Identification of dynamic nonlinear systems using artificial neural networks incorporating a priori knowledge

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.

Download Full-text

Incorporating a priori knowledge into neural networks

Electronics Letters ◽

10.1049/el:19951309 ◽

1995 ◽

Vol 31 (22) ◽

pp. 1930-1931 ◽

Cited By ~ 5

Author(s):

D. Anguita ◽

S. Rovetta ◽

S. Ridella ◽

R. Zunino

Keyword(s):

Neural Networks ◽

A Priori ◽

A Priori Knowledge ◽

Priori Knowledge

Download Full-text

An internal model control strategy using artificial neural networks for a class of nonlinear systems

IEEE International Conference on Systems, Man and Cybernetics ◽

10.1109/icsmc.2002.1176373 ◽

2003 ◽

Cited By ~ 2

Author(s):

S. Bel Hadj Ali ◽

A. El Abed-Abdelkrim ◽

M. Benrejeb

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Nonlinear Systems ◽

Control Strategy ◽

Internal Model ◽

Internal Model Control ◽

Model Control ◽

Artificial Neural

Download Full-text

A new method based on artificial neural networks for solving general nonlinear systems

International Journal of Computing Science and Mathematics ◽

10.1504/ijcsm.2018.10014203 ◽

2018 ◽

Vol 9 (3) ◽

pp. 207

Author(s):

Ahmad Jafarian ◽

H. Abbasnejad

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Nonlinear Systems ◽

New Method ◽

Artificial Neural

Download Full-text

A Comparative Study of Two Data Reduction Methods for Steel Classification Based on LIBS

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.644-650.4722 ◽

2014 ◽

Vol 644-650 ◽

pp. 4722-4725 ◽

Cited By ~ 2

Author(s):

Hai Yang Kong ◽

Lan Xiang Sun ◽

Jing Tao Hu ◽

Yong Xin ◽

Zhi Bo Cong

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Principal Component ◽

Laser Induced Breakdown Spectroscopy ◽

Breakdown Spectroscopy ◽

Characteristic Lines ◽

Laser Induced Breakdown ◽

Reduction Methods ◽

Artificial Neural ◽

Priori Knowledge

Spectra of 27 steel samples were acquired by Laser-Induced Breakdown Spectroscopy (LIBS) for steel classification. Two methods were used to reduce dimensions: the first is to select characteristic lines of elements contained in the samples manually and the second is to do principal component analysis (PCA) of original spectra. Then the data after reducing dimensions was used as the input of artificial neural networks (ANN) to classify steel samples. The results show that, the better result can be achieved by selecting peak lines manually, but this solution needs much priori knowledge and wastes much time. The principal components (PCs) of original spectra were utilized as the input of artificial neural networks can also attain a good result nevertheless and this method can be developed into an automatic solution without any priori knowledge.

Download Full-text