Loading…
Automated generation of digital twin for a built environment using scan and object detection as input for production planning
•Discrete event simulation facilitates optimization of the existing plants.•Generation of Digital Twin in the built environment can be based on scanning and object recognition.•Acquisition of three-dimensional objects in industrial facilities can be done by scanner or 3D camera.•A robust object reco...
Saved in:
Published in: | Journal of industrial information integration 2023-06, Vol.33, p.100462, Article 100462 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | •Discrete event simulation facilitates optimization of the existing plants.•Generation of Digital Twin in the built environment can be based on scanning and object recognition.•Acquisition of three-dimensional objects in industrial facilities can be done by scanner or 3D camera.•A robust object recognition under environmental impact (dirt, darkness, dust, steam, smoke) can be done by deep learning (convolutional neural networks).•Advanced challenges (update of Digital Twin, occlusion of objects) require further research.
The simulation of production processes using a digital twin can be utilized for prospective planning, analysis of existing systems or process-parallel monitoring. In all cases, the digital twin offers manufacturing companies room for improvement in production and logistics processes leading to cost savings. However, many companies, especially small and medium-sized enterprises, do not apply the technology, because the generation of a digital twin in a built environment is cost-, time- and resource-intensive and IT expertise is required. These obstacles will be overcome by generating a digital twin using a scan of the shop floor and subsequent object recognition. This paper describes the approach with multiple steps, parameters, and data which must be acquired in order to generate a digital twin automatically. It is also shown how the data is processed to generate the digital twin and how object recognition is integrated into it. An overview of the entire process chain is given as well as results in an application case. |
---|---|
ISSN: | 2452-414X 2452-414X |
DOI: | 10.1016/j.jii.2023.100462 |