On-line learning prediction of machine condition

온라인 학습에 의한 기계상태의 예측

  • Published : 1994.04.01

Abstract

A radial basis hybrid neural network (RHNN) is presented for on-line prediction of machine condition. A modular-based neural architecture is designed for modeling a machine condition process and for predicting future signal. A fast on-line learning algorithm is introduced. Experimental results showed the RHNN could be utilized efficiently for on-line machine condition monitoring.

Keywords