Prediction of Surface Roughness in End-Milling with Multiple Regression Model
In this Paper, we propose statistical package for social sciences (SPSS), to predictsurface roughness. Two independent data sets were obtained on the basis ofmeasurement: training data set and testing data set. Spindle speed, feed rate, anddepth of cut are used as independent input variables (parame...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Unviversity of Technology- Iraq
2008-03-01
|
| Series: | Engineering and Technology Journal |
| Online Access: | https://etj.uotechnology.edu.iq/article_26420_04e80df84b4b3d80cc05eb730e16ce84.pdf |
| _version_ | 1797325129388130304 |
|---|---|
| author | Saad Kareem Shather Abbas Fadhel Ibrheem |
| author_facet | Saad Kareem Shather Abbas Fadhel Ibrheem |
| author_sort | Saad Kareem Shather |
| collection | DOAJ |
| description | In this Paper, we propose statistical package for social sciences (SPSS), to predictsurface roughness. Two independent data sets were obtained on the basis ofmeasurement: training data set and testing data set. Spindle speed, feed rate, anddepth of cut are used as independent input variables (parameters) while surfaceroughness as dependent output variable. The multiple regression model by using(SPSS) could predict the surface roughness (Ra) with average percentage deviationof 7.8%, or 92.2%, accuracy from training data, and from testing data set that wasnot included in the multiple regression analysis with average percentage deviationof 11.95%, or accuracy of 88%, for 4-Flute end mill. |
| first_indexed | 2024-03-08T06:05:40Z |
| format | Article |
| id | doaj.art-7e3ac4a7cc74408080443c694dac21e5 |
| institution | Directory Open Access Journal |
| issn | 1681-6900 2412-0758 |
| language | English |
| last_indexed | 2024-03-08T06:05:40Z |
| publishDate | 2008-03-01 |
| publisher | Unviversity of Technology- Iraq |
| record_format | Article |
| series | Engineering and Technology Journal |
| spelling | doaj.art-7e3ac4a7cc74408080443c694dac21e52024-02-04T17:54:00ZengUnviversity of Technology- IraqEngineering and Technology Journal1681-69002412-07582008-03-0126332633710.30684/etj.26.3.426420Prediction of Surface Roughness in End-Milling with Multiple Regression ModelSaad Kareem ShatherAbbas Fadhel IbrheemIn this Paper, we propose statistical package for social sciences (SPSS), to predictsurface roughness. Two independent data sets were obtained on the basis ofmeasurement: training data set and testing data set. Spindle speed, feed rate, anddepth of cut are used as independent input variables (parameters) while surfaceroughness as dependent output variable. The multiple regression model by using(SPSS) could predict the surface roughness (Ra) with average percentage deviationof 7.8%, or 92.2%, accuracy from training data, and from testing data set that wasnot included in the multiple regression analysis with average percentage deviationof 11.95%, or accuracy of 88%, for 4-Flute end mill.https://etj.uotechnology.edu.iq/article_26420_04e80df84b4b3d80cc05eb730e16ce84.pdf |
| spellingShingle | Saad Kareem Shather Abbas Fadhel Ibrheem Prediction of Surface Roughness in End-Milling with Multiple Regression Model Engineering and Technology Journal |
| title | Prediction of Surface Roughness in End-Milling with Multiple Regression Model |
| title_full | Prediction of Surface Roughness in End-Milling with Multiple Regression Model |
| title_fullStr | Prediction of Surface Roughness in End-Milling with Multiple Regression Model |
| title_full_unstemmed | Prediction of Surface Roughness in End-Milling with Multiple Regression Model |
| title_short | Prediction of Surface Roughness in End-Milling with Multiple Regression Model |
| title_sort | prediction of surface roughness in end milling with multiple regression model |
| url | https://etj.uotechnology.edu.iq/article_26420_04e80df84b4b3d80cc05eb730e16ce84.pdf |
| work_keys_str_mv | AT saadkareemshather predictionofsurfaceroughnessinendmillingwithmultipleregressionmodel AT abbasfadhelibrheem predictionofsurfaceroughnessinendmillingwithmultipleregressionmodel |