Predictive Maintenance in Industrial Systems Using Machine Learning

EasyChair Preprint 12240

Abstract

Predictive maintenance has emerged as a critical strategy in industrial systems to minimize downtime, reduce maintenance costs, and optimize operational efficiency. Machine learning techniques have shown promising results in enabling predictive maintenance by leveraging historical data to anticipate equipment failures before they occur. This abstract explores the application of machine learning algorithms such as supervised learning, unsupervised learning, and deep learning in predictive maintenance tasks. It discusses various data sources utilized in predictive maintenance, including sensor data, maintenance logs, and operational parameters. Furthermore, the abstract highlights the challenges associated with implementing predictive maintenance systems, such as data quality issues, model interpretability, and scalability.

Keyphrases: Scalability, and, interpretability

@booklet{EasyChair:12240,
  author    = {Kurez Oroy and Julia Anderson},
  title     = {Predictive Maintenance in Industrial Systems Using Machine Learning},
  howpublished = {EasyChair Preprint 12240},
  year      = {EasyChair, 2024}}