基于FA-NAR动态神经网络的隧洞围岩变形时序预测研究

doi:10.13722/j.cnki.jrme.2018.0757

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (427 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对隧洞围岩变形动态性、对时间和空间的敏感性、非线性、高度复杂性等特征，为提高围岩变形预测精度，采用萤火虫算法(FA)搜索确定延时阶数和隐含层单元个数，并利用非线性自回归(NAR)动态神经网络进行预测，提出基于FA-NAR动态神经网络的隧洞围岩变形预测模型，结合北山坑探设施围岩变形监测数据进行预测，并将其与BP神经网络算法预测结果对比分析。结果表明：(1) FA-NAR动态神经网络的预测值与实测值基本吻合，其产生的平均绝对误差和平均相对误差分别约为BP神经网络的1/5和1/4，表明FA-NAR动态神经网络算法模型比BP神经网络算法模型预测精度高；(2) 采用FA-NAR动态神经网络算法模型能够很好地解决围岩变形预测问题，既减少了人为输入网络参数的盲目性，又提高了网络的学习能力和预测精度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	蔡舒凌1
	李二兵1
	陈亮2
	高磊1
	濮仕坤1
	段建立1
	谭跃虎1

关键词 ：岩石力学, NAR动态神经网络, 时间序列, 萤火虫算法, 围岩变形预测, 隧洞

Abstract：The deformations of tunnels surrounding rock have the characteristics of dynamicity，sensitivity to time and space，nonlinearity，high complexity，etc. In order to improve the prediction accuracy of the surrounding rock deformation，the firefly algorithm(FA) was used to determine the delay order and number of hidden layer elements. And the prediction was carried out by nonlinear auto-regressive(NAR) dynamic neural network. A prediction model of tunnel surrounding rock deformation based on FA-NAR dynamic neural network was proposed. The deformation monitoring data of Beishan exploration tunnel was used to predict. And the prediction results of FA-NAR dynamic neural network algorithm were compared and analyzed with the BP neural network algorithm. It shows that the predicted values of FA-NAR dynamic neural network are basically consistent with the measured values. Its mean absolute error and mean relative error are around 1/5 and 1/4 of BP neural network respectively，which proves that the FA-NAR dynamic neural network algorithm model has higher prediction accuracy than the BP neural network algorithm model. The FA-NAR dynamic neural network algorithm model can solve the problem of surrounding rock deformation prediction well. It not only reduces the blindness of human input network parameters，but also improves the learning ability and prediction accuracy of the network.

Key words： rock mechanics NAR dynamic neural network time series firefly algorithm prediction of surrounding rock deformation tunnel

引用本文:

蔡舒凌1，李二兵1，陈亮2，高磊1，濮仕坤1，段建立1，谭跃虎1. 基于FA-NAR动态神经网络的隧洞围岩变形时序预测研究[J]. 岩石力学与工程学报, 2019, 38(S2): 3346-3353.
CAI Shuling1，LI Erbing1，CHEN Liang2，GAO Lei1，PU Shikun1，DUAN Jianli1，TAN Yuehu1. The time series prediction of tunnel surrounding rock deformation based on FA-NAR dynamic neural network. , 2019, 38(S2): 3346-3353.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2018.0757 或 http://rockmech.whrsm.ac.cn/CN/Y2019/V38/IS2/3346

[25]	赵川. 基于控制理论的随机需求供应链多级库存系统优化与仿真[博士学位论文][D]. 北京：对外经济贸易大学，2016.(ZHAO Chuan. Optimization and simulation of multi-echelon inventory in supply chain under stochastic demand based on control theory[Ph. D. Thesis][D]. Beijing：University of International Business and Economics，2016.(in Chinese))
[1]	吴开健. 高地应力条件下软岩隧道的变形分析及控制研究[硕士学位论文][D]. 广州：华南理工大学，2016.(WU Kaijian. Under the condition of high ground stress soft rock tunnel deformation analysis and control research[M. S. Thesis][D]. Guangzhou：South China University of Technology，2016.(in Chinese))
[23]	JIANG Y Z，LIU H Z，LIU J Y. LS-SVM-Markov model for dam deformation prediction[J]. Applied Mechanics and Materials，2013，423–426：1 144–1 149.
[33]	YANG X S. Firefly algorithms for multimodal optimization[J]. Mathematics，2009，5792：169–178.
[12]	卜庆为. 基于ARMA时序分析模型的巷道围岩变形预测[J]. 采矿技术，2014，14(1)：56–58. (BU Qingwei. Prediction of roadway surrounding rock deformation based on ARMA time series analysis model[J]. Mining Technology，2014，14(1)：56–58.(in Chinese))
[32]	YANG X. S. Nature-inspired metaheuristic algorithms[M]. [S. l.]：Luniver Press，2010：79–89.
[34]	YANG X S，DEB S. Eagle strategy using Lévy walk and firefly algorithms for stochastic optimization[J]. Studies in Computational Intelligence，2010，284：101–111.
[2]	张云鹏，李利平，贺鹏，等. 隧道围岩大变形高斯过程回归预测模型及其工程应用[J]. 科学技术与工程，2018，18(1)：122–127. ZHANG Yunpeng，LI Liping，HE Peng，et al. Gaussian process regression prediction model for the big deformation of the tunnel rock and its application[J]. Science Technology and Engineering，2018，18(1)：122–127.(in Chinese))
[4]	王新胜，左伟芹，周成涛，等. 基于非齐次指数函数灰色模型的隧道围岩变形预测[J]. 现代隧道技术，2017，54(1)：105–109.(WANG Xinsheng，ZUO Weiqin，ZHOU Chengtao，et al. Deformation prediction of tunnel surrounding rock based on non-homogeneous exponential function grey model[J]. Modern Tunnelling Technology，2017，54(1)：105–109.(in Chinese))
[5]	WANG X R，WANG Y H. Intelligent direct analysis of physical and mechanical parameters of tunnel surrounding rock based on adaptive immunity algorithm and BP neural network[J]. Journal of Pharmaceutical Analysis，2009，21(1)：22–30.
[7]	何庆文，翟明洋. 深埋大断面巷道拱顶变形预测分析及支护优化研究[J]. 化工矿物与加工，2018，47(1)：40–43.(HE Qingwen，ZHAI Mingyang. Prediction analysis of vault deformation and support optimization of deep-buried large section tunnel[J]. Industrial Minerals and Processing，2018，47(1)：40–43.(in Chinese))
[10]	耿耘. 地下工程围岩变形的支持向量机预测方法研究[硕士学位论文][D]. 北京：北京交通大学，2014.(GENG Yun. Prediction of surrounding rock deformation for underground excavations by support vector machine[M. S. Thesis][D]. Beijing：Beijing Jiaotong University，2014.(in Chinese))
[14]	王江荣. 加权复合分位数自回归模型在隧道围岩变形预测中的应用[J]. 大地测量与地球动力学，2017，37(5)：511–515.(WANG Jiangrong. Application of weighted composite quantile autoregressive model in processing of rock surrounding tunnel displacement data[J]. Journal of Geodesy and Geodynamics，2017，37(5)：511–515.(in Chinese))
[15]	王涛，孙文龙，李磊. 基于回归分析与灰色理论的围岩变形组合预测[J]. 地下空间与工程学报，2017，13(增1)：48–51.(WANG Tao，SUN Wenlong，LI Lei. Study on surrounding rock deformation combined forecasting method based on regression analysis and grey theory[J]. Chinese Journal of Underground Space and Engineering，2017，13(Supp.1)：48–51.(in Chinese))
[17]	张倩，陈新，周武松，等. GA-BP遗传神经网络在地下厂房变形预测中的应用[J]. 水电能源科学，2016，(6)：150–152.(ZHANG Qian，CHEN Xin，ZHOU Wusong，et al. Application of BP neural network based GA optimization in prediction of underground powerhouse deformation[J]. Water Resources and Power，2016，(6)：150–152.(in Chinese))
[20]	叶超. 基于BP神经网络修正的自适应灰色模型的隧道变形预测研究[J]. 铁道标准设计，2017，61(11)：76–81.(YE Chao. Research on deformation prediction of tunnel based on adaptive grey model of BP neural network correction[J]. Railway Standard Design，2017，61(11)：76–81.(in Chinese))
[22]	WANG D D，QIU G Q，XIE W B，et al. Deformation prediction model of surrounding rock based on GA-LSSVM-markov[J]. Natural Science，2012，4(2)：85–90.
[3]	胡达，黄小林，何杰. 基于改进灰色理论模型的隧道围岩变形预测[J]. 公路工程，2017，42(5)：72–75.(HU Da，HUANG Xiaolin，HE Jie. Prediction of deformation of tunnel surrounding rock based on improved grey theory model[J]. Highway Engineering，2017，42(5)：72–75.(in Chinese))
[13]	文明，张顶立，房倩，等. 隧道围岩变形的非线性自回归时间序列预测方法研究[J]. 北京交通大学学报，2017，41(4)：1–7. (WEN Ming，ZHANG Dingli，FANG Qian，et al. Research on nonlinear auto regressive time series method for predicting deformation of surrounding rock in tunnel[J]. Journal of Beijing Jiaotong University，2017，41(4)：1–7.(in Chinese))
[27]	黄凯，陈渠森，鞠博晓. GNSS自动化监测系统的大坝变形预测方法研究[J]. 测绘通报，2018，(1)：147–150.(HUANG Kai，CHEN Qusen，JU Boxiao. Study on prediction method of dam deformation for GNSS automatic monitoring system[J]. Bulletin of Surveying and Mapping，2018，(1)：147–150.(in Chinese))
[30]	李析男，王宁，梅亚东，等. NAR神经网络的应用与检验——以城市居民生活需水定额为例[J]. 灌溉排水学报，2017，36(11)：122–128.(LI Xinan，WANG Ning，MEI Yadong，et al. Application and test of NAR neural network-taking the quota of living water demand of urban residents as an example[J]. Journal of Irrigation and Drainage，2017，36(11)：122–128.(in Chinese))
[35]	李彦苍，周书敬，吴超. 仿生智能算法及其在土木工程中的应用[M]. 北京：科学出版社，2015：153–166.(LI Yancang，ZHOU Shujing，WU Chao. Bionic intelligent algorithm and its application in Civil Engineering[M]. Beijing：Science Press，2015：153–166.(in Chinese))
[37]	李一玄. 萤火虫算法参数研究[J]. 物流工程与管理，2015，(9)：195–197.(LI Yixuan. Parameter study on firefly algorithm[J]. Logistics Engineering and Management，2015，(9)：195–197.(in Chinese))
[6]	田明杰，牟智恒，仇文革. 基于BP神经网络的隧道稳定性分析研究[J]. 土木工程学报，2017，50(增2)：260–266.(TIAN Mingjie，MOU Zhiheng，QIU Wenge. Research of the model comprehensive judgement for tunnel stability based on BP neural network[J]. China Civil Engineering Journal，2017，50(Supp.2)：260–266.(in Chinese))
[11]	宋飞. 基于支持向量机的隧道围岩变形预测[J]. 交通世界，2016，(30)：56–57.(SONG Fei. Prediction of tunnel surrounding rock deformation based on support vector machine[J]. Transport World，2016，(30)：56–57.(in Chinese))
[21]	乔正明. 基于模糊灰色新陈代谢FGM(1，1)模型预测及应用探讨[J]. 数学的实践与认识，2017，47(5)：284–288.(QIAO Zhengming. Prediction and application of FGM(1，1) model based on Fuzzy Grey metabolism[J]. Mathematics in Practice and Theory，2017，47(5)：284–288.(in Chinese))
[31]	杨绍清，吴晓飞，章新华，等. NAR模型的Korenberg算法及其应用[J]. 系统仿真学报，2001，13(4)：439–441.(YANG Shaoqing，WU Xiaofei，ZHANG Xinhua，et al. Korenberg?s algorithm for NAR model and its applications[J]. Journal of System Simulation，2001，13(4)：439–441.(in Chinese))
[8]	YAO B Z，YANG C Y， YAO J B，et al. Tunnel surrounding rock displacement prediction using support vector machine[J]. International Journal of Computational Intelligence Systems，2010，3(6)：843–852.
[9]	YAO B，YAO J，ZHANG M，et al. Improved support vector machine regression in multi-step-ahead prediction for rock displacement surrounding a tunnel[J]. Scientia Iranica，2014，21(4)：1 309–1 316.
[19]	PING J. Application of grey theory and wavelet neural network in slope displacements prediction[J]. Journal of Applied Sciences，2013，13(21)：4 764–4 768.
[29]	许任婕. 基于时滞非线性自回归神经网络的轨道交通客流预测研究[硕士学位论文][D]. 重庆：重庆大学，2017.(XU Renjie. Research of rail traffic flow forecasting based on delay nonlinear autoregressive the neural network[M. S. Thesis][D]. Chongqing：Chongqing University，2017.(in Chinese))
[16]	张志强，李化云，阚呈，等. 大相岭隧道断层破碎带围岩变形的GA-BP神经网络预测技术[J]. 现代隧道技术，2014，51(2)：83–89. (ZHANG Zhiqing，LI Huayun，KAN Cheng，et al. Prediction of surrounding rock deformation in fault fracture zone of Daxiangling tunnel by GA-BP neural network[J]. Modern Tunneling Technology，2014，51(2)：83–89.(in Chinese))
[18]	周冠南，孙玉永，贾蓬. 基于遗传算法的BP神经网络在隧道围岩参数反演和变形预测中的应用[J]. 现代隧道技术，2018，55(1)：107–113.(ZHOU Guannan，SUN Yuyong，JIA Peng. Application of genetic algorithm based BP neural network to parameter inversion surrounding rock and deformation prediction[J]. Modern Tunnelling Technology，2018，55(1)：107–113.(in Chinese))
[24]	邱志刚. 基于蚁群优化支持向量机的公路隧道围岩变形预测模型及应用[J]. 隧道建设，2014，34(1)：13–18.(QIU Zhigang. Highway tunnel surrounding rock deformation prediction model based on support vector machine optimized by ant colony optimization and its application[J]. Tunnel Construction，2014，34(1)：13–18.(in Chinese))
[26]	王军. 基于新陈代谢与神经网络组合模型的加工误差预测及补偿[硕士学位论文][D]. 重庆：重庆大学，2017.(WANG Jun. Prediction and compensation of machining error based on combined model of metabolic model and neural network[M. S. Thesis][D]. Chongqing：Chongqing University，2017.(in Chinese))
[28]	袁鲁山. 基于NAR神经网络的车速预测及应用[硕士学位论文][D]. 大连：大连理工大学，2016.(YUAN Lushan. Vehicle speed prediction and application based on NAR neural network[M. S. Thesis][D]. Dalian：Dalian University of Technology，2016.(in Chinese))
[36]	李二兵，韩阳，谭跃虎，等. 北山坑探设施开挖全过程围岩内部位移现场量测试验研究[J]. 岩石力学与工程学报，2017，36(11)： 2 741–2 754.(LI Erbing，HAN Yang，TAN Yuehu，et al. Field measuring test on internal displacement of surrounding rock during whole excavation process of Beishan exploration tunnel[J]. Chinese Journal of Rock Mechanics and Engineering，2017，36(11)：2 741–2 754.(in Chinese))