RT Journal Article
SR Electronic
A1 Lusi, Nuraini
A1 Fiveriati, Anggra
A1 Afandi, Akhmad
A1 Gusti Ngurah Bagus Catra Wedarma, I
A1 Yuliandoko, Herman
A1 Darsin, Mahros
A1 Qutaba, Syed
T1 Predictive Modelling on Machining Performance of ECDM Using Artificial Neural Network and Particle Swarm Optimization
JF Manufacturing Technology Journal
YR 2023
VO 23
IS 5
SP 649
OP 662
DO 10.21062/mft.2023.076
UL https://journalmt.com/artkey/mft-202305-0011.php
AB The electrochemical discharge machining (ECDM) process is developing into a potentially useful method of performing micromachining in conductive or non-conductive materials. The materials are machined using a combination of chemical and thermal energy. This paper examines the effect of Artificial Neural Network (ANN) architectures combined with particle swarm optimization (PSO) on the predictive ability of tungsten carbide machining. Material removal rate (MRR) and surface roughness (SR) is the response used to evaluate the performance of the ECDM process. The four selected process parameters are voltage, gap width, electrode type, and type of electrolyte, with each parameter has two levels. The 4-9-1 structure was chosen to obtain pre-dictions in the form of an optimal formula based on the statistical values for surface roughness: MSE 0.001, RMSE 0.025, MAPE 1.36, and R2 0.99.