Design requirements for wireless sensor-based novelty detection in machinery condition monitoring

  • Christos Emmanouilidis
  • Petros Pistofidis
Conference paper


Wireless sensor networks are increasingly employed in a range of applications. Condition Monitoring in particular can benefit from the introduction of distributed wireless sensing solutions, operating with a high degree of autonomy. Wireless condition monitoring can extend the toolset available to the lifecycle management of engineering assets, offering ease of installation, flexibility, portability and accessibility. A significant hurdle for the adoption of wireless condition monitoring solutions in industry is related to the extent that such solutions can operate over long time periods, while providing adequate monitoring. Wireless sensor nodes extend the sensor functionality by providing on-board CPU, memory, power management and communications capabilities. Yet these are inherently limited due to the small form factor of the devices. Even in cases of sensor nodes with power harvesting capabilities, the minimization of the node energy consumption is sought at a premium. Apart from making the hardware design more energy efficient, sensor nodes can operate more efficiently if they achieve to minimize their energy-consuming activities, while meeting condition monitoring performance requirements. Low-level power management should be dealt with at the level of the sensor operating system. At the application end, a sensor node must feature some form of smart behaviour, enabling it to recognize events that deserve further attention. This is of profound importance as engineering assets equipped with embedded novelty detection capabilities would lend themselves for enhanced and sustainable operation. In this paper we study the design requirements for developing Novelty Detection techniques, as middleware components embedded on a single sensor board. Such smart components would enable the detection of events that signal the presence of unusual behaviour in the monitored equipment. On the basis of the identified design requirements, a conceptual architecture for the development of wireless sensor – board level novelty detection is discussed.


Sensor Network Sensor Node Wireless Sensor Network Condition Monitoring Novelty Detection 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Feng, J., F. Koushanfar, and M. Potkonjak, (2002) System-architectures for sensor networks issues, alternatives, and directions. in Proceedings of IEEE International Conference on Computer Design: VLSI in Computers and Processors, Freiburg.Google Scholar
  2. 2.
    Song, E.Y. and K. Lee, (2008) Understanding IEEE 1451—Networked Smart Transducer Interface Standard. IEEE Instrumentation & Measurement Magazine, 11(2), 11-17.CrossRefGoogle Scholar
  3. 3.
    Boltryk, P., C. Harris, and N. White, (2005) Intelligent sensors-a generic software approach. Journal of Physics: Conference Series, 15, 155-160.CrossRefGoogle Scholar
  4. 4.
    Vadde, S., S. Kamarthi, and S. Gupta, (2003) Modeling smart sensor integrated manufacturing systems. in Proceedings of the SPIE International Conference on Intelligent Manufacturing. Providence, Rhode Island: SPIE.Google Scholar
  5. 5.
    Han, C., et al., (2005) A dynamic operating system for sensor nodes. in Proceedings of the 3rd international conference on Mobile systems, applications, and services. Seattle, Washington.Google Scholar
  6. 6.
    Bhatti, S., et al., (2005) MANTIS OS: An embedded multithreaded operating system for wireless micro sensor platforms. Mobile Networks and Applications, 10(4), 563-579.CrossRefGoogle Scholar
  7. 7.
    Han, C., et al., (2005) SOS: A dynamic operating system for sensor networks, in Third International Conference on Mobile Systems, Applications, And Services (Mobisys).Google Scholar
  8. 8.
    Akyildiz, I., et al., (2002) Wireless sensor networks: a survey. Computer networks, 38(4), 393-422.CrossRefGoogle Scholar
  9. 9.
    Tilak, S., N. Abu-Ghazaleh, and W. Heinzelman, (2002) A taxonomy of wireless micro-sensor network models. ACM SIGMOBILE Mobile Computing and Communications Review, 6(2), 28-36.CrossRefGoogle Scholar
  10. 10.
    Sugihara, R. and R. Gupta, (2008) Programming models for sensor networks: A survey. ACM Trans. Sen. Netw., 4(2), 1-29.CrossRefGoogle Scholar
  11. 11.
    Heinzelman, W., et al., (2004) Middleware to support sensor network applications. IEEE network, 18(1),6-14.CrossRefGoogle Scholar
  12. 12.
    Kahn, J., R. Katz, and K. Pister, (1999) Next century challenges: mobile networking for 'Smart Dust'. in Proceedings of the 5th annual ACM/IEEE Int. Conf. on Mobile computing and networking. Seattle, Washington, USA, ACM.Google Scholar
  13. 13.
    Hu, P., R. Robinson, and J. Indulska, (2007) Sensor standards: Overview and experiences. in Proceedings of International Conference on Intelligent Sensors, Sensor Networks and Information, 2007. ISSNIP 2007. Melbourne, Qld.Google Scholar
  14. 14.
    Emmanouilidis, C., C. Cox, and J. MacIntyre, (1998) Neurofuzzy Computing Aided Machine Fault Diagnosis. in Proceedings of JCIS'98, The Fourth Joint Conference on Information Sciences. Research Triangle Park, NC, USA.Google Scholar
  15. 15.
    Emmanouilidis, C., E. Jantunen, and J. MacIntyre, (2006) Flexible software for condition monitoring, incorporating novelty detection and diagnostics. Computers in Industry, 57(6), 516-527.CrossRefGoogle Scholar
  16. 16.
    Markou, M. and S. Singh, (2003) Novelty detection: a review—part 1: statistical approaches. Signal Processing, 83(12), 81-2497.Google Scholar
  17. 17.
    Markou, M. and S. Singh, (2003) Novelty detection: a review—part 2: neural network based approaches. Signal Processing, 83(12): p. 2499-2521.MATHCrossRefGoogle Scholar
  18. 18.
    Polycarpou, M. and A. Trunov, (2000) Learning approach to nonlinear fault diagnosis: detectability analysis. IEEE Transactions on Automatic Control, 45(4): 806-812.MATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    Lesser, V., C. Ortiz, and M. Tambe, Distributed sensor networks, (2003) A multiagent perspective. 1 ed. Vol. 9. Springer.Google Scholar
  20. 20.
    Gross, T., T. Egla, and N. Marquardt, Sens-ation, (2006) a service-oriented platform for developing sensor-based infrastructures. International Journal of Internet Protocol Technology, 1(3), 159-167.Google Scholar
  21. 21.
    King, J., et al., (2006) Atlas: a service-oriented sensor platform. Proceedings of SenseApp.Google Scholar
  22. 22.
    Emmanouilidis, C., (2002) Evolutionary Multiobjective Feature Selection and ROC Analysis with Application to Industrial Machinery Fault Diagnosis. Evolutionary Methods for Design Optimisation and Control.Google Scholar
  23. 23.
    Engelbrecht, A.P., (2006) Fundamentals of Computational Swarm Intelligence. John Wiley & Sons.Google Scholar
  24. 24.
    Madden, S., et al., (2005) TinyDB: an acquisitional query processing system for sensor networks. ACM Transactions on Database Systems (TODS), 30(1), 122-173.CrossRefMathSciNetGoogle Scholar
  25. 25.
    Yao, Y. and J. Gehrke, (2002) The cougar approach to in-network query processing in sensor networks. ACM Sigmod Record, 31(3), 9-18.CrossRefGoogle Scholar
  26. 26.
    Li, S., et al., (2004) Event detection services using data service middleware in distributed sensor networks. Telecommunication Systems, 26(2), 351-368.CrossRefGoogle Scholar
  27. 27.
    Emmanouilidis, C., S. Katsikas, and C. Giordamlis, (2008) Wireless Condition Monitoring and Maintenance Management: A Review and a Novel Application Development Platform, in Proceedings of the 3rd WCEAM-IMS 2008 Congress. SPRINGER: Beijing, China, 2030-2041.Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Christos Emmanouilidis
    • 1
  • Petros Pistofidis
    • 1
  1. 1.Comp Sys. & Applications DepartmentATHENA Research and Innovation Centre, CETIXanthiGreece

Personalised recommendations