NORMA eResearch @NCI Library

Predictive Maintenance In Industrial Sector using Machine Learning

Alone, Ashutosh Sudhirkumar (2024) Predictive Maintenance In Industrial Sector using Machine Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (2MB) | Preview

Abstract

In the industrial sector there is a need to have a reliable predictive maintenance system as it can help them to reduce downtime, unexpected machine failures can cause significant financial and safety risks. Traditional predictive maintenance methods are not effective enough to manage the increasing complexity and size of the data. Therefore, in this research the use of unsupervised machine learning algorithms is explored. The unsupervised algorithms used are Isolation Forest, One-Class Support Vector Machine and Local Outlier Factor. These models are compared against supervised algorithms like K-NN and Random Forest. The results showed that supervised learning algorithms performed better than unsupervised learning algorithms with perfect accuracy and precision. This high accuracy of K-NN and Random Forest is further justified by performing cross validation on them. On the other hand, the best performing unsupervised algorithm which is Isolation Forest showed high recall but due to low precision it leads to generating false positives. The overall findings of this research show that unsupervised algorithms have potential for anomaly detection in predictive maintenance, but they are currently less effective than supervised learning algorithms.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Makki, Ahmed
UNSPECIFIED
Uncontrolled Keywords: Predictive Maintenance; Unsupervised Learning; Machine Learning; Anomaly Detection; Isolation Forest; Supervised Learning; Cross-Validation
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Ciara O'Brien
Date Deposited: 06 Aug 2025 15:07
Last Modified: 06 Aug 2025 15:07
URI: https://norma.ncirl.ie/id/eprint/8451

Actions (login required)

View Item View Item