Soft sensor based on generalized support vector machines for microbiological fermentation

Microbiological fermentation is a kind of complicated batch process that is severely nonlinear and time variant. There are many process parameters need to monitor and control in order to make the microbiological fermentation process successful. So it is important to measure the process variables. But the instrumentation and sensors available for fermentation control do not cover all the desirable or necessary measurements. In fermentation processes, many important internal variables can´t be measured. Soft sensor has become an indispensable method to measure internal variables in fermentation processes. In this paper, we propose a new method of soft sensor constructed with generalized support vector machine for microbiological fermentation. We discuss how to construct soft sensor with generalized support vector machine and least square generalized support vector machine respectively. This method was compared with neural network in the experiment of soft sensor construction. Experiment results demonstrate this method of constructing soft sensor in microbiological fermentation is very valid.