Neural Network Approach to Locating Acoustic Emission Sources in Non-Destructive Evaluation

Spall, James C.; Maryak, J.L.; Asher, M.S.

doi:10.1006/jsvi.1997.1355

Cited by 7 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spall et al represented this problem with Eq. (3) which is the effect of all acoustic emission events in the system on the output of a sensor located at r, at time t [19]. This study uses the Artificial Neural Network (ANN) method.…”

Section: Ae Source Locationmentioning

confidence: 99%

Structural health monitoring of bridges with piezoelectric AE sensors

Yapar

Basu

Völgyesi

et al. 2015

Engineering Failure Analysis

View full text Add to dashboard Cite

a b s t r a c tMonitoring the health of structures using acoustic emission technique offers many advantages such as early and quick detection of damage in real-time inexpensively. This paper is concerned with health monitoring of infrastructure hardware like highway bridges using this technique for timely intervention preventing catastrophic failure. Both experimental and numerical investigations were undertaken to determine the effectiveness and applicability of the method in the case of bridge superstructures. Three types of representative bridge girders of steel, reinforced concrete and prestressed concrete were designed, fabricated and monitored in the laboratory for structural integrity under cyclic loads with the help of an acoustic emission sensor system. After laboratory work, wavelet and Fourier transform techniques were applied to the recorded signals for de-noising and to diagnose the damaged state of the structure. Finally the locations of the cracks were determined by using the artificial neural network (ANN) approach.

show abstract

Section: Ae Source Locationmentioning

confidence: 99%

Structural health monitoring of bridges with piezoelectric AE sensors

Yapar

Basu

Völgyesi

et al. 2015

Engineering Failure Analysis

View full text Add to dashboard Cite

show abstract

“…These approaches includes extended Kalman filter (EKF) [ 18 ], unscented Kalman filter (UKF) [ 15 ], particle filter (PF) [ 19 ] and Bayesian methods which are realized by Monte Carlo simulations [ 20 , 21 , 22 ]. In addition, machine learning approaches, such as artificial neural network (ANN) and support vector machine (SVM), have also been employed for AE source localization [ 23 , 24 , 25 , 26 ]. Results have demonstrated that ANN and SVM are promising ways to localize AE sources; however, they require a large amount of data sets for training, impeding their applications in practical use.…”

Section: Introductionmentioning

confidence: 99%

An Optimal Image-Based Method for Identification of Acoustic Emission (AE) Sources in Plate-Like Structures Using a Lead Zirconium Titanate (PZT) Sensor Array

Yan

Zhou

2018

Sensors

View full text Add to dashboard Cite

This paper proposes an innovative method for identifying the locations of multiple simultaneous acoustic emission (AE) events in plate-like structures from the view of image processing. By using a linear lead zirconium titanate (PZT) sensor array to record the AE wave signals, a reverse-time frequency-wavenumber (f-k) migration is employed to produce images displaying the locations of AE sources by back-propagating the AE waves. Lamb wave theory is included in the f-k migration to consider the dispersive property of the AE waves. Since the exact occurrence time of the AE events is usually unknown when recording the AE wave signals, a heuristic artificial bee colony (ABC) algorithm combined with an optimal criterion using minimum Shannon entropy is used to find the image with the identified AE source locations and occurrence time that mostly approximate the actual ones. Experimental studies on an aluminum plate with AE events simulated by PZT actuators are performed to validate the applicability and effectiveness of the proposed optimal image-based AE source identification method.

show abstract

Optimal sensor configuration for complex systems

Sadegh

Spall

1998

Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207)

View full text Add to dashboard Cite

The paper considers the problem of sensor configuration for complex systems with the aim of maximizing the useful information about certain quantities of interest. Our approach involves two fundamental contributions: (1) definition of an appropriate optimality criterion or performance measure, and (2) description of an efficient and practical algorithm for achieving the optimality objective. The criterion for optimal sensor configuration is based on maximizing the overall sensor response while minimizing the correlation among the sensor outputs, so as to minimize the redundant information being provided by the multiple sensors. The procedure for sensor configuration is based on the powerful simultaneous perturbation stochastic approximation (SPSA) algorithm. SPSA avoids the need for detailed modeling of the sensor response by simply relying on observed responses as obtained by limited experimentation with test sensor configurations. We will illustrate the approach with the optimal placement of acoustic sensors for signal detection in structures. This includes both a computer simulation study for an aluminum plate, and real experimentations on a steel Ibeam.

show abstract

Neural Network Approach to Locating Acoustic Emission Sources in Non-Destructive Evaluation

Cited by 7 publications

References 0 publications

Structural health monitoring of bridges with piezoelectric AE sensors

Structural health monitoring of bridges with piezoelectric AE sensors

An Optimal Image-Based Method for Identification of Acoustic Emission (AE) Sources in Plate-Like Structures Using a Lead Zirconium Titanate (PZT) Sensor Array

Optimal sensor configuration for complex systems

Contact Info

Product

Resources

About