ANFIS gain scheduled CSTR with genetic algorithm based PID minimizing integral square error

In this paper, a new control scheme, the artificial neuro fuzzy inference system (ANFIS) gain scheduled genetic algorithm (GA) based PID is proposed for continuous stirred tank reactor (CSTR). CSTR is a highly nonlinear process that exhibits stability in certain region and instability in some regions. The proposed control scheme implements the characteristics of the genetic algorithm's (GA) global optimization to optimize the PID's three control parameters: k
_p
, k
_i
, k
_d
, to obtain the best control effect by minimizing integral square error online. The GA tuned PID controller parameters are gain scheduled using ANFIS. ANFIS gain- scheduling is a special form of neuro-fuzzy control that uses linguistic rules and fuzzy reasoning to determine the controller parameter transition policy for the dynamic plant subject to large changes in its operating state. Simulation result shows the feasibility of using the proposed controller for the control of the dynamical nonlinear CSTR.