EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Master Theses » Sistem Manufaktur - S2
Posted by aprill@is.its.ac.id at 08/01/2015 17:39:50  •  625 Views


PEMODELAN DAN OPTIMASI PROSES EDM SINKING MATERIAL AISI 4140 MENGGUNAKAN BACK PROPAGATION ARTIFICIAL NEURAL NETWORK-GENETIC ALGORITHM BPANN-GA

MODELING AND OPTIMIZATION OF EDM SINKING PROCESSING MATERIAL AISI 4140 USING BACK PROPAGATION ARTIFICIAL NEURAL NETWORK-GENETIC ALGORITHM BPANN-GA

Author :
NAPITUPULU, ROBERT  ( 2111201013 )




ABSTRAK

Material removal rate MRR yang tinggi dan kekasaran permukaan yang rendah merupakan sasaran yang ingin dicapai pada proses pengerjaan benda kerja dengan menggunakan EDM sinking. MRR yang selambat mungkin akan menghasilkan kekasaran permukaan yang baik. Tetapi proses yang lambat akan berpengaruh terhadap waktu pengerjaan produk serta akan meningkatkan biaya produksi. Untuk mengatasi hal tersebut maka diperlukan seting parameter proses yang menghasilkan MRR yang maksimal dan kekasaran permukaan benda kerja yang minimal. Suatu penelitian dilakukan dengan menggunakan baja AISI 4140 dan elektroda tembaga copper pada proses EDM sinking. Parameter-parameter proses yang akan divariasikan adalah pulse current on time off time dan gap voltage. Rancangan percobaan yang digunakan adalah matriks ortogonal L 18 21x33 karena ada satu parameter proses yang memiliki dua level dan ada tiga parameter proses yang memiliki tiga level. Pengulangan dilakukan sebanyak dua kali. Data hasil penelitian akan dipilih untuk dijadikan sebagai data input dalam pengembangan back propagation artificial neural network BPANN. Selanjutnya optimasi karakteristik multi respon dilakukan dengan menggunakan metode genetic algorithm GA. Hasil penelitian menunjukkan bahwa MSE terkecil sebesar 000852 dari arsitektur jaringan BPANN 4-8-8-2 yang terdiri dari 4 input 2 buah hidden layer dengan 8 buah neuron pada masing-masing hidden layer dan 2 buah output. Fungsi aktivasinya adalah logsig dan jenis training adalah trainrp. Seting kombinasi parameter yang signifikan untuk meningkatkan MRR dan meminimumkan kekasaran permukaan secara serentak adalah pulse current 9 Ampere on time 50 s off time 21 s dan gap voltage 25 V. MRR terbesar dan kekasaran permukaan terkecil adalah sebesar 34135 mm 3min dan 485 m.


ABSTRACT

High material removal rate MRR and low surface roughness are targets which want to be reached by manufacturing process using EDM sinking. The slowest MRR will give good surface roughness. However it makes process get slower and increase production cost. To solve this problem the setting of process parameter which gives maximum MRR and minimum surface roughness is required. An experiment in EDM sinking has been done using AISI 4140 andcopper electrodes. Process parameters such as pulse current on time off time and gap voltage are varied. In addition the L 18 21x33 orthogonal array was applied because one of process parameters has two levels while the others have three levels. In this experiment two replications were conducted to deal with the uncertainty. Based on the experiment results back propagation artificial neural network BPANN was developed. Then the process parameter setting which gives the maximum MRR and the minimum surface roughness was determined by genetic algorithm GA. It was shown in this research that the smallest MSE of BPANN was 0.00852 which was reached using 4-8-8-2 i.e. 4 inputs 2 hidden layers with 8 neurons in each hidden layer and 2 outputs. It was used logsig as activation function and trainrp as training type in the BPANN. By applying BPANN above the parameters setting which gives the maximum combination of MRR and the minimum surface roughness simultaneously is 9 Ampere of pulse current on time 50 s off time 21 s and gap voltage 25 V. Moreover the MRR and surfacer oughness results are 34.135 mm 3min and 4.85 m.



KeywordsANN; genetic algorithm (GA); kekasaran permukaan; MRR
 
Subject:  Logam listrik -- memotong
Contributor
  1. Arif Wahyudi, S.T., M.T., Ph.D.
  2. Ir. Bobby O.P. Soepangkat, M.Sc., Ph.D.
Date Create: 20/09/2013
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Master-21103150001194
Collection ID: 21103150001194
Call Number: RTM 671.842 Nap p


Source
Master Theses of Mechanical Engineering, RTM 671.842 Nap p, 2014

Coverage
ITS Community

Rights
Copyright @2014 by ITS Library. This publication is protected by copyright and per obtained from the ITS Library prior to any prohibited reproduction, storage in a re transmission in any form or by any means, electronic, mechanical, photocopying, reco For information regarding permission(s), write to ITS Library




[ Download - Open Access ]

  1.  ITS-Master-35336-2111201013-Abstract_id.pdf - 189 KB
  2.  ITS-Master-35336-2111201013-Abstract_en.pdf - 186 KB
  3.  ITS-Master-35336-2111201013-Conclusion.pdf - 182 KB




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 54.158.31.120
using CCBot/2.0 (http://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2017 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan