Foundations of genetic algorithms
Foundations of genetic algorithms
Fundamentals of Artificial Neural Networks
Fundamentals of Artificial Neural Networks
Expert Systems with Applications: An International Journal
Journal of Intelligent Manufacturing
A method for grinding removal control of a robot belt grinding system
Journal of Intelligent Manufacturing
Journal of Intelligent Manufacturing
Combining rough set and case based reasoning for process conditions selection in camshaft grinding
Journal of Intelligent Manufacturing
Hi-index | 0.00 |
The present work is aimed to optimize creep feed grinding (CFG) process by an approach using integrated Genetic Algorithm-Neural Network (GA-NN) system. The aim of this creep feed grinding optimization is obtain the maximal metal removal rate (MRR) and the minimum of the surface roughness (R a ). For optimization, metal removal rate is calculated with a mathematic formula and a Back Propagation (BP) artificial neural-network have been used to prediction of R a . The parameters used in the optimization process were reduced to three grinding conditions which consist of wheel speed, workpiece speed and depth of cut. All of other parameters such as workpiece length, workpiece material, wheel diameter, wheel material and width of grinding were taken as constant. The BP neural network was trained using the scaled conjugate gradient algorithm (SCGA). The results of the neural network were compared with experimental values. It shows that the BP model can predict the surface roughness satisfactorily. For optimization of creep feed grinding process, an M-file program has been written in `Matlab' software to integrate GA and NN. After generation of each population by GA, firstly, the BP network predicts R a and then MRR has been calculated with mathematic formula. In this study, the importance of R a and MRR is equal in the optimization process. By using this integrated GA-NN system optimal parameters of creep feed grinding process have been achieved. The obtained results show that, the integrated GA-NN system was successful in determining the optimal process parameters.