非線形主成分分析を用いた回転機の音響監視
英字タイトル:
Acoustic Diagnosis Using Kernel Based Principal Component Analysis
著者:
兼本 茂 Shigeru KANEMOTO 玉置 哲男 Tetsuo TAMAOKI 清水 俊一 Shun-ichi SHIMIZU
発刊日:
公開日:
Acoustic diagnosisKernel-based PCAProbabilistic neural network
Acoustic Diagnosis Using Kernel Based Principal Component Analysis
著者:
兼本 茂 Shigeru KANEMOTO 玉置 哲男 Tetsuo TAMAOKI 清水 俊一 Shun-ichi SHIMIZU
発刊日:
公開日:
カテゴリ: 第5回
キーワードタグ:Acoustic diagnosisKernel-based PCAProbabilistic neural network
概要
The acoustic data remotely measured by handy type microphones are investigated for monitoring and diagnosing the ball bearing type rotational machine integrity in nucle ar power plants. The present study proposes the new signal pre-processing method which normalizes the fundamental oscillation period into the same length and timing by using zero-crossing interval of filtered acoustic signal. The pre-processed signal patterns are classified by kernel-based principal component analysis (KPCA) and prob abilistic neural network (PNN). It is shown that the monitoring index defined by KPCA and PNN is useful to classify the known and unknown states with high sensitivity.
