation dynam ics.Beijing:M etallurgical In-dustry Press,2000.
    [5]韦立德,徐为亚,蒋中明,等.基坑支护结构水平变形预测的遗传神经网络方法[J].工程地质学报,2003,11(3):297~301.W ei L ide,et al..Application of genetic neural network m ethod toforecasting horizontal deformation of support structure at foundationp it.Journal of Engineering Geology,2003,11(3):297~301.
    [6]Holland J H.Adaptation in Natural and Artificial System s[M].Ann Arbor,M I:Un iversity ofM ich igan Press,1975.
    [7]Goldberg D E.Genetic A lgorithm in Search,Optim ization,andMa-ch ine Learn ing[M].New York:Add ison-W esley,1989.
    [8]罗先启,詹振彪,葛修润等.BP网络与遗传算法在水布垭工程中的应用[J].岩石力学与工程学报,2002,21(7):963~967.Luo X ianq i,et al.Application of artificial neural network and ge-netic algorithm into Shu iBuYa project.Ch inese Journal of RockM echan ics and Engineering,2002,21(7):963~967.
    [9]Charles L K,lgor Y,Keith N.Solving inverse in itial-valueboundary-value prob lem s via genetic algorithm[J].EngineeringApplication ofArtificial Intelligence,2000,13(6):625~633.
    [10]陈方泽,陈丙珍,何小容.遗传算法与神经网络-用改进的遗传算法训练神经网络[J].化工学报,1996,47(3):280~286.Chen Fangze,et al..Genetic algorithm s and artificial neural net-work-Train ing artificial neural network by EGA-GDR.Journalof Chem ical Industry and Engineering,1996,47(3):280~286.
    [11]金菊良,魏一鸣,杨小华.基于遗传算法的神经网络及其在洪水灾害承灾体易损性建模中的应用[J].自然灾害学报,1998,7(2):53~59.Jin Ju liang,et al..Genetic algorithm based neural network andits application in modeling the vu lnerab ility of flood hazard-af-fected body,1998,7(2):53~59.
    [12]董亮,史存林,蔡德钩,叶阳升.地基沉降计算新方法的探索法[J].工程地质学报,2005,13(2):227~230.Dong L iang,Sh i Cun lin,et al..On new computational m ethodon settlem ent of ground.Journal ofEngineering Geology,2005,13(2):227~230.
    [13]李晋,谢永利,冯忠居.土体参数对大直径空心桩承载性状影响的仿真分析[J].工程地质学报,2005,13(1):129~134.L i Jin,et al..Emu lation analysis of the soil param eters'effects onthe bearing performance of the large d iam eter hollow p ile.Journalof Engineering Geology,2005,13(1):129~134.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心