Cereal Chem 72:308-311  |  VIEW ARTICLE

Prediction of Dough Rheological Properties Using Neural Networks.

R. Ruan, S. Almaer, and J. Zhang. Copyright 1995 by the American Association of Cereal Chemists, Inc. 

A neural network was designed to predict the rheological properties of dough from the torque developed during mixing. Dough rheological properties were determined using traditional equipment such as farinograph and extensigraph. The back-propagation neural network was designed and trained with the acquired mixer torque curve (input) and the measured rheological properties (output). The trained neural network accurately predicted the rheological properties (greater than 94%) based on the mixer torque curve. The ability to measure the rheology of every batch of dough enables online process control by modifying subsequent process conditions. This development has significant potential to improve product quality and reduce cost by minimizing process variability during dough mixing.