PENGEMBANGAN SISTEM KLASIFIKASI KEKASARAN PERMUKAAN MENGGUNAKAN MACHINE LEARNING

HARTITA, CINDY and Yani, Irsyadi (2024) PENGEMBANGAN SISTEM KLASIFIKASI KEKASARAN PERMUKAAN MENGGUNAKAN MACHINE LEARNING. Masters thesis, Sriwijaya University.

	Text RAMA_21101_03032622327002.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_21101_03032622327002_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13MB) | Request a copy
	Text RAMA_21101_03032622327002_0025127104_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (5MB)
	Text RAMA_21101_03032622327002_0025127104_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (532kB) | Request a copy
	Text RAMA_21101_03032622327002_0025127104_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (495kB) | Request a copy
	Text RAMA_21101_03032622327002_0025127104_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (429kB) | Request a copy
	Text RAMA_21101_03032622327002_0025127104_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (206kB) | Request a copy
	Text RAMA_21101_03032622327002_0025127104_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (193kB) | Request a copy
	Text RAMA_21101_03032622327002_0025127104_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4kB) | Request a copy

Abstract

Machining is a material-shaping process using cutting tools to achieve specific shapes and surface quality. Surface roughness (Ra) is influenced by machining variables such as feed rate (f), cutting speed (Vc), and depth of cut (a). To support environmentally friendly machining (green machining), the Minimum Quantity Lubricant (MQL) method is applied to significantly reduce the use of cutting fluids. This study developed a surface roughness classification system using the Naive Bayes method to predict the relationship between machining variables and surface roughness. Data from the turning process were measured, analyzed, and grouped using Pearson correlation to determine the relationship between independent and dependent variables. The analysis revealed that the feed rate (f) is the most dominant variable affecting surface roughness, contributing 86.36%, while the depth of cut (a) had the least influence. The developed classification system demonstrated an accuracy of 87.50% in grouping surface roughness data based on input variables. This study proves that the Naive Bayes method effectively analyzes and predicts variable relationships in machining processes. Future research should include additional independent variables such as Fz, Fy, Rz, and Rt and explore other classification methods, such as K-NN and Fuzzy Naive Bayes, to improve accuracy and analysis flexibility.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Naive Bayes, Surface Roughness, Classification
Subjects:	T Technology > TJ Mechanical engineering and machinery > TJ1-1570 Mechanical engineering and machinery
Divisions:	03-Faculty of Engineering > 21101-Mechanical Engineering (S2)
Depositing User:	Cindy Hartita
Date Deposited:	26 Nov 2024 03:52
Last Modified:	26 Nov 2024 03:52
URI:	http://repository.unsri.ac.id/id/eprint/159845

Actions (login required)

View Item