Prediction of Abnormal Situation in Nonlinear Systems Using EKF

In this paper, an advanced monitoring method is proposed to predict the time instants that process variables will exceed specific abnormal limits. Presented method estimates unknown disturbances that enter the process and predicts process variables based on extended Kalman filter (EKF). Suggested strategy predicts future variables without linearization, so the results are more precise and reliable. Disturbance outset is computed based on residuals analysis. Using this method, control system (or operator) will have additional time before the abnormal or emergency situation occurs, thus more effective decisions can be made. To ensure the method efficiency, a nonlinear continuous stirred tank reactor (CSTR) is simulated and results are presented.