A numerical study on multi‐site damage identification: A data‐driven method via constrained independent component analysis

Zhang, Zhiming; Sun, Cai

doi:10.1002/stc.2583

Cited by 10 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regression models [28], blind source separation techniques [29], the Mahalanobis squared distance [30,31], principal component analysis (PCA), and factor analysis have been implemented to treat environmental and operational effects [32]. Extensive works on damage identification, modeling approaches, and EOF treatment may be found in [33][34][35][36][37][38][39].…”

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

“…19,20 Thanks to the recent progress in machine learning techniques, they have been frequently employed on SHM data of bridges. [21][22][23][24] The state-of-the-art algorithms include artificial neural networks (ANNs), 25,26 independent component analysis, 27 cluster analysis, 28,29 support vector machines (SVMs), 30,31 transfer learning, 32 and ensemble learning methods, 33 which have been proved to be accurate and efficient. Particularly, Lu et al 34 developed a stochastic fatigue truck-load model for investigating fatigue reliability of welded steel bridge decks.…”

Section: Introductionmentioning

confidence: 99%

Data‐driven prediction and interpretation of fatigue damage in a road‐rail suspension bridge considering multiple loads

Sun

Santos

Caetano

2022

Structural Contr & Hlth

View full text Add to dashboard Cite

Summary In long‐span suspension bridges, fatigue is a significant concern for steel members as they are continuously under multiple effects such as wind, temperature, and traffic loads. Therefore, it is important to quantify the fatigue damage at critical details for effective maintenance countermeasures. This paper proposes an ensemble machine‐learning‐based method with physical interpretation, which predicts fatigue damage with monitored parameters of temperature, wind, train, and roadway loads. Interpretation of the machine learning model is achieved regarding the different contributions of the monitored parameters to the fatigue damage. Datasets from the structural health monitoring (SHM) system of a long‐span rail‐road suspension bridge are utilized to verify the proposed method. They are divided into 80% of training datasets and 20% of testing datasets. The ensemble machine learning model is established with Gradient Boosting Regression Tree (GBRT), and the fatigue damage for top chords on the upstream and downstream sides is predicted. The results are compared with other state‐of‐the‐art machine learning algorithms, namely, artificial neural network (ANN), support vector machine (SVM), decision tree (DT), and random forest (RF). It is found that GBRT demonstrates the highest accuracy for fatigue damage prediction with R2 of 0.9016 and 0.9180, respectively. Furthermore, interpretation of the results is carried out with feature importance estimates (FIE) and individual conditional expectation (ICE). FIE results indicate that the train load has the most significant influence on fatigue damage of the suspension bridge, and ICE results can provide insights on better maintenance plans to avoid severe fatigue damage.

show abstract

“…SHM is mainly classified into two categories: data-driven methods based on statistical pattern recognition and physics-based methods based on finite element model updating [4]. Compared with physics-based methods building a numerical model, data-driven methods have many advantages over physics-based methods while identifying structural damage under load and environmental influence such as temperature and moisture effect [5]. Thus, many researchers have focused on data-driven methods for structural damage detection to protect the safety of civil structures.…”

Section: Introductionmentioning

confidence: 99%

A Framework of Structural Damage Detection for Civil Structures Using Fast Fourier Transform and Deep Convolutional Neural Networks

Chen

Liu

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

In the field of structural health monitoring (SHM), vibration-based structural damage detection is an important technology to ensure the safety of civil structures. By taking advantage of deep learning, this study introduces a data-driven structural damage detection method that combines deep convolutional neural networks (DCNN) and fast Fourier transform (FFT). In this method, the structural vibration data are fed into FFT method to acquire frequency information reflecting structural conditions. Then, DCNN is utilized to automatically extract damage features from frequency information to identify structural damage conditions. To verify the effectiveness of the proposed method, FFT-DCNN is carried out on a three-story building structure and ASCE benchmark. The experimental result shows that the proposed method achieves high accuracy, compared with classic machine-learning algorithms such as support vector machine (SVM), random forest (RF), K-Nearest Neighbor (KNN), and eXtreme Gradient boosting (xgboost).

show abstract

A numerical study on multi‐site damage identification: A data‐driven method via constrained independent component analysis

Cited by 10 publications

References 38 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

Data‐driven prediction and interpretation of fatigue damage in a road‐rail suspension bridge considering multiple loads

A Framework of Structural Damage Detection for Civil Structures Using Fast Fourier Transform and Deep Convolutional Neural Networks

Contact Info

Product

Resources

About