A Digital Twin Design for Conveyor Belts Predictive Maintenance

被引：1

作者：

Mafia, Marina Meireles Pereira ^{[1
]}

Ayoub, Naeem ^{[1
]}

Trumpler, Lennart ^{[1
]}

Hansen, Jesper Puggaard de Oliveira ^{[1
]}

机构：

[1] Univ Southern Denmark, Technol Entrepreneurship & Innovat, Sonderborg, Denmark

来源：

MACHINE LEARNING FOR CYBER-PHYSICAL SYSTEMS, ML4CPS 2023 | 2024年

关键词：

Predictive maintenance; Digital twin; Artificial intelligence; Data quality;

D O I：

10.1007/978-3-031-47062-2_11

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Artificial intelligence has been widely used to enable predictive maintenance. However, AI systems need a large amount of data to generate accurate results that can be used reliably in terms of data quality. One of the ways to obtain data from the system is through the development of a digital twin. Therefore, a digital twin design might be of key value for the predictive maintenance of systems enabling the simulation of the system's performance, anticipating potential malfunctions, and consequently reducing the cost of unforeseen failures of the physical system. In this paper, we present a framework of a digital twin system for a conveyor belt along with different sensors that collect various types of data to be analyzed by a digital system. This way, the digital twin can generate more data focusing on reducing the time to obtain enough data to train the AI algorithm properly. Furthermore, the digital twin model is designed to develop the simulation environment and integrate it with the physical system.

引用

页码：111 / 119

页数：9

共 15 条

[1]

Allen B.D., 2021, DIG TWIN SUMM

[2] Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time [J].

Ayvaz, Serkan ;

Alpay, Koray .

EXPERT SYSTEMS WITH APPLICATIONS, 2021, 173 (173)

[3] LIVE Digital Twin: Developing a Sensor Network to Monitor the Health of Belt Conveyor System [J].

Bondoc, Andrew E. ;

Tayefeh, Mohsen ;

Barari, Ahmad .

IFAC PAPERSONLINE, 2022, 55 (19) :49-54

[4] Digital Twin Architecture for Mining Industry: Case Study of a Stacker Machine in an Experimental Open-Pit Mine [J].

Elbazi, Nabil ;

Mabrouki, Mustapha ;

Chebak, Ahmed ;

Hammouch, FatimaEzzahrae .

2022 IEEE 4TH GLOBAL POWER, ENERGY AND COMMUNICATION CONFERENCE (IEEE GPECOM2022), 2022, :232-237

[5]

Haghshenas Amirashkan, 2023, Energy Informatics, DOI [10.1186/s42162-023-00257-4, 10.1186/s42162-023-00257-4]

[6]

Hoffmann M. W., 2021, MACHINE LEARNING CYB, V2021, P63, DOI DOI 10.1007/978-3-662-62746-4_7

[7] A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems [J].

Lee, Jay ;

Bagheri, Behrad ;

Kao, Hung-An .

Manufacturing Letters, 2015, 3 :18-23

[8] Development of Digital Twin for Intelligent Maintenance of Civil Infrastructure [J].

Mahmoodian, Mojtaba ;

Shahrivar, Farham ;

Setunge, Sujeeva ;

Mazaheri, Sam .

SUSTAINABILITY, 2022, 14 (14)

[9]

Pagano D, 2023, Decision Analytics Journal, V6, P100174, DOI [10.1016/j.dajour.2023.100174, 10.1016/j.dajour.2023.100174, DOI 10.1016/J.DAJOUR.2023.100174]

[10] Integrating the Digital Twin of a Shop Floor Conveyor in the Manufacturing Control System [J].

Raileanu, Silviu ;

Borangiu, Theodor ;

Ivanescu, Nick ;

Morariu, Octavian ;

Anton, Florin .

SERVICE ORIENTED, HOLONIC AND MULTI-AGENT MANUFACTURING SYSTEMS FOR INDUSTRY OF THE FUTURE, 2020, 853 :134-145

← 1 2 →