ANALISIS KLASIFIKASI KEKASARAN PERMUKAAN PADA PROSES MILLING CNC BAJA S45C MENGGUNAKAN METODE RANDOM FOREST

RENALDI, M. ELAN and Yani, Irsyadi (2024) ANALISIS KLASIFIKASI KEKASARAN PERMUKAAN PADA PROSES MILLING CNC BAJA S45C MENGGUNAKAN METODE RANDOM FOREST. Undergraduate thesis, Sriwijaya University.

	Text RAMA_21201_03051282025060.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_21201_03051282025060_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_21201_03051282025060_0025127104__01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_21201_03051282025060__0025127104_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (882kB) | Request a copy
	Text RAMA_21201_03051282025060__0025127104_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (796kB) | Request a copy
	Text RAMA_21201_03051282025060__0025127104_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (998kB) | Request a copy
	Text RAMA_21201_03051282025060__0025127104_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (207kB) | Request a copy
	Text RAMA_21201_03051282025060__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_21201_03051282025060__0025127104_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

Applying machine learning to the CNC milling process reduces costs and saves time while optimizing surface roughness. When used to develop CNC milling processes, machine learning can minimize machine downtime, optimize CNC machinery, forecast tool wear, simulate cutting forces, maintain CNC machinery, keep an eye on milling operations, and forecast surface quality. Random Forest is the machine learning approach method that has been shown to have the highest model accuracy. Determining the optimal surface roughness accuracy value using the Random Forest algorithm approach and examining the effects of three milling process parameters—cutting speed (Vc), feed motion (fz), and depth of cut (ax)—are the goals of this study. The procedure for gathering data in Using a CNC milling machine of the Richon XK 7132A type, data was collected for this study. This study makes use of 200 mm x 100 mm x 25 mm S45C steel workpieces and coated carbide endmill tools. Google Colab was selected as the primary platform for the Random Forest (RF) method of predictive analysis in the S45C Steel CNC milling process. The test_size parameters in this study were modified by the author into three values: 0.2, 0.3, and 0.4. In this instance, the Google Colab parameter test_size controls how the dataset's data is split into test and training subsets. The author then utilized parameters 30 for the number of decision variables in the random forest model. Next, the author employed parameters 4 for the maximum depth (max_depth) and 30 for the number of decision trees (n_estimators) for constructing the random forest model. In order to increase the variety of the data used in model construction, the data distribution was also 42 times randomized using the random state feature. Based on research done on the CNC milling process using the random forest method and three different test size parameters in Google Colab—0.2, 0.3, and 0.4—the findings demonstrate that, at 83.34%, test size 0.2 yields the highest accuracy value, highlighting the significance of the test data to training ratio in the creation of successful models. Next, the outcomes of the computations for the gain parameter and entropy. Then the results of the entropy and gain parameter calculations that most influence the surface roughness class value are cutting speed (Vc) because there is the highest gain value, namely 1.29907202.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	surface roughness, cnc milling, random forest, accuracy
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning T Technology > TJ Mechanical engineering and machinery > TJ1-1570 Mechanical engineering and machinery
Divisions:	03-Faculty of Engineering > 21201-Mechanical Engineering (S1)
Depositing User:	M. Elan Renaldi
Date Deposited:	24 Jun 2024 07:36
Last Modified:	24 Jun 2024 07:36
URI:	http://repository.unsri.ac.id/id/eprint/147785

Actions (login required)

View Item