Prediction of mass-transfer kinetics on product quality changes during a dehydration-impregnation-soaking process using artificial neural networks. Application to pork curing

Boucané is a cured pork belly product ftom Réunion. This product is traditionally processed by salting, drying, cooking and smoking raw pork belly in one step or sequentially. A technique involving immersion in a concentrated solution (consisting of water, salt, glucose syrup and liquid smoke flavoring) is proposed with the aim of improving the efficiency of the boucané manufacturing process and enhancing the sanitary quality, of the end product. The product could thus be directly dehydrated and formulated in a single operation by this alternative process. An artificial neural network model was developed to analyse and optimize this process. The model mathematically correlates the process command variables (temperature, sugar and liquid smoke flavoring concentrations of the immersion solution) with the end-product characteristics (water loss, salt, phenol and sugar gains, water activity and pH patterns). (Résumé d'auteur