Some of the material in is restricted to members of the community. By logging in, you may be able to gain additional access to certain collections or items. If you have questions about access or logging in, please use the form on the Contact Page.
Nyanteh, Y. D. (2013). Application of Artificial Intelligence to Rotating Machine Condition Monitoring. Retrieved from http://purl.flvc.org/fsu/fd/FSU_migr_etd-8713
Systems with critical functionality and are prone to damage due to excessive stress level from operation conditions and working environment requires health monitoring. Condition or health monitoring involves acquiring data that can be analyzed to determine the occurrence of faults, determine the type of fault, determine the severity of a fault and determine when the next fault would occur. This research has considered new fault analysis techniques for rotating electrical machines using Artificial Intelligence (AI) techniques. The analysis has been carried out in three sections: fault diagnosis, fault detection and fault prognosis. By way of fault diagnosis, Finite Element Analysis (FEA) has been used to model different faults in a Permanent Magnet Synchronous Machine (PMSM) which has been analyzed by way of classification using five Artificial Intelligence Techniques. The original large dimensional dataset is first used in the classification process and the different fault classifiers compared based on their performance using different fault classifiers from the FEA model. The dimensions of the dataset are reduced, using four different manifold reduction techniques. Manifold reduction is carried out to reduce the computational burden of fault classification on high dimensionality data. Two new techniques for fault detection using AI is presented and applied to PMSMs by way of computer simulations and experimental data from an actual PMSM. One technique called the Peak-to-Peak technique uses an Artificial Neural Network (ANN) trained using PSO and can distinguish short circuit faults from loading transients. In the second method, called Turn-to-Turn method, the zero current components is used to determine the number of shorted turns in the stator windings using an ANN trained using the Extended Kalman Filter (EKF) method. Finally a new method of determining the time-to-breakdown of insulation systems is presented as a fault prognosis approach. Also a new micro simulation model is presented for simulating the breakdown of dielectric materials. The new prognostics method is based on a macro model developed in conjunction with ANNs. The prognosis approach is based on associating the breakdown characteristics of dielectrics to Partial Discharge (PD) that take place during dielectric breakdown.
A Dissertation submitted to the Department of Electrical and Computer Engineering in partial fulfillment of the requirements for the degree of Doctor of Philosophy.
Bibliography Note
Includes bibliographical references.
Advisory Committee
Chris S. Edrington, Professor Co-Directing Dissertation; David A. Cartes, Professor Co-Directing Dissertation; William Oates, University Representative; Rodney Roberts, Committee Member; Petru Andrei, Committee Member; Sanjeev K. Srivastava, Committee Member.
Publisher
Florida State University
Identifier
FSU_migr_etd-8713
Use and Reproduction
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). The copyright in theses and dissertations completed at Florida State University is held by the students who author them.
Nyanteh, Y. D. (2013). Application of Artificial Intelligence to Rotating Machine Condition Monitoring. Retrieved from http://purl.flvc.org/fsu/fd/FSU_migr_etd-8713