@inproceedings{55336,
  abstract     = {{Predicting the remaining useful life of technical 
systems has gained significant attention in recent years due to 
increasing demands for extending the lifespan of degrading system 
components. Therefore, already used systems are retrofitted by 
integrating sensors to monitor their performance and 
functionality, enabling accurate diagnosis of their condition and 
prediction of their remaining useful life. One of the main 
challenges in this field is identified in the missing data from the 
time where the retrofitted system has already run but without 
being monitored by sensors. In this paper, a novel approach for 
the combined diagnostics and prognostics of retrofitted systems is 
proposed. The methodology aims to provide an accurate diagnosis 
of the system’s health state and estimation of the remaining useful 
life by a combination of a machine learning and expert knowledge. 
To evaluate the effectiveness of the proposed methodology, a case 
study involving a retrofitted system in an industrial setting is 
selected and applied. It is demonstrated that the approach 
effectively diagnose the current system’s health state and 
accurately predict its remaining useful life, thereby enabling 
predictive maintenance and decision-making. Overall, our 
research contributes to advancing the field of condition 
monitoring for retrofitted systems by providing a comprehensive 
methodology that addresses the challenge of missing data.}},
  author       = {{Bender, Amelie and Aimiyekagbon, Osarenren Kennedy and Sextro, Walter}},
  booktitle    = {{Proceedings of the 2024 Prognostics and System Health Management Conference (PHM)}},
  isbn         = {{979-8-3503-6058-5}},
  keywords     = {{retrofit, diagnosis, prognostics, RUL prediction, missing data, ball bearings}},
  location     = {{Stockholm, Schweden}},
  publisher    = {{IEEE Computer Society}},
  title        = {{{Diagnostics and Prognostics for Retrofitted Systems: A Comprehensive Approach for Enhanced System Health Assessment}}},
  doi          = {{10.1109/PHM61473.2024.00038}},
  year         = {{2024}},
}

@inproceedings{13460,
  abstract     = {{Remaining useful lifetime (RUL) predictions as part of a condition monitoring system are focused in more and more research and industrial applications. To establish an efficient and precise estimate of the RUL of a technical product, different  uncertainties  have  to  be  handled.  To  minimize  the  uncertainties  of  the  RUL  estimation,  a  reliable and accurate prognostic approach as well as a good failure threshold are important. Regarding the failure threshold, most often  an  expert  sets  a  fixed  failure  threshold.  However,  neither  the  a  priori  known  failure  threshold  nor  a  fixedthreshold value are feasible in every application. Especially in the case of varying characteristics of the monitored system, an adaptive failure threshold is of great importance concerning the accuracy of the RUL estimation.  Rubber-metal-elements, which are used in a wide range of applications for vibration and sound isolation, are mon-itored by thermocouples to allow for lifetime predictions. Therefore, the element’s state is described by its temper-ature during its service life. Aiming to establish accurate RUL predictions of a rubber-metal-element, uncertainties due to nonlinear material characteristics and changing operational conditions have to be considered. Consequently, different temperature-based failure threshold definitions are implemented and compared within a particle filtering approach. }},
  author       = {{Bender, Amelie and Schinke, Lennart and Sextro, Walter}},
  booktitle    = {{Proceedings of the 29th European Safety and Reliability Conference (ESREL2019)}},
  editor       = {{Beer, Michael and Zio, Enrico}},
  isbn         = {{978-981-11-2724-3}},
  keywords     = {{RUL prediction, adaptive threshold, prognostics, condition monitoring}},
  location     = {{Hannover}},
  number       = {{29}},
  pages        = {{1262--1269}},
  title        = {{{Remaining useful lifetime prediction based on adaptive failure thresholds}}},
  year         = {{2019}},
}