Soft Sensor Based Fault Diagnosis of Industrial Fluid Catalytic Cracking Reactor

Abstract

Abstract Much of the earlier work presented in the area of on-line fault diagnosis focuses on knowledge based and qualitatively reasoning principles and attempts to present possible root causes and consequences in terms of a range of measured data. However, there are many unmeasured operating variables in chemical define the state of the system. Such variables essentially characterise the efficiency and really need to be known in order to diagnose possible malfunction and provide a basis for deciding on appropriate action to be taken by. This paper is concerned with developing soft sensors to assist in on-line fault diagnosis by providing information on the critical variables which are not directly accessible and is illustrated by reference to an industrial fluid catalytic cracker. A soft sensor is developed for estimating the circulation rate of catalyst and used in a fuzzy-neural network fault diagnosis system