Advancing Wine Fermentation: Extended Kalman Filter for Early Fault Detection

Abstract

This work proposes an Extended Kalman Filter (EKF) state estimation approach for early detection of stuck and sluggish wine fermentations. The goal is to provide accurate information to enologists during fermentation to facilitate timely intervention and decision making. The study investigates the sensitivity of the fermentation process to various factors such as model parameters and initial conditions, especially for unmeasured nitrogen. It also shows how the estimation depends on meaningful sugar measurements, which are not available during the lag phase of fermentation. According to Monte Carlo simulations, the estimation algorithm was able to predict 95% of the problematic fermentations within the first few days. When initial nitrogen measurements are taken into account, a reliable prediction is available on the first day in 80% of the cases, justifying the additional cost. These results support the use of advanced control and monitoring methods in wine production and other alcoholic fermentation processes.