Prediction of Grinding Machinability when Grind P20 Tool Steel Using Water Based Zno Nano-Coolant
Grinding is often an important finishing process for many engineering components and for some components it is even a major production process. In this study, prediction model have been developed to find the effect of grinding condition in term of depth of cut and type of grinding coolant. Zinc Oxid...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iceland Journal of Life Sciences
2014
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/5271/ http://umpir.ump.edu.my/id/eprint/5271/ http://umpir.ump.edu.my/id/eprint/5271/1/paper.pdf |
| Summary: | Grinding is often an important finishing process for many engineering components and for some components it is even a major production process. In this study, prediction model have been developed to find the effect of grinding condition in term of depth of cut and type of grinding coolant. Zinc Oxide (ZnO) nano-coolant was used as a coolant with water as a based liquid. The experiments
conducted with grinding depth in the range of 5 to 21μm. Silicon Carbide wheel are used to grind the AISI P20 tool work piece. Artificial intelligence model has been developed using Artificial Neural Network(ANN). Result shows that the lower surface roughness and wheel wear obtain at the lowest cutting depth which is 5 μm. Besides that, grind using ZnO nano-coolant gives best surface roughness and minimum wheel wears compared to grind using normal soluble coolant. The surface roughness have been reduced approximately 47.84% for single pass experiment and 126.1% for multi pass experiment. However, there is no wheel wheel wear obtain for grinding using ZnO nanocoolant. From the prediction of ANN, it can predict the surface roughness closely with the experimental value. |
|---|