A Deep Learning-Based Method for Automatic Abnormal Data Detection: Case Study for Bridge Structural Health Monitoring
Authors:
- 12 January 2023
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 23 (11)
Abstract
Ideally, the monitoring data collected by the Structural health monitoring (SHM) system should purely reflect the structure status. However, sensors deployed in the field can be very vulnerable to extreme conditions such as heavy rainfall, which results in large quantities of anomalous data and unavoidably leads to the inaccuracy of structural condition assessment and even false alarms. To automatically identify whether the collected data are abnormal or not, a novel deep learning-based data anomaly detection technique combining the time-frequency method and the Convolutional Neural Network (CNN) is proposed in this paper. First, the original time-series data of the SHM system were converted to the red green blue (RGB) images by using the wavelet scalograms. Subsequently, the GoogLeNet deep neural network is applied to construct a classification model by incorporating the generated 2D images. In order to evaluate the performance of the proposed technique, the SHM data (containing seven abnormal patterns) lasting for one month of a long-span cable-stayed bridge were utilized for experimental validation. The results indicate that compared with traditional deep neural network methods, the data anomaly identification accuracy can be improved by using the proposed technique. Different types of data anomaly patterns can be accurately identified, even in the case of small samples. The proposed technique exhibits good accuracy and can be integrated into advanced SHM systems with high fidelity and intelligence.Keywords
Funding Information
- China Postdoctoral Science Foundation (2022M710886)
- 111 Project (D21021)
- Science and Technology Planning Project of Guangzhou (20212200004)
- Science and Technology Plan Project of the Guangzhou Municipal Construction Group Co., Ltd (2021KJ005)
This publication has 35 references indexed in Scilit:
- Development of sensor validation methodologies for structural health monitoring: A comprehensive reviewMeasurement, 2017
- Sensor Fault Diagnosis for Structural Health Monitoring Based on Statistical Hypothesis Test and Missing Variable ApproachJournal of Aerospace Engineering, 2017
- Detection of Shifts in GPS Measurements for a Long-Span Bridge Using CUSUM ChartInternational Journal of Structural Stability and Dynamics, 2016
- Distributed model-based nonlinear sensor fault diagnosis in wireless sensor networksMechanical Systems and Signal Processing, 2016
- Iterative deep learning for image set based face and object recognitionNeurocomputing, 2016
- On robust regression analysis as a means of exploring environmental and operational conditions for SHM dataJournal of Sound and Vibration, 2015
- Decentralized fault detection and isolation in wireless structural health monitoring systems using analytical redundancyAdvances in Engineering Software, 2014
- Identification of multiple damage in beams based on robust curvature mode shapesMechanical Systems and Signal Processing, 2014
- Finite element model updating in structural dynamics by using the response surface methodEngineering Structures, 2010
- Effective Cycle Slip Detection and Identification for High Precision GPS/INS Integrated SystemsJournal of Navigation, 2003