Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Rekayasa Mesin
Ahmad Mujaddid An-Najiy
Unknown Affiliation
Aerospace Engineering Automotive Engineering Control & Systems Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Kekasaran Permukaan Hasil Proses Side Milling Menggunakan Artificial Neural Networks (ANN) Muhammad Yanis; Ahmad Mujaddid An-Najiy
Jurnal Rekayasa Mesin Vol. 20 No. 2 (2020): Jurnal Rekayasa Mesin
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/jrm.v20i2.63

Abstract

Surface roughness is one of the aberrations caused by cutting conditions in the machining process. In this test, the application of cutting fluid was carried out using the MQL (minimum quantitylubricant) method with the AISI 1045 workpiece. Experimental testing was carried out based on theCentral Composite Design with a level point adjusted to the conditions of the vertical freis machine used, with variable cutting speed (Vc), motion feed (fz) and depth of cut (a). Surface roughness prediction is done using Artificial Neural Networks method. The requirements set in ANN are a network structure with 3 inputs, n hidden layers and 1 output, feed forward back propagation network algorithms, training and learning functions with Levenberg-Marquardt and performance calculated by MSE. The results show that the effect of cutting speed on roughness is inversely proportional, the higher the cutting speed will produce a smooth roughness value and vice versa, while the effect of feeding motion and feeding depth on roughness is directly proportional, the higher the value of feeding motion and the depth of feeding, the higher the roughness value. the more rough it gets. Surface roughness prediction resulted in the lowest MSE in the 3-8-1 structural network with MSE 0.001648738 with an error prediction of 3.2415% in all training data and testing data. And the test data get a deviation value range of 0.99% to 15.199%.
Co-Authors Muhammad Yanis