BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns

Hongyang He; Xiao Liang; Ziliang Feng

doi:doi:10.11648/j.ajist.20230701.13

| Peer-Reviewed

BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns

Hongyang He, Xiao Liang, Ziliang Feng

Published in American Journal of Information Science and Technology (Volume 7, Issue 1)

Received: 3 January 2023 Accepted: 25 January 2023 Published: 4 February 2023

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

SHM systems have been widely implemented in long-span bridges, and seas of field measurement data have been accumulated. Due to the imperfect sensors, data transmission and acquisition, various anomalies inevitably exist in the SHM data, which may lead to unreliable structural condition assessment. Thus, an effective approach for detecting data anomalies is highly desirable. Due to the imbalanced data, some anomalous patterns are undertrained in popular end-to-end deep neural network models, resulting in a reduction in detection precision. In this paper, a hierarchical classification model with deep neural network tree is proposed for imbalanced data. The DNN tree contains three levels: (1) CNN to divide seven types of data into four categories (134, 2, 5, 67), denoted as C4; (2) two DNNs to classify to two classes separately (1, 34, 6, 7), denoted as D2D2; (3) DNNs to classify to two classes (3, 4). So, the DNN tree is presented as C4_D2D2_D2. The DNN tree is an open framework and can be defined based on the data characteristics. In the data processing, three data sets are built for training, namely single-channel data set, dual-channel data set and statistical data set. To validate our work, we considered the effects of balanced and imbalanced training sets and training ratios. The results show that our model can detect the multi-pattern anomalies of SHM data efficiently with 95.5% high accuracy. Besides, the proportion of abnormal data classified to normal data has been reduced, especially 3-minor. This model successfully solves the problem in a simple and easy to understand way, which has certain reference significance for the bridge structure anomaly judgment in the future.

Published in	American Journal of Information Science and Technology (Volume 7, Issue 1)
DOI	10.11648/j.ajist.20230701.13
Page(s)	20-29
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

SHM System, Bridge Anomaly Detection, CNN, Hierarchical Classification, DNN

References

[1]	Sun L, Shang Z, Xia Y, Bhowmick S, Nagarajaiah S. Review of bridge structural health monitoring aided by big data and artificial intelligence: From condition assessment to damage detection. Journal of Structural Engineering. 2020; 1464020073.
[2]	Housner GW, Bergman LA, Caughey TK, Chassiakos AG, Claus RO, Masri SF, et al. Structural control: Past, present, and future. Journal of Engineering Mechanics-ASCE. 1997; 123897-971.
[3]	Ou J, Li H. Structural Health Monitoring in mainland China: Review and Future Trends. Structural Health Monitoring. 2010; 9219-31.
[4]	Bao Y, Chen Z, Wei S, Xu Y, Tang Z, Li H. The state of the art of data science and engineering in structural health monitoring. Engineering-PRC. 2019; 5234-42.
[5]	Spencer BF Jr., Hoskere V, Narazaki Y. Advances in computer vision-based civil infrastructure inspection and monitoring. Engineering-PRC. 2019; 5199-222.
[6]	Fujino Y, Siringoringo DM, Ikeda Y, Nagayama T, Mizutani T. Research and implementations of structural monitoring for bridges and buildings in Japan. Engineering-PRC. 2019; 51093-119.
[7]	Bao Y, Tang Z, Li H, Zhang Y. Computer vision and deep learning-based data anomaly detection method for structural health monitoring. Structural Health Monitoring. 2018; 18401-21.
[8]	Tang Z, Chen Z, Bao Y, Li H. Convolutional neural network-based data anomaly detection method using multiple information for structural health monitoring. Structural Control and Health Monitoring. 2019; 26e2296.
[9]	Geoffrey E. Hinton, Simon Osindero, Yee-Whye Teh: A fast learning algorithm for deep belief nets. Neural Computation, 18 (7): 1527-1554, 2006.
[10]	Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton: Imagenet classification with deep convolutional neural networks. NIPS, 2012.
[11]	Karen Simonyan, Andrew Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition. CVPR, 2015.
[12]	Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. Going Deeper with Convolutions. CVPR, 2015.
[13]	Kaiming He, Xiangyu Zhang, Shaoqing Ren, et al: Deep Residual Learning for Image Recognition. http://arxiv.org/abs/1512.03385
[14]	Gu J, Gul M, Wu X. Damage detection under varying temperature using artificial neural networks. Structural Control and Health Monitoring. 2017; 24 (11): e1998.
[15]	Ye XW, Ni YQ, Wai TT, et al. A vision-based system for dynamic displacement measurement of long-span bridges: algorithm and verification. Smart Structures and Systems. 2013; 12: 363–379.
[16]	Zhou YL, Maia NM, Sampaio RP, Wahab MA. Structural damage detection using transmissibility together with hierarchical clustering analysis and similarity measure. Structural Health Monitoring. 2017; 16 (6): 711-731.
[17]	Ma WF. Research on crack Detection Algorithm based on Deep learning [D]. Shaanxi Normal University, 2018.

Cite This Article

Plain Text BibTeX RIS

APA Style

Hongyang He, Xiao Liang, Ziliang Feng. (2023). BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns. American Journal of Information Science and Technology, 7(1), 20-29. https://doi.org/10.11648/j.ajist.20230701.13

Copy | Download

ACS Style

Hongyang He; Xiao Liang; Ziliang Feng. BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns. Am. J. Inf. Sci. Technol. 2023, 7(1), 20-29. doi: 10.11648/j.ajist.20230701.13

Copy | Download

AMA Style

Hongyang He, Xiao Liang, Ziliang Feng. BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns. Am J Inf Sci Technol. 2023;7(1):20-29. doi: 10.11648/j.ajist.20230701.13

Copy | Download

@article{10.11648/j.ajist.20230701.13,
  author = {Hongyang He and Xiao Liang and Ziliang Feng},
  title = {BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns},
  journal = {American Journal of Information Science and Technology},
  volume = {7},
  number = {1},
  pages = {20-29},
  doi = {10.11648/j.ajist.20230701.13},
  url = {https://doi.org/10.11648/j.ajist.20230701.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajist.20230701.13},
  abstract = {SHM systems have been widely implemented in long-span bridges, and seas of field measurement data have been accumulated. Due to the imperfect sensors, data transmission and acquisition, various anomalies inevitably exist in the SHM data, which may lead to unreliable structural condition assessment. Thus, an effective approach for detecting data anomalies is highly desirable. Due to the imbalanced data, some anomalous patterns are undertrained in popular end-to-end deep neural network models, resulting in a reduction in detection precision. In this paper, a hierarchical classification model with deep neural network tree is proposed for imbalanced data. The DNN tree contains three levels: (1) CNN to divide seven types of data into four categories (134, 2, 5, 67), denoted as C4; (2) two DNNs to classify to two classes separately (1, 34, 6, 7), denoted as D2D2; (3) DNNs to classify to two classes (3, 4). So, the DNN tree is presented as C4_D2D2_D2. The DNN tree is an open framework and can be defined based on the data characteristics. In the data processing, three data sets are built for training, namely single-channel data set, dual-channel data set and statistical data set. To validate our work, we considered the effects of balanced and imbalanced training sets and training ratios. The results show that our model can detect the multi-pattern anomalies of SHM data efficiently with 95.5% high accuracy. Besides, the proportion of abnormal data classified to normal data has been reduced, especially 3-minor. This model successfully solves the problem in a simple and easy to understand way, which has certain reference significance for the bridge structure anomaly judgment in the future.},
 year = {2023}
}

Copy | Download

TY - JOUR
T1 - BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns
AU - Hongyang He
AU - Xiao Liang
AU - Ziliang Feng
Y1 - 2023/02/04
PY - 2023
N1 - https://doi.org/10.11648/j.ajist.20230701.13
DO - 10.11648/j.ajist.20230701.13
T2 - American Journal of Information Science and Technology
JF - American Journal of Information Science and Technology
JO - American Journal of Information Science and Technology
SP - 20
EP - 29
PB - Science Publishing Group
SN - 2640-0588
UR - https://doi.org/10.11648/j.ajist.20230701.13
AB - SHM systems have been widely implemented in long-span bridges, and seas of field measurement data have been accumulated. Due to the imperfect sensors, data transmission and acquisition, various anomalies inevitably exist in the SHM data, which may lead to unreliable structural condition assessment. Thus, an effective approach for detecting data anomalies is highly desirable. Due to the imbalanced data, some anomalous patterns are undertrained in popular end-to-end deep neural network models, resulting in a reduction in detection precision. In this paper, a hierarchical classification model with deep neural network tree is proposed for imbalanced data. The DNN tree contains three levels: (1) CNN to divide seven types of data into four categories (134, 2, 5, 67), denoted as C4; (2) two DNNs to classify to two classes separately (1, 34, 6, 7), denoted as D2D2; (3) DNNs to classify to two classes (3, 4). So, the DNN tree is presented as C4_D2D2_D2. The DNN tree is an open framework and can be defined based on the data characteristics. In the data processing, three data sets are built for training, namely single-channel data set, dual-channel data set and statistical data set. To validate our work, we considered the effects of balanced and imbalanced training sets and training ratios. The results show that our model can detect the multi-pattern anomalies of SHM data efficiently with 95.5% high accuracy. Besides, the proportion of abnormal data classified to normal data has been reduced, especially 3-minor. This model successfully solves the problem in a simple and easy to understand way, which has certain reference significance for the bridge structure anomaly judgment in the future.
VL - 7
IS - 1
ER -

Copy | Download

Author Information

Hongyang He

College of Engineering and Physical Sciences, The University of Birmingham, Birmingham, United Kingdom
Xiao Liang

College of Engineering and Physical Sciences, The University of Birmingham, Birmingham, United Kingdom
Ziliang Feng

Institute of Image and Graphics, Air Traffic Management College, Civil Aviation Flight University, Sichuan University, Chengdu, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Hongyang He, Xiao Liang, Ziliang Feng. (2023). BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns. American Journal of Information Science and Technology, 7(1), 20-29. https://doi.org/10.11648/j.ajist.20230701.13

Copy | Download

ACS Style

Hongyang He; Xiao Liang; Ziliang Feng. BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns. Am. J. Inf. Sci. Technol. 2023, 7(1), 20-29. doi: 10.11648/j.ajist.20230701.13

Copy | Download

AMA Style

Hongyang He, Xiao Liang, Ziliang Feng. BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns. Am J Inf Sci Technol. 2023;7(1):20-29. doi: 10.11648/j.ajist.20230701.13

Copy | Download

@article{10.11648/j.ajist.20230701.13,
  author = {Hongyang He and Xiao Liang and Ziliang Feng},
  title = {BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns},
  journal = {American Journal of Information Science and Technology},
  volume = {7},
  number = {1},
  pages = {20-29},
  doi = {10.11648/j.ajist.20230701.13},
  url = {https://doi.org/10.11648/j.ajist.20230701.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajist.20230701.13},
  abstract = {SHM systems have been widely implemented in long-span bridges, and seas of field measurement data have been accumulated. Due to the imperfect sensors, data transmission and acquisition, various anomalies inevitably exist in the SHM data, which may lead to unreliable structural condition assessment. Thus, an effective approach for detecting data anomalies is highly desirable. Due to the imbalanced data, some anomalous patterns are undertrained in popular end-to-end deep neural network models, resulting in a reduction in detection precision. In this paper, a hierarchical classification model with deep neural network tree is proposed for imbalanced data. The DNN tree contains three levels: (1) CNN to divide seven types of data into four categories (134, 2, 5, 67), denoted as C4; (2) two DNNs to classify to two classes separately (1, 34, 6, 7), denoted as D2D2; (3) DNNs to classify to two classes (3, 4). So, the DNN tree is presented as C4_D2D2_D2. The DNN tree is an open framework and can be defined based on the data characteristics. In the data processing, three data sets are built for training, namely single-channel data set, dual-channel data set and statistical data set. To validate our work, we considered the effects of balanced and imbalanced training sets and training ratios. The results show that our model can detect the multi-pattern anomalies of SHM data efficiently with 95.5% high accuracy. Besides, the proportion of abnormal data classified to normal data has been reduced, especially 3-minor. This model successfully solves the problem in a simple and easy to understand way, which has certain reference significance for the bridge structure anomaly judgment in the future.},
 year = {2023}
}

Copy | Download