Potential for combining semantics and data analysis in the context of digital twins

Area of Science:

• Industrial Engineering and Production Systems
• Computer Science and Artificial Intelligence
• Systems Engineering

Background:

• Modern production systems increasingly require integrated digital representations for various applications.
• Digital twins serve as comprehensive models, integrating data, information, and knowledge throughout a production system's lifecycle.
• Existing applications utilize data analysis, expert knowledge, and knowledge-based systems for production system management.

Purpose of the Study:

• To provide an overview of data, information, and knowledge available across production system lifecycles.
• To explore the potential of integrating data analysis with knowledge-based systems for production systems.
• To demonstrate the creation of knowledge-based systems using data analysis through feasibility studies.

Main Methods:

• Literature review of data, information, and knowledge in production systems.
• Analysis of applications driven by data analysis, expert knowledge, and knowledge-based systems.
• Development and evaluation of two feasibility studies showcasing data-driven knowledge-based system creation.

Main Results:

• Identified typical data, information, and knowledge assets throughout production system lifecycles.
• Demonstrated the synergistic potential of combining data analysis and knowledge-based systems.
• Successfully created knowledge-based systems using data analysis techniques in feasibility studies.

Conclusions:

• Integrated digital twins are crucial for modern production systems, enhancing efficiency and support.
• Combining data analysis with knowledge-based systems offers significant potential for advanced production management.
• Data analysis is a viable method for constructing knowledge-based systems, paving the way for symbiotic autonomous systems.