正常モードのデータのみを用いたニューラルネットワークによるボールベアリングの異常診断法

DOI Web Site Web Site 参考文献16件

書誌事項

タイトル別名
  • A Method of Ball-bearing Diagnosis by Neural Network Using the Normal Mode Data
  • セイジョウ モード ノ データ ノミ オ モチイタ ニュラル ネットワーク ニ

この論文をさがす

抄録

This paper presents a new method of failure diagnosis by neural network which has been learning with spectra of normal mode and artificial abnormal mode. The data of normal mode can be obtained easily from normal operating machine before failure, and artificial abnormal data are made with the pseud-random numbers. In actuality, it is difficult to make preliminary arrangements for varied abnormal mode. Therefore, the method using artificial abnormal data is practically very usefull.<br>The effectiveness of proposed method is confirmed by diagnosis of ball-bearing defects. We consider also the degree of spectral resolution have an effect on the rate of correct diagnosis.

収録刊行物

参考文献 (16)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ