A Method of Detecting Abnormal Signals using Recursive Maximum Likelihood Method and Baysian Statistical Inference

Abstract

A method of detecting abnormal process signals in fault diagnosis using recursive maximum likelihood method and baysian statistical inference was developed. It involves the sequential probability ratio test using baysian statistical inference for residual sequence of model estimation error by recursive maximum likelihood method. The method proposed in this study has the advantage of detecting online abnormal signals in industrial use. It was applied to abnormal detection of the catalyst feed flow in a linear low-density polyethylene plant to confirm the design philosophy. The actual result indicates that the proposed method is effective in detecting abnormal process signals.