Industry 4.0 factories become more and more complex with increased maintenance costs. Reducing costs by cyber-physical (CP) controllers should ensure the commercialization of the CPS for smart factory project results. We implement multi-adaptive CP controllers in the following domains: industrial robot arms, car manufacturing, steel industry, and assembly lines in general. The main objective is to implement such controllers for these application domains and let the industry partners provide feedback about the cost reduction potential. In this paper, we describe the technical infrastructure including deep learning and knowledge acquisition submodules, followed by anomaly detection modules and intelligent user interfaces in the IoT (Internet of Things) paradigm. In addition, we report on three concrete use case implementations of industrial robots and anomaly modeling, knowledge management and anomaly treatment in the steel domain, and anomaly detection in the energy domain.
%0 Book Section
%1 SonntagZillnerEtAl17p487
%A Sonntag, Daniel
%A Zillner, Sonja
%A van der Smagt, Patrick
%A Lörincz, András
%B Industrial Internet of Things
%C Cham
%D 2017
%E Jeschke, Sabina
%E Brecher, Christian
%E Song, Houbing
%E Rawat, Danda B.
%I Springer
%K 01821 springer paper dfki embedded ai factory data pattern recognition knowledge management robot user interface interaction admin optimize learn zzz.big zzz.i40 zzz.iui
%P 487--504
%R 10.1007/978-3-319-42559-7_19
%T Overview of the CPS for Smart Factories Project: Deep Learning, Knowledge Acquisition, Anomaly Detection and Intelligent User Interfaces
%X Industry 4.0 factories become more and more complex with increased maintenance costs. Reducing costs by cyber-physical (CP) controllers should ensure the commercialization of the CPS for smart factory project results. We implement multi-adaptive CP controllers in the following domains: industrial robot arms, car manufacturing, steel industry, and assembly lines in general. The main objective is to implement such controllers for these application domains and let the industry partners provide feedback about the cost reduction potential. In this paper, we describe the technical infrastructure including deep learning and knowledge acquisition submodules, followed by anomaly detection modules and intelligent user interfaces in the IoT (Internet of Things) paradigm. In addition, we report on three concrete use case implementations of industrial robots and anomaly modeling, knowledge management and anomaly treatment in the steel domain, and anomaly detection in the energy domain.
%@ 978-3-319-42558-0
@incollection{SonntagZillnerEtAl17p487,
abstract = {Industry 4.0 factories become more and more complex with increased maintenance costs. Reducing costs by cyber-physical (CP) controllers should ensure the commercialization of the CPS for smart factory project results. We implement multi-adaptive CP controllers in the following domains: industrial robot arms, car manufacturing, steel industry, and assembly lines in general. The main objective is to implement such controllers for these application domains and let the industry partners provide feedback about the cost reduction potential. In this paper, we describe the technical infrastructure including deep learning and knowledge acquisition submodules, followed by anomaly detection modules and intelligent user interfaces in the IoT (Internet of Things) paradigm. In addition, we report on three concrete use case implementations of industrial robots and anomaly modeling, knowledge management and anomaly treatment in the steel domain, and anomaly detection in the energy domain.},
added-at = {2017-01-01T15:27:31.000+0100},
address = {Cham},
author = {Sonntag, Daniel and Zillner, Sonja and van der Smagt, Patrick and L\"{o}rincz, Andr\'{a}s},
biburl = {https://www.bibsonomy.org/bibtex/232b8f8590dbd9668bc779d313339db86/flint63},
booktitle = {Industrial Internet of Things},
crossref = {JeschkeBrecherEtAl2017},
doi = {10.1007/978-3-319-42559-7_19},
editor = {Jeschke, Sabina and Brecher, Christian and Song, Houbing and Rawat, Danda B.},
file = {SpringerLink:2017/SonntagZillnerEtAl17p487.pdf:PDF},
groups = {public},
interhash = {7306f06a0b9140a6972849e6e39de26c},
intrahash = {32b8f8590dbd9668bc779d313339db86},
isbn = {978-3-319-42558-0},
issn = {2365-4139},
keywords = {01821 springer paper dfki embedded ai factory data pattern recognition knowledge management robot user interface interaction admin optimize learn zzz.big zzz.i40 zzz.iui},
pages = {487--504},
publisher = {Springer},
series = {Springer Series in Wireless Technology},
timestamp = {2018-04-16T11:55:57.000+0200},
title = {Overview of the {CPS for Smart Factories} Project: Deep Learning, Knowledge Acquisition, Anomaly Detection and Intelligent User Interfaces},
username = {flint63},
year = 2017
}