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 tondoindra@gmail.com at 13/10/2015 18:12:39  •  1259 Views


OPTIMASI MULTI-RESPON PROSES INJEKSI PLASTIK KABEL TIES DENGAN MENGGUNAKAN METODE BACK PROPAGATION NEURAL NETWORK DAN GENETIC ALGORITHM BPNN-GA

MULTI RESPONSE OPTIMIZATION OF INJECTION MOLDING PROCESS CABLE TIES USING BACK PROPAGATION NEURAL NETWORK-GENETIC ALGORITHM BPNN-GA METHODE

Author :
ARRIYANI, YANG FITRI  ( 2111201008 )




ABSTRAK

Kabel ties adalah tali pengikat yang digunakan untuk mengikat sekelompok kabel agar rapi dan dibuat dengan menggunakan proses injeksi plastik. Pengaturan variabel proses pembuatan kabel ties di mesin injeksi plastik masih menggunakan proses coba-coba. Hal ini sangat berpengaruh terhadap kualitas kabel ties yang dihasilkan. Penelitian ini dilakukan untuk menentukan nilai variabel proses yaitu nozzle temperature injection pressure injection flow dan switch-over to holding pressure. Respon yang diamati adalah kekuatan tarik yang semaksimal mungkin berat kabel ties tanpa flash sebesar 8 01 gr dan berat flash seminimal mungkin dengan menggunakan metode back propagation neural network-genetic algorithm BPNN-GA. Data training BPNN untuk empat level variabel proses dan tiga respon yang digunakan merupakan hasil eksperimen yang berjumlah 27 buah data dengan level nozzle temperature 250 C 260 C 270 C injection pressure 1200 bar 1300 bar 1400 bar injection flow 35 cm3s 45 cm3s 55 cm3s serta switchover to holding pressure 115 cm3 125 cm3 dan 135 cm3. Hasil penelitian menunjukkan bahwa arsitektur jaringan untuk model prediksi terbaik adalah 4-8-8-3 dengan MSE terkecil sebesar 0004161. Nilai variabel untuk menghasilkan respon optimum pada nozzle temperature adalah sebesar 267 C injection pressure sebesar 1205 bar injection flow sebesar 52 cm3s dan switch-over to holding pressure sebesar 133 cm3 dengan respon kekuatan tarik sebesar 2731 MPa berat kabel ties 791 gr dan berat flash sebesar 049 gr. Hasil verifikasi yang telah dilakukan menunjukkan bahwa metode BPNNGA dapat memberikan hasil yang cukup memuaskan untuk optimasi proses injeksi plastik kabel ties.


ABSTRACT

A cable tie is a kind of fastener which is usually used to tie a bunch of electric cables such that they can be neatly organized. It is made using plastic injection process. Unfortunately variables setting of this process is still conducted by trial and error. Hence it will affect the quality of produced cable ties. This research is proposed to obtain the plastic injection process variables such as nozzle temperature injection pressure injection flow and switch-over to holding pressure. The observed responses of this research are tensile strength weight without flash and flash weight. The desired tensile strength is as maximum as possible weight without flash is 8 01 gr and flash weight is as minimum as possible. They are analyzed using back propagation neural network-genetic algorithm BPNN-GA method. The training data of BPNN for four process variable levels and three responses is based on 27 experiment results. The levels of nozzle temperature are 250 C 260 C 270 C injection pressure are 1200 bar 1300 bar 1400 bar injection flow are 35 cm3s 45 cm3s 55 cm3s and switchover to holding pressure are 115 cm3 125 cm3 dan 135 cm3. The result of this research shows that the best prediction model of network architecture is 4-8-8-3 which has the smallest MSE i.e. 0004161. Variables setting which obtain the optimum responses are 267 C of nozzle temperature 1205 bar of injection pressure 52 cm3s of injection flow and 133 cm3 of switch-over to holding pressure. Based on the verification experiment the setting variables generated by BPNN-GA will produce cable ties which have 2731 MPa of tensile strength 791 gr of weight without flash and 049 gr of flash weight. In addition BPNNGA method gives satisfied result in the optimal quality of cable ties using plastic injection process.



Keywordsback propagation neural network, genetic algorithm, kabel ties, proses injeksi plastik
 
Subject:  Propagasi
Contributor
  1. Arif Wahyudi, S.T., M.T., Ph. D.
Date Create: 27/01/2014
Type: Text
Format: PDF
Language: Indonesian
Identifier: ITS-Master-21103150001405
Collection ID: 21103150001405
Call Number: RTM 006.32 Arr o


Source
Master Theses Of Mechanical Engineering RTM 006.32 Arr o, 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-39173-2111201008-Abstract_id.pdf - 256 KB
  2.  ITS-Master-39173-2111201008-Abstract_en.pdf - 256 KB
  3.  ITS-Master-39173-2111201008-Conclusion.pdf - 201 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 54.158.50.26
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