Image of ANALISIS KEKASARAN PERMUKAAN PADA PROSES FREIS DAN OPTIMASI MENGGUNAKAN METODE MACHINE LEARNING RANDOM FOREST REGRESSION DAN LINEAR REGRESSION

Skripsi

ANALISIS KEKASARAN PERMUKAAN PADA PROSES FREIS DAN OPTIMASI MENGGUNAKAN METODE MACHINE LEARNING RANDOM FOREST REGRESSION DAN LINEAR REGRESSION

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

In an effort to optimize surface roughness in the milling process, a cutting fluid based on coconut oil with the addition of 1% MoS₂ nanoparticles was utilized using the Minimum Quantity Lubrication (MQL) method. This research aims to analyze the effects of cutting speed (Vc), feed rate (fz), and depth of cut (a) on the surface roughness of AISI 1045 steel. Optimization and machining result prediction were carried out using Random Forest Regression and Linear Regression algorithms. The experimental data consisted of 27 training data and 3 testing data, and the coding process was performed using Google Colab as the programming platform. The machining tests were conducted through face milling using carbide cutting tools and the MQL system with a flow rate of 150 ml/hour. The results indicated that the optimum parameters were achieved at Vc = 4,82 m/min, fz = 0,028 mm/tooth, and a = 0,5 mm. The Random Forest Regression model demonstrated higher accuracy with a Mean Absolute Percentage Error (MAPE) of 9,86% and Mean Squared Error (MSE) of 0,0038, compared to Linear Regression which yielded a MAPE of 17,85% and MSE of 0,0081. Therefore, Random Forest Regression is considered to be the most effective and reliable method for predicting and optimizing surface roughness in the milling machining process using coconut oil-based cutting fluid with MoS₂ nanoparticles.

Availability
Inventory Code Barcode Call Number Location Status
2507006319T185825T1858252025Central Library (Reference)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1858252025
Publisher
Indralaya : Prodi Teknik Mesin, Fakultas Teknik Universitas Sriwijaya.,
Collation
xxix, 127 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
620.07
Content Type
Text
Media Type
unmediated
Carrier Type
other (computer)
Edition
-
Subject(s)
Ilmu Teknik
Prodi Teknik Mesin
Specific Detail Info
-
Statement of Responsibility
Other version/related
File Attachment
Comments
You must be logged in to post a comment