DigiTwin: An Approach for Production Process Optimization in a Built Environment (Springer Series in Advanced Manufacturing)

Acknowledgment
Used Trademarks
Contents
Editors and Contributors
1 Introduction to the Book
	1.1 Origins of the Digital Twin
	1.2 Origins of the Book
	1.3 Goals of the Book
	1.4 Audience
	1.5 Content of the Book
	1.6 Contributors of the Book
	References
2 Requirements for the Optimization of Processes Using a Digital Twin of Production Systems
	2.1 Introduction
	2.2 Investigated Use Cases
	2.3 Parameters for the Framework of the Digital Twin
	2.4 Parameter Properties for Implementation in the Digital Twin
	2.5 Summary and Outlook
	Appendix
	References
3 Digital Twin: A Conceptual View
	3.1 Introduction
	3.2 Taxonomy of Digital Twin
	3.3 Conception of Digital Twin
		3.3.1 Digital Master
		3.3.2 Digital Manufacturing Twin
		3.3.3 Digital Instance Twin
	3.4 Main Expressions of Digital Twin in Context of Industry 4.0
	3.5 Simulations as the Backbone of the Digital Twin
	3.6 Proposed Approach
	3.7 Summary and Further Research
	References
4 Scan Methods and Tools for Reconstruction of Built Environments as Basis for Digital Twins
	4.1 Introduction
	4.2 Requirements for Acquisition of Shape and Position of Physical Objects in a Factory
		4.2.1 Requirements for the Scan of Manufacturing Facilities
		4.2.2 Requirements from a Production Point of View
	4.3 Acquisition Approaches in a Comparative View
		4.3.1 Laser Scanner
		4.3.2 Photogrammetry
		4.3.3 Comparison of the Different Steps in Generating a Point Cloud by Photogrammetry or Laser Scanner
		4.3.4 Application of the Different Technologies
	4.4 SLAM, Structure from Motion, Photogrammetry
		4.4.1 Photogrammetry
		4.4.2 Structure from Motion (SfM)
		4.4.3 Simultaneous Localization and Mapping (SLAM)
	4.5 Image-Based 3D Reconstruction
		4.5.1 Step 1: Feature Extraction
		4.5.2 Step 2: Correspondence Generation
		4.5.3 Step 3: 3D Reconstruction
	4.6 3D Reconstruction in Production Environments
		4.6.1 Definition of the Test Environment
		4.6.2 Monocular Method
		4.6.3 Stereo Images (Stereo Camera)
		4.6.4 Spherical Images
	4.7 Conclusions and Outlook
	References
5 Machine Learning in Manufacturing in the Era of Industry 4.0
	5.1 Introduction
	5.2 Fundamental and Problems Concepts
		5.2.1 When Is Machine Learning Used?
		5.2.2 Where Are Evolutionary Algorithms Used?
		5.2.3 A Combination of Several Methods of AI?
		5.2.4 Procedure for Creating a Behavioral Model/Digital Twin
	5.3 Gains of Machine Learning
		5.3.1 Efficient Derivation of the Model Configuration Based on the Data
		5.3.2 Generating Behavioral Model Through Training with Data
		5.3.3 Easy Validation of the Model
		5.3.4 Optimization of the Real System Based on the Model
	5.4 Use Cases in Plant Engineering
		5.4.1 Mechanical Model of a Pneumatic Cylinder
		5.4.2 Forecast Models Solar System
	5.5 Data Analysis
	5.6 Discussion
	5.7 Conclusions and Outlook
	References
6 Object Recognition Methods in a Built Environment
	6.1 Introduction
	6.2 Methodology for Object Recognition
		6.2.1 Challenges in Object Recognition
		6.2.2 Image-Oriented Methods
		6.2.3 Point Cloud-Oriented Methods
		6.2.4 Video-Oriented Methods
	6.3 Approaches for Point Cloud Generation
	6.4 Test Base
	6.5 Impact of Data Acquisition Accuracy
	6.6 Methods for Point Cloud Processing
		6.6.1 Point Cloud Preprocessing
		6.6.2 Mesh Reconstruction
		6.6.3 Point Cloud Segmentation
		6.6.4 Point Cloud Modeling
	6.7 Comparison of Recognition Methods
	6.8 Application of Methods
	6.9 Discussion and Future Perspectives
	6.10 Conclusions and Outlook
	References
7 Data Quality Management for Interoperability
	7.1 Introduction
	7.2 Digital Thread
	7.3 Data Quality Classification
		7.3.1 Data Quality Dimensions
		7.3.2 Related Standards
	7.4 Data Quality Metrics
	7.5 Practical Examples
		7.5.1 Design
		7.5.2 Manufacturing
		7.5.3 Data Migration
	7.6 Discussion and Future Perspectives
	7.7 Conclusions and Outlook
	References
8 Object Recognition Findings in a Built Environment
	8.1 Introduction
	8.2 Process Design
	8.3 Automation of Workflow
	8.4 Model Preparation
	8.5 Model Segmentation
	8.6 Training and Testing, Rebuild of Structures
	8.7 Discussion
	8.8 Conclusions and Outlook
	References
9 Design of Simulation Models
	9.1 Introduction
	9.2 Ontology of Production Systems
		9.2.1 Ontology-Based Information System for Generating Simulations of Production Systems
		9.2.2 Information System for the Description of Production Systems
		9.2.3 Exemplary Applications
	9.3 Data Model
	9.4 Model Design
		9.4.1 Design of the Functional Model
		9.4.2 Design of the Graphical Model
	9.5 Results and Summary
	References
10 The Commercialization of Digital Twin by an Extension of a Business Ecosystem
	10.1 Introduction
	10.2 Supplier Networks, Engineering Collaboration and Network-Centric Operations
	10.3 Shift from Product to Service Platform and Ecosystem
	10.4 The Rise of OpenDESC.Com
	10.5 Use Cases of OpenDESC.Com
		10.5.1 CAD Data Translation
		10.5.2 CAD Data Migration
		10.5.3 Data Transfer
		10.5.4 Intellectual Property Protection
		10.5.5 Portal Services
	10.6 Planning of Extension by Enterprise Architecture Integration
	10.7 Adoption of Extended Services
		10.7.1 Working Procedure
		10.7.2 Input and Outcome
	10.8 Adoption of Digital Twin Offering
	10.9 Discussion
	10.10 Conclusions and Outlook
	References
11 Digital Twin: Conclusion and Future Perspectives
	11.1 Introduction
	11.2 Further Developments of DigiTwin Solution
		11.2.1 Parameter-Based Updating of the Digital Twin
		11.2.2 Structural Partial Update of the Digital Twin
		11.2.3 Structural Update of the Digital Twin
	11.3 Self-X Digital Twin on Backend
	11.4 Self-X Digital Twin on Edge-Devices
	11.5 Trends in Digital Twin
	11.6 Challenges in Digital Twin
	11.7 Closing Remarks and Conclusions
	References