THE IMPLEMENTATION OF A NOVEL DIAGNOSTIC TECHNIQUE BY COMBINING MINIMUM-DISTANCE PATTERN RECOGNITION AND DISCRETE WAVELET TRANSFORMATION IN VIBRATION TESTING
This final project is focused on experimental verification of a novel method for machinery fault diagnostics. The method has been developed through numerical simulation in the master thesis compiled by Hilarius Tutut Sandewan (2010). In this respect, the method starts by forming the feature vector....
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/15023 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | This final project is focused on experimental verification of a novel method for machinery fault diagnostics. The method has been developed through numerical simulation in the master thesis compiled by Hilarius Tutut Sandewan (2010). In this respect, the method starts by forming the feature vector. Fault identification is performed based on the distance between the measured feature vector and the feature vectors in the data base. The main contribution of this final project is to verify the effectiveness of the method which combines the minimum distance pattern recognition and wavelet transform. The wavelet transform used in this method is the decimated discrete wavelet transform (DWT). The feature vector is assembled from the wavelet filter coefficients. The effectiveness of this method will be proved by experimental <br />
<br />
<br />
verification. In this case, two standard faults are simulated, namely the unbalance and mechanical looseness. The outcomes of the experiment show promising results, <br />
<br />
<br />
which concludes the effectiveness of the method. |
|---|