LABELLED ISPACES

i-Space name:  Smart Data Innovation Lab, SDIL.

Country of infrastructure hosting:  germany

Contact Person:  PROF. MICHAEL BEIGL

PHONE:  +49 (0)-721 6084-1701

COMPANY WEBSITE: SDIL.DE

GENERAL INFORMATION

DESCRIPTION

The Smart Data Innovation Lab (SDIL) offers big data researchers unique access to a large variety of big data and in-memory
technologies. Industry and science collaborate closely to find hidden value in big data and generate smart data. Projects focus on
the strategic research areas of Industry 4.0, Energy, Smart Cities and Personalized Medicine.

COORDINATOR

Karlsruhe Institute of Technology (KIT), Kaiserstraße 12 – 76131 Karlsruhe – Germany.

PARTNERS

Bayer Technology Services GmbH, Robert Bosch GmbH, Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, EnBW
Energie Baden-Württemberg AG, IBM Deutschland GmbH, Karlsruher Institut für Technologie (KIT), Fraunhofer Institut
Intelligente Analyse- und Informationssysteme IAIS, Huawei Deutschland, Forschungszentrum Jülich GmbH, SAP SE, Siemens AG,
Software AG, TRUMPF Werkzeugmaschinen GmbH + Co. KG.

PLATFORM AND SERVICES INFORMATION

PLATFORMS

SAP HANA. Cores: 320 (4 servers with 80 cores each), RAM: 4TB (each server hosts 1TB of RAM, Disk Space: 80TB (each server
hosts 20TB of disk space, Network: 10Gbit/s Ethernet. Software: SAP HANA Database System, Predictive Analysis Library,
Business Function Library, etc.
Software AG Terracotta. Cores: on request, RAM: on request, Disk Space: on request. Software BigMemory Max
IBM Watson Foundation Power 8. Cores: 140 (7 servers with 20 cores each), RAM: 4TB, Disk Space: 300TB, Network: 40Gbit/s
Ethernet. Software: IBM Open Platform with Hadoop/Spark, SPSS Modeler, SPSS Analytic Server, DB2 with BLU Acceleration
Huawei FusionInsight. Cores: 356 (13 servers), RAM: 5TB, Disk Space: 362TB, Network: 10Gbit/s Ethernet. Software: Hadoop,
Spark, Storm, Hive
System: HTCondor. Cores: 32 x 4 = 128, RAM: 1TB, Network: 1Gbit/s Ethernet. Software: RapidMiner, Python, R, Matlab

PROVIDED SERVICES

Infrastructure providing: The infrastructure, including technical support, is provided free-of-charge by the SDIL operation
partners to any SDIL project.
Communities: SDIL provides access to experts and domain-specific skills within Data Innovation Communities fostering the
exchange of project results. They further provide the possibility for open innovation and bilateral matchmaking between
industrial partners and academic institutions.
Data curation: The SDIL guarantees a sustainable investment to all partners by curating industrial data sources, best practices,
and code artefacts, that are contributed on a fair share basis.
Data Anonymization: The SDIL offers various anonymization tools to its projects which are applicable to data from research and
industrial sources.

SELECTED PROJECTS AND/OR SUCCESS STORIES

CONDITION MONITORING AND PREDICTION OF SEALING SYSTEMS

The Industrie 4.0 project was carried by Trelleborg Sealing Solutions, IBM, Karlsruhe Institute of Technology (KIT) and SDIL.
Trelleborg Sealing Solutions is a world-leading developer, manufacturer and supplier of precision seals. The company is
continuously working on the measuring and predicting of the condition of seals and it, therefore, runs a wide variety of
instrumented tests on its test rigs. Measurements such as temperatures, speed, pressures and vibration are captured in very
high frequencies. By leveraging Big Data Technology from its partners, Trelleborg is applying advanced machine learning in order
to gain new insights, reduce testing costs and lay the foundation for advanced condition monitoring of sealing solutions in the
field.

VDAR: DISTRIBUTED DECENTRALIZED AUTONOMOUS CONTROL SYSTEMS FOR DISTRIBUTED
ENERGY MARKETS

In this project, the energy data from electricity grid and electricity market are analysed for evaluating the concept of a
decentralized electricity market. Within the scope of the VDAR-research project, control concepts have been explored that
combine the economic system of the electricity market and the physical system of the electricity grid in a decoupled control
circuit. The application increased the control speed of the physical electricity grid and the decentralized energy market.
Therefore, the availability of energy has been being ultimately improved.

CONDITION-BASED MAINTENANCE

The enterprise “TRUMPF Machine Tools” is the global leader in the production of machine tools for sheet metal forming. At
specified, but irregular intervals a “digital image” in the form of a data collection of logging and configuration information is
created in a TRUMPF machine tool. Using these data, the project aimed at detecting deviations (anomalies) from the so-called
“normal operation”. For example, it can be detected if the safety devices, such as guard door monitors, are not working properly
because they were electrically bridged. The project also enables prediction of critical states in the machine.

ASSOCIATION RULE MINING FOR HIGH DIMENSIONAL MASTER DATA

Master Data is a key asset for enterprises today. The quality of Master Data is of critical importance for organizations since
business decisions depend on it. Therefore, much effort goes into ensuring high-quality Master Data. The SDIL project leveraged
rule-based approaches combined with supervised machine learning to discover interesting patterns in a unique industrial data
set provided by SAP within the SDIL

SMART AIR QUALITY NETWORK

Air quality and the associated subjective and health-related quality of life are one of the great themes of our time. Nonetheless, it
is very difficult for many cities to take action on today’s mobility, living and working needs because a consistent data base with
fine-grained data on the action chains is lacking. However, meanwhile, both basic data, as well as promising measuring
approaches, would be available. The project “Smart Air Quality Network” (SmartAQnet) is based on a pragmatic, data driven
approach since the existing data treasures of mcloud.de are combined for the first time and linked with a networked mobile
measurement strategy. By combining open data, such as weather or map data with new mobile measurement approaches, such
as “scientific scouts” and lightweight UAVs, a new analysis concept is tested within the model region of Augsburg. In addition, a
technology stack is to be created prototypically, as modern analysis methods combined with Big Data and IoT technologies
create a scalable, comprehensive application.

PORTS AS INTELLIGENT LOGISTICS HUBS

This project is part of the Transforming Transport EU lighthouse project that aims to demonstrate, in a realistic, measurable, and
replicable way the transformative effects that Big Data will have to the mobility and logistics market. Transforming Transport
brings together knowledge, solutions and impact potential of major European ICT and Big Data technology providers with the
competence and experience of key European industry players and public bodies in the mobility and logistics domain. This project
should demonstrate how solutions for objectives of a seaport pilot can be replicated and reused for the more challenging setting
of an inland port. Compared to a seaport, the added complexity in inland port stems e.g. from the fact that the port is situated in
the middle of a large city and at the centre of a large metropolitan area. This means that it has a multitude of roads, tracks and
water ways that serve as entry and exit points for containers to and from the actual terminals and ports. In addition, roads need
to be shared with many other cars within the metropolitan area. This task will extend the results of a large national innovation
project on logistics control towers and enhances it with advanced Big Data analytics and visualization capabilities that integrate
the various relevant data sources from the port and terminals.

Visit their website to hear more about SDIL success stories.

For further information, please visit BDVA website or contact ispace-label#arroba#core.bdva.eu

X