Prioritizing Life Cycle Cost In Design For Remanufacturing Using Intelligent Tool

Mohamed Noor, Ahamad Zaki (2018) Prioritizing Life Cycle Cost In Design For Remanufacturing Using Intelligent Tool. Doctoral thesis, UTeM.

	Text (24 Pages) Prioritizing Life Cycle Cost In Design For Remanufacturing Using Intelligent Tool.pdf - Submitted Version Download (636kB)
	Text (Full Text) Prioritizing Life Cycle Cost In Design For Remanufacturing Using Intelligent Tool.pdf - Submitted Version Restricted to Registered users only Download (3MB)

Abstract

Sustainable practice is needed in every manufacturing industry.There are three indicators and problem arising with the economy indicator is that the variable used is not finalised during substitution value.Decisions made by decision makers are not synchronised and staff from different departments tend to argue until final decision is made.Different industries prioritize different cost resulting different in final answer.Therefore,this research will make the staff from the industry to substitute value and utilised well the Life Cycle Cost (LCC) equation to identify the suitability of Design for Remanufacturing (DFReM) practice.First objective was to determine parameter’s weightage concerning LCC equation. The data obtained from industries are direct overhead cost,indirect overhead cost,spare parts cost and packaging cost.Survey forms were distributed among 20 decision makers resulting in different perceptive and their answers were recorded.To make best cost prioritization from 20 different companies’ expenses, second objective is to propose three methods that are used in this experiment.The methods proposed are Fuzzy Analytic Hierarchy Process (FAHP),Artificial Neural Network (ANN) and combination of both techniques.Before the main research was conducted,a preliminary experiment was carried out to identify which FAHP will give answer almost same as AHP.AHP is compared because other FAHP are created based on AHP,therefore AHP will give almost correct but not as accurate as FAHP.The findings of this experiment show that Triangular AHP gives the near sequence and suitable material selection to fabricate a table fan.From this preliminary experiment,Triangular FAHP is implemented for cost selection in DFReM.Next part of experiment is to make decision using ANN. Before this part of experiment is carried out,a small experiment was carried out to determine the number of hidden neuron.The outcome of this experiment for this application,the suitable hidden neuron is 2. The last proposed method for cost prioritizing is combination of both FAHP and ANN. The improvement made is used as output from FAHP and introduced as target file.Input remained the same as previous part of ANN experiment.Final objective is to validate life cycle cost prioritizing through comparison of proposed decision making tool outputs.All proposed method’s output were identified and result shows that combination of FAHP and ANN will make the company save more expenses compared to carrying single technique.FAHP manage the company to save up to RM 91,353.The result from ANN makes the company to save up to RM 95,093. However the combination method saves the company to a total of RM 95,633.To conclude,combination of FAHP and ANN is the best technique used for cost selection before substituting in an economy indicator for DFReM. Contribution made towards body of knowledge is to adapt FAHP answer as target file for neural network simulation. Contribution made to industry is that by introducing AI technique,LCC equation gives out profit and make DFReM practice suitable for any manufacturing industry.

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	System analysis, Data processing,Data structures(Computer science),Artificial intelligence, Life Cycle Cost, Remanufacturing, Intelligent Tool
Subjects:	T Technology > T Technology (General)
Divisions:	Library > Tesis > FKP
Depositing User:	Mohd. Nazir Taib
Date Deposited:	05 Sep 2019 04:00
Last Modified:	15 Mar 2022 15:27
URI:	http://eprints.utem.edu.my/id/eprint/23388
Statistic Details:	View Download Statistic

Actions (login required)

View Item