Abstract
An approach to detect and to classify incipient faults in an AC motor is introduced in this paper. This approach is based in an ART based neuro fuzzy system, (FasArt Fuzzy Adaptive System ART based), and in the fuzzy k nearest neighbor algorithm that is employing in an auxiliary way to complete the learning set.
A set of 15 non destructive faults has been tested and both a high degree of early detection and recognition has been reached. As well as, using the neuro-fuzzy nature of the FasArt model a database of fuzzy rules has been obtained permitting a fault description by linguistics terms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Arnanz, R., L.J. Miguel, E.J. Moya and J.R. Perán (2000). Model-based diagnostics of AC motors. In: IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS’2000). Budapest, Hungary. pp. 1145–1150.
Benbouzid, M.E.H. (1999). Bibliography on induction motors faults detection and diagnosis. IEEE Transactions on Energy Conversion 14(4), 1065–1074.
Cano, J.M., Y.A. Dimitriadis, M. Arauzo and J. Lopez (1996). Fasart: A new neurofuzzy architecture for incremental learning in system identification. In: Proceedings of the 13th World Congress of IFAC, IFAC’96. San Francisco, USA. pp. 133–138.
Carpenter, G., S. Grossberg, N. Markuzon and J. Reynolds (1992). Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional Maps. IEEE Transactions on Neural Networks 3(4), 698–713.
Chow, M. (1997). Motor fault detection and diagnosis. IEEE Industrial electronics society News Letter 42, 4–7.
Chow, M., Altug S. and H.J. Trusell (1999). Heuristic constraints enforcement for trainig of and knowledge extraction from a fuzzy/neural architecture-part i: Foundation. IEEEFuzzy 7(2), 143–150.
Costa Branco, P.J. and J.A. Dente (1998). An experiment in automatic modelling an electrical drive system using fuzzy logic. IEEE Transactions on systemas, man and cybernetics-Part C 28(2), 254–261.
Finley, W.R. and R.R. Burke (1994).Troubleshooting motor problems. IEEE Transactions on Industry Applications 30(5), 1383–1397.
Keller, J.M., M.R. Gray and Givens J.A. (1985). A fuzzy k-nearest neighbor algorithm. SMC 15(4), 580–585.
Nandi, S. and H.A. Tolyat (n.d.). Fault diagnosis of electrical machines-a review. Submitted to IEEE Transactions on Industry Applications.
Pouliezos, A.D. and G.S. Stavrakakis (1994). Real Time Fault Monitoring of Industrial Processes. Kluwer academic publishers. The Netherlands.
Sainz Palmero, G.I., Y. Dimitriadis, J.M. Cano Izquierdo, E. Gómez Sánchez and E. Parrado Hernández (December 2000). ART based model set for pattern recognition: FasArt family. In: Neuro-fuzzy pattern recognition (H. Bunke and A. Kandel, Eds.). World Scientific Pub. Co.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Juez, J., Sainz, G.I., Moya, E.J., Perán, J.R. (2001). Early Detection and Diagnosis of Faults in an AC Motor Using Neuro Fuzzy Techniques: FasArt + Fuzzy k Nearest Neighbors. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_69
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_69
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive