M.R. Hedayati, S.A. Alavian, and M.S. Ghimati (Iran)
Plant maintenance, diagnostic techniques, Asymmetries of Magnetic Circuit, eml , expert system
Modern industrial plants have become so complex that the technicians cannot be entrusted the task of fault detection without serious risk of very costly failures. Increased production level per plant, rigid production schedules, high sensitivity services, and above all very high capital investments have led to a change of attitude and philosophy towards plant maintenance. If the production process happens to be power generation then the plant maintenance assumes an extraordinary importance. In order to ensure maximum plant availability and reliability it is necessary to have a properly planned plant maintenance programme in conjunction with production requirements. During the operation of large rotating electrical machines, undesirable voltages occur between the shaft ends and result in a circulating shaft current through vital metallic parts like bearing, etc, in its path, which may result in bearing damage. The most important cause of asymmetries of magnetic circuit of an alternating ring flux with the shaft are due to uneven air gaps caused by displacement of the rotor etc… such asymmetries are inevitable in large machines[5]. Reduction of the human experts involvement in the diagnosis process has gradually taken place upon the recent developments in the modern artificial intelligence (AI) tools. Artificial neural networks (ANNs), fuzzy and adaptive fuzzy systems, and expert systems are good candidates for the automation of the diagnostic procedures and e-maintenance application [1, 2, 3]. The present work surveys the principles and criteria of the diagnosis process and introduces the current research achievements to apply expert system techniques in the diagnostic systems of electrical machines and drives. In this paper a new sensor design is discussed and experimental results are presented for an expert system application.
Important Links:
Go Back
