ATZoffhighway worldwide

, Volume 11, Issue 4, pp 62–68 | Cite as

Determining Customer Usage Profiles Using Online Process Pattern Recognition

  • Martin Starke
  • Frank Will
  • Sebastian Mieth
Research Simulation

The application spectrum of mobile machines can be broken down to a limited number of process patterns. A suitable design of the machines requires knowledge of the frequency of occurrence of the respective process pattern. Therefore, an online recognition system was developed at the Technical University of Dresden and implemented on a development control unit.

1 Motivation

In addition to classical criteria such as technological capability and reliability, resource-efficient material input and cost-effective manufacturing are playing an increasingly significant role in the development of mobile construction machines. The qualified design of the structural-mechanical part of the machine requires an operational strength calculation, which is only possible by representative assumptions of the component loads. It was in view of the absence of such load assumptions in the field of mobile machines that researchers from Technische Universität Dresden established the AiF research project Load...


  1. [1]
    Kunze, G.; Mieth, S.: Lastkollektivmethode FVB. Final report IGF research project No. 15852 BR, Dresden, 2012Google Scholar
  2. [2]
    Weber, J.; Mieth, S.: Process Assist: Methode zur Online Prozessmustererkennung für die Ermittlung von Kundenkollektiven an mobilen Baumaschinen. Final report IGF research project No. 18014 BR, Dresden, 2016Google Scholar
  3. [3]
    Gruen, A. W.: Adaptive Least Squares Correlation: A Powerful Image Matching Technique. In: South African Journal of Photogrammetry, Remote Sensing and Cartography 14 (1985), No. 3, pp. 175–187Google Scholar
  4. [4]
    D’Apuzzo, N.: Surface Measurement and Tracking of Human Body Parts from Multi Station Video Sequences. ETH Zurich, Dissertation, 2003Google Scholar
  5. [5]
    Siebler, C.: Gesichtsbasierte Geschlechtserkennung auf Bildsequenzen. Karlsruhe: University, Student Research Project, 2008Google Scholar
  6. [6]
    Eickeler, S.; Rigoll, G.: Kontinuierliche Erkennung von spontan ausgeführten Gesten mit neuen stochastischen Dekodierverfahren. Workshop Dynamische Perzeption, Bielefeld, 1998Google Scholar
  7. [7]
    Juang, B. H.; Rabiner, L. R.: Hidden Markov Models for Speech Recognition. In: Technometrics 33 (1991), No. 3, pp. 251–272MathSciNetCrossRefGoogle Scholar
  8. [8]
    Abdulla, W.; Kasabov, N.: The Concepts of Hidden Markov Model in Speech Recognition. Otago: University of Otago, Technical Report, 1999Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, part of Springer Nature 2018

Authors and Affiliations

  • Martin Starke
    • 1
  • Frank Will
    • 1
  • Sebastian Mieth
    • 2
  1. 1.Technische Universität DresdenDresdenGermany
  2. 2.IBAF GmbHDresdenGermany

Personalised recommendations