修剪型神经网络在锚杆锚固缺陷识别中的应用

PDF(986 KB)

振动与冲击 ›› 2018, Vol. 37 ›› Issue (5) : 221-227.

论文

孙晓云1，吴世星1，韩广1 ，田军2，成琦1

作者信息 +

Application of pruning type neural network in defect identification of blot anchoring systems

SUN Xiaoyun1，WU Shixing1, HAN Guang1，TIAN Jun2，CHENG Qi1

Author information +

文章历史 +

摘要

锚杆在桥梁、隧道、建筑等方面应用越来越广泛。在施工的过程中，由于地质条件、材料和施工等因素的影响，锚固系统会产生许多缺陷。这些缺陷都会对锚杆的寿命和安全性能造成影响，所以对锚杆的缺陷识别是一项很有价值的研究。人工神经网络作为一个智能的分类器，可以对锚杆的缺陷进行识别分类，本文提出一种自适应阈值前馈神经网络修剪算法，其实质是通过判断隐含层神经元在学习过程中对输出的贡献值，利用显著性指数作为指标来删除网络中的冗余节点，实现网络结构的动态优化调整。结果表明，该方法能够降低网络结构的复杂度，同时提高了锚杆缺陷分类识别的精度。

Abstract

Rock bolts are widely applied in bridges, tunnels, and buildings etc. In construction processes, due to influences of geological conditions, materials, architectures and other factors, there are many defects in anchoring systems. All these defects affect the life and safety of rock bolts, so it is very valuable to identify defects of anchor bolts. Artificial neural network can be used as an intelligent classifier to identify and classify defects of anchor bolts. Here, an adaptive threshold feed-forward neural network pruning algorithm was proposed, its essence was to judge the contribution value of hidden layer neurons in their learning processes to output, take the significant exponent as an index to delete redundant nodes of the network, and realize dynamic optimization and adjustment of the network structure. The simulation results showed that the proposed method can not only reduce the complexity of the network structure, but also improve classification and identification accuracies of anchor bolt defects.

导出引用

孙晓云1，吴世星1，韩广1,田军2，成琦1. 修剪型神经网络在锚杆锚固缺陷识别中的应用[J]. 振动与冲击, 2018, 37(5): 221-227

SUN Xiaoyun1，WU Shixing1, HAN Guang1，TIAN Jun2，CHENG Qi1. Application of pruning type neural network in defect identification of blot anchoring systems[J]. Journal of Vibration and Shock, 2018, 37(5): 221-227

参考文献

[1]贺若兰, 张平, 刘宝琛. 锚杆拉拔试验的理论和数值分析[J]. 岩土力学, 2006, S2: 855-859.
HE Ruolan, ZHANG Ping, LIU Baochen. Theoretical and numerical analysis of bolt pullout test[J].Rock and soil mechanics, 2006, S2: 855-859.
[2]朱自强, 何现启. 全长锚固锚杆拉拔试验研究[J]. 探矿工程(岩土钻掘工程), 2005, S1: 115-118.
ZHU Ziqiang, HE Xianqi.Study on pullout test of full size anchoring bolt[J].exploration engineering ( rock& soildrilling and tunneling)2005, S1: 115-118.
[3]蒋剑雄. 在桩基检测中低应变反射法与钻孔取芯法的应用[J].广西城镇建设,2008,08:268-269.
JIANG Jianxiong. Application of low strain reflection method and drilling core method in pile foundation detection[J].Urban construction in Guangxi 2008,08:268-269.
[4]Thumer H F. Boltometer-Instrument for non-destructive testing of grouted rock bolts [C]//2nd International Symposium onFiled Measurements in Geomachanices. Balkema:Rotterdam,1988:135-143.
[5]汪明武, 王鹤龄. 锚固质量的无损检测技术[J].岩石力学与工程学报,2002,01(21):126-129.
WANG Mingwu, WANG Heling. Nondestructive testing technique of anchorage quality[J].chinese journal of rock mechanics and engineering , 2002,01(21):126-129.
[6]汪明武, 王鹤龄. 声频应力波在锚杆锚固状态检测中的应用[J].地质与勘探,1998,04(34):56-58+61.
WANG Mingwu, WANGHeling. The application of audio frequency stress wave in theanchoring of state detection[J]. Geology and exploration, 1998,04(34):56-58+61.
[7]汪明武, 王鹤龄, 罗国煜, 谢焰. 锚杆锚固质量无损检测的研究[J].工程地质学报,1999,01(7):72-76.
WANG Mingwu, WANG Heling, LUO Guoyu, XIE Yan. Research on nondestructive testing of anchorage quality of anchor bolts[J].Journal of engineering geology, 1999,01(7):72-76.
[8]李义, 王成. 应力反射波法检测锚杆锚固质量的实验研究[J].煤炭学报,2000,02(25):160-164.
LI Yi, WANG Cheng. Experimental study on the detection of anchorage quality of anchor rod by stress reflection wave method[J].China Coal Society, 2000,02(25):160-164.
[9] 王猛, 李义, 董嘉. 应力波法锚杆锚固质量无损检测现场实验研究[J]. 煤炭技术, 2013, 32(1): 203-204.
WANG Meng, LIYi, DONG Jia.Field experimental study on ondestructive testing of anchorage quality of anchor bolt
by stress wave method[J]. China Coal Society, 2013, 32(1): 203-204.)
[10] LeCun Y, Denker J S,Solla S A Optimal Brain Damage.In Advances in Neural informationProcessing System,D.S.Touretzly,Ed.San Mateo,CA:Morgan Kauffman,1990,2:598-605.
[11] Hassibi. B, Strok. D.G Second Order Derivativs for Network Pruning:Optimal Brain Surgeon. In Advances in Neural information Processing System,S.J.Hanson,J.D.Cowan,and C.L.Giles,Eds.San Mateo,CA:Morgan Kauffman,1993,5:164-171.
[12] 李倩, 王永县, 朱友芹.人工神经网络混合剪枝算法.清华大学学报（自然科学版）,2005,45(6):831-834.
LI Qian, WANG Yongxian, ZHU Youqin. Hybrid pruning algorithm for artificial neural network training .Journal of Tsinghua University( Natural Science), 2005,45(6):831-834.)
[13]Philippe L, Eric F, and Thierry A M. A Node Pruning Algorithm Based on a Fourier Amplitude Sensitivity Test Method. IEEE Transactions on Neural Networks, 2006, 17(2): 273–293
[14] 乔俊飞, 李淼, 刘江. 一种神经网络快速修剪算法.电子学报.2010,4(38):831-834.
QIAO Junfei, LI Miao, LIU Jiang. A fast pruning algorithm for neural networks. Chinese Journal ofelectronics. 2010,4(38):831-834.
[15] 乔俊飞, 张颖. 一种多层前馈神经网络的快速修剪算法.智能系统学报.2008,3(2):206-210.
QIAO Junfei, ZHANG Ying. A fast pruning algorithm for multi layer feedforward neural networks. CAAI Transactions on Intelligent Systems. 2008,3(2):206-210.
[16] 许明, 张永兴, 阴可. 某隧道锚杆完整性的无损检测方法[J]. 土木工程学报,2004,05(37):78-80+100.
XU Ming. ZHANG Yongxing, YIN Ke. Study on nondestructive detection of bolts 'integrality in a tunnel[J]. China Civil Engineering Journal. 2004,05(37):78-80+100.