Cutting Parameters Optimization of Mild Steel via AIS Heuristics Algorithm
The minimum cost and higher productivity represent the main challengers in recent Industrial renaissance. Selecting the optimal cutting parameters play a big role in achieving these aims. Heat generated in cutting zone area is an important factor affects on work piece and cutting tool properties. Th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/13545/1/idecon2014_submission_126_%281%29.docx http://eprints.utem.edu.my/id/eprint/13545/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The minimum cost and higher productivity represent the main challengers in recent Industrial renaissance. Selecting the optimal cutting parameters play a big role in achieving these aims. Heat generated in cutting zone area is an important factor affects on work piece and cutting tool properties. The surface finish quality specifies the product success and integrity. In this paper, the temperature generated in cutting zone (shear zone and chip-tool interface zone) and work piece surface roughness will be optimized. The results analysis achieved using Artificial Immune System (AIS) intelligent algorithm. A mild steel type (S45C) work piece and tungsten insert cutting tool type (SPG 422) via dry CNC turning operation used in experimental results. The optimum cutting parameters (cutting velocity, depth of cut and feed rate) calculated by (AIS) algorithm to obtain the simulated and ideal cutting temperature and surface roughness. An infrared camera type (Flir E60) used for temperature measurement and a portable surface roughness device used for roughness measurement. The experimental results showed that the ideal cutting temperature (110 Cо) and surface roughness (0.49 µm) occurred at (0.3 mm) depth of cut , (0.06 mm) feed rate and (60 m/min) cutting velocity. AIS accuracy in finding the ideal cutting temperature and surface roughness is (91.7 %) and (89.2 %) respectively. The analysis showed that the predicted results compared with experimental are very close which referred that this intelligent system can be used to estimate the cutting temperature and surface roughness in the turning operation of mild steel. |
|---|