Forecasting Research Of Aero-engine Rotate Speed Signal Based on ARMA Model

Abstract

This paper presents a method to analyze and forecast the rotate speed signal of one type of aero-engine that is based on time series theory by establishing ARMA model, and establishes ARMA (3, 1) model to predict the value and transformation trend of rotate speed signal. The application results show that the established ARMA (3, 1) model can simulate rotate speed signal series quite well with good prediction accuracy, so it suggests that the method which is based on time series and ARMA model can be affectively and applicably used in aero-engine condition monitoring and fault diagnosis.