Procedia Engineering · 2012 · 15 citations · 9 references
EngineeringChemical EngineeringProcess ControlProcess DynamicsProcess Systems EngineeringControl SystemsControl TheoryController DesignNeural Control SystemsNonlinear Process ControlSystem IdentificationFuzzy ControlFuzzy Control SystemsIntelligent ControlInternal Model ControlNeural Network ControlNonlinear Control Of Process SystemsPid Control DesignStep Response
In this paper, a neural network (NN) based internal model control (IMC) -PID controller is proposed for a non–linear process. The controller structure has been outlined and its performance is demonstrated on a conical tank process. The control of liquid level in a conical tank is nonlinear due to the variation in the area of cross section of the tank system with its change in shape. The model of the process is identified using standard step response based system identification technique and it is approximated to be first order plus dead time (FOPDT) model. From the results it is observed that fuzzy controller shows much better integral absolute error (IAE) and integral squared error (ISE) performance criteria than the conventional controller.
9
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations