Degree
Master of Science in Computer Science
Department
Department of Computer Science
School
School of Mathematics and Computer Science (SMCS)
Date of Submission
Spring 2023
Supervisor
Saiyed Shahab Ahmed, Visiting Faculty, Department of Computer Science
Abstract
Amongst the biggest problems faced by manufacturing and oil and gas facilities is the maintenance and upkeep of machinery or plant assets. Most maintenance activities carried out are either pre-planned, called preventive maintenance, or executed after a fault has been detected, usually referred to as corrective, reactive or breakdown maintenance. These processes are available in nearly all Computerized Maintenance Management Systems (CMMS), such as HippoCMMS and SAP EAM. Reactive maintenance and to a lesser degree preventive maintenance processes incur significant asset downtime, increased costs and result in generally lower returns over machine lifetime, as measured by Overall Equipment Effectiveness or OEE. These problems can be mitigated by moving towards predictive maintenance. Predictive maintenance processes rely on real-time asset data, historical performance data, and analytics to forecast when asset failure will occur. The goal of this project is to design a solution for predictive maintenance on cloud, which will use machine learning to detect and predict impending machine faults, and alert users to take actions before a breakdown occurs.
Document Type
Restricted Access
Submission Type
Research Project
Recommended Citation
Rizvi, Taha. "Cloud-based Predictive Maintenance for Enterprise Asset Management." Unpublished graduate research project. Institute of Business Administration. 2023. https://ir.iba.edu.pk/research-projects-mscs/11
The full text of this document is only accessible to authorized users.
