Establishment of Detection and Prediction Model of Induction Motor Bearing Faults by Current and Vibration Signals

• Main Authors: Jei-Wei Liao, 廖哲緯
• Other Authors: Meng-Kun Liu
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/ddnwzp

碩士 === 國立臺灣科技大學 === 機械工程系 === 107 === The motor has played an indispensable role in the technological development since the Industrial Revolution. The motor damage or motor failure would cause the shutdown of the entire production line and result in huge loss. Therefore, the motor fault detection and preventive maintenance will attract more and more attentions. Nowadays, the motor detection methods are mainly divided into vibration analysis and MCSA (Motor Current Signature Analysis). Although the vibration analysis can detect the abnormality of the machine immediately, it is an intrusive detection method mainly for local damage observation. It is difficult to detect the abnormality at low rotation speed. On the other hand, the MCSA is non-intrusive and is more comprehensive in observing motor faults. Its price is much lower than the vibration detection. Therefore, MCSA technology has become more and more popular in the industry. In this paper, the vibration and current analysis are used to observe the bearing wear condition of the rotating equipment over time. Moreover, the characteristics of the vibration trend not only are selected from the current signal to establish the regression model, but are also used to estimate the condition of the motor bearing to achieve pre-emptive action before the machine is damaged.