Vibration-based multi-fault diagnosis for centrifugal pumps
The thesis proposes a new method for vibration fault diagnosis of centrifugal pumps by combining statistical features, Symlet Wavelet transform, Principal Component Analysis and k-Nearest Neighbors. Six statistical features were extracted from the low frequency part of wavelet decomposition which wa...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Curtin University
2015
|
| Online Access: | http://hdl.handle.net/20.500.11937/1532 |
| _version_ | 1848743693832421376 |
|---|---|
| author | Kamiel, Berli Paripurna |
| author_facet | Kamiel, Berli Paripurna |
| author_sort | Kamiel, Berli Paripurna |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | The thesis proposes a new method for vibration fault diagnosis of centrifugal pumps by combining statistical features, Symlet Wavelet transform, Principal Component Analysis and k-Nearest Neighbors. Six statistical features were extracted from the low frequency part of wavelet decomposition which was then used as input features for the PCA model. The fault detection utilised T2 and Q statistics while fault classification and identification were carried out using score matrices and k-Nearest Neighbors respectively. |
| first_indexed | 2025-11-14T05:49:38Z |
| format | Thesis |
| id | curtin-20.500.11937-1532 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T05:49:38Z |
| publishDate | 2015 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-15322017-02-20T06:37:42Z Vibration-based multi-fault diagnosis for centrifugal pumps Kamiel, Berli Paripurna The thesis proposes a new method for vibration fault diagnosis of centrifugal pumps by combining statistical features, Symlet Wavelet transform, Principal Component Analysis and k-Nearest Neighbors. Six statistical features were extracted from the low frequency part of wavelet decomposition which was then used as input features for the PCA model. The fault detection utilised T2 and Q statistics while fault classification and identification were carried out using score matrices and k-Nearest Neighbors respectively. 2015 Thesis http://hdl.handle.net/20.500.11937/1532 en Curtin University fulltext |
| spellingShingle | Kamiel, Berli Paripurna Vibration-based multi-fault diagnosis for centrifugal pumps |
| title | Vibration-based multi-fault diagnosis for centrifugal pumps |
| title_full | Vibration-based multi-fault diagnosis for centrifugal pumps |
| title_fullStr | Vibration-based multi-fault diagnosis for centrifugal pumps |
| title_full_unstemmed | Vibration-based multi-fault diagnosis for centrifugal pumps |
| title_short | Vibration-based multi-fault diagnosis for centrifugal pumps |
| title_sort | vibration-based multi-fault diagnosis for centrifugal pumps |
| url | http://hdl.handle.net/20.500.11937/1532 |