Institute for Industrial Information Technology

Digital twin and artificial intelligence in production processes

The Institute for Industrial Information Technology (inIT) at the OWL University of Applied Sciences and Arts is one of the leading research institutes in the field of industrial automation. Among others, the institute is currently working on the two projects ML4Pro2 and TeDZ, which were to be presented at the Hanover Fair 2020 with two exhibits.

In the project "ML4Pro2", inIT is researching the transferability of machine learning in the context of the technology network it's OWL together with various research partners. The project aims to compile an interactive toolbox with industry-suitable AI and learning algorithms, thus enabling small and medium-sized manufacturing companies to use AI. The project "Technical Infrastructure for Digital Twins - TeDZ" aims at enabling and significantly increasing the access and interaction of products and resources along their life cycle by means of an interoperable end-to-end technical infrastructure.

The digital twin
[in German]

Benefits for companies

Artificial intelligence (AI) in industrial production processes has the potential to facilitate the development of technical solutions as well as the maintenance and service of industrial machines. However, AI methods are often not simply one-to-one applicable to industrial

Production processes transferable. Technical processes place increased demands on algorithms, such as high accuracy and precision, robustness against dynamic effects and transparency in decision-making. Research work at inIT identifies and addresses corresponding weaknesses in AI algorithms.

In it's OWL project ML4Pro², inIT is researching AI and methods of information fusion to determine, predict and visualize states of technical systems in a robust and transparent way. Patterns and information hidden in time-series signals are learned through targeted transformations and presented to the user in an understandable way. Inaccuracies and uncertainties in individual sensors and the resulting inconsistencies in multi-sensor systems are solved by conflict-reducing information fusion. On the one hand, complex concepts are learned from training data, and on the other hand, the fusion ensures that sensor failures and errors have no effect on the actual application.

Digital twins are the virtual representation of physical, technical objects in the real world. Digital twins store data, map current and potential states, name special characteristics of technical units and inform about available services and algorithms. This holistic representation of information is what enables Digital Twins to enable the meaningful and target-oriented use of AI solutions in technical systems.

AI competencies

Intelligent technical systems, AI-based machine diagnosis and industrial image processing are among the core competencies at inIT. The goal of the research activities at the institute is a networked intelligent automation, which is characterized by self-organization, self-optimization and self-diagnosis. Using methods of machine learning, cognitive systems, information fusion and orchestration, machines are evaluated with respect to their condition (condition monitoring), their need for maintenance is predicted (predictive maintenance) and their behaviour is optimised (e.g. according to resource consumption or production quality). In doing so, specific features and conditions of industrial systems are taken into account. In order to provide added value to technical systems, AI algorithms and models must be able to run on resource-limited hardware. They must also be able to handle uncertainties and handle inaccuracies in data, be explainable, transparent and adaptable, and meet real-time requirements.