This report presents optimization of abrasives machining of ductile cast iron using water based SiO2 nanocoolant. Conventional and nanocoolant grinding was peerformed using the precision surface grinding machine. Study was made to invetigate the effect of table speed and depth of cut towards the surface roughness and MRR. The best output parameters between conventional and SiO2 nanocoolant are carry out at the end of the experiment. Mathematical modeling is developed using the response surface method. Artificial neural network (ANN) model is developed for predicting the results of the surface roughness and MRR. Multi-Layer Perception (MLP) along with batch back propagation algorithm are used. MLP is a gradient descent technique to minimize the error through a particular training pattern in which it adjusts the weight by a small amount at a time. From the experiment, depth of cut is directly proportional with the surface roughness but for the table speed, it is inversely proportional to the surface roughness. For the MRR, the higher the value of depth of cut, the lower the value of MRR and for the table speed is vice versa. As the conclusion, the optimize value for each parameters are obtain where the value of surface roughness and MRR itself was 0.174 µm and 0.101 3cm/s for the conventional- single pass, 0.186 µm and 0.010 cm3/s for SiO2- single pass, 0.191µm and 0.115cm3 /s for conventional-multiple pass, and 0.240µm and 0.112 cm3 /s for the SiO2 - multiple pass.
展开▼
