Integration of AI-based predictive maintenance for energy-efficient mechanical systems
ITM SLS Baroda University, India.
Review
World Journal of Advanced Engineering Technology and Sciences, 2024, 11(02), 664-673.
Article DOI: 10.30574/wjaets.2024.11.2.0153
Publication history:
Received on 18 March 2024; revised on 26 April 2024; accepted on 29 April 2024
Abstract:
Predictive maintenance enabled by Artificial Intelligence (AI) transforms mechanical systems by improving their reliability levels as well as energy efficiency attributes. The conventional maintenance methods that include reactive and preventive measures repeatedly produce inefficient energy usage together with elevated operation expenses. Using AI alongside machine learning predictive maintenance transforms real-time sensor data into predictions which help maintainers schedule optimal maintenance times. The proactive system helps prevent downtime and cuts down energy loss and delivers improved operational results. Current industrial applications benefit from AI methods made up of deep learning and IoT-enabled data analytics and digital twins to anticipate anomalies and detect faults in HVAC systems and production facilities as well as power generation facilities. The ongoing implementation challenges involve poor quality data as well as cybersecurity threats together with difficult integration between systems. Self-learning AI models combined with edge computing and automated intelligent systems will enable better predictive maintenance through future advancements which will generate more sustainable and energy-efficient mechanical systems.
Keywords:
Predictive Maintenance; Artificial Intelligence; Energy Efficiency; Machine Learning, IoT
Full text article in PDF:
This article has received Best Paper Award of Volume 11 - Issue 2 (March - April 2024)
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0