|
|||
|---|---|---|---|
Neural Networks-based Fault Detection with Application in Ink Jet Printer
In this paper, we explore the feasibility of using both feedforward and Elman neural networks to detect assembly faults in ink jet printers. The method is an extension of the motor fault detection scheme recently proposed by the authors. Two types of cartridge faults are studied here: encoder belt misalignment and encoder strip error. These two faults are detected from the characteristics variants in the neural networks-based prediction of cartridge velocity signals. Simulation results demonstrate that neural networks can be trained to effectively detect the inherent encoder faults. Some discussions on the selection of appropriate fault detection criteria are also given. Keywords: Fault detection, Elman neural network, feedforward neural network, prediction, ink jet printers.
Biographies: X. Z. Gao received his B.Sc. and M.Sc. degrees in electrical engineering from Harbin Institute of Technology, Harbin, China in 1993 and 1996, respectively. He got his Doctor of Science in Technology degree from Helsinki University of Technology, Espoo, Finland in 1999. Since January 2004, he has been appointed as a Docent of Soft Computing Methods and Applications in the Helsinki University of Technology. He is also a Guest Professor of the Harbin Institute of Technology and Beijing City University, China. He has published more than 80 technical papers on refereed journals and international conferences. His current research interests are soft computing methods with applications in motor fault detection/diagnosis and control instrumentation. Dr. Gao is an Associate Editor of the International Journal of Intelligent Automation and Soft Computing. He is a member of the Editorial Board of the Applied Soft Computing Journal. He serves in the International Technical Committees of numerous recent conferences on soft computing and intelligent systems, and also acts as a regular reviewer for several IEEE top publications and conferences. Dr. Gao will be the General Chair of the 2005 IEEE Mid-Summer Workshop on Soft Computing Methods in Industrial Applications in Espoo, Finland. S. J. Ovaska received the M.Sc. degree in electrical engineering from Tampere University of Technology, Tampere, Finland, in 1980, the Lic.Sc. degree in computer science and engineering from Helsinki University of Technology, Espoo, Finland, in 1987, and the D.Sc. degree in electrical engineering from Tampere University of Technology in 1989. He is currently a Professor of Industrial Electronics in the Department of Electrical and Communications Engineering, Helsinki University of Technology. Before joining Helsinki University of Technology in 1996, he was a Professor of Electronics at Lap-peenranta University of Technology, Lappeenranta, Finland. From 1980 to 1992, he held engineering, research, and R&D management positions with Kone Elevators and Nokia Research Center, both in Finland and the U.S. His research interests are soft computing, signal processing, fault diagnosis, and control instrumentation. During his career, he has authored or coauthored more than 180 technical papers published in peer-reviewed journals and international conference proceedings. He is the holder of nine patents in the area of systems and control. Prof. Ovaska is an Associate Editor of the IEEE TRANSACTIONS ON INDUS-TRIAL ELECTRONICS. He served as an Elected Member of the IEEE Systems, Man, and Cybernetics Society's Board of Governors (2001 2003). Also, he was the Founding General Chair of the 1998 IEEE Nordic Workshop on Power and Industrial Electronics, as well as the Founding General Chair of the 1999 IEEE Midnight-Sun Workshop on Soft Computing Methods in Industrial Applications. In addition, he was the recipient of two Outstanding Contribution Awards from the IEEE Systems, Man, and Cybernetics Society (2000 and 2002). X. Wang received her B.Sc. degree in technical physics from Heilongjiang University,
Harbin, China in 2001. In September 2002, she was admitted to study
in the International Master's Program in Electrical Engineering, Helsinki University of Tech-nology, Espoo, Finland. From September 2001 to August 2002, she worked as a Teaching/Research Assistant at the Electronics Laboratory, Heilongjiang University. Since March 2003, she has been acting as a Research Assistant on her M.Sc. degree at the Institute of Intelligent Power Electronics, Helsinki University of Technology.
 ISSUE={I}
|
|||
|
