Neural Network Based Predictive, Narma-l2 and Neuro-fuzzy Control for a Cstr Process

In recent years, there has been an expansive growth in the study and implementation of neural networks over a spectrum of research domains. Neural network based Predictive control is recognized as an efficient methodology to address difficult control problems. The NARMA model is an exact representation of the input-output behaviour of finite dimensional non-linear discrete time dynamical systems in the neighbourhood of the equilibrium state. There has been a significant increase in the number of control system techniques that are based on nonlinear concepts. With the increasing research activities in the field of structural control, many control methods have been proposed and implemented. These methods are fuzzy control, optimal control, pole placement, sliding mode control, etc. Designing an effective criterion and learning algorithm for find the best structure is a major problem in the control design process. The fusion of ideas from fuzzy control and neural networks had acknowledged a significant role in improving controller performances. Fuzzy logic has proven effective for complex, nonlinear and imprecisely defined systems. Neural network derives its computing power through it’s massively distributed structure and its ability to learn and therefore generalize. The fuzzy logic and neural networks can be integrated to form a connectionist adaptive network based fuzzy logic controller. To implement Neural network based Predictive and NARMA-L2 control, first step is modeling of the process for system identification and the second step is the controller design. Neural network based Predictive controller, NARMA-L2, Neuro fuzzy logic controller are implemented for a CSTR process and their performance are compared.