THE INFLUENCE OF THE FILM FORMED ON THE PRATO CHEESE SURFACE DURING THE NACL AND KCL SALTING PROCESS: APPLICATION OF THE FINITE ELEMENT METHOD AND NEURAL NETWORKS OF THE SELF-ORGANIZING MAP (SOM) AND MULTILAYER PERCEPTRON (MLP) TYPES

• Autor(a) principal: Borsato,Dionisio
• Data de Publicação: 2022
• Outros Autores: Silva,Hágata C., Mantovani,Ana Carolina G., Clemente,Marco A. J., Oliveira,Talita F. de, Angilelli,Karina B.
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Química Nova (Online)
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-40422022000600666
• topic: Prato cheese; brine; low sodium; SOM; MPL; neural networks.

Sodium chloride is used in the cheese salting process as it promotes sensory changes and food preservation. However, in excess can cause hypertension problems, and for this reason, it has been partially replaced by potassium chloride. In the present work, Prato cheese was subjected to joint diffusion of NaCl and KCl by immersion in static and stirred brine. The salt concentration values on the cheese surface were determined as a function of time. They were tabulated and presented to the self-organizing map (SOM)-type neural networks and the multilayer perceptron (MLP) for analysis and modeling of the film formed on the surface of the cheese during static and dynamic salting. The SOM network showed that the behavior of the diffusive process, on the surface of the cheese, depends on the analyzed position and that the points in which occupy similar positions, concerning the distance from the edge, have similar behavior. Regression models for NaCl and KCl were significant at the 5% level and can be used for predictive purposes.