Closing the Lifecycle Loop with Installed Base Products

  • Martin ImbodenEmail author
  • Bernhard Fradl
  • Felix Nyffenegger
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 540)


Industry trends indicate that in the future, more systems will be rented then sold. The customer rents production capacity and demands a guaranteed high operational readiness, which is hard to achieve with conventional maintenance. Downtimes can never be completely ruled out. In order to solve this problem and guarantee high operational reliability, the predictive maintenance approach is widely discussed: By means of indicators, measured by sensors, a potential problem can be identified before it actually occurs. The application of this concept to new products gets a lot of attention in many areas. However, industrial products such as machines or plants are long living objects. It seems interesting to extend these new technologies and eventually new services business models to the installed base, too.

This paper explores and demonstrates, what it takes to upgrade an operating product in its mid-of-life stage to a smart, connected products with predictive maintenance capabilities. The showcase consists of a jointed-arm industrial robot with six axes. The robot’s motions will be retraced in order to determine the state and position of the robot and finally predict, what the robot is about to do. To achieve this, the robot was made IoT-capable by attachment of sensors which communicate directly to a cloud database. Finally, a trained machine learning model allows predication on the robots’ behavior. On the way to the final result, many little lessons about sensing, protocols, the right place to process or tag data in the IoT stack had to learnt and will be shared in this publication.


Closed-loop PLM Predictive maintenance Machine learning IoT Installed base 


  1. 1.
    Fradl, B., Sohrweide, A., Nyffenegger, F.: PLM in education – the escape from boredom. In: Ríos, J., Bernard, A., Bouras, A., Foufou, S. (eds.) PLM 2017. IAICT, vol. 517, pp. 297–307. Springer, Cham (2017). Scholar
  2. 2.
    Nyffenegger, F.: Aufgabenstellung_BA_2017_imboden. HSR, Rapperswil (2017)Google Scholar
  3. 3.
  4. 4.
    Hermann, M., Pentek, T., Otto, B.: Design principles for industrie 4.0 scenarios. In: 2016 49th Hawaii International Conference on System Sciences (HICSS), Hawaii (2016)Google Scholar
  5. 5.
    Orhan, S., Aktürk, N., Çelik, V.: Vibration monitoring for defect diagnosis of rolling element bearings as a predictive maintenance tool: comprehensive case studies. NDT E Int. 39(4), 293–298 (2005)CrossRefGoogle Scholar
  6. 6.
    Pedregal, D.J., García, F.P., Schmid, F.: RCM2 predictive maintenance of railway systems based on unobserved components models. Reliab. Eng. Syst. Saf. 88(1), 103–110 (2004)CrossRefGoogle Scholar
  7. 7.
    Gilabert, E., Arnaiz, A.: Intelligent automation systems for predictive maintenance: a case study. Robot. Comput.-Integr. Manuf. 22(5–6), 543–549 (2006)CrossRefGoogle Scholar
  8. 8.
    Barnes, J.: Azure Machine Learning - Microsoft Azure Essentials. Microsoft Press, Redmond (2015)Google Scholar
  9. 9.
  10. 10.
    Diamond, S., Marfatia, A.: Predictive Maintenance for Dummies. Wiley, Hoboken (2013)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2018

Authors and Affiliations

  • Martin Imboden
    • 1
    Email author
  • Bernhard Fradl
    • 1
  • Felix Nyffenegger
    • 1
  1. 1.HSRRapperswilSwitzerland

Personalised recommendations