Fault Diagnosis of Rotating Machinery based on Acoustic Emission using PARAFAC-Source Separation

Anindita Adikaputri Vinaya (Institut Teknologi Sepuluh Nopember, Surabaya)
Dhany Arifianto (Institut Teknologi Sepuluh Nopember, Surabaya)

IPTEK Journal of Proceedings Series
No 1 (2015): 1st International Seminar on Science and Technology (ISST) 2015

A common technique of vibration spectrum analysis is used for fault diagnosis of rotating machine in industry. The technique, however, requires a significant man power and has the risk of the direct measurement of vibration signal. This paper presents a remote maintenance technique based on acoustic emission of rotating machinery. The mixing matrix and the source signals are estimated using PARAFAC source separation by performing PARAFAC decomposition algorithm, permutation, and capon beamforming. This proposed technique prove the suitability and effectiveness of acoustic emission technique to diagnose Ball Pass Frequency of The Outer Race (BPFO) defect and misalignment coupling motor to pump.