Detection of crack development with Al/SiCp using tensile with online acoustic emission

• Published in: Journal of alloys and compounds 2019-03, Vol.778, p.951-961
• Main Authors: Christopher, C. Mahil Loo, Sasikumar, T., Suresh, S.
• Format: Article
• Language: English
• Subjects: Acoustic emission; Acoustic emission testing; Acoustics; Alloy development; Amplitude; Artificial neural network- feed forward algorithm; Artificial neural networks; Cracks; Emission analysis; Felicity ratio; Metal matrix composites; Neural networks; Particulate composites; Rise angle; Silicon carbide
• ISSN: 0925-8388; 1873-4669
• DOI: 10.1016/j.jallcom.2018.11.162

It is important to find an easy and efficient way of finding the tensile strength of the alloys by detecting the crack development in alloys. In the present project by having used fourteen samples of Al-SiC composite pieces the energy discharge during the cracks were found out. The Acoustic Emission technique was used in this experiment. The tensile testing was achieved by tensile loading on a 100 kN universal testing machine. The values obtained using the parameters such as hits; Felicity Ratio and Rise Angle were fed into the Artificial Neural Network. The network could foresee the errors at the rate of 3.125%, – 3.515% and −2.73% of hits, felicity ratio and rise angle respectively. Among these the value −2.73% seems to be the best while using Acoustic Emission technique. Though all the three have demonstrated significantly the value obtained using the Rise Angle can be taken as the best, since it is closer to the ideal error value ‘zero’. [Display omitted] •Characterization of Al6601-SiC particles is examined by using SEM.•Tensile strength using online AE test were obtained in the Al-SiC composite.•AE data generated by AE data acquisition system and are analyzed.•AE data of the specimens are handled by ANN and their failure was mapped.•The RA values of AE parameter proved their uniqueness in the failure prediction.