Master of Science in Electrical Engineering (MSEE)
Electrical and Computer Engineering
The problem of fault diagnosis and condition monitoring of ball bearings is a multidisciplinary subject. It involves research subjects from diverse disciplines of mechanical engineering, electrical engineering and in particular signal processing. In the first step, one should identify the correct method of investigation. The methods of investigation for condition monitoring of ball bearings include acoustic emission measurements, temperature monitoring, electrical current monitoring, debris analysis and vibration signal analysis. In this thesis the vibration signal analysis is employed. Once the method of analysis is selected, then features sensitive to faults should be calculated from the signal. While some of the features may be useful for condition monitoring, some of the calculated features might be extra and may not be helpful. Therefore, a feature reduction module should be employed. Initially, six features are selected as a candidate for the diagnosis feature space. After analyzing the trend of the features, it was concluded that three of the features are not appropriate for fault diagnosis. In this thesis, two problem is investigated. First the problem of identifying the effects of the fault size on the vibration signal is investigated. Also the performance of the feature space is tested in distinguishing the healthy ball bearings from the defective vibration signals.
Document Availability at the Time of Submission
Secure the entire work for patent and/or proprietary purposes for a period of one year. Student has submitted appropriate documentation which states: During this period the copyright owner also agrees not to exercise her/his ownership rights, including public use in works, without prior authorization from LSU. At the end of the one year period, either we or LSU may request an automatic extension for one additional year. At the end of the one year secure period (or its extension, if such is requested), the work will be released for access worldwide.
Kahirdeh, Ali, "A Diagnosis Feature Space for Condition Monitoring and Fault Diagnosis of Ball Bearings" (2014). LSU Master's Theses. 1579.