Predikce Životnosti Izolačních Materiálů Elektrických Strojů pomocí Neuronových sítí

The Life Prediction of Insulating Materials for Electric Machines with Insulating Materials

conference paper

en

The life of the insulating systems of electric rotary machines is strongly depent upon electrical and thermal features of the insulating material used. The subject of the diagnistic prediction is to specify the condition of insulation used. At present days, the most popular prediction tools are the methods of artifical intelligence, 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 electric machine windings. In this case, the condition of insulating in a time step k+1 is predicated from input quantity in time steps k, k-1, k-2, etc. Anyway the prediction means forecasting of quantity in future form N previous measurement this or other quantities in the past. The first part of the paper describes the use of artificial neural networks which forecast the life of insulating material for windings in electric rotary machines, the description of training and test data and setting of neural network for prediction. The second part shows (in the figures) the curves of prediction and the simulation of insulating material behaviour with neural networks. Tables evaluate the application of this tool for the solution of the problems investigated. We have used the above-mentioned neural networks for the prediction of insulating materials that were programmed in the Matlab 6 enviroment. All simulations and the values calculated were also obtained by means of this product.

V dnešní moderní době, která se vyznačuje technickým růstem a rozvojem je nezbytně nutné zajistit extenzivní a intenzivní využití technických prostředků a zařízení. Každý konkurence schopný výrobní proces se neobejde bez nutné kontroly a údržby výrobních zařízení, neboť každá nečekaná závada nebo porucha může značně ovlivnit výrobní produkci, zisk a životaschopnost výroby. Otázka životnosti a spolehlivosti izolačních materiálů elektrických strojů točivých je velmi důležitá, neboť izolační materiál, u elektrickým strojů pak izolace vinutí stroje patří k nejcitlivější a nejnákladnější části elektrického zařízení. Z tohoto důvodu se vyvíjejí nové a zdokonalují již známé diagnostické metody, které zhodnocují stav izolačního systému stroje v provozních podmínkách. Nejprogresivnějšími z diagnostických metod jsou pak ty, které nejen zhodnocují současný stav izolace, ale současně umožňují určitou prognózu její životnosti v daných provozních podmínkách.

The life of the insulating systems of electric rotary machines is strongly depent upon electrical and thermal features of the insulating material used. The subject of the diagnistic prediction is to specify the condition of insulation used. At present days, the most popular prediction tools are the methods of artifical intelligence, 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 electric machine windings. In this case, the condition of insulating in a time step k+1 is predicated from input quantity in time steps k, k-1, k-2, etc. Anyway the prediction means forecasting of quantity in future form N previous measurement this or other quantities in the past. The first part of the paper describes the use of artificial neural networks which forecast the life of insulating material for windings in electric rotary machines, the description of training and test data and setting of neural network for prediction. The second part shows (in the figures) the curves of prediction and the simulation of insulating material behaviour with neural networks. Tables evaluate the application of this tool for the solution of the problems investigated. We have used the above-mentioned neural networks for the prediction of insulating materials that were programmed in the Matlab 6 enviroment. All simulations and the values calculated were also obtained by means of this product.

Izolační materiál

Insulating Materials

01.01.2003

University of South Florida

Tampa - Florida

FAIM 2003 Proceedings of the 13th International Conference on Flexible Automation & Intelligent Manufacturing

12