Success story EFPF

Success stories

Connecting smart factories across Europe

EFPF

In an increasingly digitized world, digital manufacturing platforms, intelligent factory tools, and Industry 4.0 concepts are merging to create a connected and intelligent ecosystem of the future. The aim of this fusion is to transform the manufacturing landscape and generate innovative opportunities for the industry by realizing a highly connected and intelligent ecosystem of the future.

The EFPF project received funding from EC H2020 program to develop a federation of digital manufacturing platforms and systems in the EU. The main asset is the EFPF platform, that interlinks digital manufacturing platforms, smart factory tools and Industry 4.0 concepts. The platform is offered to users through a unified EFPF portal with value-added features to hide the complexity of dealing with different platform and solution providers.

Motivation

 

fortiss Success Stories Motivation

The increasing digitalisation and servitization in the manufacturing companies opens new opportunities for them to collaborate, share data, reuse each other’s resources such as products, tools, and services, etc., to enable a variety of new business models and revenue streams. However, enabling collaboration among the manufacturing companies to realise innovative B2B scenarios is still challenging because of the interoperability gaps between their digital resources such as tools, services, systems, platforms, and data APIs (Application Programming Interface).

The objective of the EFPF ecosystem is to interlink the heterogeneous Data Management Platforms (DMPs) and enable interoperability, communication and sharing of resources in order to enable companies to make a transition from traditional mass production to a lot-size-one manufacturing.

The primary objectives of the EFPF architecture definition task are to make the design of the EFPF ecosystem modular, scalable, and extensible and to define the enablers and the methodologies that are necessary for its creation and for sustaining its operation.

In EFPF fortiss conceived and developed a novel Machine Learning semantic matchmaking Edge-based solution, TSMatch (Thing to Service Matching). TSMatch is an EFPF open-source middleware solution, which enables end-users to specify IoT services, e.g., environmental monitoring, providing an accurate matching result to existing IoT infrastructures, in a way that is vendor neutral.

TSMatch v2.0 relies on semantic matchmaking based on Natural Language Processing (NLP)with a neural network model to achieve a semi-automated matchmaking between descriptions of IoT data sources (Things) and IoT services. The result is an optimized use of data on the Edge. The key innovation blocks addressed with the research developed in TSMatch are:

  • Semantic interoperability contributions, for which a partial answer is the application of AI/ML to support a better categorization of existing semantic descriptions of sensors and machines.
  • fortiss has analysed different AI/ML approaches, showing that, based on ontological approaches, NLP coupled with neural network models can achieve better performance incomparison, for instance to regular lexical similarity approaches, or to clustering approaches.

Approach

fortiss success stories approach

Value proposition

fortiss success stories value proposition

TSMatch offers benefits such as optimized data processing through Machine Learning-based matchmaking between IoT services and IoT Things descriptions, scalability achieved by the semi-automated matchmaking process, and improved Edge-based data aggregation.

The EFPF consortium is highly interdisciplinary and transnational. It consists of 30 partner organizations representing European excellence in the fields of industry and solution development.

Practice partner

fortiss success story practice partner

Your contact

Prof. Dr. Rute Sofia

sofia@fortiss.org

 

 

 

 

fortiss field of competence

Industrial Internet of Things

Read more

 

 

 

 

fortiss project

EFPF

Read more

fortiss software

TSMatch

Read more