Abstract
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.
Similar content being viewed by others
References
Blateyron L, Sablayrolles JM (2001) Stuck and slow fermentations in enology: statistical study of causes and effectiveness of combined additions of oxygen and diammonium phosphate. J Biosci Bioeng 91:184–189
Bisson L, Butzke C (2000) Diagnosis and rectification of stuck and sluggish fermentations. Am J Enol Viticult 51:168–177
Pszczólkowski P, Carriles P, Cumsille M, Maklouf M (2001) Reflexiones sobre la madurez de Cosecha y las condiciones de vinificación, con relación a la Problemática de Fermentaciones Alcohólicas Lentas y/o paralizante, en Chile. Facultad de Agronomía, Pontificia Universidad Católica de Chile, Chile
Huang J, Nanami H, Kanda A, Shimizu H, Shioya S (2002) Classification of fermentation performance by multivariate analysis based on Mean Hypothesis Testing. J Biosci Bioeng 94:251–257
Lee JM, Yoo Ch, Lee IB (2003) On-line batch process monitoring using a consecutively updated multiway principal component analysis model. Comput Chem Eng 27:1903–1912
Chiang L, Leardi R, Pell R, Seasholtz M (2006) Industrial experiences with multivariate statistical analysis of batch process data. Chemom Intell Lab Syst 81:109–119
Ferreira A, Lopes J, Menezes J (2007) Study of the application of multiway multivariate techniques to model data from an industrial fermentation process. Anal Chim Acta 595:120–127
Faggian A, Facco P, Doplicher F, Bezzo F, Barolo M (2009) Multivariate statistical real-time monitoring of an industrial fed-batch process for the production of specialty chemicals. Chem Eng Res Des 87:325–334
Bevin C, Dambergs R, Fergusson A, Cozzolino D (2008) Varietal discrimination of Australian wines by means of mid-infrared spectroscopy and multivariate analysis. Anal Chim Acta 621:19–23
Cozzolino D, Parker M, Dambergs R, Herderich M, Gishen M (2006) Chemometrics and visible-near infrared spectroscopic monitoring of red wine fermentation in a pilot scale. Biotechnol Bioeng 95:1101–1107
Urtubia A, Pérez-Correa J, Soto A, Pszczólkowski P (2007) Using data mining techniques to predict industrial wine problem fermentations. Food Control 18:1512–1517
Urtubia A, Emparan M, Almonacid S, Pinto M, Valdenegro M (2010) Application of MPCA and MPLS on industrial batch bioprocesses. J Biotechnol 150:310
Urtubia A, Roger JM (2011). Predictive power of LDA to discriminate abnormal wine fermentations. J Chemom. http://onlinelibrary.wiley.com/doi/10.1002/cem.1362/pdf
Thissen U, Melsen W, Buydens L (2001) Nonlinear process monitoring using bottle-neck neural networks. Anal Chim Acta 446:369–381
Marini F, Bucci R, Magri A (2008) Artificial neural networks in chemometrics: history, examples and perspectives. Microchem J 88:178–185
Lopes J, Menezes J (2004) Multivariate monitoring of fermentation processes with non-linear modeling methods. Anal Chim Acta 515:101–108
Jain A, Mao J, Mohiuddin K (1996) Artificial neural networks: a tutorial. Computer 9:31–44
Bishop CM (1996) Neural networks for pattern recognition. Oxford University Press, Oxford
Ripley B (2008) Pattern recognition and neural networks. Cambridge University Press, Cambridge
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366
Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4:251–257
Rumelheart D, Durbin R, Golden R, Chauvin Y (1995) Backpropagation: the basic theory. In: Chauvin Y, Rumelheart D (eds) Backpropagation: theory architectures and applications. Lawrence Erlbaum, Hillsdale
Beltran N, Duarte-Mermoud M, Bustos M, Salah S, Loyola E, Pena-Neira A, Jalocha J (2006) Feature extraction and classification of Chilean wines. J Food Eng 75:1–10
Penza M, Cassano G (2004) Chemometric characterization of Italian wines by thin-film multisensors array and artificial neural networks. Food Chem 86:283–296
Perez-Magariño S, Ortega-Heras M, Gonzalez-San Jose M, Boger Z (2004) Comparative study of artificial neural network and multivariate methods to classify Spanish DO rose wines. Talanta 62:983–990
Kruzlicova D, Mocak J, Balla B, Petka J, Farkova M, Havel J (2009) Classification of Slovak white wines using artificial neural networks and discriminant techniques. Food Chem 112:1046–1052
Urtubia A (2006) Monitoring of wine fermentations using MIR spectroscopy and data mining techniques. PhD Thesis of Engineering Science. Pontificia Universidad Católica de Chile, Chile
Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform 35:352–359
King S (2003) Using ROC curves to compare neural networks and logistic regression for modeling individual noncatastrophic tree mortality. In: Proceedings of the 13th Central Hardwood Forest Conference, pp 349–358
Palmer P, Montaño M (1999) ¿Qué son las Redes Neuronales Artificiales? Aplicaciones realizadas en el ámbito de las adicciones. Adicciones 11(3):243–255
Acknowledgments
A. Urtubia thanks the financial support from FONDECYT Project (Grant Number 11070251).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Román, R.C., Hernández, O.G. & Urtubia, U.A. Prediction of problematic wine fermentations using artificial neural networks. Bioprocess Biosyst Eng 34, 1057–1065 (2011). https://doi.org/10.1007/s00449-011-0557-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00449-011-0557-4