Research library / 2024 / Conference paper
Enhancing Digital Twins with Deep Reinforcement Learning: A Use Case in Maintenance Prioritization
Proceedings - Winter Simulation Conference · 2024
Abstract
Original English abstract
This paper introduces an innovative framework that enhances digital twins with deep reinforcement learning (DRL) to support maintenance in manufacturing systems. Utilizing a sophisticated artificial intelligence (AI) layer, this framework integrates real-time and historical production data from a physical manufacturing system to a digital twin, enabling dynamic simulation and analysis. Maintenance decisions are informed by DRL algorithms that analyze this data, facilitating smart maintenance strategies that adaptively prioritize tasks based on predictive analytics. The effectiveness of this approach is demonstrated through a case study in a lab-scale drone factory, where maintenance tasks are prioritized using a proximal policy optimization. This integration not only refines maintenance decisions but also aligns with the broader goals of operational efficiency and sustainability in Industry 4.0. Our results highlight the potential of combining DRL with digital twins to significantly enhance decision-making in industrial maintenance, offering a novel approach to predictive and prescriptive maintenance practices.
Original source: Chalmers Research ↗
In brief
Maintenance priorities change with the state of a production system. This study combines a digital twin with proximal policy optimization to prioritize maintenance tasks in a lab-scale drone factory.
Key points
- Connects real-time and historical production data to an AI-enhanced digital twin.
- Uses proximal policy optimization to prioritize maintenance tasks dynamically.
- Demonstrates the approach in a lab-scale drone factory rather than claiming factory-wide deployment.
Cite this work
Siyuan Chen, Paulo Victor Lopes, Silvan Marti, Mohan Rajashekarappa, Sunith Bandaru, Christina Windmark, Jon Bokrantz, Anders Skoogh (2024). Enhancing Digital Twins with Deep Reinforcement Learning: A Use Case in Maintenance Prioritization. Proceedings - Winter Simulation Conference, pp. 1611–1622. https://doi.org/10.1109/WSC63780.2024.10838867
@inproceedings{Chen2024DigitalTwinsDeep,
title = {{Enhancing Digital Twins with Deep Reinforcement Learning: A Use Case in Maintenance Prioritization}},
author = {Chen, Siyuan and Lopes, Paulo Victor and Marti, Silvan and Rajashekarappa, Mohan and Bandaru, Sunith and Windmark, Christina and Bokrantz, Jon and Skoogh, Anders},
year = {2024},
booktitle = {2024 Winter Simulation Conference (WSC)},
pages = {1611--1622},
doi = {10.1109/WSC63780.2024.10838867},
url = {https://research.chalmers.se/en/publication/545197}
}
Abstract reproduced from the linked source record. The overview and key points are concise explanations of the study.