소형 항공기 엔진 고장 검출을 위한 주성분 분석(PCA) 연구

초록

This paper describes the results of the experiment to the failure of engine using a model airplane to satisfy the similarity dynamic for avoid the cost and risk of large aircraft in accordance with the actual experiment. The Averaged Normalized Power Spectral Density (ANPSD) analyze engine vibration signal and the principal component analysis (PCA) is proposed a fault diagnosis algorithm of reciprocating engine aircraft. Because ANPSD of the rotating shaft is sensitive to the rotating speed, this paper proposes to use a post-processing method of ANPSD is used to reduce the sensitivity. The PCA extracts compressed information from the post-processed ANPSDs and the information means the difference between current and normal cases of the engine.

키워드