Selection of optimal cutting conditions by using the genetically optimized neural network system (GONNS)

  • Authors:

  • W. Y. Bao;Peng Chen;I. N. Tansel;N. S. Reen;S. Y. Yang;D. Rincon

  • Affiliations:

  • Mechanical Engineering Department, Florida International University, Center for Engineering and Applied Sciences, Miami, FL;Mechanical Engineering Department, Florida International University, Center for Engineering and Applied Sciences, Miami, FL;Mechanical Engineering Department, Florida International University, Center for Engineering and Applied Sciences, Miami, FL;Mechanical Engineering Department, Florida International University, Center for Engineering and Applied Sciences, Miami, FL;Mechanical Engineering Department, Florida International University, Center for Engineering and Applied Sciences, Miami, FL;Mechanical Engineering Department, Florida International University, Center for Engineering and Applied Sciences, Miami, FL

  • Venue:
  • ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Genetically Optimized Neural Network System (GONNS) is proposed to select the optimal cutting conditions in micro-end-milling operations. Two Backpropagation (BP) type Artificial Neural Networks (ANN) represented the characteristics of feed and thrust direction cutting forces. Genetic algorithm found the optimal cutting conditions by evaluating the cutting force estimations of two ANNs. The GONNS is a very convenient computational tool for optimization problems when systems have complex relationship and some experimental data is available.