Identification and Comparison of Characteristics of Different Application Areas in Fleet Prognostics and Health Management

Prognostics and Health Management (PHM) is a field of research, which addresses the detection of incipient failures, the assessment of the current machine health as well as the prediction of the remaining useful machine life (Lee et al., 2014). It therefore facilitates the planning of required maintenance activities and spare parts demand before the actual machine breakdown. Data-driven approaches for PHM use available machine sensor data to develop suitable prognostic models for the estimation of the time-to failure estimation of machines. Besides historical data, data from identical or similar machines (fleet of machines) could be used to improve the algorithm accuracy.

PHM has been applied to several different application areas, including among others automotive, railway, aviation and wind energy. Each component under investigation as well as each application area in general exhibits its own characteristics and peculiarities, which have to be considered during the design and implementation of a suitable PHM system. An example is the availability of complete run-to failure data. While historical breakdown data from wind turbines are often available, in aviation components are maintained always prior to failure due to safety regulations.

The objective of this thesis is the identification and comparison of characteristics of different application areas for the implementation of fleet prognostics and health management. In order to achieve this objective, the thesis covers a literature review to identify different PHM application areas as well as their main objects/ components of investigation. Based on these results, it should be assessed for which application areas data from a fleet of units / machines is available. The most interesting and relevant application areas (approximately 4-6) are taken for further analysis. In a second step, the identified relevant application areas should be analyzed in detail considering their peculiarities and challenges for the implementation of fleet PHM applying a structured literature review. Results should be prepared and presented with regard to these categories (including among others data structure and fleet composition) highlighting the differences between the relevant application areas.

This thesis can be written in either English or German. Since scientific literature and domain-related terms are primary available in English, it is recommended to write the thesis in English.

Further Reading:

  • Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., & Siegel, D. (2014). Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications. Mechanical Systems and Signal Processing, 42(1–2), 314–334.
  • Jardine, A. K., Lin, D., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical systems and signal processing, 20(7), 1483-1510.
  • Peng, Y., Dong, M., & Zuo, M. J. (2010). Current status of machine prognostics in condition-based maintenance: a review. The International Journal of Advanced Manufacturing Technology, 50(1-4), 297-313.
  • Wagner, C. & Hellingrath, B. (2017). Fleet Knowledge for Prognostics and Health Management – Identifying Fleet Dimensions and Characteristics for the Categorization of Fleets. Annual Conference of the Prognostics and Health Management Society 2017. St.Petersburg, USA