An adaptive integral plus states neural control of aerobic continuous stirred tank reactor

An identification and direct adaptive neural control system with and without integral term is proposed. The system contains a neural identifier, and a neural controller, based on the recurrent trainable neural network model. The applicability of the proposed direct adaptive neural control system of both proportional and integral-term direct adaptive neural control schemes is confirmed by comparative simulation results, obtained with a nonlinear mathematical model of an aerobic continuous stirred tank reactor. The comparison is done also with respect to the lambda-tracking method of control. The obtained comparative graphical simulation results show that the proposed control system exhibit good convergence, but the I-term control system could compensate a constant offset and proportional control systems could not.