Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion
Over the past few decades, rapid economic development has led to the establishment of numerous monitoring systems, resulting in the accumulation of vast amounts of monitoring data. Among these data, dynamic acceleration data stand out prominently. However, the quality of collected acceleration data...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/21/12045 |
_version_ | 1797632137039446016 |
---|---|
author | Yichao Xu Yufeng Zhang Jian Zhang |
author_facet | Yichao Xu Yufeng Zhang Jian Zhang |
author_sort | Yichao Xu |
collection | DOAJ |
description | Over the past few decades, rapid economic development has led to the establishment of numerous monitoring systems, resulting in the accumulation of vast amounts of monitoring data. Among these data, dynamic acceleration data stand out prominently. However, the quality of collected acceleration data is often compromised due to factors such as challenging operational environments and sensor malfunctions. This severely hampers the value extracted from the data. Although manual identification and classification of data anomalies are more reliable, they are time consuming and labor intensive. To address the challenge of identifying and classifying anomalies in massive acceleration data, this paper proposes a two-stage model for intelligent data cleaning. Firstly, raw acceleration data are transformed into IPDF and PSD features, and a one-dimensional convolutional neural network is trained to preliminarily identify and classify acceleration data anomalies. Subsequently, the RPV indicator is extracted from the original data of the normal and outlier categories to achieve precise classification based on threshold values. The proposed method is successfully validated using acceleration monitoring data from a large-span arch bridge, achieving an accuracy of over 99%. Furthermore, compared to directly employing a one-dimensional CNN classification model, the approach significantly enhances the model’s perception of local significant disturbances. |
first_indexed | 2024-03-11T11:32:39Z |
format | Article |
id | doaj.art-6b2f5a2069af4fb4aca2c4d46613e659 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T11:32:39Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-6b2f5a2069af4fb4aca2c4d46613e6592023-11-10T14:59:40ZengMDPI AGApplied Sciences2076-34172023-11-0113211204510.3390/app132112045Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature FusionYichao Xu0Yufeng Zhang1Jian Zhang2School of Civil Engineering, Southeast University, Nanjing 210096, ChinaJiangsu Transportation Institute Group, Nanjing 211112, ChinaSchool of Civil Engineering, Southeast University, Nanjing 210096, ChinaOver the past few decades, rapid economic development has led to the establishment of numerous monitoring systems, resulting in the accumulation of vast amounts of monitoring data. Among these data, dynamic acceleration data stand out prominently. However, the quality of collected acceleration data is often compromised due to factors such as challenging operational environments and sensor malfunctions. This severely hampers the value extracted from the data. Although manual identification and classification of data anomalies are more reliable, they are time consuming and labor intensive. To address the challenge of identifying and classifying anomalies in massive acceleration data, this paper proposes a two-stage model for intelligent data cleaning. Firstly, raw acceleration data are transformed into IPDF and PSD features, and a one-dimensional convolutional neural network is trained to preliminarily identify and classify acceleration data anomalies. Subsequently, the RPV indicator is extracted from the original data of the normal and outlier categories to achieve precise classification based on threshold values. The proposed method is successfully validated using acceleration monitoring data from a large-span arch bridge, achieving an accuracy of over 99%. Furthermore, compared to directly employing a one-dimensional CNN classification model, the approach significantly enhances the model’s perception of local significant disturbances.https://www.mdpi.com/2076-3417/13/21/12045bridge structural health monitoringdata cleaningone-dimensional convolutional neutral networktwo-stage classification model |
spellingShingle | Yichao Xu Yufeng Zhang Jian Zhang Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion Applied Sciences bridge structural health monitoring data cleaning one-dimensional convolutional neutral network two-stage classification model |
title | Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion |
title_full | Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion |
title_fullStr | Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion |
title_full_unstemmed | Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion |
title_short | Bridge Acceleration Data Cleaning Based on Two-Stage Classification Model with Multiple Feature Fusion |
title_sort | bridge acceleration data cleaning based on two stage classification model with multiple feature fusion |
topic | bridge structural health monitoring data cleaning one-dimensional convolutional neutral network two-stage classification model |
url | https://www.mdpi.com/2076-3417/13/21/12045 |
work_keys_str_mv | AT yichaoxu bridgeaccelerationdatacleaningbasedontwostageclassificationmodelwithmultiplefeaturefusion AT yufengzhang bridgeaccelerationdatacleaningbasedontwostageclassificationmodelwithmultiplefeaturefusion AT jianzhang bridgeaccelerationdatacleaningbasedontwostageclassificationmodelwithmultiplefeaturefusion |