Fuzzy neural networks for machine maintenance in mass transit railway system

You are here: Homepage > Search

Fuzzy neural networks for machine maintenance in mass transit railway system

Liu, J.N.K. / Sin, K.Y.

This paper describes an application of fuzzy knowledge-based neural-network system (FKNNS) being developed by the Hong Kong Mass Transit Railway Corporation (MTRC) for the maintenance of its ticket machines in one of the busiest transit systems in the world. The model utilizes specific experts' knowledge which is transformed into fuzzy membership functions through certain control rules. The error backpropagation network was selected for the network training in which various activation functions were tested. After extensive training of the network, the FastProp with hyperbolic tangent was recommended, Input patterns were decomposed to facilitate the training process and eliminate the effect of local minima. Both the test and forecast results indicated that the FKNNS is an excellent aid for machine maintenance planning since there are too much difficulties in deriving the analytical solution otherwise. Beta test result shows a 20.08% improvement over the existing maintenance methodology. Moreover, the developed model can smoothly handle more types of industrial machine maintenance problems and generate intangible benefits toward MTRC in terms of improved customer service and better corporation image.

Access

Access via TIB

Check availability in my library

Order at Subito €

Export, share and cite

Document information

Title :

Fuzzy neural networks for machine maintenance in mass transit railway system

Additional title:

Ein neuronales Netz, dessen wissensbasierte Komponente auf fuzzy sets beruht, unterstützt die Wartung von Fahrkartenautomaten eines schienengebundenen Massenverkehrssystems

Contributors:

Liu, J.N.K. (author) / Sin, K.Y. (author)

Published in:

IEEE Transactions on Neural Networks ; 8 , 4 ; 932-941

Publication date :

1997

Size :

10 Seiten, 8 Quellen

ISSN :

1045-9227

DOI :

https://doi.org/10.1109/72.595893