FAULT DETECTION AND CONTROLLING OF SHELL AND TUBE HEAT EXCHANGER USING ANN

Abstract

Fault Detection and controlling is important in many industries to provide safe operation of a process. Heat Exchangers are generally used in process industries. Shell and Tube Heat Exchanger  is a common type of heat exchanger used in oil refineries, chemical processes .It is suited for higher-pressure applications. Actuator faults, sensor faults and process faults are the common faults occurring in chemical processes. To identify and remove these type of faults in the system fault detection and controlling techniques are proposed.  In this present work Sensor and Process faults of Shell and Tube Heat Exchanger is detected and controlled using Artificial Neural Network(ANN).NARX network (Nonlinear Auto regressive with External input) is used as ANN network structure. Network is trained using Levenberg Marquardt and Bayesian Regularization algorithms. The performance parameters such as Mean Square Error, Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE) and Integral Square Error (ISE) are obtained for the above said methods which are shown in simulation results. Tabulated results shows the comparison between the three algorithms. Simulation results also shows the comparison between the controlled response obtained from ANN with and without PID Controller.