Designing fuzzy-genetic controllers in optimizing process parameters in feed production using metaheuristic algorithm

Soheil Seirafi¹ Mohsen Javanbakht² Kowsarnoosh company³

1) Department of Electrical Engineering, Ostim Teknik University, Ankara,
2) Iran university of Science and
3) Kowsarnoosh

Publication : 5th. International Congress On Engineering, Technology and Innovation(eticong.com)
Abstract :
Artificial neural network is a method used to optimize process parameters. Root mean square error and coefficient of determination and calculation time are used as performance measures, and it is observed that the Polak-Ribiere conjugate gradient backpropagation training function combined with the log-sigmoid-net linear transfer function provides good results among the available options. Then the process parameters are optimized using the ideal settings of the neural network parametersThis paper provides a brief overview of various processes in feed manufacturing and identifies critical process parameters. Five critical parameters are identified where production rate is the output parameter. Feed size, steam temperature, ventilation time and feed rate are input parameters
Keywords : root mean square error neural network Conjugate gradient Optimization metaheuristic Optimal controllers matlab simulink