ADIMA:
Adaptive assistance system for maintenance of intelligent machines and plants

Project Duration: 1.5.2016 to 30.4.2019 (Finished)
Area of Research: Industrial Communications : Industrial Communication, Industrielle Signalverarbeitung : Human-Machine-Interaction
Project Manager: Prof. Dr.-Ing. Dr. phil. Dr. rer. soc. Carsten Röcker , Prof. Dr. Jürgen Jasperneite


  

The term industry 4.0 describes the increasing use of information and communication technologies (ICT) in industrial processes, whereby a complete networking of all actors involved is achieved - from the sensor on the product and the means of production through to systems for corporate management.

 

While the first prototypes of such systems are already in practical use (see, for example SmartFactoryOWL), maintenance prompt questions because of larger plants, stronger modularization and complex products. Errors cannot be adequately addressed by local diagnostic methods because of particular propagation of errors by the concatenation of the system components. In addition, error handling, which may occur through the interaction of different components and subsystems in a dynamically configured production system, is difficult to estimate in advance today. Consequently, it is not even possible to define fixed routines for troubleshooting, to a maintenance technician for access in case of service.


The aim of the project is therefore the development of an assistance system for the maintenance of intelligent machines and systems, the maintenance information is generated based on machine learning algorithms independently of machine data and thus visualized that repair work can be carried out by locally based technicians without machine-specific knowledge in a quickly and successfully way. It is estimated that the availability on the client side, the plant operator, can be increased by such a system up to 20%. Furthermore, up to 20% less service technician visits are necessary, which should lead to a cost reduction in maintenance between 25 and 50%. At the same time, these points also enable significant yield increases on the part of the system manufacturer. Because in the area of technical customer service factors such as travel, logistics, and personnel costs for service calls is currently up to 64% of total costs - which are indeed made to client accounts, but yield only minimal profits. With a reduction of the necessary service calls, the equipment manufacturer could focus in the maintenance area on the profitable aftermarket business.

 

 


Herbert Kannegiesser GmbH,

ISI Automation GmbH & Co. KG

Image: Adaptive assistance system for maintenance of intelligent machines and plantsImage: Adaptive assistance system for maintenance of intelligent machines and plants


Publications:

Büttner, Sebastian; Wunderlich, Paul; Heinz, Mario; Niggemann, Oliver; Röcker, Carsten: Managing Complexity: Towards Intelligent Error-Handling Assistance Trough Interactive Alarm Flood Reduction. In: International Cross Domain Conference for Machine Learning & Knowledge Extraction (CD-MAKE '17) Springer, Reggio Calabria, Italien, Aug 2017 (More)

Wunderlich, Paul; Niggemann, Oliver: Structure Learning Methods for Bayesian Networks to Reduce Alarm Floods by Identifying the Root Cause. In: 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2017) Sep 2017 (More)

Wunderlich, Paul; Niggemann, Oliver: Challenges in Learning Causal Models of Alarms in Industrial Plants. In: 16th IEEE International Conference on Industrial Informatics (INDIN) Porto, Portugal, Jul 2018 (More)

Wunderlich, Paul; Niggemann, Oliver: Inference Methods for Detecting the Root Cause of Alarm Floods in Causal Models. In: 23rd International Conference on Methods and Models in Automation and Robotics (MMAR) Międzyzdroje, Poland, Aug 2018 (More)

Lang, Dorota; Wunderlich, Paul; Heinz, Mario; Wisniewski, Lukasz; Jasperneite, Jürgen; Niggemann, Oliver; Röcker, Carsten: Assistance System to Support Troubleshooting of Complex Industrial Systems. In: 14th IEEE International Workshop on Factory Communication Systems (WFCS) Imperia (Italy), Jun 2018 (More)

Ali Khan, Waqas ; Wisniewski, Lukasz; Lang, Dorota; Jasperneite, Jürgen: Analysis of the Requirements for offering Industrie 4.0 applications as a Cloud Service. In: 26th IEEE International Symposium on Industrial Electronics (ISIE 2017) In: 26th IEEE International Symposium on Industrial Electronics (ISIE 2017) Edinburgh, Scotland, UK, Jun 2017 (More)

Lang, Dorota; Friesen, Maxim; Ehrlich, Marco; Wisniewski, Lukasz; Jasperneite, Jürgen: Pursuing the Vision of Industrie 4.0: Secure Plug and Produce by Means of the Asset Administration Shell and Blockchain Technology. In: 16th IEEE International Conference on Industrial Informatics, INDIN 2018 Porto, Portugal, Jul 2018 (More)

Wunderlich, Paul; Niggemann, Oliver: Concept for Alarm Flood Reduction with Bayesian Networks by Identifying the Root Cause. In: IMPROVE - Innovative Modelling Approaches for Production Systems to Raise Validatable Efficiency: Intelligent Methods for the Factory of the Future S.: 111-129, Springer Vieweg, Aug 2018 (More)

Lang, Dorota; Grunau, Sergej; Wisniewski, Lukasz; Jasperneite, Jürgen: Utilization of the Asset Administration Shell to Support Humans During the Maintenance Process. In: 17th International Conference on Industrial Informatics (IEEE-INDIN 2019) Helsinki, Finland, Jul 2019 (More)

Wunderlich, Paul; Hranisavljevic, Nemanja: Comparison of Different Probabilistic Graphical Models as Causal Models in Alarm Flood Reduction. In: 17th IEEE International Conference on Industrial Informatics (INDIN) Helsinki, Finnland, Jul 2019 (More)


Funded by: BMBF
Project Management: VDI Technologiezentrum GmbH
Grant ID: 13FH019PX5
Funding: FHprofUnt 2015
Contact Person: M.Sc. Mario Heinz
Research Assistant: M.Sc. Paul Wunderlich , M.Sc. Mario Heinz , M. Sc Dorota Lang