Prediction of extensograph properties of wheat-flour dough: artificial neural networks and a genetic algorithm approach

Hajar Abbasi, Seyyed Mahdi Seyedain Ardabili, Zahra Emam-Djomeh, Mohammad Amin Mohammadifar, Maryam Zekri, Roya Aghagholizadeh

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Wheat-flour dough is a viscoelastic material with nonlinear rheological behavior. Extensograph is a useful system for dough rheological measurement. Our purpose in this research was to apply soft computation tools for predicting the extensograph properties of dough from several physicochemical properties of flour. This study used the resulting model to suggest modifications of processing conditions for reducing economic loss and minimizing product quality deterioration. A generalized feed-forward artificial neural network (ANN) with a back-propagation learning algorithm was employed to estimate the extensograph properties of dough. Trial and error and genetic algorithm (GA) were applied in the training phase for developing an ANN with an optimized structure. Developed ANN using GA has excellent potential for predicting the extensograph properties of dough. Sensitivity analyses were conducted to explore the ability of inputs in predicting the extensograph properties of dough. Results showed gluten index was the most sensitive input in dough extensograph characterizations. PRACTICAL APPLICATIONS Extensograph is a suitable instrument for measuring the stretching properties of dough to make reliable statements about the baking behavior of the wheat-flour dough in practical industrial applications and in research. Rheological measurements of each batch in the production line are very useful and make online and in-time process adjustments possible, but this is usually impractical in an industrial setting. Therefore, accurate prediction of dough rheology could provide many benefits to the baking industry for satisfying consumer demands. In the current study, genetic algorithm-neural network approach was applied to predict extensograph properties of dough as affected by physicochemical properties of flour. In comparison with trial and error, genetic algorithm can determine an artificial neural network's topology and inputs in less time with excellent performance in prediction. According to the results of sensitivity analyses, of the seven investigated inputs, changes in gluten index have the most effect on estimating extensograph properties of dough.
Original languageEnglish
JournalJournal of Texture Studies
Volume43
Issue number4
Pages (from-to)326-337
Number of pages12
ISSN0022-4901
DOIs
Publication statusPublished - 2012
Externally publishedYes

Keywords

  • Food Science
  • Pharmaceutical Science
  • Artificial neural network
  • Extensograph
  • Genetic algorithm
  • Wheat-flour dough
  • Backpropagation learning algorithm
  • Economic loss
  • Feed-forward artificial neural networks
  • Genetic algorithm approach
  • Optimized structures
  • Physicochemical property
  • Processing condition
  • Product quality
  • Rheological behaviors
  • Rheological measurements
  • Soft computation
  • Training phase
  • Trial and error
  • Visco-elastic material
  • Genetic algorithms
  • Learning algorithms
  • Losses
  • Neural networks
  • Rheology
  • Forecasting
  • Triticum aestivum
  • FOOD
  • RHEOLOGICAL PROPERTIES
  • FOOD-INDUSTRY
  • BREAD DOUGH
  • QUALITY
  • SIMULATION
  • PARAMETERS
  • GLUTEN
  • MODEL
  • VARIETIES
  • DYNAMICS
  • extensograph
  • genetic algorithm
  • wheat-flour dough
  • FLOUR
  • APPARATUS
  • ARTIFICIAL NEURAL NETWORKS
  • DOUGH
  • EXTENSOGRAPHS
  • INFORMATION TECHNOLOGY
  • MODELLING
  • WHEAT
  • WHEAT DOUGH
  • Cereals and bakery products
  • Wheat and rye

Fingerprint Dive into the research topics of 'Prediction of extensograph properties of wheat-flour dough: artificial neural networks and a genetic algorithm approach'. Together they form a unique fingerprint.

Cite this