[1]HU Lei,QIU Yunjun,WANG Xizhao,et al.Point cloud big data analysis and deep model research for line and slope fine-tuning[J].CAAI Transactions on Intelligent Systems,2020,15(4):795-803.[doi:10.11992/tis.201911027]
Copy

Point cloud big data analysis and deep model research for line and slope fine-tuning

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 15 Number of periods: 2020 4 Page number: 795-803 Column: 吴文俊人工智能科学技术奖论坛 Public date: 2020-07-05
Title:
Point cloud big data analysis and deep model research for line and slope fine-tuning
Author(s):
HU Lei1;  QIU Yunjun2;  WANG Xizhao1;  ZHANG Zhiyi3
1. Department of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518061, China;
2. China Construction South Investment Co., Ltd., Shenzhen 518022, China;
3. China Construction Railway Electrification Engineering Co., Ltd., Beijing 100089, China
Keywords:
actual tunnel; theoretical tunnel; deviation; point cloud big data; invasion limit value; design line; deep learning; gradient descent; extreme value
CLC:
TP391
DOI:
10.11992/tis.201911027
Abstract:
The deviation information between the completed tunnel and the originally designed tunnel is very important for the safety adjustment of metro lines. However, there is no clear mathematical formula that can be used to accurately describe and measure the deviation. At present, the mainstream approach is to measure the invasion value of each section with the same interval manually and then sum up these values to get the deviation. This method has the disadvantages of large error, time-consuming and high cost. To solve these problems, a novel deviation representation method based on deep neural network is proposed, which can learn the internal relationship between the parameters of the designed tunnel and the invasion values based on the point cloud data, and then predict the parameters that can make the sum of the invasion values minimum. These parameters can be used to assist the safety adjustment of metro lines. The experimental results on a data set collected from a real subway project show that the proposed method can quickly obtain the appropriate adjustment scheme of the lines and slopes with only a small amount of computer memory resources.
References:
[1] 常占奎. 三维激光扫描仪在轨距提取中的应用研究[J]. 铁道建筑, 2018, 58(6): 137-139
CHANG Zhankui. Application research of 3D laser scanner in gauge extraction[J]. Railway engineering, 2018, 58(6): 137-139
[2] 薛懋, 王霄. 论三维激光扫描技术在地质测绘中的应用[J]. 世界有色金属, 2019(10): 87-91
XUE Mao, WANG Xiao. On the application of 3D laser scanning technology in geological surveying and mapping[J]. World nonferrous metals, 2019(10): 87-91
[3] 毕俊, 冯琰, 顾星晔, 等. 三维激光扫描技术在地铁隧道收敛变形监测中的应用研究[J]. 测绘科学, 2008(S2): 14-15
BI Jun, FENG Yan, GU Xingye, et al. Research on application of 3D laser scanning technology in metro tunnel convergence and deformation monitoring[J]. Science of surveying and mapping, 2008(S2): 14-15
[4] 托雷, 康志忠, 谢远成, 等. 利用三维点云大数据的地铁隧道断面连续截取方法研究[J]. 武汉大学学报(信息科学版), 2013(2): 49-53, 63
TUO Lei, KANG Zhizhong, XIE Yuancheng, et al. Research on continuous intercepting method of metro tunnel section using 3D point cloud big data[J]. Journal of Wuhan university( information science edition), 2013(2): 49-53, 63
[5] 康志忠, 托雷, 王保前, 等. 基于三维激光扫描的地铁隧道连续形变监测数据处理软件系统[J]. 测绘工程, 2013, 22(5): 82-86
KANG Zhizhong, TUO Lei, WANG Baoqian, et al. Data processing software system for continuous deformation monitoring of subway tunnel based on 3D laser scanning[J]. Engineering of surveying and mapping, 2013, 22(5): 82-86
[6] 谢雄耀, 卢晓智, 田海洋, 等. 基于地面三维激光扫描技术的隧道全断面变形测量方法[J]. 岩石力学与工程学报, 2013(11): 59-69
XIE Xiongyao, LU Xiaozhi, TIAN Haiyang, et al. Tunnel full-section deformation measurement method based on 3D ground laser scanning technology[J]. Chinese journal of rock mechanics and engineering, 2013(11): 59-69
[7] 潘国荣, 张超. 三维激光扫描在地铁隧道变形监测中的开发应用[J]. 东华理工大学学报(自然科学版), 2016(S1): 4-8
PAN Guorong, ZHANG Chao. Development and application of 3D laser scanning in metro tunnel deformation monitoring[J]. Journal of east China institute of technology(natural science edition), 2016(S1): 4-8
[8] 张明智, 张明栋. 三维激光扫描技术在地铁隧道变形监测中的应用[J]. 城市勘测, 2018(3): 25-29
ZHANG Mingzhi, ZHANG Mingdong. Application of 3D laser scanning technology in metro tunnel deformation monitoring[J]. Urban geotechnical investigation & surveying, 2018(3): 25-29
[9] 赵凌. 地铁站出入通道多摄像机移动目标跟踪研究[J]. 重庆理工大学学报( 自然科学版), 2019, 33(5): 95-101
ZHAO Ling. Study on moving target tracking of multi camera in subway access channel[J]. Journal of Chongqing university of technology( natural science edition), 2019, 33(5): 95-101
[10] 张瀚, 高飞. 一种点云配准新方法在隧道变形监测中的应用研究[J]. 信息通信, 2016(5): 21-23
ZHANG Han, GAO Fei. Application study of a new method of point cloud registration in tunnel deformation monitoring[J]. Introduction of bluetooth technology, 2016(5): 21-23
[11] 陈仁朋, 王诚杰, 鲁立, 等. 开挖对地铁盾构隧道影响及控制措施[J]. 工程力学, 2017(12): 1-13
CHEN Renpeng, WANG Chengjie, LU Li, et al. Influence of excavation on metro shield tunnel and control measures[J]. Engineering mechanics, 2017(12): 1-13
[12] 王兆宁. 铁路隧道建筑限界快速检测技术研究与应用[J]. 铁道建筑, 2019(3): 141-144
WANG Zhaoning. Research and application of rapid inspection technology for railway tunnel building boundary[J]. Railway engineering, 2019(3): 141-144
[13] HORNIK K, STINCHCOMBE M, WHITE H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks[J]. Neural networks, 1990, 3(5): 551-560.
[14] CHEN L, WU C. A note on the expressive power of deep rectified linear unit networks in high-dimensional spaces[J]. Mathematical methods in the applied sciences, 2019, 42(9): 3400-3404.
[15] CHEN Yali, YANG Yanping, FANG Qing. Discriminative region guided deep neural network towards food image classification[C]// CCF Chinese Conference on Computer Vision. Singapere, 2017: 425-434.
[16] 燕续峰, 翟少鹏, 王治华, 等. 深度神经网络在非侵入式负荷分解中的应用[J]. 电力系统自动化, 2019, 43(1): 171-180,224
YAN Xufeng, ZHAI Shaopeng, WANG Zhihua, et al. Application of deep neural network in non-intrusive load decomposition[J]. Automation of electrical power sytstem, 2019, 43(1): 171-180,224
[17] CAO W, GAO J, MING Z, et al. Fuzziness-based online sequential extreme learning machine for classification problems[J]. Soft Computing, 2018, 22: 3487-3494.
[18] CAO W, MING Z, XU Z, et al. Online sequential extreme learning machine with dynamic forgetting factor[J]. IEEE access, 2019, 7: 179746-179757.
[19] 何原荣, 郑渊茂, 潘火平, 等. 基于点云数据的复杂建筑体真三维建模与应用[J]. 遥感技术与应用, 2016(6): 1091-1099
HE Yuanrong, ZHENG Yuanmao, PAN Huoping, et al. 3D modeling and application of complex building based on point cloud data[J]. Remote sensing technology and application, 2016(6): 1091-1099
[20] 贾鹤鸣, 孟羽佳, 邢致恺, 等. 基于点云拼接的植物三维模型重建[J]. 应用科技, 2019, 46(1): 19-24
JIA Heming, MENG Yujia, XING Zhikai, et al. Reconstruction of three dimensional model of plant based on point cloud stitching[J]. Applied Science and Technology, 2019, 46(1): 19-24
[21] 陈兵. 轨道交通调线调坡设计相关研究[J]. 铁道勘测与设计, 2014(3): 25-29
CHEN Bing. Relative research on slope design of rail transit[J]. Railway survey and design, 2014(3): 25-29
[22] 王智, 李勇, 张洪德, 等. 三维激光扫描技术在地铁隧道施工质量检测中的应用研究[J]. 城市勘测, 2018(3): 114-116
WANG Zhi, LI Yong, ZHANG Hongde, et al. Application research of 3D laser scanning technology in metro tunnel construction quality inspection[J]. Urban exploration and survey, 2018(3): 114-116
[23] WANG J, WEN Y, GOU Y, et al. Fractional-order gradient descent learning of BP neural networks with Caputo derivative.[J]. Neural networks, 2017, 89: 19-30.
[24] HAN K, YU D. Speech emotion recognition using deep neural network and extreme learning machine[J]. Interspeech, 2014(4): 223-227.
[25] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[J]. Journal of machine learning research, 2010, 15: 315-323.
[26] KERMANY D, GOLDBAUM M, CAI W. Identifying medical diagnoses and treatable diseases by image-based deep learning. [J]. Cell, 2018, 172(5): 1122.
Similar References:

Memo

-

Last Update: 2020-07-25

Copyright © CAAI Transactions on Intelligent Systems