A Real-Time Prognostic Methodology Based on Feature Extraction and Multivariate Control Charting for Improving Reliability and Maintenance




Chakamehgooyemotlagh, Mehdi

Journal Title

Journal ISSN

Volume Title



In Condition based maintenance (CBM) decision will be made based on the data which have been collected in condition monitoring and a comprehensive maintenance program would be recommended. There are three phases: data gathering, data processing and maintenance decision-making. Diagnostics and prognostics are two important aspects of a CBM program. CBM program is more beneficial and realistic. With CBM, better maintenance decisions can be made to elude or minimize unnecessary maintenance expenditure. Unlike TPM in which prescheduled maintenance will be done, in CBM necessary maintenance would be predicted. Condition based maintenance is performed only after an alarm is received from one of the equipment. Compared with other maintenance methods, this method increases the time between maintenance because maintenance is performed as necessary. The foundation of condition based maintenance is to discover upcoming equipment failure so maintenance can be performed when it is necessary, not before and the job can be ended right before equipment fails by applying three methods for data analytics: Principal Component Analysis, Hoteling's T-Square Control Chart and Logistic Regression. CBM improves machine reliability and minimizes unscheduled downtime due to failure. Many manufacturing industries accept this method of efficient maintenance such as; aircraft, automobile, health care industries and to many other industries. The CBM approach is the most reliable of other approaches. The main purpose of this approach is to predict equipment abnormality and implement efficient maintenance operations such as correction and replacement before critical issues arise.


This item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.


Advanced Manufacturing and Enterprise Engineering



Mechanical Engineering