基于数字钻进技术和量子遗传-径向基函数神经网络的围岩类别超前识别技术研究

发布时间：2018-04-06 23:14

本文选题：围岩分类　切入点：超前识别　出处：《岩土力学》2014年07期

【摘要】：围岩类别超前分类是隧道施工过程中必须开展的一项工作,其直接关系到后续的开挖及施工支护方案。为有效地进行隧道围岩类别超前分类,提出了基于数字钻进技术和量子遗传(QGA)-径向基函数(RBF)神经网络的围岩类别超前分类方法。以数字钻进技术为基础,从钻进参数中提取有用信息,构建围岩类别超前分类指标体系。采用量子计算原理对遗传算法进行改进,通过量子位编码和量子旋转门更新种群,以此来确定RBF神经网络的参数,建立了基于QGA-RBF神经网络的围岩类别超前识别系统。最后将该方法应用于青岛胶州湾海底隧道的围岩类别超前识别中,结果表明,该方法具有较高的准确性,其结果为围岩类别超前分类提供了一种新思路。
[Abstract]:The advance classification of surrounding rock classification is a necessary work in tunnel construction, which is directly related to the subsequent excavation and construction support scheme.In order to effectively classify the surrounding rock categories ahead of the tunnel, an advanced classification method of surrounding rock classes based on digital drilling technique and quantum genetic QGA-radial basis function (RBF) neural network is proposed.On the basis of digital drilling technology, useful information is extracted from drilling parameters, and the advanced classification index system of surrounding rock category is constructed.The genetic algorithm is improved by using quantum computing principle, and the parameters of RBF neural network are determined by qubit coding and quantum rotation gate updating population, and the advance recognition system of surrounding rock category based on QGA-RBF neural network is established.Finally, the method is applied to the classification of surrounding rock in Jiaozhou Bay subsea tunnel in Qingdao. The results show that the method has high accuracy and provides a new way for the classification of surrounding rock.
【作者单位】：山东大学岩土与结构工程研究中心;成都理工大学地质灾害防治与地质环境保护国家重点实验室;
【基金】：国家自然科学基金(No.51309144) 地质灾害防治与地质环境保护国家重点实验室开放基金(No.SKLGP2013K019) 山东大学自主创新基金(No.2012TS063)
【分类号】：U452.12

【相似文献】