Forskningsbibliotek / 2024 / Konferensbidrag
Enhancing Digital Twins with Deep Reinforcement Learning: A Use Case in Maintenance Prioritization
Proceedings - Winter Simulation Conference · 2024
Abstract
Engelskt originalabstract
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.
Originalkälla: Chalmers Research ↗
I korthet
Underhållsprioriteringar förändras med produktionssystemets tillstånd. Studien kombinerar en digital tvilling med proximal policy optimization för att prioritera underhåll i en drönarfabrik i laboratorieskala.
Huvudpunkter
- Kopplar realtidsdata och historiska produktionsdata till en AI-förstärkt digital tvilling.
- Prioriterar underhåll dynamiskt med proximal policy optimization.
- Demonstrerar metoden i en drönarfabrik i laboratorieskala.
Citera arbetet
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}
}
Originalabstractet återges från den länkade källposten. Översikten och huvudpunkterna ger korta förklaringar av studien.