`a`

The changes of air gap in inductive engines as vibration indicator aided by mathematical model and artificial neural network

Pages: 1005 - 1012, Issue Special, September 2007

 Abstract        Full Text (690.6K)              

Boguslaw Twarog - University of Rzeszow, Institute of Technology, 35-959 Rzeszow, 16A Rejtana Str., Poland (email)
Robert Pekala - University of Rzeszow, Institute of Technology, 35-959 Rzeszow, 16A Rejtana Str., Poland (email)
Jacek Bartman - University of Rzeszow, Institute of Technology, 35-959 Rzeszow, 16A Rejtana Str., Poland (email)
Zbigniew Gomolka - University of Rzeszow, Institute of Technology, 35-959 Rzeszow, 16A Rejtana Str., Poland (email)

Abstract: The method of analyzing vibration of electric engines or electro- magnetic generators proposed in the work is based on the analyzing of course current of load. In considerations were used the method based on specialized mathematics model and advanced calculation technique. It allow to create of patterns for artificial neural networks. These patterns represented different states of machine for the diagnostic and they are enable to define precisely the changes caused by failure. Received experiments showed that the designed architecture of the net enables to achieve good properties of generalization correct answer for entrance date which weren't a part of training process.

Keywords:  Mathematical modeling, stiff problem, Gear method, vibration analyzing, Fourier's series, Artificial Neural Network.
Mathematics Subject Classification:  Primary: 58F15, 58F17; Secondary: 53C35.

Received: September 2006;      Revised: February 2007;      Published: September 2007.