ENHANCING DIGITAL TWINS WITH DEEP REINFORCEMENT LEARNING : A USE CASE IN MAINTENANCE PRIORITIZATION
Chen, Siyuan ; Lopes, Paulo Victor ; Marti, Silvan ; Rajashekarappa, Mohan ; Bandaru, Sunith ; Windmark, Christina LU
; Bokrantz, Jon
and Skoogh, Anders
(2024)
2024 Winter Simulation Conference, WSC 2024
In Proceedings - Winter Simulation Conference
p.1611-1622
- 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... (More)
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.
(Less)
- author
- Chen, Siyuan
; Lopes, Paulo Victor
; Marti, Silvan
; Rajashekarappa, Mohan
; Bandaru, Sunith
; Windmark, Christina
LU
; Bokrantz, Jon
and Skoogh, Anders
- organization
- publishing date
- 2024
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2024 Winter Simulation Conference, WSC 2024
- series title
- Proceedings - Winter Simulation Conference
- pages
- 12 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2024 Winter Simulation Conference, WSC 2024
- conference location
- Orlando, United States
- conference dates
- 2024-12-15 - 2024-12-18
- external identifiers
-
- scopus:85217619419
- ISSN
- 0891-7736
- ISBN
- 9798331534202
- DOI
- 10.1109/WSC63780.2024.10838867
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2024 IEEE.
- id
- 98045e2b-c96d-4145-947f-a31017aa1335
- date added to LUP
- 2025-05-06 10:25:13
- date last changed
- 2025-05-06 10:25:55
@inproceedings{98045e2b-c96d-4145-947f-a31017aa1335,
abstract = {{<p>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.</p>}},
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}},
booktitle = {{2024 Winter Simulation Conference, WSC 2024}},
isbn = {{9798331534202}},
issn = {{0891-7736}},
language = {{eng}},
pages = {{1611--1622}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{Proceedings - Winter Simulation Conference}},
title = {{ENHANCING DIGITAL TWINS WITH DEEP REINFORCEMENT LEARNING : A USE CASE IN MAINTENANCE PRIORITIZATION}},
url = {{http://dx.doi.org/10.1109/WSC63780.2024.10838867}},
doi = {{10.1109/WSC63780.2024.10838867}},
year = {{2024}},
}