Controllers implementation based on softcomputing for non-linear process

The work described in his paper aims at exploring the use of soft computing techniques for designing a controller to perform control of level in a spherical tank. First, system identification of this nonlinear process is done using black box model, which is identified to be non linear and approximated to be a first order plus dead time (FOPDT) model. Then the controller tuning strategy has been applied using Skogestadpsilas PI tuning technique. This technique has been compared with the soft computing techniques such as genetic algorithm (GA) for this non linear process using cost effective data acquisition ADAMpsilas module in real time. It is observed from the results that for both set point tracking and for regulatory change, controller based on soft computing techniques shows substantial improvement over the PI controller based on performance indices like integral squared error (ISE) and integral absolute error (IAE).