Skip to content. | Skip to navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Sections
Personal tools
You are here: Home Theses Incompatible Data?! Dynamic Communication for Machine Learning in the of “Internet of Production”

Contact

Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

Incompatible Data?! Dynamic Communication for Machine Learning in the of “Internet of Production”

Thesis type
  • Bachelor
  • Master
Status Running
Supervisor(s)
Advisor(s)

The goal of this thesis is to extend a service-oriented architecture by semantic descriptions of the interfaces using ontologies. Finally, the dynamic exchange of a component in the machine will be demonstrated in a demo scenario.

iopExample

Scientific Question

In the context of digitization and Industry 4.0, numerous machines and components communicate intensively with each other. The replacement of individual devices in such a closely networked system is often associated with high costs and time expenditure.

In the Cluster of Excellence "Internet of Production", we develop a service-oriented architecture which divides a production system into its components and manages them. Using the example of ultra-short pulse lasers (USP), scanner, slicer and camera are implemented as individual services and built up modularly. The individual components specify syntactic self-definitions such as Integer or String, but a semantic meaning of the values is required indeed.

The goal of this master thesis is to extend a service-oriented architecture by semantic descriptions of the interfaces using ontologies. Finally, the dynamic exchange of a component in the machine will be demonstrated in a demo scenario. 

 

Scientific Methodology

• Extension of existing RPC interfaces by semantics (meaning of the parameters)

• Integration of an existing ontology

• Design of a system architecture for the dynamic exchange of components

• Setup and demonstration in scenarios, including data usage, e.g. by machine learning

 

Objective and Expected Results

• Concept and implementation of interfaces with semantic descriptions

• Use of an ontology for common concepts such as "Celsius”

• Functional verification of the created architecture

 

The results of this work are an important step towards interoperability between production machines in the context of Industry 4.0, including a methodology for the semantic description of interfaces, as well as a concept and an implementation of a SOA with an integrated common ontology. The results support data scientists in their work and promote the interoperability of production machines.

 
Document Actions