i-Twin – Semantic Integration Patterns for Data-driven Digital Twins in the Manufacturing Industry
i-Twin investigates interoperability concepts for data-driven digital twins in the manufacturing industry. The project propagates an open source middleware for the integration of operational management systems and connected assets based on semantic integration pat-terns. It aims at reducing the integration effort and allowing exchange of master data and operational data in manufacturing networks. The results are validated in a research laboratory set-up and in an industrial asset management scenario.
In the manufacturing industry, digital twins have emerged as a significant technological concept for the creation and use of digital representations of assets and their associated processes. Data-driven digital twins model i) the master data of the manufacturing plant ii) the parameters with which the plant is operated and iii) the dynamic sensor data acquired from plant equipment, which are then used for a variety of accompanying processes such as monitoring, analytics, forecasting, and optimization (e.g. KPI determination, maintenance planning, increase of equipment availability).
However, to exploit the interoperability potential of data-driven Digital Twins manufacturers have to combine their enterprise IT systems with the data ecosystem representing the assets and related data and functions. The consortium’s and industry analysts’ experience shows, that the effort required to integrate operational systems is very high and represents a major hurdle, especially for medium-sized companies.
The goal of the i-Twin project is to lower this integration hurdle for SMEs. For this purpose, the project designs interoperability concepts for an open-source middleware platform, which creates a standards-based, semantic integration layer for manufacturing plant information, especially for small and medium-sized enterprises. A functional prototype of the platform will be validated in a research and an industrial lab scenario.
Based on “Semantic Integration Patterns”, the platform creates a common “vocabulary” for the master and operating data of assets and their use for the applications used in a manufacturing network. This enables companies to leverage the potential of digital twins in less time and at lower cost compared to individual solutions, and to establish a sustainable basis for operational asset management.
The conceptual cornerstones of the i-Twin solution are:
- Semantic Integration Patterns based on relevant standards for the semantic description of asset information (e.g. RAMI4.0/AAS, OPC UA Companion Specifications) as well as recommendations for industrially used protocols and domain standards.
- Semantic Integration Patterns for minimally invasive integration of manufacturing applications.
- Semantic Integration Patterns for analytics systems based on available standards for the exchange of machine learning and AI models.
- A messaging system for semantically annotated data streams.
- A security and identity management service to protect data processed in the integration platform’s middleware.
The project consortium, led by a research group specialized in semantic data integration, combines the research interests of three system providers (CMMS, OT software platform, edge nodes) and an industrial company (discrete manufacturing) with the expertise of the participating research partners (Data Science, Motion Data Intelligence).
i-Twin is funded by BMK (Austrian Federal Ministry for Climate Action, Environment, Energy, Mobility, Innovation, and Technology) and FFG (Austrian Research Promotion Agency) in the research program “ICT for the future”.
