Structural Damage Identification Based on Convolutional Neural Network Group Considering the Sensor Fault

Luo, Yongpeng; Wang, Linkun; Guo, Xu; Zheng, Jinlin; Liao, Fei-Yu; Guo, Zi‐Xiong

doi:10.1007/s12205-023-0683-y

Cited by 2 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even the 3DS-CNN trained with only one channel acceleration signal can obtain a high ξ ′ > 95%, which reflects the strong learning ability of 3DS-CNN for catching structural damage features just using single channel data. In this case, the sensor position has little influence on SDI, which is consistent with the literature [34].…”

Section: Influence Of Sensor Placement On Case Studysupporting

confidence: 92%

“…At present, there is little research on the influence of sensor placement in deep learning SDI. The literature [34] discussed the impact of single sensor location on SDI.…”

Section: Influence Of Sensor Placement On Sdimentioning

confidence: 99%

“…Luo et al [34] used the Gramian angular field method to transform the single sensor data into 2-dimensional data, and realized the SDI based on a shallow CNN, but did not discuss the impact of the number and location of sensors on the results. Although the influence of the number and location of sensors on SDI has been studied, the analysis of sensor combinations is relatively scarce.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

Yang

Peng

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the application of data driven Structural Damage Identification (SDI) based on supervised deep learning technology, valid data demarcation is the foundation; a convolutional neural network model with learning ability and capability of processing rich signal information is the core. Based on this understanding, this work makes three contributions: Firstly, the structural damage location and severity are jointly demarcated, and the SDI problem is transformed into a multi-classification task. Secondly, a 3D Signal processing Convolutional Neural Networks (3DS-CNN) is designed with an attempt to identify the complex and slight damages using the most basic network structure. Thirdly, a “Major and Subsidiary” Data Construction (MSDC) method integrating the key Intrinsic Mode Function (IMF) is proposed to construct 3D data. Then the proposed schemes are verified by two different structures. The results show that the 3DS-CNN has excellent damage identification ability for small-size data with noise pollution. MSDC method can enrich the feature information of the damage signals and help the network with deep feature excavation, even if the vibration signals are heavily polluted. Going one step further, the impact of sensor placement is discussed, and it is found that when external excitation is obvious, better SDI accuracy can be achieved even using a single sensor signal with slight noise. When the noise interference is obvious, the generalization ability and noise robustness of the network can be enhanced by optimizing sensor placement. In this case, the sensor placement criteria and the sensitive nodes of the structure should be comprehensively and carefully considered to avoid mutual “coupling” interference of data between sensors.

show abstract

Section: Influence Of Sensor Placement On Case Studysupporting

confidence: 92%

“…At present, there is little research on the influence of sensor placement in deep learning SDI. The literature [34] discussed the impact of single sensor location on SDI.…”

Section: Influence Of Sensor Placement On Sdimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

Yang

Peng

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…A CNN-based 3-channel imagery approach has been reported by Shajihan et al (2022) for sensor fault identification, comprising time histories, histograms, and probability density function representations of sensor data. Luo et al (2023) have reported a structural damage identification approach considering sensor faults aiming to identify types of structural damage and sensor faults occurring separately or simultaneously. Mou et al (2022) have introduced a 2D CNN-based approach for fault identification in strain gauges for offshore SHM, considering bias, gain, and complete failure.…”

Section: Introductionmentioning

confidence: 99%

“…SHM relies on sensors operating continuously over long periods of time to collect sensor data used for structural assessment (Dong and Catbas 2021). Exposure to aging, degradation, and harsh environmental conditions may lead to sensor faults in SHM systems (Luo et al 2023). Undiagnosed sensor faults may cause system malfunctions and even system failures, highlighting the importance of fault diagnosis (FD) in SHM systems, which includes fault detection, isolation, identification, and accommodation (Patton 1990).…”

Section: Introductionmentioning

confidence: 99%

Identification of combined sensor faults in structural health monitoring systems

Al-Nasser,

Al-Zuriqat,

Dragos

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

Fault diagnosis (FD), comprising fault detection, isolation, identification and accommodation, enables structural health monitoring (SHM) systems to operate reliably by allowing timely rectification of sensor faults that may cause data corruption or loss. Although sensor fault identification is scarce in FD of SHM systems, recent FD methods have included fault identification assuming one sensor fault at a time. However, real-world SHM systems may include combined faults that simultaneously affect individual sensors. This paper presents a methodology for identifying combined sensor faults occurring simultaneously in individual sensors. To improve the quality of FD and comprehend the causes leading to sensor faults, the identification of combined sensor faults (ICSF) methodology is based on a formal classification of the types of combined sensor faults. Specifically, the ICSF methodology builds upon long short-term memory networks, i.e. a type of recurrent neural networks, used for classifying “sequences”, such as sets of acceleration measurements. The ICSF methodology is validated using real-world acceleration measurements from an SHM system installed on a bridge, demonstrating the capability of the long short-term memory networks in identifying combined sensor faults, thus improving the quality of FD in SHM systems. Future research aims to decentralize the ICSF methodology and to reformulate the classification models in a mathematical form with an explanation interface, using explainable artificial intelligence, for increased transparency.

show abstract

Structural Damage Identification Based on Convolutional Neural Network Group Considering the Sensor Fault

Cited by 2 publications

References 31 publications

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

A new convolutional neural network-based framework and data construction method for structural damage identification considering sensor placement

Identification of combined sensor faults in structural health monitoring systems

Contact Info

Product

Resources

About