Bearing fault detection using vibration responds : a statistical based analysis / Mohd Qayyuum Mohd Ridzuan
Material type:
TextPublication details: Kuantan, Pahang : UMP, 2012Description: xix, 98 p. : ill. (some col.) ; 30 cm. + 1 CD-ROMISBN: - THE0006479(Local)
| Item type | Current library | Call number | Copy number | Status | Date due | Barcode | |
|---|---|---|---|---|---|---|---|
Final Year Report
|
UMPLIB PEKAN | TJ1071 .Q29 2012 rs Bc. (Browse shelf(Opens below)) | 1 | Not for loan | 0000072741 | ||
|
Final Year Report
|
UMPLIB PEKAN | CD 6898 | TJ1071 .Q29 2012 rs Bc. (Browse shelf(Opens below)) | 1 | Not for loan | 0000072742 |
Project paper (Bachelor of Mechanical Engineering) -- Universiti Malaysia Pahang - 2012
Bibliography : 71-73
Bearing is one of the vital parts in any rotating machinery. Failure of this particular part can affect the machinery performance and in time will cause major failure to the machinery. Due to this crucial problem, on-line monitoring has become an alternative in prevention maintenance. The objective of this project is to analyze the vibration signal of both good bearing and defect bearing gain from an accelerometer. A set of good condition bearing is used along five types of defective bearing which are outer race defect, inner race defect, corroded defect, contaminated defect and lastly point defect. The data is acquired using a Bruel & Kjaer accelerometer and a National Instrument Data Acquisition System (NiDAQ). The bearing will be run on three speed rotation which is 287, 1466 and 2664 RPM. The data is then analyzed using DASYLab software. From there it is further analyzed using global statistical parameters of Variance, Standard Deviation, Kurtosis, Skewness, Root Mean Square and also Crest Factor. The data then plotted on statistical distribution to obtain a trend where, the value of this trend is used in Principal Component Analysis (PCA) to form a scatter plot of the data. Where all types of bearing will remain in their scatter area itself. Then it will be clustered using Agglomerative Hierarchical Clustering where a dendrogram is used to show a cluster of data in which the respective data for all types of bearing tested remain in their cluster. Finally, this method is suggested as an alternative in bearing fault detection, especially online monitoring.