An adaptive signal classification procedure. Application to aircraft engine condition monitoring

作者:

Highlights:

摘要

A method (C) for adaptive signal classification is described, and closely related to actual diagnostic problems in monitored aircraft engines for which an input-output model is available. This new method is based on the prediction in parallel of the output residual and of discriminant functions, thus yielding a predictive state classification into overall degradation classes. Updating is achieved by monitoring the actual output and requesting an a posteriori classification from a “teacher”. The main applications are in the field of degradation analysis, and early warning of overall degradation in monitored control systems. (C) has been implemented in the engine maintenance department of an airline.

论文关键词:Signal classification,Failure diagnosis,Dual filtering,Kalman filter,Autoregressive process,Discriminant functions,Engine condition monitoring

论文评审过程:Received 2 December 1976, Revised 29 March 1977, Available online 19 May 2003.

论文官网地址:https://doi.org/10.1016/0031-3203(77)90009-7