Kale, Sakshi Sanjay (2024) Predictive Maintenance of Equipment using Machine Learning Algorithms. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (901kB) | Preview |
Abstract
The main objective of this work is to minimize superior equipment failures in an industrial environment by employing predictive maintenance. Machine Learning techniques are applied on the AI4I 2020 dataset which includes online data of industrial machines for the prediction of the failures. In this work three machine learning algorithms namely XGBoost, Random Forest and Decision Tree models have been applied. The objective is to improve the model's predictive capabilities leveraging better feature engineering and efficient hyperparameter tuning techniques. The findings reveal the practical applicability of machine learning for the Industrial Predictive Maintenance (IPM) industry and show that there is a consistent enhancement in the model accuracy, especially, in identifying the occurrence of rare failure cases. To minimize the variance and to give the data a better standard normal distribution the data went through a cleaning process followed by normalization and then applied power transformer. For each model, the grid search was performed to define the most suitable parameter values in the experiment. The process of feature transformation improved indicators of model performance such as accuracy, precision, recall, and F1 score as well as improving the stability of the model.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Alam, Naushad UNSPECIFIED |
Uncontrolled Keywords: | Predictive Maintenance; XGBoost; Random Forest; Decision Tree |
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: | 20 Aug 2025 09:08 |
Last Modified: | 20 Aug 2025 09:08 |
URI: | https://norma.ncirl.ie/id/eprint/8576 |
Actions (login required)
![]() |
View Item |