The use of neural networks for the life prediction of insulating material of electric rotary machines

The use of neural networks for the life prediction of insulating material of electric rotary machines

Paper in proceedings (conference paper)

The life of the insulating systems of electric rotary machines is strongly depend upon electrical and thermal features of the insulating material used. The subject of the diagnostic prediction is to specify the condition of insulation used. At present days, the most popular prediction tools are the methods of artifical inteligence, and one method is the neural networks. This paper is concentrated on the use of neural networks in the life prediction of Relanex insulating material that is applied as insulation of electrical machines windings. In this case the condition of insulating in a time step k+1 is predicate from input quantity in time steps k, k-1, k-2, etc. Anyway the prediction means forecastings of quantity in future from N previous measurement this or other quantities in the past. We have used the above-mentioned neural networks for the prediction of insulating materials that were programmed in Matlab 6 enviroment. All simulations and the values calculated were also obtained by means of this product.

The life of the insulating systems of electric rotary machines is strongly depend upon electrical and thermal features of the insulating material used. The subject of the diagnostic prediction is to specify the condition of insulation used. At present days, the most popular prediction tools are the methods of artifical inteligence, and one method is the neural networks. This paper is concentrated on the use of neural networks in the life prediction of Relanex insulating material that is applied as insulation of electrical machines windings. In this case the condition of insulating in a time step k+1 is predicate from input quantity in time steps k, k-1, k-2, etc. Anyway the prediction means forecastings of quantity in future from N previous measurement this or other quantities in the past. We have used the above-mentioned neural networks for the prediction of insulating materials that were programmed in Matlab 6 enviroment. All simulations and the values calculated were also obtained by means of this product.

prediction, electric rotary machines

prediction, electric rotary machines

HAMMER, M.

01.01.2003

Zaklad Poligrafii Fundacji Rozwoju Uniwersytetu Gdanskiego

Polsko

83-88829-69-6

39th International Symposium on Electrical Machines

68

1