Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification

The big data collected from structural health monitoring systems (SHMs), combined with the rapid advances in machine learning (ML), have enabled data-driven methods in practical SHM applications. These methods typically use ML algorithms to identify patterns within features extracted from data repre...

Full description

Saved in:
Bibliographic Details
Main Authors: Long Li, Xiaoming Tao, Hui Song, Xiaolong Li, Zhilong Ye, Yao Jin, Qiuyu He, Shiyin Wei, Wenli Chen
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/6/145
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849431934595235840
author Long Li
Xiaoming Tao
Hui Song
Xiaolong Li
Zhilong Ye
Yao Jin
Qiuyu He
Shiyin Wei
Wenli Chen
author_facet Long Li
Xiaoming Tao
Hui Song
Xiaolong Li
Zhilong Ye
Yao Jin
Qiuyu He
Shiyin Wei
Wenli Chen
author_sort Long Li
collection DOAJ
description The big data collected from structural health monitoring systems (SHMs), combined with the rapid advances in machine learning (ML), have enabled data-driven methods in practical SHM applications. These methods typically use ML algorithms to identify patterns within features extracted from data representing structural conditions, thereby inferring damage from changes in these patterns. However, data-driven models often struggle to generalize effectively to unseen datasets. This study addresses this challenge through three key contributions: dataset augmentation, an efficient feature representation, and a probabilistic modeling approach. First, a data augmentation method leveraging the symmetric properties of bridge structures is introduced to enhance dataset diversity. Second, a novel damage indicator named Fre-GraRMSC1 is proposed, capable of distinguishing both damage locations and severity. Finally, a probabilistic generative model based on a deep belief network (DBN) is developed to predict damage locations and degrees. The proposed methods are validated using vibration data from a numerical three-span continuous bridge subjected to random vehicle excitations. Results demonstrate high accuracy in damage identification and improved generalization performance.
format Article
id doaj-art-7457003b5471491e9c680eb97bc8ed62
institution Kabale University
issn 2412-3811
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-7457003b5471491e9c680eb97bc8ed622025-08-20T03:27:29ZengMDPI AGInfrastructures2412-38112025-06-0110614510.3390/infrastructures10060145Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage IdentificationLong Li0Xiaoming Tao1Hui Song2Xiaolong Li3Zhilong Ye4Yao Jin5Qiuyu He6Shiyin Wei7Wenli Chen8CCCC Highway Consultants Co., Ltd., Beijing 100088, ChinaSchool of Civil Engineering, Harbin Institute of Technology, Harbin 150090, ChinaCCCC Highway Consultants Co., Ltd., Beijing 100088, ChinaCCCC Highway Consultants Co., Ltd., Beijing 100088, ChinaCCCC Highway Consultants Co., Ltd., Beijing 100088, ChinaCCCC Highway Consultants Co., Ltd., Beijing 100088, ChinaCCCC Highway Consultants Co., Ltd., Beijing 100088, ChinaSchool of Civil Engineering, Harbin Institute of Technology, Harbin 150090, ChinaSchool of Civil Engineering, Harbin Institute of Technology, Harbin 150090, ChinaThe big data collected from structural health monitoring systems (SHMs), combined with the rapid advances in machine learning (ML), have enabled data-driven methods in practical SHM applications. These methods typically use ML algorithms to identify patterns within features extracted from data representing structural conditions, thereby inferring damage from changes in these patterns. However, data-driven models often struggle to generalize effectively to unseen datasets. This study addresses this challenge through three key contributions: dataset augmentation, an efficient feature representation, and a probabilistic modeling approach. First, a data augmentation method leveraging the symmetric properties of bridge structures is introduced to enhance dataset diversity. Second, a novel damage indicator named Fre-GraRMSC1 is proposed, capable of distinguishing both damage locations and severity. Finally, a probabilistic generative model based on a deep belief network (DBN) is developed to predict damage locations and degrees. The proposed methods are validated using vibration data from a numerical three-span continuous bridge subjected to random vehicle excitations. Results demonstrate high accuracy in damage identification and improved generalization performance.https://www.mdpi.com/2412-3811/10/6/145structural health monitoringdamage identificationdeep learningdata augmentationdeep belief network
spellingShingle Long Li
Xiaoming Tao
Hui Song
Xiaolong Li
Zhilong Ye
Yao Jin
Qiuyu He
Shiyin Wei
Wenli Chen
Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification
Infrastructures
structural health monitoring
damage identification
deep learning
data augmentation
deep belief network
title Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification
title_full Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification
title_fullStr Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification
title_full_unstemmed Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification
title_short Symmetry-Based Data Augmentation Method for Deep Learning-Based Structural Damage Identification
title_sort symmetry based data augmentation method for deep learning based structural damage identification
topic structural health monitoring
damage identification
deep learning
data augmentation
deep belief network
url https://www.mdpi.com/2412-3811/10/6/145
work_keys_str_mv AT longli symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT xiaomingtao symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT huisong symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT xiaolongli symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT zhilongye symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT yaojin symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT qiuyuhe symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT shiyinwei symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification
AT wenlichen symmetrybaseddataaugmentationmethodfordeeplearningbasedstructuraldamageidentification