[1]李宝奇,贺昱曜,郭元术,等.基于DBN的隧道地质超前预报自动解释算法[J].长安大学学报(自然科学版),2017,37(03):90-96.
 LI Bao-qi,HE Yu-yao,GUO Yuan-shu,et al.Automatic interpretation algorithm for tunnel geological prediction based on DBN[J].Journal of Chang’an University (Natural Science Edition),2017,37(03):90-96.
点击复制

基于DBN的隧道地质超前预报自动解释算法()
分享到:

长安大学学报(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
第37卷
期数:
2017年03期
页码:
90-96
栏目:
桥梁与隧道工程
出版日期:
2017-05-31

文章信息/Info

Title:
Automatic interpretation algorithm for tunnel geological prediction based on DBN
作者:
李宝奇贺昱曜郭元术邱业绩
1. 西北工业大学 航海学院,陕西 西安 710072;2. 长安大学 信息工程学院,陕西 西安 710064;3. 西安公路研究院,陕西 西安 710065
Author(s):
LI Bao-qi HE Yu-yao GUO Yuan-shu QIU Ye-ji
1. School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, Shaanxi, China; 2. School of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, China; 3. Xi’an Highway Institute, Xi’an 710065, Shaanxi, China
关键词:
隧道工程隧道地质超前预报探地雷达深度置信网络压缩感知深度学习
Keywords:
tunnel engineering tunnel geological prediction GPR DBN compressed sensing deep learning
分类号:
U452.11
文献标志码:
A
摘要:
针对隧道地质超前预报过程中,探地雷达(ground penetrating radar, GPR)线测图解释仅依靠专家经验,且存在准确率不高的问题,通过对GPR成像原理和隧道地质特性的研究,以及对深度置信网络(deep belief networks, DBN)计算复杂度的分析,提出一种改进的基于压缩感知和DBN的GPR线测图分类解释模型。该模型首先利用压缩感知技术对原始GPR线测图进行压缩处理,通过选择图像压缩比得到合理的压缩图像;然后将压缩后的图像送入DBN模型进行分类,根据分类结果对原始GPR线测图进行解释;最后利用广西六宜(六寨—宜州)高速公路隧道实测数据对模型的有效性进行验证,试验数据共20 000幅GPR图像,包括6种隧道地质类型,其中15 000幅图像作为训练样本集,5 000幅图像作为测试样本集。研究结果表明:当GPR线测图压缩比为256,反向微调数据为1 000幅图像,DBN模型迭代次数为30时,模型对测试数据中6类探地雷达线测图的分类准确率达100%,单次训练时间降低为原DBN模型的8%左右;大量仿真试验发现GPR线测图的合理图像压缩比区间为64~1 024,在此区间压缩的图像能最大限度地降低图像维度并且保留原始图像信息。该模型具有解释准确率高、训练速度快等优点,可为制定隧道施工和开挖计划提供合理依据。
Abstract:
In the process of tunnel geological prediction, Interpretations of GPR (ground penetrating radar) line images are mainly determined by experience of experts, so that the accuracy is low. Through in-depth study on the principle of GPR, the geological characteristics of tunnel as well as the analysis on computational complexity of DBN (deep belief networks), an interpretation model of GPR line images was proposed based on compressed sensing and DBN. Firstly, the raw GPR line images were compressed by compressed sensing to obtain reasonable image with compression ratio. Secondly, the compressed images were sent to DBN model for classification. Then, the raw GPR line images were interpreted according to the classification results. Finally, the measured data of Liuyi (Liuzhai to Yizhou) Highway tunnels in Guangxi were used to verify the effectiveness of the proposed model. The experimental data contained 20 000 images which could be classified into 6 types of tunnel geology. 15 000 images of the experimental data were used as training dataset, and the other 5 000 images were used as testing dataset. The results show that when the compression ratio of GPR line images is 256, the reserve fine turning data is 1 000 images and the iteration number of DBN model is 30, the classification accuracy of the proposed model on the 6 types in testing dataset is 100%, and the single training time reduces to about 8% of that of the original DBN model. According to a large number of simulation experiments, the reasonable range of image compression ratio is 64 to 1 024, among which, the size of image can be greatly reduced and the information of raw image can be effectively preserved. Thus, it can be seen that the proposed model has the advantages of high accuracy of interpretation and fast training speed, and can provide reasonable basis for construction and excavation plan of tunnel.

相似文献/References:

[1]罗 刚,石研玉,申 奇,等.水中悬浮隧道锚索横向动力特性分析[J].长安大学学报(自然科学版),2012,32(03):73.
 LUO Gang,SHI Yan-yu,SHENG Qi,et al.Lateral dynamic characteristics analysis for cable of submerged floating tunnel in water[J].Journal of Chang’an University (Natural Science Edition),2012,32(03):73.
[2]易富君,韩 直,邓 卫.公路隧道群运营安全性综合评价方法[J].长安大学学报(自然科学版),2012,32(03):79.
 YI Fu-jun,HAN Zhi,DENG Wei.Comprehensive safety evaluation method of expressway tunnel group[J].Journal of Chang’an University (Natural Science Edition),2012,32(03):79.
[3]王 磊,郭洋洋.特长公路隧道运营网络通风技术[J].长安大学学报(自然科学版),2012,32(04):51.
 WANG Lei,GUO Yang-yang.Network ventilation technology of operation period in super long highway tunnel[J].Journal of Chang’an University (Natural Science Edition),2012,32(03):51.
[4]韩日美,宋战平,谢永利,等.土压平衡盾构土仓压力对地表沉降的影响[J].长安大学学报(自然科学版),2010,30(01):59.
 HAN Ri-mei,SONG Zhan-ping,XIE Yong-li,et al.Affection of soil warehouses pressure of EPB shield on ground settlement[J].Journal of Chang’an University (Natural Science Edition),2010,30(03):59.
[5]朱正国,陈明长,孙明磊.双连拱公路隧道围岩压力计算方法[J].长安大学学报(自然科学版),2010,30(02):75.
 ZHU Zheng-guo,CHEN Ming-zhang,SUN Ming-lei.Calculation method of pressure of surrounding rock on double-arch road tunnel[J].Journal of Chang’an University (Natural Science Edition),2010,30(03):75.
[6]刘 辉,李 波,吴从师,等.岩溶隧道掘进爆破震动效应分析[J].长安大学学报(自然科学版),2010,30(04):56.
 LIU Hui,LI Bo,WU Cong-shi,et al.Analysis on effects of vibration resulted from driving blasting in Karst tunnel[J].Journal of Chang’an University (Natural Science Edition),2010,30(03):56.
[7]朱春生,杨晓华,来弘鹏,等.公路隧道衬砌后空洞对结构安全的影响[J].长安大学学报(自然科学版),2010,30(05):63.
 ZHU Chun-sheng,YANG Xiao-hua,LAI Hong-peng,et al.Impact of empty hole behind expressway tunnel lining on structure safety[J].Journal of Chang’an University (Natural Science Edition),2010,30(03):63.
[8]来弘鹏,谢永利,杨晓华.不同应力场软弱围岩公路连拱隧道中墙受力特征[J].长安大学学报(自然科学版),2010,30(06):50.
 LAI Hong-peng,XIE Yong-li,YANG Xiao-hua.Stress characteristics of middle wall in soft-wreak surrounding rocks highway multiple-arch tunnel under different stress field[J].Journal of Chang’an University (Natural Science Edition),2010,30(03):50.
[9]来弘鹏,谢永利,杨晓华,等.不同应力场软弱围岩公路连拱隧道力学特征试验[J].长安大学学报(自然科学版),2008,28(06):60.
 LAI Hong-peng,XIE Yong-li,YANG Xiao-hua.Model tests for soft-weak surrounding rocks highway multiple-arch tunnel stress characteristics in different stress fields[J].Journal of Chang’an University (Natural Science Edition),2008,28(03):60.
[10]郭建新,高永涛.基于围岩破坏区和承载力的锚杆支护设计[J].长安大学学报(自然科学版),2008,28(06):65.
 GUO Jian-xin,GAO Yong-tao.Design of anchor bolt support based on analysis of surround rock damage area and bear force[J].Journal of Chang’an University (Natural Science Edition),2008,28(03):65.

更新日期/Last Update: 2017-06-06