A Review on Technological Advancements in the Field of Data Driven Structural Health Monitoring

Katam, Rakesh; Kalapatapu, Prafulla; Pasupuleti, Venkata Dilip Kumar

doi:10.1007/978-3-031-07322-9_38

Cited by 5 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the model-based approach, there is no need for a real-structure-representing simulated model. Instead, datasets collected from the target structure using sensors are processed to identify trends, recognize patterns, and observe statistical measurements [11][12][13][14][15]. These extracted features will be used to train machine learning models and make acceptable predictions.…”

Section: Introduction and State Of The Artmentioning

confidence: 99%

Damage Detection with Data-Driven Machine Learning Models on an Experimental Structure

Alemu,

Lahmer,

Walther

2024

Eng

View full text Add to dashboard Cite

Various techniques have been employed to detect damage in civil engineering structures. Apart from the model-based approach, which demands the frequent updating of its corresponding finite element method (FEM)-built model, data-driven methods have gained prominence. Environmental and operational effects significantly affect damage detection due to the presence of damage-related trends in their analyses. Time-domain approaches such as autoregression and metrics such as the Mahalanobis squared distance have been utilized to mitigate these effects. In the realm of machine learning (ML) models, their effectiveness relies heavily on the type and quality of the extracted features, making this aspect a focal point of attention. The objective of this work is therefore to deploy and observe potential feature extraction approaches used as input in training fully data-driven damage detection machine learning models. The most damage-sensitive segment (MDSS) feature extraction technique, which potentially treats signals under multiple conditions, is also proposed and deployed. It identifies potential segments for each feature coefficient under a defined criterion. Therefore, 680 signals, each consisting of 8192 data points, are recorded using accelerometer sensors at the Los Alamos National Laboratory in the USA. The data are obtained from a three-story 3D building frame and are utilized in this research for a mainly data-driven damage detection task. Three approaches are implemented to replace four missing signals with the generated ones. In this paper, multiple fast Fourier and wavelet-transformed features are employed to evaluate their performance. Most importantly, a power spectral density (PSD)-based feature extraction approach that considers the maximum variability criterion to identify the most sensitive segments is developed and implemented. The performance of the MDSS selection technique, proposed in this work, surpasses that of all 18 trained neural networks (NN) and recurrent neural network (RNN) models, achieving more than 80% prediction accuracy on an unseen prediction dataset. It also significantly reduces the feature dimension. Furthermore, a sensitivity analysis is conducted on signal segmentation, overlapping, the treatment of a training dataset imbalance, and principal component analysis (PCA) implementation across various combinations of features. Binary and multiclass classification models are employed to primarily detect and additionally locate and identify the severity class of the damage. The collaborative approach of feature extraction and machine learning models effectively addresses the impact of environmental and operational effects (EOFs), suppressing their influences on the damage detection process.

show abstract

Section: Introduction and State Of The Artmentioning

confidence: 99%

Damage Detection with Data-Driven Machine Learning Models on an Experimental Structure

Alemu,

Lahmer,

Walther

2024

Eng

View full text Add to dashboard Cite

show abstract

“…Focusing on direct approaches, a further classification can be done depending on the frequency range of interest, distinguishing between static and quasi-static analysis (low frequency range) and dynamic analysis (high frequency range). With regards to the data analysis framework, instead, a distinction can be made between modelbased approaches (e.g., [6]) and data-driven ones [7]. While the second allows the detection of anomalies in the bridge behaviour without the need of a structural model, the first allows for a physical interpretation of the anomalies identified by the monitoring system, but it requires a proper estimation of model parameters and model validation.…”

Section: Introductionmentioning

confidence: 99%

Structural Health Monitoring of a steel truss railway bridge studying its low frequency response

Radicioni,

Bernardini,

Bono

et al. 2023

ce papers

View full text Add to dashboard Cite

In the framework of direct Structural Health Monitoring approaches, this paper presents a low frequency range analysis performed on a steel truss bridge designed in 1946 and built up in Northern Italy. The bridge is instrumented with a permanent structural health monitoring system, that guarantees a continuous flux of data and information from a heterogeneous set of sensors. In this analysis, static and quasistatic bridge responses are considered. These experimental data are merged with the analogous outputs obtained from numerical simulations, performed on FE models representative of the actual bridge, with the purpose of identifying damage‐sensitive indexes. Simulations are performed considering the healthy structure and modelling different damage scenarios. The static analysis consists in the construction of a regressive model able to estimate sensor output responses starting from environmental measurements, with the primary purpose to reduce the effect of temperature over measured static response. This procedure allows to relate the damages simulated by means of a numerical model with the real data, so that the monitoring rules can effectively defined.

show abstract

Digital twin based lifecycle modeling and state evaluation of cable-stayed bridges

Guo

Fang

2023

Engineering with Computers

View full text Add to dashboard Cite

A Review on Technological Advancements in the Field of Data Driven Structural Health Monitoring

Cited by 5 publications

References 40 publications

Damage Detection with Data-Driven Machine Learning Models on an Experimental Structure

Damage Detection with Data-Driven Machine Learning Models on an Experimental Structure

Structural Health Monitoring of a steel truss railway bridge studying its low frequency response

Digital twin based lifecycle modeling and state evaluation of cable-stayed bridges

Contact Info

Product

Resources

About