Diagnostics and Prognostics for Retrofitted Systems: A Comprehensive Approach for Enhanced System Health Assessment

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.