| Autor: |
N. I. Bouraou, O. V. Zazhitsky, A. G. Protasov, Yu. V. Sopilka |
| Rok vydání: |
2005 |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings. |
| ISSN: |
0094-243X |
| DOI: |
10.1063/1.1916751 |
| Popis: |
In this paper the simulation of vibroacoustical signals radiated by the engine turbine at the stationary vibration excitation is carried out for situations when all turbine blades have no defects and one blade has a small fatigue crack. Bispectral analysis is used for diagnostic information processing. It demonstrates that appearance and evolution of the fatigue crack in a blade change intensity of global and local extremums of bispectral modules. The results of bispectral processing and Probability Neural Network (PNN) are used to recognize of the turbine blades condition. The efficiency factor is used for precision analysis. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
