Deterioration and damage identification in building structures using a novel feature selection method

Gharehbaghi, Vahidreza; Farsangi, Ehsan Noroozinejad; Yang, T.Y.; Hajirasouliha, Iman

doi:10.1016/j.istruc.2020.11.040

Cited by 16 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The polynomial order defines the time-series model order, which is an unknown term and is determined through different techniques, namely Akaike's information criterion (AIC), Minimum description length (MDL), Root Mean Squared Error (RMSE), and best model order (BMO) ( 14) (177). Skewness, crest factor, kurtosis analysis, and RMS amplitudes are some of the popular features that apply to time series (178).…”

Section: Time-domainmentioning

confidence: 99%

A Critical Review on Structural Health Monitoring: Definitions, Methods, and Perspectives

Gharehbaghi

Farsangi

Noori

et al. 2021

Arch Computat Methods Eng

Self Cite

View full text Add to dashboard Cite

The benefits of tracking, identifying, measuring features of interest from structure responses have endless applications for saving cost, time and improving safety. To date, structural health monitoring (SHM) has been extensively applied in several fields, such as aerospace, automotive, and mechanical engineering. However, the focus of this paper is to provide a comprehensive upto-date review of civil engineering structures such as buildings, bridges, and other infrastructures. For this reason, this article commences with a concise introduction to the fundamental definitions of SHM. The next section presents the general concepts and factors that determine the best strategy to be employed for SHM. Afterward, a thorough review of the most prevalent anomaly detection approaches, from classic techniques to advanced methods, is presented. Subsequently, some popular benchmarks, including laboratory specimens and real structures for validating the proposed methodologies, are demonstrated and discussed. Finally, the advantages and disadvantages of each method are summarized, which can be helpful in future studies.

show abstract

Section: Time-domainmentioning

confidence: 99%

A Critical Review on Structural Health Monitoring: Definitions, Methods, and Perspectives

Gharehbaghi

Farsangi

Noori

et al. 2021

Arch Computat Methods Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…A detailed review of different vibration-based damage detection (VBDD) techniques based on EMA was conducted in different investigations (Doebling et al ., 1996), (Moaveni et al ., 2010). Researchers used progressive damage analysis through EMA as a tool to analyze the effectiveness of different retrofitting techniques (Prado et al ., 2016; Capozucca and Bossoletti, 2014, 2015; Badri and Moghadam, 2021; Gharehbaghi et al ., 2021). This technique is also finding its way to develop non-destructive tests to know about the current condition of the structures and to predict their remaining useful life.…”

Section: Introductionmentioning

confidence: 99%

Progressive deterioration of reinforced concrete structures: effect on dynamic properties of flexural members

Khan

Farhan

Raza

2023

MMMS

View full text Add to dashboard Cite

PurposeThe main purpose of this study is to examine the damage behavior of flexural members under different loading conditions. The finite element model is proposed for the prediction of modal parameters, damage assessment and damage detection of flexural members. Moreover, the analysis of flexural members has been done for the sensor arrangement to accurately predict the damage parameters without the laborious work of experimentation in the laboratory.Design/methodology/approachBeam-like structures are structures that are subjected to flexural loadings that are involved in almost every type of civil engineering construction like buildings, bridges, etc. Experimental Modal Analysis (EMA) is a popular technique to detect damages in structures without requiring tough and complex methods. Experimental work conducted in this study concludes that a structure experiences high changes in modal properties once when cracking occurs and then at the stage where cracks start at the critical neutral axis. Moreover, among the various modal parameters of the flexural members, natural frequency and mode shapes are the viable parameters for the damage detection.FindingsFor torsional mode, drop in natural frequency is high for higher damages as compared to low levels. This is because of the opening and closing of cracks in modal testing. When damage occurs in the structure, there is a reduction in the magnitude of the FRF plot. The measure of this drop can also lead to damage assessment in addition to damage detection. The natural frequency of the system is the most reliable modal parameter in detecting damages. However, for damage localization, the next step after damage assessment, mode shapes can be more helpful as compared to all other parameters.Originality/valueEffect on Dynamic Properties of Flexural Members during the Progressive Deterioration of Reinforced Concrete Structures is studied.

show abstract

“…In many LSTF tasks, feature extraction methods [27][28][29] have been applied to time series data, which are able to explain sequence relationships and help forecasting models learn the nonlinear characteristics of structural state data. Moreover, extracted features, which reflect the state of the structure to a certain extent, are also widely used in the SHM [30,31], especially the amplitude and phase of data [32,33]. Among them, FFT has been widely recognized for its characteristics of decomposing data to make them stable, fast convergence, and reflecting the trend to a certain extent [29,34].…”

Section: Introductionmentioning

confidence: 99%

Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model

Dan

2023

Applied Sciences

View full text Add to dashboard Cite

Machine learning has been widely applied in structural health monitoring. While most existing methods, which are limited to forecasting structural state evolution of large infrastructures. forecast the structural state in a step-by-step manner, extracting feature of structural state trends and the negative effects of data collection under abnormal conditions are big challenges. To address these issues, a long-term structural state trend forecasting method based on long sequence time-series forecasting (LSTF) with an improved Informer model integrated with Fast Fourier transform (FFT) is proposed, named the FFT–Informer model. In this method, by using FFT, structural state trend features are represented by extracting amplitude and phase of a certain period of data sequence. Structural state trend, a long sequence, can be forecasted in a one-forward operation by the Informer model that can achieve high inference speed and accuracy of prediction based on the Transformer model. Furthermore, a Hampel filter that filters the abnormal deviation of the data sequence is integrated into the Multi-head ProbSparse self-attention in the Informer model to improve forecasting accuracy by reducing the effect of abnormal data points. Experimental results on two classical data sets show that the FFT–Informer model achieves high and stable accuracy and outperforms the comparative models in forecasting accuracy. It indicates that this model can effectively forecast the long-term state trend change of a structure and is proposed to be applied to structural state trend forecasting and early damage warning.

show abstract

Deterioration and damage identification in building structures using a novel feature selection method

Cited by 16 publications

References 19 publications

A Critical Review on Structural Health Monitoring: Definitions, Methods, and Perspectives

A Critical Review on Structural Health Monitoring: Definitions, Methods, and Perspectives

Progressive deterioration of reinforced concrete structures: effect on dynamic properties of flexural members

Long-Term Structural State Trend Forecasting Based on an FFT–Informer Model

Contact Info

Product

Resources

About