| 000 | 02691nam a2200253 a 4500 | ||
|---|---|---|---|
| 001 | vtls000075704 | ||
| 003 | KUKTEM | ||
| 005 | 20251114204549.0 | ||
| 008 | 131022t2012 my da f abm 000 0 eng d | ||
| 020 | _aTHE0007421(Local) | ||
| 039 | 9 |
_a201905160945 _bfawwaz _y201310221213 _znabilah |
|
| 040 | _aUMP | ||
| 090 | _aTP156.S5 H39 2012 rs Bc. | ||
| 100 | 0 | _aHazwani Sidik | |
| 245 | 1 | 0 |
_aPrediction of grinding machanability when grinds Haynes 242 using water based coolant / _cHazwani Sidik |
| 260 |
_aKuantan, Pahang : _bUMP, _c2012 |
||
| 300 |
_axvi, 76 p. : _bill. ; _c30 cm. + _e1 CD-ROM |
||
| 502 | _aProject paper (Bachelor of Mechanical Engineering (Manufacturing Engineering)) -- Universiti Malaysia Pahang – 2012 | ||
| 504 | _aBibliography : p. 60-63 | ||
| 520 | 3 | _aGrinding is one of the important finishing machining operations. It is applied at the last stage of manufacturing process so that the high dimensional accuracy and desirable surface finish product can be achieved. However, there is a lot of problem occur in order to achieve the high dimensional accuracy and desirable surface finish. For examples, surface burning due to excessive heat produce and undesirable surface finish outcomes. This report deals with the prediction of grinding machanability when grind Haynes 242 using water based coolant. The aims of this report are to find the optimum parameter of the grinding process which is depth of cut ( m) where the type of surface roughness produces will be investigate and to develop prediction model of surface roughness by using an artificial neural network analysis. This report describes the experimental setups and procedures in finding the optimum value of the depth of cut and thus leading with the development of the prediction model. The material used is Haynes 242 and the depth of cut is independent variables. Calculations of the data were done which had obtained by using Perthometer and analysis was made by using ANN. The grindability results have shown optimum parameter which is gives the lowest surface roughness value. The results from the experiment show that the Al2O3 wheel gives a good surface roughness compare to the SiC at the depth of cut 5μm. By the end of the projects, prediction model had been developed by using ANN and was compared in the graph. The ANN model obtained from predicted value is accurate and effective in predicting the correlation and R-squared which is give 1% of minimum error and 2% of maximum error when using the Al2O3 grinding wheel. | |
| 650 | 0 | _aGrinding machines | |
| 650 | 0 | _aSurface roughnes | |
| 999 |
_aVIRTUA40 _c4185 _d4191 |
||
| 999 | _aVTLSSORT0080*0200*0400*0900*1000*2450*2600*3000*5020*5040*5200*6500*6501*9992 | ||