1794. An overview on the predictive maintenance planning: the integration of learning algorithms and digital twins
Invited abstract in session TA-28: AI and Machine Learning for Decision Support, stream Decision Support Systems.
Tuesday, 8:30-10:00Room: Maurice Keyworth 1.03
Authors (first author is the speaker)
| 1. | Anıl Akpunar
|
| The Graduate School of Natural and Applied Sciences, Dokuz Eylül University | |
| 2. | Şener Akpınar
|
| Industrial Engineering, Dokuz Eylül University |
Abstract
The advancement of Industry 4.0 has introduced transformative technologies that enhance industrial efficiency, reliability, and decision-making capabilities. Among these, the digital twin stands out as a key innovation that creates a real-time virtual representation of physical systems, enabling comprehensive evaluation, optimization, and predictive analysis while supporting data-driven decision-making processes. Learning algorithms further enhances this digital ecosystem by leveraging real-time data from digital twins, such as condition monitoring and production progress metrics, to enable adaptive and autonomous decision-making. Predictive maintenance plays a crucial role in improving machine availability by preventing unexpected failures and enabling just-in-time maintenance actions. By utilizing advanced analytics on condition monitoring data collected through high-performance sensors, predictive models can assess the current health status of machines and estimate their remaining useful life. This predictive capability facilitates the adoption of proactive maintenance strategies, optimizing resource allocation, reducing downtime, and improving overall operational efficiency. In this study, the integration of digital twins, learning algorithms, and predictive maintenance establishes a framework for intelligent industrial management, while a systematic literature review categorizes relevant studies on learning algorithm applications in maintenance planning and optimization.
Keywords
- Decision Support Systems
- Machine Learning
Status: accepted
Back to the list of papers