Computer control of pH and DO in a laboratory fermenter using a neural network technique

Abstract

In this contribution, the advantages of the artificial neural network approach to the identification and control of a laboratory-scale biochemical reactor are demonstrated. It is very important to be able to maintain the levels of two process variables, pH and dissolved oxygen (DO) concentration, over the course of fermentation in biosystems control. A PC-supported, fully automated, multi-task control system has been designed and built by the authors. Forward and inverse neural process models are used to identify and control both the pH and the DO concentration in a fermenter containing a Saccharomyces cerevisiae based-culture. The models are trained off-line, using a modified back-propagation algorithm based on conjugate gradients. The inverse neural controller is augmented by a new adaptive term that results in a system with robust performance. Experimental results have confirmed that the regulatory and tracking performances of the control system proposed are good.

Bioreactor profile design and optimization for ethanol production

“…The pH and DO control by 2DOF-PID was compared with the robust artificial neural network controller given in [3] and the results are shown in Figure 6 and 7 respectively.…”

“…The pH controller in [3] shows significant amount of chattering apart from the delays in rise time with oscillations around the target value. The output never settles down to desired value, whereas the designed controller manages to follow the target profile with high degree of accuracy without any chattering.…”

“…The quality and quantity of ethanol produced is highly dependent on the process parameters during fermentation. The fermentation is carried out in vessels called bioreactors in which the process parameters are maintained at levels that provide optimum fermentation conditions for higher quantity and better quality of ethanol [3,4]. Controllers are used to adjust theflow of cooling agent (F ca ), stirring speed (S sp ) and the flow of acid (F ac ) or base (F ba ) based on the sensor outputs measuring temperature, DO and pH respectively.…”

Bioreactor profile control by a nonlinear auto regressive moving average neuro and two degree of freedom PID controllers

“…But the variations in process parameters namely temperature, DO and pH greatly affect the yield and quality of product. Hence to increase the yield and to maintain the quality of ethanol these three parameters must follow a precise profile [7,8]. Appropriate sensors are used to measure temperature, dissolved oxygen and pH level.…”

Nonlinear PI controllers for continuous bioreactors using population balance models

“…According to those issues, two manipulated variables are required and the nonlinear model-based control framework is sophisticated on the real-time implementation. Therefore, the PC-supported control system has been developed in some fermentation processes irrelevant to mathematical models [11].…”