基于IPSO-BP混合模型的TBM掘进参数预测

doi:10.13722/j.cnki.jrme.2019.1084

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1358 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要通过TBM上升段数据预测稳定段的掘进参数，可以在每个掘进循环的起始阶段预测出各掘进参数的建议值，辅助进行TBM掘进参数的设置和优化调整。提出一种基于改进粒子群算法优化BP神经网络(Improved particle swarm optimization-back propagation，IPSO-BP)的TBM掘进参数预测模型，采用自适应惯性权重对标准PSO算法进行改进，并基于改进PSO算法对BP网络的连接权值和偏置进行优化。基于吉林引松工程TBM3标段802 d的TBM运行数据对训练集和测试集进行划分。选取TBM掘进上升段前30 s的刀盘扭矩、贯入度、刀盘功率、推进速度、总推进力5个掘进参数变化特征(均值和线性拟合斜率)，以及岩性、围岩分级和地下水活动情况3个地质参数作为模型的输入，并通过试验法确定模型的3个关键超参数(隐含层节点数、学习率和粒子群种群规模)，预测稳定掘进时的推进速度v、总推进力F和刀盘扭矩T。结果表明，所提出的模型对TBM稳定掘进段参数的预测拟合优度均达0.85以上，平均绝对百分误差均小于12.68%，相比于BP模型和PSO-BP模型具有更高的预测精度。

	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
	侯少康
	刘耀儒
	张凯

关键词 ：隧道工程, TBM, 改进粒子群算法(IPSO), BP神经网络, 掘进参数预测

Abstract：It is of great significance to predict the TBM tunnelling parameters in stable phase based on the data of the rising phase，which can predict the recommended values of the tunnelling parameters at the early phase of each tunnelling cycle and assist to set and optimize the TBM tunnelling parameters. A TBM tunnelling parameter prediction model based on improved particle swarm integrated back propagation(IPSO-BP) is proposed，in which the standard PSO algorithm is improved by using adaptive inertia weight and the connection weight and bias of BP network are optimized based on improved PSO algorithm. Based on the 802-day TBM operation data of Songhua River water conveyance project，the training and test sets are divided. The variation characteristics(mean value and linear fitting slope) of cutterhead torque，penetration，cutterhead power，advance rate and total thrust in the first 30 s of TBM rising phase，as well as three geological parameters(i.e.，lithology, surrounding rock level and groundwater level) are selected as the inputs of IPSO-BP model. Three key hyper-parameters including number of the hidden layer nodes，learning rate and population size are determined by experimental method，and the advance rate v，total thrust F and cutterhead torque T in stable phase are predicted. The results show that the R2 of the proposed model is over 0.85 and the mean absolute percentage error is less than 12.68%. Compared with BP and PSO-BP models，the proposed model has higher prediction accuracy.

Key words： tunneling engineering TBM improved particle swarm optimization(IPSO) BP network tunnelling parameter prediction

引用本文:

侯少康，刘耀儒，张凯. 基于IPSO-BP混合模型的TBM掘进参数预测[J]. 岩石力学与工程学报, 2020, 39(8): 1648-1657.
HOU Shaokang，LIU Yaoru，ZHANG Kai. Prediction of TBM tunnelling parameters based on IPSO-BP hybrid model#br#. , 2020, 39(8): 1648-1657.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2019.1084 或 http://rockmech.whrsm.ac.cn/CN/Y2020/V39/I8/1648

[28]	焦斌，叶明星. BP神经网络隐层单元数确定方法[J]. 上海电机学院学报，2013，16(3)：113-116.(JIAO Bin，YE Mingxing. Determination of hidden unit number in a BP neural network[J]. Journal of Shanghai Dianji University，2013，16(3)：113-116.(in Chinese))
[17]	BENGIO Y. Practical recommendations for gradient-based training of deep architectures[M]. Berlin：Springer，2012：437-478.
[5]	YAGIZ S. A model for the prediction of tunnel boring machine performance[C]// Proceedings of 10th IAEG Congress. London：Lyell Collection，2006： 1-10.
[31]	CARLISLE A，DOZIER G. An off-the-shelf PSO[C]// Proceedings of the workshop on particle swarm optimization. Indianapolis：[s. n.]，2001：1-6.
[9]	BRULAND A. Hard rock tunnel boring[Ph. D. Thesis][D]. Trondheim：Norwegian University of Science and Technology，1998.
[29]	龚安，张敏. BP网络自适应学习率研究[J]. 科学技术与工程，2006，6(1)：64-66.(GONG An，ZHANG Min. BP neural network with adaptive learning rate[J]. Science Technology and Engineering，2006，6(1)：64-66.(in Chinese))
[2]	刘泉声，刘建平，潘玉丛，等. 硬岩隧道掘进机性能预测模型研究进展[J]. 岩石力学与工程学报，2016，35(增1)：2 766-2 786.(LIU Quansheng，LIU Jianping，PAN Yucong，et al. Research advances of tunnel boring machine performance prediction models for hard rock[J]. Chinese Journal of Rock Mechanics and Engineering，2016，35(Supp.1)：2 766-2 786.(in Chinese))
[10]	HASSANPOUR J，ROSTAMI J，ZHAO J. A new hard rock TBM performance prediction model for project planning[J]. Tunnelling and Underground Space Technology，2011，26(5)：595-603.
[12]	熊帆. 基于PSO-SVR算法的TBM掘进效率预测及围岩分级研究[硕士学位论文][D]. 西安：长安大学，2016.(XIONG Fan. Research of the TBM excavation efficiency prediction and rock classification based on the PSO-SVR algorithm[M. S. Thesis][D]. Xi¢an：Chang'an University，2016.(in Chinese))
[20]	周俊，陈璟华，刘国祥，等. 粒子群优化算法中惯性权重综述[J]. 广东电力，2013，26(7)：6-12.(ZHOU Jun，CHEN Jinghua，LIU Guoxiang，et al. Summary on inertia weight in particle swarm optimization algorithm[J]. Guangdong Electric Power，2013，26(7)：6-12.(in Chinese))
[22]	宋振雷，吴雪松. 分组合作多智能体算法优化BP神经网络的权值以及阈值[J]. 电子测试，2010，(4)：22-25.(SONG Zhenlei，WU Xuesong. Group cooperation Multi-agent optimize the weight and threshold of BP neural network[J]. Electronic Test，2010，(4)：22-25.(in Chinese))
[24]	罗华. 基于线性回归和深度置信网络的TBM性能预测研究[硕士学位论文][D]. 杭州：浙江大学，2018.(LUO Hua. Application of linear regression analysis and deep belief network for performance prediction of TBM[M. S. Thesis][D]. Hangzhou：Zhejiang University，2018.(in Chinese))
[1]	周红，班树春，韩颖. TBM最佳掘进工作参数研究与应用[J]. 水利建设与管理，2009，29(4)：86-88.(ZHOU Hong，BAN Shuchun，HAN Ying. Research and application of the best TBM driving parameters[J]. Water Conservancy Construction and Management，2009，29(4)：86-88.(in Chinese))
[4]	周思阳，亢一澜，苏翠侠，等. 基于力学分析的TBM掘进总推力预测模型研究[J]. 机械工程学报，2016，52(20)：76-82.(ZHOU Siyang，KANG Yilan，SU Cuixia，et al. Prediction of Thrust Force Requirements for TBMs Based on Mechanical Analysis[J]. Journal of Mechanical Engineering，2016，52(20)：76-82.(in Chinese))
[6]	刘泉声，时凯，朱元广，等. TBM盘形滚刀破岩力计算模型研究[J]. 煤炭学报，2013，38(7)：38-44.(LIU Quansheng，SHI Kai，ZHU Guangyuan，et al. Calculation model for rock disc cutting forces of TBM[J]. Journal of China coal society，2013，38(7)：38-44.(in Chinese))
[7]	王健，王瑞睿，张欣欣，等. 基于RMR岩体分级系统的TBM掘进性能参数预测[J]. 隧道建设，2017，37(6)：59-66.(WANG Jian，WANG Ruirui，ZHANG Xinxin，et al. Estimation of tbm performance parameters based on rock mass rating(RMR) system[J]. Tunnel Construction，2017，37(6)：59-66.(in Chinese))
[11]	ROSTAMI J，OZDEMIR L，NILSON B. Comparison between CSM and NTH hard rock TBM performance prediction models[C]// Proceedings of Annual Technical Meeting of the Institute of Shaft Drilling Technology. Las Vegas：[s. n.]，1996：1-10.
[14]	SALIMI A，ROSTAMI J，MOORMANN C，et al. Application of non-linear regression analysis and artificial intelligence algorithms for performance prediction of hard rock TBMs[J]. Tunnelling and Underground Space Technology，2016，58(5)：236-246.
[16]	SU J，WANG L G，ZHANG H L，et al. Application of fuzzy neural network in predicting the risk of rock burst[J]. Procedia Earth and Planetary Science，2009，1(1)：536-543.
[19]	ARUMUGAM M S，RAO M V C. On the improved performances of the particle swarm optimization algorithms with adaptive parameters，cross-over operators and root mean square(RMS) variants for computing optimal control of a class of hybrid systems[J]. Applied Soft Computing Journal，2008，8(1)：324-336.
[3]	ROSTAMI J. Development of a force estimation model for rock fragmentation with disc cutters through theoretical modeling and physical measurement of crushed zone pressure[Ph. D. Thesis][D]. Golden：Colorado School of Mines，1997.
[8]	O'ROURKE J E，SPRINGER J E，COUDRAY S V. Geotechnical parameters and tunnel boring machine performance at Goodwin Tunnel，California[C]// 1st North American Rock Mechanics Symposium. Rotterdam：A. A. Balkema，1994：467-473.
[13]	GE Y. Prediction of hard rock TBM penetration rate using least square support vector machine[J]. IFAC Proceedings Volumes，2013，46(13)：347-352.
[15]	温森，赵延喜，杨圣奇，等. 基于MonteCarlo-BP神经网络TBM掘进速度预测[J]. 岩土力学，2009，30(10)：3 127-3 132.(WEN Sen，ZHAO Yanxi，YANG Shengqi，et al. Prediction on penetration rate of TBM based on Monte Carlo-BP neural network[J]. Rock and Soil Mechanics，2009，30(10)：3 127-3 132.(in Chinese))
[18]	ZHOU J，LI X B，SHI X Z. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines[J]. Safety Science，2012，50(4)：629-644.
[23]	王超，龚国芳，杨华勇，等. NSVR硬岩隧道掘进机刀盘扭矩预测分析[J]. 浙江大学学报：自然科学版，2018，52(3)：479-486.(WANG Chao，GONG Guofang，YANG Huayong，et al. NSVR based predictive analysis of cutterhead torque for hard rock TBM[J]. Journal of Zhejiang University：Engineering Science，2018，52(3)：479-486.(in Chinese))
[25]	沈花玉，王兆霞，高成耀，等. BP神经网络隐含层单元数的确定[J]. 天津理工大学学报，2008，24(5)：15-17.(SHEN Huayu，WANG Zhaoxia，GAO Chengyao，et al. Determining the number of BP neural network hidden layer units[J]. Journal of Tianjin University of Technology，2008，24(5)：15-17.(in Chinese))
[30]	张雯雰，王刚，朱朝晖，等. 粒子群优化算法种群规模的选择[J]. 计算机系统应用，2010，19(5)：125-128.(ZHANG Wenwen，WANG Gang，ZHU Zhaohui，et al. Population size selection of particle swarm optimizer algorithm[J]. Computer Systems and Applications，2010，19(5)：125-128.(in Chinese))
[21]	李明军，王均星，王亚洲. 基于改进粒子群优化算法和极限学习机的混凝土坝变形预测[J]. 天津大学学报：自然科学与工程技术版，2019，52(11)：1 136-1 144.(LI Mingjun，WANG Junxing，WANG Yazhou. Deformation prediction of concrete dam based on improved swarm optimization algorithm and extreme learning machine[J]. Journal of Tianjin University：Science and Technology，2019，52(11)：1 136-1 144.(in Chinese))
[26]	JADID M N，FAIRBAIRN D R. The application of neural network techniques to structural analysis by implementing an adaptive finite-element mesh generation[J]. Artificial Intelligence for Engineering，Design，Analysis and Manufacturing，1994，8(3)：177-191.
[27]	张清良，李先明. 一种确定神经网络隐层节点数的新方法[J]. 吉首大学学报：自然科学版，2002，23(1)：89-91.(ZHANG Qingliang，LI Xianming. A new method to determine hidden note number in neural network[J]. Journal of Jishou University：Natural Science，2002，23(1)：89-91.(in Chinese))
[32]	王维博，林川，郑永康. 粒子群算法中参数的实验与分析[J]. 西华大学学报：自然科学版，2008，27(1)：76-80.(WANG Weibo，LIN Chuan，ZHENG Yongkang. Experiment and analysis of parameters in particle swarm optimization[J]. Journal of Xihua University：Natural Science，2008，27(1)：76-80.(in Chinese))