In this work, a multivariable adaptive self-tuning controller (STC) was developed for a biotechnological process application. Due to the difficulties involving the measurements or the excessive amount of variables normally found in industrial process, it is highly recommended to develop 'soft-sensors' which, in this work, were based fundamentally on artificial neural networks (ANN). These methods are especially suitable for the identification of time-varying and nonlinear models. An advanced control strategy based on STC was applied to a fermentation process to produce ethanol (ethyl alcohol) in industrial scale. The reaction rate considered for substratum consumption, cells and ethanol productions are validated with industrial data for typical operating conditions. Tho results obtained show that the procedure proposed in this work has a great potential for application.