ARTIFICIAL NEURAL NETWORK APPROACH COUPLED WITH GENETIC ALGORITHM FOR PREDICTING DOUGH ALVEOGRAPH CHARACTERISTICS

作者：Abbasi Hajar^*; Emam Djomeh Zahra; Ardabili Seyyed Mahdi Seyedain

来源：Journal of Texture Studies, 2014, 45(2): 110-120.

DOI：10.1111/jtxs.12054

• Physicochemical
• rheological properties
• sensitivity
• wheat-flour dough

Alveograph is a useful device for rheological measurement of dough from biaxial extension. Our purpose in the current research was to apply soft computing tools for predicting the alveograph properties (maximum pressure for blowing the bubble [P], abscissa at bubble rupture [L], deformation energy [W]) using physicochemical properties of flour (protein, ash, wet gluten, gluten index, amylase activity, zeleny and particle size). Generalized feed-forward artificial neural networks (ANN) with back-propagation learning algorithms were employed to model the alveograph properties. A genetic algorithm (GA) was applied to optimize the parameters of the ANN's structure and inputs. Sensitivity analyses were conducted to explore the ability of the networks with using physicochemical properties of flour as inputs in predicting alveograph properties. The developed ANNs using GA were shown to have excellent potential in predicting the alveograph properties. Sensitivity analyses showed that zeleny (Sedimentation value) is the most sensitive input in predicting alveograph characteristics.
Practical ApplicationsThe alveograph is a device to measure empirical rheological properties of dough during bubble inflation. Accurate prediction of dough rheology could provide many benefits to the baking industry, for example making inline process adjustments and modifying product formulation to satisfy consumer demands. In the current study, an ANN approach was applied to predict the alveograph properties of dough (P, L and W). The physicochemical properties of flour (protein, ash, wet gluten, gluten index, amylase activity, zeleny and particle size) and the parameters of alveography were set as inputs and outputs of the networks, respectively. A GA was applied as a suitable optimizer method to determine the best topology and inputs of the networks. The developed networks have excellent performance in prediction of outputs when compared with test data. Sensitivity analyses were also performed to investigate the suitability of inputs on estimating alveograph properties (outputs) of the dough.

• 出版日期2014-4