Discrete system identification and self-tuning control of dissolved oxygen concentration in a stirred reactor

This work presents the applications of discrete-time system identification and generalized minimum variance (GMV) control of dissolved oxygen (DO) level in a batch bioreactor in which Saccharomyces cerevisiae is produced at aerobic condition. Air flow rate and mixing rate were varied to determine the maximum local liquid phase volumetric mass transfer coefficient (K L a). Maximum K L a value was determined at a mixing rate of 600 rpm and air flow rate of 3.4 Lmin −1 . For control purpose, manipulated variable was selected as air flow rate due to its effectiveness on the K L a. To examine the dynamic behavior of the bioreactor, various input signals were utilized as a forcing function and three different model orders were tested. A second0order controlled auto regressive moving average (CARMA) model was used as the process model in the control algorithm and in the system identification step. It is concluded that the ternary input is more suitable than the other input types used in this work for system identification. Recursive least squares method (RLS) was used to determine the model parameters. GMV control results were compared with the traditional PID control results by using performance criteria of IAE and ITAE for different types of DO set point trajectories. DO concentration in the batch bioreactor was controlled more successfully with an adaptive controller structure of GMV than the PID controller with fixed parameters.