Failure strength prediction of unidirectional tensile coupons using acoustic emission peak amplitude and energy parameter with artificial neural networks

Sasikumar, T.; Rajendraboopathy, S.; Usha, K.; Vasudev, E.S.

doi:10.1016/j.compscitech.2009.02.014

Cited by 24 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of middle layer permits the system to portray the inconspicuous varieties in the conveyance and relate them to the known extreme strength in the preparation set [24]. The network engineering was constructed around a 61 neuron input layer, a 59 neuron hidden layer, a completely associated bias, furthermore, one output layer neuron for anticipating the ultimate failure strength.…”

Section: Neural Network Analysismentioning

confidence: 99%

Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data

Christopher¹,

Sasikumar²,

Santulli³

et al. 2018

FME Transaction

Self Cite

View full text Add to dashboard Cite

In this work, the ultimate strength of aluminum/silicon carbide (Al/SiC) composites was predicted by using acoustic emission (AE) parameters through artificial neural network (ANN) analysis. With this aim, a series of fourteen Al/SiC tensile samples were loaded up to the failure to investigate the amplitude distribution of AE events detected during loading. A back propagation ANN was prepared to correlate the amplitude values generated during loading up to 60% of known ultimate strength with ultimate failure strength of the samples. Three individual neural networks generated with parameters like hits, the Felicity ratio and rise angle were trained towards anticipating the ultimate strength value, which was predicted within the worst case error of-3.51 %,-4.73 %, and-2.73 %, respectively. The failure prediction accuracy by using rise angle as input was found to be slightly better, although the three neural networks all proved effective.

show abstract

Section: Neural Network Analysismentioning

confidence: 99%

Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data

Christopher¹,

Sasikumar²,

Santulli³

et al. 2018

FME Transaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…The significant AE parameters such as rise time, count, energy, duration and amplitude were used for materials characterisation and structural integrity evaluation [10][11][12][13]. AE peak amplitude and energy parameter were fed in to neural network (NN) for predicting the tensile strength of carbon/epoxy composite laminates [14,15]. Arumugam et al [16] predicted residual tensile strength of impacted carbon/epoxy laminates using ANN with AE as input cumulative counts and amplitude frequency data collected up to 50% of failure loads.…”

Section: Introductionmentioning

confidence: 99%

Failure strength prediction of glass/epoxy composite laminates from acoustic emission parameters using artificial neural network

et al. 2017

View full text Add to dashboard Cite

“…Yuyama et al . mentioned that although the majority of investigations employing AE in bridge cable monitoring has focused in detecting and locating wire breaks, limited work successfully classified recorded AE activity based on statistical pattern recognition (SPR), such as clustering , artificial neural networks , fuzzy clustering , and outlier analysis , that could be used to train the SHM system to detect anomalous behavior especially in challenging environmental conditions, increasing in this way the reliability of the detection scheme.…”

Section: Introductionmentioning

confidence: 99%

“…This interaction between the modes is typically encountered when the wavelength and diameter of the waveguide are comparable. The dispersive behavior of isotropic circular waveguides are governed by the Pochhammer–Chree equation

\frac{2 p}{a} (q^{2} + k^{2}) J_{1} (p a) J_{1} (q a) - {((), q^{2} - k^{2})}^{2} J_{0} (p a) J_{1} (q a) - 4 k^{2} p q J_{1} (p a) J_{0} (q a) = 0

…”

Section: Introductionmentioning

confidence: 99%

Novel optico-acoustic nondestructive testing for wire break detection in cables

Vanniamparambil

Khan

Hazeli

et al. 2013

Struct. Control Health Monit.

View full text Add to dashboard Cite

SUMMARY A novel optico‐acoustic sensing system based on digital image correlation (DIC), guided ultrasonic waves (GUW), and acoustic emission (AE) and its application in detecting breaks on seven‐wire steel strands is presented. The implementation of the emerging optical nondestructive testing (NDT) method of DIC in parallel with established acoustic NDT techniques enables the cross‐correlation/validation of in situ recorded information related to progressive damage accumulation, which is the focal point of this research. To the authors' best knowledge, it is the first time that full field strain accumulations have been obtained on the surface of the seven‐wire strands. Furthermore, acoustic waveforms and their extracted features are found complementary to full field strain measurements and prove capable to detect damage initiation in critical structural sites (‘hot spots’). To demonstrate the potential of the novel NDT system, pristine and prenotched strands were loaded using a mechanical testing frame while simultaneously recording DIC, GUW, and AE data. The DIC and GUW were acquired and excited at specific load intervals to avoid overlapping of GUW with AE activity. The reported DIC results directly reveal strain accumulations at the notched areas prior to breaking, whereas AE waveforms and related features show sudden changes at time instances that correspond to wire breaks. In addition, the GUW signals show a decrease in their amplitude upon progressive load of the strands and wave speed variations. Detailed post‐processing of the acoustic results was performed to cross‐correlate recorded information from novel optico‐acoustic sensing system and create methodologies for effective data filtering, alignment, synchronization, and fusion (through unsupervised pattern recognition techniques) that could lead to robust damage identification in structural health monitoring applications. The results demonstrate for the first time that the use of full field strains in correlation with acoustic techniques visually validates the damage source location and, in turn, enhances the damage predictive capabilities of each NDT method for prestressed and post‐tensioned cables found in stay cable bridges. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

Failure strength prediction of unidirectional tensile coupons using acoustic emission peak amplitude and energy parameter with artificial neural networks

Cited by 24 publications

References 2 publications

Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data

Neural network prediction of aluminum-silicon carbide tensile strength from acoustic emission rise angle data

Failure strength prediction of glass/epoxy composite laminates from acoustic emission parameters using artificial neural network

Novel optico-acoustic nondestructive testing for wire break detection in cables

Contact Info

Product

Resources

About