Application possibilities of artificial neural networks for recognizing partial discharges measured by the acoustic emission method

2009 ◽  
Vol 16 (1) ◽  
pp. 214-223 ◽  
Author(s):  
T. Boczar ◽  
S. Borucki ◽  
A. Cichon ◽  
D. Zmarzly
Keyword(s):  
Neural Networks ◽  
Acoustic Emission ◽  
Artificial Neural Networks ◽  
Partial Discharges ◽  
Acoustic Emission Method ◽  
Emission Method ◽  
Artificial Neural

scholarly journals Identification of the Degree of Degradation of Fibre-Cement Boards Exposed to Fire by Means of the Acoustic Emission Method and Artificial Neural Networks

Materials ◽  
2019 ◽  
Vol 12 (4) ◽  
pp. 656 ◽  
Author(s):  
Krzysztof Schabowicz ◽  
Tomasz Gorzelańczyk ◽  
Mateusz Szymków
Keyword(s):  
Neural Networks ◽  
Acoustic Emission ◽  
Artificial Neural Networks ◽  
Bending Strength ◽  
Acoustic Emission Method ◽  
Emission Method ◽  
Three Point Bending ◽  
Fibre Cement ◽  
Artificial Neural ◽  
Degree Of Degradation

This paper presents the results of research aimed at identifying the degree of degradation of fibre-cement boards exposed to fire. The fibre-cement board samples were initially exposed to fire at various durations in the range of 1–15 min. The samples were then subjected to three-point bending and were investigated using the acoustic emission method. Artificial neural networks (ANNs) were employed to analyse the results yielded by the acoustic emission method. Fire was found to have a degrading effect on the fibres contained in the boards. As the length of exposure to fire increased, the fibres underwent gradual degradation, which was reflected in a decrease in the number of acoustic emission (AE) events recognised by the artificial neural networks as accompanying the breaking of the fibres during the three-point bending of the sample. It was shown that it is not sufficient to determine the degree of degradation of fibre-cement boards solely on the basis of bending strength (MOR).

scholarly journals Effect of Freeze–Thaw Cycling on the Failure of Fibre-Cement Boards, Assessed Using Acoustic Emission Method and Artificial Neural Network

Materials ◽  
2019 ◽  
Vol 12 (13) ◽  
pp. 2181 ◽  
Author(s):  
Tomasz Gorzelańczyk ◽  
Krzysztof Schabowicz
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Acoustic Emission ◽  
Acoustic Emission Method ◽  
Emission Method ◽  
Three Point Bending ◽  
Freeze Thaw ◽  
Fibre Cement ◽  
Artificial Neural ◽  
Building Practice

This paper presents the results of investigations into the effect of freeze–thaw cycling on the failure of fibre-cement boards and on the changes taking place in their structure. Fibre-cement board specimens were subjected to one and ten freeze–thaw cycles and then investigated under three-point bending by means of the acoustic emission method. An artificial neural network was employed to analyse the results yielded by the acoustic emission method. The investigations conclusively proved that freeze–thaw cycling had an effect on the failure of fibre-cement boards, as indicated mainly by the fall in the number of acoustic emission (AE) events recognized as accompanying the breaking of fibres during the three-point bending of the specimens. SEM examinations were carried out to gain better insight into the changes taking place in the structure of the tested boards. Interesting results with significance for building practice were obtained.

Damage Mechanisms Identification in FRP Using Acoustic Emission and Artificial Neural Networks

2006 ◽  
Vol 514-516 ◽  
pp. 789-793 ◽  
Author(s):  
Rui de Oliveira ◽  
António Torres Marques
Keyword(s):  
Neural Networks ◽  
Acoustic Emission ◽  
Artificial Neural Networks ◽  
Tensile Test ◽  
A Priori ◽  
The Self ◽  
A Priori Knowledge ◽  
Self Organizing Maps ◽  
Damage Mechanisms ◽  
Artificial Neural

In this study is proposed a procedure for damage discrimination based on acoustic emission signals clustering using artificial neural networks. An unsupervised methodology based on the self-organizing maps of Kohonen is developed considering the lack of a priori knowledge of the different signal classes. The methodology is described and applied to a cross-ply glassfibre/ polyester laminate submitted to a tensile test. In this case, six different AE waveforms were identified. The damage sequence could so be identified from the modal nature of those waves.

ACOUSTIC EMISSION TESTING OF POWER TRANSFORMERS INSULATION

2020 ◽  
pp. 40-44
Author(s):  
V. V. Bardakov ◽  
S. V. Elizarov ◽  
V. A. Barat ◽  
V. G. Kharebov ◽  
K. A. Medvedev
Keyword(s):  
Acoustic Emission ◽  
High Sensitivity ◽  
Partial Discharges ◽  
Power Transformers ◽  
Acoustic Emission Method ◽  
Emission Method ◽  
Emission Data ◽  
Emission Testing ◽  
Insulation Defect ◽  
Acoustic Emission Testing

Testing results of power transformers insulation for the presence of insulation defects, accompanied by the partial discharges occurrence, by means of the acoustic emission method are presented in this article. In particular, the testing of two power transformers with different lifetime was carried out. One transformer was defect-free and one with a willing insulation defect. Based on the testing results, the features of acoustic emission data for power transformers in the presence of partial discharges are found. High sensitivity of acoustic emission method for acoustic wave registration from partial discharges is shown in the article. A method for filtering of noise hits and extraction of hits from partial discharges is proposed. This method is based on excretion of acoustic emission hits from partial discharges out of total number of hits by means of periodicity of their registration, which is synchronized with power supply frequency on the first step. On the next step based on acoustic emission parameters of hits excretion on the previous step, filtration was carried out. The location of the insulation defect which led to the appearance of partial discharges was determined based on the volume location algorithm, by means of acoustic emission method. The insulation defect was confirmed by verification.

scholarly journals Crack Propagation Analysis Using Acoustic Emission Sensors for Structural Health Monitoring Systems

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Zachary Kral ◽  
Walter Horn ◽  
James Steck
Keyword(s):  
Neural Networks ◽  
Acoustic Emission ◽  
Artificial Neural Networks ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Structural Health ◽  
Aerospace Systems ◽  
Acoustic Emission Sensors ◽  
Artificial Neural ◽  
The Difference

Aerospace systems are expected to remain in service well beyond their designed life. Consequently, maintenance is an important issue. A novel method of implementing artificial neural networks and acoustic emission sensors to form a structural health monitoring (SHM) system for aerospace inspection routines was the focus of this research. Simple structural elements, consisting of flat aluminum plates of AL 2024-T3, were subjected to increasing static tensile loading. As the loading increased, designed cracks extended in length, releasing strain waves in the process. Strain wave signals, measured by acoustic emission sensors, were further analyzed in post-processing by artificial neural networks (ANN). Several experiments were performed to determine the severity and location of the crack extensions in the structure. ANNs were trained on a portion of the data acquired by the sensors and the ANNs were then validated with the remaining data. The combination of a system of acoustic emission sensors, and an ANN could determine crack extension accurately. The difference between predicted and actual crack extensions was determined to be between 0.004 in. and 0.015 in. with 95% confidence. These ANNs, coupled with acoustic emission sensors, showed promise for the creation of an SHM system for aerospace systems.

Sign in / Sign up

Export Citation Format

Share Document