文章詳目資料

先進工程學刊

  • 加入收藏
  • 下載文章
篇名 Hilbert-Huang 轉換及類神經網路結合運用於非穩態振動信號之故障診斷
卷期 6:1
並列篇名 Fault Diagnosis for Nonstationary Vibration Signal Using Combined Hilbert-Huang Transform and Neural Network
作者 張永鵬王俊傑鐘裕亮曾獻毅林忠賢康淵
頁次 059-067
關鍵字 故障Hilbert-Huang 轉換時頻分析類神經網路故障診斷Hilbert-Huang Transformtime-frequency analysisneural networkfault diagnosis
出刊日期 201101

中文摘要

本文以Hilbert-Huang 轉換方法應用於非穩態振動信號之故障診斷,先以經驗模態分解將振動信號轉換到固有模態函數分量,再使用Hilbert 轉換得到瞬時振幅及瞬時頻率,以時頻函數呈現出不同類型信號的能量分佈,最後針對各固有模態函數分量之瞬時振幅取能量特徵,輸入至倒傳遞類神經網路中,實現人工智慧識別故障狀態,本文並以實測驗證所提方法的可行性。

英文摘要

The paper applies Hilbert-Huang Transform (HHT) in the vibration signals by the empirical mode decomposition (EMD), and the data can be decomposed into several intrinsic mode functions (IMFs). With the Hilbert transform (HT), the presentation of the instantaneous frequencies and amplitude that is a time-frequency-energy distribution. The energy features is excited from each intrinsic mode function and entered the back-propagation neural network to prove the intelligence fault diagnosis.

相關文獻