This paper proposes a hybrid approach based on the Artificial Neural network and Genetic algorithm to optimize surface roughness at the abrasive water jet (AWJ) cutting of glass material. At first, Artificial Neural Network (ANN) was developed in order to model and predict surface roughness by considering the controllable cutting parameters such as water pressure, abrasive flow rate, jet traverse rate and stand of distance. Then the results of the neural network were compared with corresponding experimental tests. According to the obtained results, it was shown that the ANN model is able to present a predictive model of the process in order to estimate the surface roughness successfully. After that, ANN model was combined by genetic algorithm to obtain suitable machining parameters yield to minimal surface roughness. Finally, obtained results showed that, utilized hybrid technique in this paper was employed properly for optimizing AWJ cutting process.
Amirabadi, , Amirabadi, , Ashori, , & Jafarian, (2010). Optimising the Abrasive Water Jet Cutting of Glass Using Artificial Neural Network and Genetic algorithm. Journal of Modeling in Engineering, 8(23), 25-35. doi: 10.22075/jme.2017.1572
MLA
Amirabadi; Amirabadi; Ashori; Jafarian. "Optimising the Abrasive Water Jet Cutting of Glass Using Artificial Neural Network and Genetic algorithm". Journal of Modeling in Engineering, 8, 23, 2010, 25-35. doi: 10.22075/jme.2017.1572
HARVARD
Amirabadi, , Amirabadi, , Ashori, , Jafarian, (2010). 'Optimising the Abrasive Water Jet Cutting of Glass Using Artificial Neural Network and Genetic algorithm', Journal of Modeling in Engineering, 8(23), pp. 25-35. doi: 10.22075/jme.2017.1572
VANCOUVER
Amirabadi, , Amirabadi, , Ashori, , Jafarian, Optimising the Abrasive Water Jet Cutting of Glass Using Artificial Neural Network and Genetic algorithm. Journal of Modeling in Engineering, 2010; 8(23): 25-35. doi: 10.22075/jme.2017.1572
)