Please use this identifier to cite or link to this item:
Title: Risk analysis of machine maintenance using Markov chains
Authors: Gulati, Yuvraj Singh.
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2013
Abstract: Maintenance and risk management are important issues in any manufacturing company. In order to keep equipment running efficiently and reduce maintenance cost for better profit margin, manufacturing plants have always been seeking a effective way to replace Corrective Maintenances (CM) that occur after unscheduled downtimes with more cost-effective Predictive Maintenance (PdM). Most often, sensors are used at crucial parts of a machine to gather data. Therefore, the effectiveness of predictive maintenance is enhanced by using historical measured event data that exists in most manufacturing equipment log database. This report, utilizing a log database from a semiconductor company plant as a study example, investigates a Recipe Based Approach (PBA) for failure risk analysis. For this approach, three different analyzing methods are used to perform a risk analysis of the system; these are – Statistical Regression Analysis, Back-Propagation Neural Network Analysis and Markov Chain analysis. The significance of this project is to create a platform to perform risk profiling of a system. Another feature of the program is its ease of use to update and understand data. The main program is designed using Visual Basic for Applications and neural network algorithm is implemented using MatLabScripts.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
Main report2.9 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 21, 2024


Updated on Jun 21, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.