A Deep Learning-Based Framework for Damage Detection With Time Series

Yang, Qun; Shen, Dejian; Wei, Du; Li, Weijun

doi:10.1109/access.2021.3076436

Cited by 4 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm is verified with the vibration responses of two beam structures and a long-span cable-stayed bridge and can reliably detect and quantify various damage scenarios. Yang et al [18] proposed a novel damage recognition network designed as an encoder-decoder-encoder combination for detecting damage in a building. They trained the model using the Fourier spectra of acceleration signals in the undamaged state to recognize the pattern that is related to damage.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Damage Representations with Sequence-to-Sequence Models

Yang

Shen

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Natural hazards have caused damages to structures and economic losses worldwide. Post-hazard responses require accurate and fast damage detection and assessment. In many studies, the development of data-driven damage detection within the research community of structural health monitoring has emerged due to the advances in deep learning models. Most data-driven models for damage detection focus on classifying different damage states and hence damage states cannot be effectively quantified. To address such a deficiency in data-driven damage detection, we propose a sequence-to-sequence (Seq2Seq) model to quantify a probability of damage. The model was trained to learn damage representations with only undamaged signals and then quantify the probability of damage by feeding damaged signals into models. We tested the validity of our proposed Seq2Seq model with a signal dataset which was collected from a two-story timber building subjected to shake table tests. Our results show that our Seq2Seq model has a strong capability of distinguishing damage representations and quantifying the probability of damage in terms of highlighting the regions of interest.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We trained a Seq2Seq model with only undamaged signals to learn their representations and hence the model's reconstruction results are supposed to deviate when inputting damaged signals. The probability of damage according to the extent of deviation is defined as suggested in [18]:…”

Section: Probability Of Damagementioning

confidence: 99%

Learning Damage Representations with Sequence-to-Sequence Models

Yang

Shen

2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Damage assessment based on sensor data, such as acceleration responses, may be improved with the use of vibration-based models, which give potential solutions [2]. These models account for shifts in vibration characteristics that occur due to damage and identify aspects in vibration data that are related to the occurrence of damage.…”

Section: Introductionmentioning

confidence: 99%

Structural damage detection pre-training in time series

Li,

Yang

2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

Natural disasters have incurred damages and economic losses in many countries. Post-disaster response requires an efficient and prompt damage detection. Although the deep learning-based approach has been emerged as an alternative to the conventional structural health monitoring, the understanding of representations for damage detection is lacking. To this end, we design a pre-training task based on a Seq2Seq model to learn high-quality representations by reconstructing acceleration accelerations. We evaluate the Seq2Seq model using a real-world dataset of shake table tests on a 2-story timber building. It is found that the Seq2Seq model outperforms the baseline in terms of reconstruction error and the capability of distinguishing representations for different damage states.

show abstract

“…In the literature, a Fourier transform-based denoising approach has been employed to eliminate noisy components in stock market index data, particularly those that adversely impact the model’s performance in predicting closing prices for the S&P500, KOSPI, and SSE indices ( Song, Baek & Kim, 2021 ). In addition, the Fourier transform has also been used to eliminate the noise in the signals collected from the sensors for the damage detection module ( Yang et al, 2021 ). In these studies, various deep-learning approaches were employed to develop models on denoised data.…”

Section: Introductionmentioning

confidence: 99%

A new denoising approach based on mode decomposition applied to the stock market time series: 2LE-CEEMDAN

Akşehir,

Kılıç

2024

PeerJ Computer Science

View full text Add to dashboard Cite

Time series, including noise, non-linearity, and non-stationary properties, are frequently used in prediction problems. Due to these inherent characteristics of time series data, forecasting based on this data type is a highly challenging problem. In many studies within the literature, high-frequency components are commonly excluded from time series data. However, these high-frequency components can contain valuable information, and their removal may adversely impact the prediction performance of models. In this study, a novel method called Two-Level Entropy Ratio-Based Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (2LE-CEEMDAN) is proposed for the first time to effectively denoise time series data. Financial time series with high noise levels are utilized to validate the effectiveness of the proposed method. The 2LE-CEEMDAN-LSTM-SVR model is introduced to predict the next day’s closing value of stock market indices within the scope of financial time series. This model comprises two main components: denoising and forecasting. In the denoising section, the proposed 2LE-CEEMDAN method eliminates noise in financial time series, resulting in denoised intrinsic mode functions (IMFs). In the forecasting part, the next-day value of the indices is estimated by training on the denoised IMFs obtained. Two different artificial intelligence methods, Long Short-Term Memory (LSTM) and Support Vector Regression (SVR), are utilized during the training process. The IMF, characterized by more linear characteristics than the denoised IMFs, is trained using the SVR, while the others are trained using the LSTM method. The final prediction result of the 2LE-CEEMDAN-LSTM-SVR model is obtained by integrating the prediction results of each IMF. Experimental results demonstrate that the proposed 2LE-CEEMDAN denoising method positively influences the model’s prediction performance, and the 2LE-CEEMDAN-LSTM-SVR model outperforms other prediction models in the existing literature.

show abstract

A Deep Learning-Based Framework for Damage Detection With Time Series

Cited by 4 publications

References 32 publications

Learning Damage Representations with Sequence-to-Sequence Models

Learning Damage Representations with Sequence-to-Sequence Models

Structural damage detection pre-training in time series

A new denoising approach based on mode decomposition applied to the stock market time series: 2LE-CEEMDAN

Contact Info

Product

Resources

About