Remaining Useful Lifetime for New and Used Technical Systems under Non-Stationary Conditions

• Applicants: Professor Dr. Eyke Hüllermeier; Professor Dr.-Ing. Walter Sextro
• Subject Area: Mechanics
• Term: from 2021 to 2025
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 451737409

• Final Report Year: 2025

Final Report Abstract

The primary goal of prognostics and health management (PHM) is to estimate the remaining useful life (RUL), that is the time a system or component remains operational before failing. In real-world applications, systems often operate under time-varying operating conditions (OCs) throughout their lifetime. However, many existing methods and data sets focus on systems with either constant OC or OC that only vary across different run-to-failure experiments. This project aimed to bridge this gap by addressing more realistic scenarios where OC can vary almost arbitrarily during a system’s lifetime. The project included initial studies on incorporating the OC information into pipelines for predicting the RUL. Furthermore, the project aimed at developing methods for predicting the RUL of already used systems without measurements of the past degradation. To this end, appropriate methods were developed and evaluated on three different application examples. The first application example involves run-to-failure experiments of ball bearings, where a suitable test rig was designed and constructed for simulating time-varying operating conditions. The second application example involves run-to-failure experiments of piezoelectric bending transducers. In the experiments, cracks on the piezoelectric layer of the transducers, as the main failure mode, were monitored. The third application example is based on the simulated data of a turbofan engine, whose degradation was detected under six operating conditions with different sensors. The major project goals were successfully achieved in the project’s approval period. However, the proposed methodology could not be validated on already used systems without measurements of the past degradation, where the operating conditions and time information are also not available up till the current time.

Publications

• Extraktion und Selektion geeigneter Merkmale für die Restlebensdauerprognose von technischen Systemen trotz aleatorischen Unsicherheiten. Schwingungen 2021, 197-210. VDI Verlag.
  Kennedy, Aimiyekagbon O.; Bender, A. & Sextro, W.
  
• “On the applicability of time series features as health indicators for technical systems operating under varying conditions”. In: Proceedings of the Seventeenth International Conference on Condition Monitoring and Asset Management (CM 2021). 2021.
  O. K. Aimiyekagbon, A. Bender & W. Sextro
  
• On the applicability of time series features as health indicators for technical systems operating under varying conditions. In: Condition Monitor 425 (2022), pp. 5–10.
  O. K. Aimiyekagbon, A. Bender & W. Sextro
  
• Conformal Prediction Intervals for Remaining Useful Lifetime Estimation. International Journal of Prognostics and Health Management, 14(2).
  Javanmardi, Alireza & Hüllermeier, Eyke
  
• Conformal Prediction with Partially Labeled Data. In: Proceedings of the Twelfth Symposium on Conformal and Probabilistic Prediction with Applications. PMLR, 2023.
  A. Javanmardi, Y. Sale, P. Hofman & E. Hullermeier
  
• Expert-Informed Hierarchical Diagnostics of Multiple Fault Modes of a Spacecraft Propulsion System. PHM Society Asia-Pacific Conference, 4(1).
  Aimiyekagbon, Osarenren Kennedy; Lowen, Alexander; Bender, Amelie; Muth, Lars & Sextro, Walter
  
• Bearing-RUL Code. 2024.
  A. Javanmardi
  
• Conformalized Credal Set Predictors. Advances in Neural Information Processing Systems 37, 116987-117014. Neural Information Processing Systems Foundation, Inc. (NeurIPS).
  Hüllermeier, Eyke; Javanmardi, Alireza & Stutz, David
  
• Diagnostics and Prognostics for Retrofitted Systems: A Comprehensive Approach for Enhanced System Health Assessment. 2024 Prognostics and System Health Management Conference (PHM), 159-164. IEEE.
  Bender, Amelie; Aimiyekagbon, Osarenren K. & Sextro, Walter
  
• Diagnostics of Piezoelectric Bending Actuators Subjected to Varying Operating Conditions. Electronics, 13(3), 521.
  Aimiyekagbon, Osarenren Kennedy; Bender, Amelie; Hemsel, Tobias & Sextro, Walter
  
• Remaining Useful Lifetime Estimation of Bearings Operating under Time-Varying Conditions. PHM Society European Conference, 8(1), 9.
  Javanmardi, Alireza; Aimiyekagbon, Osarenren Kennedy; Bender, Amelie; Kimotho, James Kuria; Sextro, Walter & Hüllermeier, Eyke
  
• Run-to-failure data set of ball bearings subjected to time-varying load and speed conditions. Version 2023-04-02. Zenodo, June 2024.
  O. K. Aimiyekagbon