Lamb Wave Damage Quantification Using GA-Based LS-SVM

Sun, Fuqiang; Wang, Ning; He, Jingjing; Guan, Xuefei; Yang, Jann N.

doi:10.3390/ma10060648

Cited by 36 publications

(19 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the uniform initial values of the weights and posterior probabilities, the mean vectors m jk and covariance matrices S jk of UIGMM are calculated using equations ( 13) and (14), respectively. The weights and posterior probabilities are then used to update the weights and posterior probabilities according to equations (15) and (16).…”

Section: Gmm Clustering Distribution Of the Observation Can Be Expressed Asmentioning

confidence: 99%

“…Since guided wave (GW)-based SHM method has been proved to be a promising method which is sensitive to small damage and has capability for a relative large area monitoring, a lot of literatures focus on research regarding this method, including environmental parameter compensation methods, 3,4 baseline signal dependency reduction methods, 5,6 data normalization methods 7 and probabilistic and statistical models. [8][9][10][11][12][13][14][15] Some statistical approaches published include statistical process control, 9,10 outlier analysis, 11,12 artificial neural networks, 13 support vector machines (SVM) 14 and Gaussian mixture models (GMM). 15 Though these methods have some progress, most of them only deal with one environment factor, usually temperature, and the structures applied only are simple structure styles.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A uniform initialization Gaussian mixture model–based guided wave–hidden Markov model with stable damage evaluation performance

Yuan

Zhang

Chen

2018

Structural Health Monitoring

View full text Add to dashboard Cite

During practical applications, the time-varying service conditions usually lead to difficulties in properly interpreting structural health monitoring signals. The guided wave–hidden Markov model–based damage evaluation method is a promising approach to address the uncertainties caused by the time-varying service condition. However, researches that have been performed to date are not comprehensive. Most of these research studies did not introduce serious time-varying factors, such as those that exist in reality, and hidden Markov model was applied directly without deep consideration of the performance improvement of hidden Markov model itself. In this article, the training stability problem when constructing the guided wave–hidden Markov model initialized by usually adopted k-means clustering method and its influence to damage evaluation were researched first by applying it to fatigue crack propagation evaluation of an attachment lug. After illustrating the problem of stability induced by k-means clustering, a novel uniform initialization Gaussian mixture model–based guided wave–hidden Markov model was proposed that provides steady and reliable construction of the guided wave–hidden Markov model. The advantage of the proposed method is demonstrated by lug fatigue crack propagation evaluation experiments.

show abstract

Section: Gmm Clustering Distribution Of the Observation Can Be Expressed Asmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A uniform initialization Gaussian mixture model–based guided wave–hidden Markov model with stable damage evaluation performance

Yuan

Zhang

Chen

2018

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…De [14] detected the damage location and degree of composite plates by using the combination of an artificial neural network and the method of probabilistic ellipse. Sun [15] proposed a method of damage quantification using Lamb wave based on least squares support vector machine and a genetic algorithm. Yet, this technique with pattern recognition as the basis is in the need of a large amount of sample data, which is regarded as a significant factor that restricts its rapid development.…”

Section: Introductionmentioning

confidence: 99%

Damage Localization of Composites Based on Difference Signal and Lamb Wave Tomography

Jiang

Liang

et al. 2020

Materials

View full text Add to dashboard Cite

In order to deal with the problem of composite damage location, an imaging technique based on differential signal and Lamb wave tomography was proposed. Firstly, the feasibility of the technique put forward was verified by simulation. In this process, the composite model was regularly set down by the circular sensor array, with each sensor acting as an actuator in sequence to generate Lamb waves. Apart from that, other sensors were used to collect response signals. With regard to the damage factor, it was mainly determined by the difference between the damage signal and the non-damage signal. The probabilistic imaging algorithm was employed to carry out damage location imaging. Then, experiments were carried out so as to study the selected composite plate. Finally, the tentative outcomes have illustrated that the maximum error of damage imaging position was 7.07 mm. The relative error was 1.6%. In addition, the method has the characteristics of simple calculation and high imaging efficiency. Therefore, it has large technical potential and wide applications in the damage location and damage recognition for composite material.

show abstract

“…Agarwal 24 employed SVM and artificial neural network to recognize the damage by combining the simulation database and MP algorithm. Sun 25 proposed an SVM‐based quantitative detection method to recognize the crack length. Fendzi 26 improved a damage location method of composite plate based on baseline signal stretch, which can compensate for the signal change caused by temperature change.…”

Section: Introductionmentioning

confidence: 99%

Deep‐learning‐based guided wave detection for liquid‐level state in porcelain bushing type terminal

Hong

Zhang

Liu

et al. 2020

Struct Control Health Monit

View full text Add to dashboard Cite

The structural security of civil energy equipment is significant for the steady operation of power supply system, and porcelain bushing type terminal is a typical energy equipment that needs long-term monitoring. As a nondestructive structural health monitoring method, ultrasonic guided wave (UGW) technology is extremely suitable for state detection of energy equipment. However, most current UGW methods still need to manually select the guided wave features, which rely heavily on the guidance of expert experience. This article presents a deep-learning method to directly utilize original-guided wave signals to quantitatively detect the liquid-level state. Firstly, the original signals were fed into convolutional autoencoder (CAE) to catch the low-dimension representation and realize the automatic feature extraction. Then, the low-dimension representations were orderly input into the long short-term memory (LSTM) recurrent neural network for liquidlevel regression. In feature extraction step, CAE method can effectively extract the useful features and remove the interference and signal distortion. In regression step, both the accuracy and the robustness of proposed method are better than backpropagation network and convolutional neural network. Experimental results show that proposed CAE-LSTM method can accurately inspect the liquid level by original signals and implement maintenance monitoring.

show abstract

Lamb Wave Damage Quantification Using GA-Based LS-SVM

Cited by 36 publications

References 30 publications

A uniform initialization Gaussian mixture model–based guided wave–hidden Markov model with stable damage evaluation performance

A uniform initialization Gaussian mixture model–based guided wave–hidden Markov model with stable damage evaluation performance

Damage Localization of Composites Based on Difference Signal and Lamb Wave Tomography

Deep‐learning‐based guided wave detection for liquid‐level state in porcelain bushing type terminal

Contact Info

Product

Resources

About