Roman R.C.,University of Valparaíso |
Hernandez O.G.,University of Valparaíso |
Hernandez O.G.,University of Chile |
Urtubia U.A.,Federico Santa María Technical University |
Urtubia U.A.,Centro Regional Of Estudios Of Alimentos Saludables
Bioprocess and Biosystems Engineering | Year: 2011
Artificial neural networks (ANNs) have been used for the recognition of non-linear patterns, a characteristic of bioprocesses like wine production. In this work, ANNs were tested to predict problems of wine fermentation. A database of about 20,000 data from industrial fermentations of Cabernet Sauvignon and 33 variables was used. Two different ways of inputting data into the model were studied, by points and by fermentation. Additionally, different sub-cases were studied by varying the predictor variables (total sugar, alcohol, glycerol, density, organic acids and nitrogen compounds) and the time of fermentation (72, 96 and 256 h). The input of data by fermentations gave better results than the input of data by points. In fact, it was possible to predict 100% of normal and problematic fermentations using three predictor variables: sugars, density and alcohol at 72 h (3 days). Overall, ANNs were capable of obtaining 80% of prediction using only one predictor variable at 72 h; however, it is recommended to add more fermentations to confirm this promising result. © 2011 Springer-Verlag.
Emparan M.,University of Valparaíso |
Simpson R.,Federico Santa María Technical University |
Simpson R.,Centro Regional Of Estudios Of Alimentos Saludables |
Almonacid S.,Federico Santa María Technical University |
And 4 more authors.
Food Control | Year: 2012
Multiway principal component analysis (MPCA) and multiway partial least squares (MPLS) were applied to unfolded fermentation data, and compared for early recognition of problematic behavior in wine fermentations, such as late onset, slow or stuck (premature termination of fermentation). Information from 17 industrial wine fermentations (batches) were used, consisting of measured values for 32 variables, consisting of sugars, density, alcohols, organic acids and nitrogen compounds (including all amino acids). Curve smoothing and curve fitting techniques were applied as necessary pre-treatment of the data. Then, MPCA and MPLS were applied to four different data sets with different combinations of variables to identify the principal components responsible for the problematic behavior. Density, sugars, alcohols and selected organic acids were identified as the principal components. The MPCA application detected only 67% of problematic batches in the data sets after 72 h into the fermentation process. Whereas, the MPLS application was able to predict all of the problematic batches (100%) using the same variables and at the same time into the fermentation process. The ability to identify a problematic fermentation within 72 h can have significant economic impact on operating costs in a commercial winery. © 2012 Elsevier Ltd.
Urtubia A.,Federico Santa María Technical University |
Urtubia A.,Centro Regional Of Estudios Of Alimentos Saludables |
Journal of Chemometrics | Year: 2011
Wine fermentation is a critical step of winemaking. Unfavorable conditions can seriously affect the quality of the final product; however, it is difficult to anticipate these abnormal behaviors. In this study, the predictive power of stepwise linear discriminant analysis (SLDA) was evaluated to discriminate the behavior of wine fermentation. Information on different chemical concentrations from 18 industrial wine fermentations of Cabernet Sauvignon was used in this study. The statistical procedure consisted of curve fitting with exponential curve, and Stepwise LDA applied to the parameters of the curve. This methodology was applied to different times between the beginning and the end of fermentation (72, 95, 100, 150, 200 and 400h). The results revealed that between seven and eight, of the 28 variables studied, minimized the Standard Error of Cross-Validation (SECV) for the different times. In almost all times studied, correlation coefficient of alcoholic degree, initial concentration of glucose, initial density and correlation coefficient of tartaric acid were the variables more discriminant, and they indicated some differences between a normal and an abnormal fermentation, which need to be corroborated with more information. In this work, before 95h, it was not possible to minimize the prediction error and find the most discriminant variables. © 2011 John Wiley & Sons, Ltd.