Skripsi

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407003839	T147785	T1477852024	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1477852024

Publisher

Indralaya : Prodi Teknik Mesin, Fakultas Teknik Universitas Sriwijaya., 2024

Collation

xii, 80 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

670.420 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Mesin
Metode Random Forest

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment