Determination of beer quality parameters using artificial intelligence techniques

• Grant number: 16/20839-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2017
• End date: January 31, 2018
• Field of knowledge: Engineering - Chemical Engineering
• Principal Investigator: José Celso Rocha
• Grantee: Júlio Cézar Elias da Cunha Filho
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

Quality control is of major importance for the bioprocess industry, and it may require considerable resources, as in the case of beer production. The parameters analyzed to characterize beer quality are related to the occurrence of certain molecules in the beverage, which have characteristic UV-Vis spectra. UV-Vis spectroscopy is suitable for quality monitoring of final products, when associated to mathematical techniques able to correlate spectral data with quality parameters. In this context, artificial intelligence techniques, mainly artificial neural networks and genetic algorithms, provide good results in mathematical modeling of bioprocess, because they are better in solving nonlinear problems. Therefore, the present work aims to develop a software, based on two artificial intelligence techniques, that determine simultaneously eight beer quality parameters (total acidity, color, haze, alcohol content, protein concentration, foam stability, vicinal diketones and bitterness) using UV-Vis spectra, and to build a computational interface, creating a technological tool that can be used for academic and/or commercial purposes. Once implemented, this method enables to save time and resources in the beer industry. (AU)