A Master thesis "Application of Artificial
Intelligence in Predictive Maintenance" was made at Faculty of Information
Technology at Czech Technical University in 2020.
This repository contains text of the thesis in PDF including LaTeX sources codes
(directory text) and source codes of the experiments made in the thesis
(directory experiments).
Predictive maintenance (PdM) is a maintenance strategy where the maintenance actions are scheduled only when the subject is malfunctioning or is likely to fail soon. PdM reduces costs and prevents downtime in comparison to classical preventive and reactive maintenance strategies. PdM can be realized by using artificial intelligence (AI) techniques to build a model that predicts health state of the subject based on its condition monitoring data. However, there exist various approaches to PdM including fault detection, failure prediction and remaining useful life prediction, each having different data requirements and goals. Each of the approaches utilizes different AI techniques and should be evaluated using different evaluation metrics. This thesis provides an overview of the approaches to PdM to help the practitioners choose a suitable approach, AI technique and evaluation metric for their problem at hand.