Comparative performance analysis of extended Kalman filter and neural observer for state estimation of continuous stirred tank reactor

Abstract

In this paper, a systematic approach to design a non-linear observer to estimate the states of a non-linear system is proposed. The neural network based state filtering algorithm proposed by A.G. Parlos et al. has been used to estimate the state variables, concentration and temperature in the Continuous Stirred Tank Reactor (CSTR) process. CSTR is a typical chemical reactor system with complex nonlinear dynamics characteristics. The variables which characterize the quality of the final product in CSTR are often difficult to measure in realtime and cannot be directly measured using the feedback configuration. In this work, the authors compare the performance of an Extended Kalman Filter (EKF) with respect to Neural Network (NN) based state filter for CSTR that rely solely on concentration estimation of CSTR via measured reactor temperature. The performance of these two filters is analyzed in simulation with Gaussian noise source under various operating conditions and model uncertainties.