A probabilistic crack size quantification method using in-situ Lamb wave test and Bayesian updating

et al. 2020

Sensors

Lamb wave approaches have been accepted as efficiently non-destructive evaluations in structural health monitoring for identifying damage in different states. Despite significant efforts in signal process of Lamb waves, physics-based prediction is still a big challenge due to complexity nature of the Lamb wave when it propagates, scatters and disperses. Machine learning in recent years has created transformative opportunities for accelerating knowledge discovery and accurately disseminating information where conventional Lamb wave approaches cannot work. Therefore, the learning framework was proposed with a workflow from dataset generation, to sensitive feature extraction, to prediction model for lamb-wave-based damage detection. A total of 17 damage states in terms of different damage type, sizes and orientations were designed to train the feature extraction and sensitive feature selection. A machine learning method, support vector machine (SVM), was employed for the learning model. A grid searching (GS) technique was adopted to optimize the parameters of the SVM model. The results show that the machine learning-enriched Lamb wave-based damage detection method is an efficient and accuracy wave to identify the damage severity and orientation. Results demonstrated that different features generated from different domains had certain levels of sensitivity to damage, while the feature selection method revealed that time-frequency features and wavelet coefficients exhibited the highest damage-sensitivity. These features were also much more robust to noise. With increase of noise, the accuracy of the classification dramatically dropped.

Section: Effectiveness Of Damage Orientation To the Robustness Of Thementioning

confidence: 99%

Machine Learning-Enriched Lamb Wave Approaches for Automated Damage Detection

Zhang

Pan

et al. 2020

Sensors

“…The probability of detection (POD) of the damage identification method can be quantified using classical linear models [10,20,45]. Denote the reported stiffness multiplier asθ and the actual stiffness multiplier as θ.…”

Section: Probability Of Detectionmentioning

confidence: 99%

“…Several non-destructive evaluation methods such as ultrasound inspection [7][8][9][10][11][12][13], eddy-current testing [14,15], and Lamb wave-based methods [16][17][18][19][20][21] can effectively identify local damages in a component. To identify the component damage on a global basis, capturing the changes in vibration characteristics of the entire structure is one of the few methods that can be applied in practice [22,23].…”

Section: Introductionmentioning

confidence: 99%

A Probabilistic Damage Identification Method for Shear Structure Components Based on Cross-Entropy Optimizations

Guan

2017

Entropy

Self Cite

A probabilistic damage identification method for shear structure components is presented. The method uses the extracted modal frequencies from the measured dynamical responses in conjunction with a representative finite element model. The damage of each component is modeled using a stiffness multiplier in the finite element model. By coupling the extracted features and the probabilistic structural model, the damage identification problem is recast to an equivalent optimization problem, which is iteratively solved using the cross-entropy optimization technique. An application example is used to demonstrate the proposed method and validate its effectiveness. Influencing factors such as the location of damaged components, measurement location, measurement noise level, and damage severity are studied. The detection reliability under different measurement noise levels is also discussed in detail.

“…Bayes’ theorem has been extensively used in various structural health monitoring applications [54,55,56,57,58]. Bayes’ theorem combines the information of the prior guess with the belief on the current system response through a so-called likelihood function to update the distribution of the parameters of interest [59].…”

Section: Probabilistic Fatigue Crack Sizing Using Experimental Datamentioning

confidence: 99%

Probabilistic Model Updating for Sizing of Hole-Edge Crack Using Fiber Bragg Grating Sensors and the High-Order Extended Finite Element Method

Yang

et al. 2016

Sensors

Self Cite

This paper presents a novel framework for probabilistic crack size quantification using fiber Bragg grating (FBG) sensors. The key idea is to use a high-order extended finite element method (XFEM) together with a transfer (T)-matrix method to analyze the reflection intensity spectra of FBG sensors, for various crack sizes. Compared with the standard FEM, the XFEM offers two superior capabilities: (i) a more accurate representation of fields in the vicinity of the crack tip singularity and (ii) alleviation of the need for costly re-meshing as the crack size changes. Apart from the classical four-term asymptotic enrichment functions in XFEM, we also propose to incorporate higher-order functions, aiming to further improve the accuracy of strain fields upon which the reflection intensity spectra are based. The wavelength of the reflection intensity spectra is extracted as a damage sensitive quantity, and a baseline model with five parameters is established to quantify its correlation with the crack size. In order to test the feasibility of the predictive model, we design FBG sensor-based experiments to detect fatigue crack growth in structures. Furthermore, a Bayesian method is proposed to update the parameters of the baseline model using only a few available experimental data points (wavelength versus crack size) measured by one of the FBG sensors and an optical microscope, respectively. Given the remaining data points of wavelengths, even measured by FBG sensors at different positions, the updated model is shown to give crack size predictions that match well with the experimental observations.