Overview of the CPS for Smart Factories Project: Deep Learning, Knowledge Acquisition, Anomaly Detection and Intelligent User Interfaces

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.

[1]  Zoltán TźSér,et al.  The Cyber-Physical System Approach Towards Artificial General Intelligence: The Problem of Verification , 2015, AGI 2015.

[2]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[3]  Hans-Böckler-Stiftung.  Integration von Produktion und Instandhaltung , 2003 .

[4]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[5]  András Lörincz,et al.  Cost and risk sensitive decision making and control for highway overtaking maneuver , 2015, 2015 International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS).

[6]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[7]  J. Stephen Judd,et al.  On the complexity of loading shallow neural networks , 1988, J. Complex..

[8]  Klaus-Peter Engelbrecht,et al.  Interaction and Humans in Internet of Things , 2015, INTERACT.

[9]  Daniel Sonntag,et al.  On-Body IE: A Head-Mounted Multimodal Augmented Reality System for Learning and Recalling Faces , 2013, 2013 9th International Conference on Intelligent Environments.

[10]  Patrick van der Smagt,et al.  Robust Detection of Anomalies via Sparse Methods , 2015, ICONIP.

[11]  Daniel Sonntag,et al.  LabelMovie: Semi-supervised machine annotation tool with quality assurance and crowd-sourcing options for videos , 2014, 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI).

[12]  Wolfgang Wahlster.  The Semantic Product Memory: An Interactive Black Box for Smart Objects , 2013, SemProM.

[13]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[14]  Klaus Schöffmann,et al.  Video Interaction Tools , 2015, ACM Comput. Surv..

[15]  Wenyi Zhang,et al.  A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA , 2015, Adv. Eng. Informatics.

[16]  Jean-Philippe Vert,et al.  The group fused Lasso for multiple change-point detection , 2011, 1106.4199.

[17]  Daniel Sonntag.  ERmed - Towards Medical Multimodal Cyber-Physical Environments , 2014, HCI.

[18]  Balázs Pintér,et al.  Columnar Machine: Fast estimation of structured sparse codes , 2016, BICA 2016.

[19]  Daniel Sonntag,et al.  The Medical Cyber-physical Systems Activity at EIT: A Look under the Hood , 2014, 2014 IEEE 27th International Symposium on Computer-Based Medical Systems.

[20]  Jens Haupert,et al.  The Object Memory Server for Semantic Product Memories , 2013, SemProM.

[21]  Martin Schneider,et al.  Supporting Interaction with Digital Product Memories , 2013, SemProM.

[22]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[23]  Daniel Sonntag.  Tutorial 3: Intelligent User Interfaces , 2015, ISMAR.

[24]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[25]  Tianqi Chen,et al.  Net2Net: Accelerating Learning via Knowledge Transfer , 2015, ICLR.

[26]  Christian Osendorfer,et al.  Training Neural Networks with Implicit Variance , 2013, ICONIP.

[27]  Patrick Gebhard,et al.  Controlling Interaction with Digital Product Memories , 2013, SemProM.