TY - GEN
T1 - Machinery fault diagnosis using Independent Component Analysis (ICA) and Instantaneous Frequency (IF)
AU - Atmaja, B. T.
AU - Arifianto, D.
PY - 2009
Y1 - 2009
N2 - Machine condition monitoring plays an important role in industry to ensure the continuity of the process. This work presents a simple and yet, fast approach to detect simultaneous machinery faults using sound mixture emitted by machines. We developed a microphone array as the sensor. By exploiting the independency of each individual signal, we estimated the mixture of the signals and compared time-domain independent component analysis (TDICA), frequency-domain independent component analysis (FDICA) and Multi-stage ICA. In this research, four fault conditions commonly occurred in industry were evaluated, namely normal (as baseline), unbalance, misalignment and bearing fault. The results showed that the best separation process by SNR criterion was time-domain ICA. At the final stage, the separated signal was analyzed using Instantaneous Frequency technique to determine the exact location of the frequency at the specific time better than spectrogram.
AB - Machine condition monitoring plays an important role in industry to ensure the continuity of the process. This work presents a simple and yet, fast approach to detect simultaneous machinery faults using sound mixture emitted by machines. We developed a microphone array as the sensor. By exploiting the independency of each individual signal, we estimated the mixture of the signals and compared time-domain independent component analysis (TDICA), frequency-domain independent component analysis (FDICA) and Multi-stage ICA. In this research, four fault conditions commonly occurred in industry were evaluated, namely normal (as baseline), unbalance, misalignment and bearing fault. The results showed that the best separation process by SNR criterion was time-domain ICA. At the final stage, the separated signal was analyzed using Instantaneous Frequency technique to determine the exact location of the frequency at the specific time better than spectrogram.
KW - Independent component analysis
KW - Instantaneous frequency
KW - Machinery fault diagnosis
KW - Natural gradient
KW - Spectrogram
UR - http://www.scopus.com/inward/record.url?scp=77950921350&partnerID=8YFLogxK
U2 - 10.1109/ICICI-BME.2009.5417257
DO - 10.1109/ICICI-BME.2009.5417257
M3 - Conference contribution
AN - SCOPUS:77950921350
SN - 9781424449996
T3 - International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering 2009, ICICI-BME 2009
BT - International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering 2009, ICICI-BME 2009
T2 - International Conference on Instrumentation, Communication, Information Technology, and Biomedical Engineering 2009, ICICI-BME 2009
Y2 - 23 November 2009 through 25 November 2009
ER -