The application of statistical pattern recognition methods for damage detection to field data

Cheung, Allen; Cabrera, Carlos; Sarabandi, Pooya; Nair, K. Krishnan; Kiremidjian, Anne S.; Wenzel, Helmut

doi:10.1088/0964-1726/17/6/065023

Cited by 49 publications

(26 citation statements)

References 9 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus a statistical analysis is needed to consider these various uncertainties. Since outlier analysis have been demonstrated as a robust unsupervised learning pattern recognition tool for damage detection [40][41][42][43][44], it is employed in this study to analyze the WPT features obtained from the response guided wave signals under different fatigue states.…”

Section: Statistical Multivariate Outlier Analysismentioning

confidence: 99%

Guided Wave-Based Monitoring of Evolution of Fatigue Damage in Glass Fiber/Epoxy Composites

Yan

Tang

2019

Applied Sciences

View full text Add to dashboard Cite

This paper presents an experimental study on detecting and monitoring of evolution of fatigue damage in composites under cyclic loads by using guided waves. Composite specimens fabricated by glass fiber/epoxy laminates and surface mounted with piezoelectric wafers are fatigued under tension–tension loads. A laser extensometer is used to obtain the degradation of longitudinal stiffness of the specimens under fatigue states to reflect the accumulation of internal fatigue damage. Meanwhile, at different fatigue cycles, one wafer acts as actuator to excite diagnostic guided waves, and the other acts as sensor to receive corresponding response waves. These guided wave signals are then processed by wavelet packet transform to extract characteristic features of energies in multiple frequency bands. A statistical multivariate outlier analysis is then performed to determine the existence of fatigue damage and to characterize their evolution using Mahalanobis squared distance. Experimental results have demonstrated the potential applicability and effectiveness of guided waves for continuous monitoring of fatigue damage in composite structures.

show abstract

Section: Statistical Multivariate Outlier Analysismentioning

confidence: 99%

Guided Wave-Based Monitoring of Evolution of Fatigue Damage in Glass Fiber/Epoxy Composites

Yan

Tang

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Cremona 7 have used supervised learning methods like Bayesian decision tree and Support-vector machine to discriminate structural features. Cheung 8 have used auto-regressive (AR) coefficients as the DSF, and supervised form of Mahalanobis distance to quantify the damage extent.…”

Section: Relevant Literature On Discriminant Analysis In Shmmentioning

confidence: 99%

Regularized discriminant analysis for multi-sensor decision fusion and damage detection with Lamb waves

et al. 2016

View full text Add to dashboard Cite

In this study we propose a regularized linear discriminant analysis approach for damage detection which does not require an intermediate feature extraction step and therefore more efficient in handling data with highdimensionality. A robust discriminant model is obtained by shrinking of the covariance matrix to a diagonal matrix and thresholding redundant predictors without hurting the predictive power of the model. The shrinking and threshold parameters of the discriminant function (decision boundary) are estimated to minimize the classification error. Furthermore, it is shown how the damage classification achieved by the proposed method can be extended to multiple sensors by following a Bayesian decision-fusion formulation. The detection probability of each sensor is used as a prior condition to estimate the posterior detection probability of the entire network and the posterior detection probability is used as a quantitative basis to make the final decision about the damage.

show abstract

“…After obtaining the vibration data under the white noise excitation and before applying any AR model, these data are normalized according to Eqn (9) [5,6,24] to eliminate amplitude differences because of various environmental and operational conditions at sensor locations.…”

Section: Drop Weight Excitation Source and Ar Modelsmentioning

confidence: 99%

Full-scale bridge damage identification using time series analysis of a dense array of geophones excited by drop weight

Farahani

Penumadu

2015

Struct. Control Health Monit.

View full text Add to dashboard Cite

SUMMARYThis paper presents a simple and inexpensive technique for damage identification of bridges using drop weight vibration data of bridges recorded by an array of geophones, highly sensitive sensors to record vibration, and time series analysis. The dynamic response of bridges obtained using drop weight as an excitation source is convolved with white noise to create suitable input for autoregressive (AR) models. A two-stage prediction model, combined AR and autoregressive with exogenous input (ARX), is employed to obtain a damage-sensitive feature. An outlier analysis method is developed based on the Monte Carlo simulation to identify the existence of damage. The proposed technique is verified using unique vibration data of two full-scale steel-girder bridges located on I-40 through downtown Knoxville, Tennessee, and subjected to progressive damage scenarios induced to steel girders. The results of the analysis for the vertical vibration data of the test bridges indicate that the proposed technique is able to detect the damage induced on the real bridge girders consistently even when the damage level is small and damage is located near a support; however, damage is not well localized or quantified in these two highly redundant bridges.

show abstract

The application of statistical pattern recognition methods for damage detection to field data

Cited by 49 publications

References 9 publications

Guided Wave-Based Monitoring of Evolution of Fatigue Damage in Glass Fiber/Epoxy Composites

Guided Wave-Based Monitoring of Evolution of Fatigue Damage in Glass Fiber/Epoxy Composites

Regularized discriminant analysis for multi-sensor decision fusion and damage detection with Lamb waves

Full-scale bridge damage identification using time series analysis of a dense array of geophones excited by drop weight

Contact Info

Product

Resources

About