Advertisement

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

  • Daniel SonntagEmail author
  • Sonja Zillner
  • Patrick van der Smagt
  • András Lörincz
Chapter
Part of the Springer Series in Wireless Technology book series (SSWT)

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.

Keywords

Anomaly Detection Deep Learning Deep Neural Network Maintenance Process Seamless Integration 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgments

We thank our project partners in CPS for Smart Factories, funded by EIT Digital (EU, Horizon 2020). See http://dfki.de/smartfactories/.

References

  1. 1.
    der Arbeitsdirektionen Stahl, AEM (2003) Integration von produktion und instandhaltung. Arbeitspapier, Hans-Boeckler-StiftungGoogle Scholar
  2. 2.
    Arora S, Bhaskara A, Ge R, Ma T (2013) Provable bounds for learning some deep representations. arXiv preprint arXiv:1310.6343
  3. 3.
    Bayer J, Karl M, Korhammer D, van der Smagt P (2015) Fast adaptive weight noise. arXiv preprint arXiv:1507.05331
  4. 4.
    Bayer J, Osendorfer C, Urban S, van der Smagt P (2013) Training neural networks with implicit variance. In: Lee M, Hirose A, Hou Z-G, Kil RM (eds) Neural information processing. Springer, Heidelberg, pp 132–139CrossRefGoogle Scholar
  5. 5.
    Bengio Y (2009) Learning deep architectures for AI. Found Trends® Mach Learn 2(1):1–127MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Jabar HB, Sdn Bhd, SP (2003) Plant maintenance strategy: key for enhancing profitability (2003)Google Scholar
  7. 7.
    Bleakley K, Vert JP (2011) The group fused lasso for multiple change-point detection. arXiv preprint arXiv:1106.4199
  8. 8.
    Candès EJ, Li X, Ma Y, Wright J (2011) Robust principal component analysis? J ACM (JACM) 58(3):11MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM Comput Surv 41(3):15:1–15:58 http://doi.acm.org/10.1145/1541880.1541882 CrossRefGoogle Scholar
  10. 10.
    Chen T, Goodfellow IJ, Shlens J (2015) Net2net: accelerating learning via knowledge transfer. CoRR abs/1511.05641. http://arxiv.org/abs/1511.05641
  11. 11.
    Dasiopoulou S, Giannakidou E, Litos G, Malasioti P, Kompatsiaris Y (2011) Knowledge-driven multimedia information extraction and ontology evolution. In: Paliouras G, Spyropoulos CD, Tsatsaronis G (eds) A survey of semantic image and video annotation tools. Springer, Heidelberg, pp 196–239Google Scholar
  12. 12.
    Gebhard P (2013) Controlling interaction with digital product memories. In: Wahlster, W. (ed.) SemProM. Cognitive technologies. Springer, Berlin, pp 243–259Google Scholar
  13. 13.
    Haupert J, Schneider M (2013) The object memory server for semantic product memories. In: Wahlster W (ed.) SemProM. Cognitive technologies. Springer, Berlin, pp. 175–189 (2013)Google Scholar
  14. 14.
    Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18:1527–1554MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Jeni LA, Lorincz A, Szabó Z, Cohn J, Kanade T (2014) Spatio-temporal event classification using time-series kernel based structured sparsity. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision—ECCV 2014. Lecture notes in computer science, vol 8692. Springer, Switzerland, pp 135–150Google Scholar
  16. 16.
    Rezende DJ, Mohamed S, Wierstra D (2014) Stochastic backpropagation and approximate inference in deep generative models. ArXiv e-printsGoogle Scholar
  17. 17.
    Judd S (1988) On the complexity of loading shallow neural networks. J Complex 4(3):177–192MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Kingma DP, Welling M (2013) Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114
  19. 19.
    Kroener A, Haupert J, de Gea Fernandez J, Steffen R, Kleegrewe C, Schneider M (2013) Supporting interaction with digital product memories. In: Wahlster W (ed) SemProM. Cognitive technologies. Springer, Berlin, pp. 223–242Google Scholar
  20. 20.
    Lörincz A, Milacski ZÁ, Pintér B, Verö AL (2016) Columnar machine: fast estimation of structured sparse codes. Biol Inspired Cogn Architect 15:19–33CrossRefGoogle Scholar
  21. 21.
    Mihaly A, Milacski ZA, Toser Z, Lőrincz A, Tettamanti T, Varga I (2015) Cost and risk sensitive decision making and control for highway overtaking maneuver. In: 2015 International conference on models and technologies for intelligent transportation systems (MT-ITS), pp 87–92. IEEEGoogle Scholar
  22. 22.
    Milacski ZÁ, Ludersdorfer M, Lőrincz A, van der Smagt P (2015) Robust detection of anomalies via sparse methods. In: Arik S, Huang T, Lai WK, Liu Q (eds) Neural information processing. Springer, Heidelberg, pp 419–426CrossRefGoogle Scholar
  23. 23.
    Palotai Z, Lang M, Sarkany A, Toser Z, Sonntag D, Toyama T, Lörincz A (2014) Labelmovie: semi-supervised machine annotation tool with quality assurance and crowd-sourcing options for videos. In: 12th International workshop on content-based multimedia indexing, CBMI 2014, Klagenfurt, Austria, 18–20 June 2014. pp. 1–4. IEEE http://dx.doi.org/10.1109/CBMI.2014.6849850
  24. 24.
    Pistofidis P, Emmanouilidis C, Papadopoulos A, Botsaris P (2014) In: Proceedings of the European conference of the prognostics and health management societyGoogle Scholar
  25. 25.
    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Networks 61:85–117CrossRefGoogle Scholar
  26. 26.
    Schoeffmann K, Hudelist MA, Huber J (2015) Video interaction tools: a survey of recent work. ACM Comput Surv 48(1):14:1–14:34 http://doi.acm.org/10.1145/2808796 CrossRefGoogle Scholar
  27. 27.
    Sonntag D (2014) Ermed—towards medical multimodal cyber-physical environments. In: Schmorrow DD, Fidopiastis CM (eds) Foundations of augmented cognition advancing human performance and decision-making through adaptive systems. Springer, Heidelberg, pp 359–370Google Scholar
  28. 28.
    Sonntag, D (2015) Tutorial 3: intelligent user interfaces. In: Proceedings of the 2015 IEEE international symposium on mixed and augmented reality, ISMAR 2015. IEEE Computer Society, Washington, DC, USA, pp. xxxii–xxxiiGoogle Scholar
  29. 29.
    Sonntag D, Toyama T (2013) On-body IE: a head-mounted multimodal augmented reality system for learning and recalling faces. In: 9th International conference on intelligent environments (IE), pp. 151–156Google Scholar
  30. 30.
    Sonntag D, Weihrauch C, Jacobs O, Porta D (2010) THESEUS usability guidelines for use case applications. Technical report, DFKI and Federal Ministry of Education and Research GermanyGoogle Scholar
  31. 31.
    Sonntag D, Zillner S, Chakraborty S, Lőrincz A, Strommer E, Serafini L (2014) The medical cyber-physical systems activity at EIT: a look under the hood. In: 2014 IEEE 27th International symposium on computer-based medical systems, 27–29 May 2014. IEEE Computer Society, New York, pp 351–356Google Scholar
  32. 32.
    Tösér Z, Lörincz A (2015) The cyber-physical system approach towards artificial general intelligence: the problem of verification. In: Bieger J, Goertzel B, Potapov A (eds) Artificial general intelligence. Springer, Heidelberg, pp 373–383CrossRefGoogle Scholar
  33. 33.
    Turunen M, Sonntag D, Engelbrecht K, Olsson T, Schnelle-Walka D, Lucero A (2015) Interaction and humans in internet of things. In: Abascal J, Barbosa SDJ, Fetter M, Gross T, Palanque PA, Winckler M (eds) Proceedings of the 15th IFIP TC 13 international conference on human-computer interaction Part IV—INTERACT 2015, Bamberg, Germany, 14–18 September 2015. Lecture notes in computer science, vol. 9299. Springer, Heidelberg, pp 633–636 (2015)Google Scholar
  34. 34.
    Šarić M (2011) Libhand: a library for hand articulation. http://www.libhand.org/, version 0.9
  35. 35.
    Wahlster W (2013) The semantic product memory: an interactive black box for smart objects. In: Wahlster W (ed) SemProM—foundations of semantic product memories for the internet of things. Cognitive technologies. Springer, Heidelberg, pp 3–21Google Scholar
  36. 36.
    Zhou A, Yu D, Zhang W (2015) A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA. Adv Eng Inform 29(1):115–125CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  • Daniel Sonntag
    • 1
    Email author
  • Sonja Zillner
    • 2
  • Patrick van der Smagt
    • 3
  • András Lörincz
    • 4
  1. 1.DFKISaarbrückenGermany
  2. 2.SiemensMunichGermany
  3. 3.FortissTUMMunichGermany
  4. 4.ELTEBudapestHungary

Personalised recommendations