.png){kind=icon}
.png){kind=icon}
Return
Health Prognostics in Multi-Sensor Systems Based on Multivariate Functional Data Analysis
.png){kind=icon}
PRE
AI
DOI：10.1002/asmb.70093.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent developments in big data analysis, machine learning, Industry 4.0, and IoT applications have enabled the monitoring and processing of multi-sensor data collected from systems, allowing for the prediction of the "Remaining Useful Life" (RUL) of system components. Particularly in the aviation industry, Prognostic Health Management (PHM) has become one of the most important practices to ensure reliability and safety. Beyond RUL prediction accuracy, modern PHM methodologies must also offer interpretability for system degradation behaviors, practical implementability, and domain adaptability. This paper introduces FLARE (Functional Lifecycle Analysis for RUL Estimation), a Functional Data Analysis (FDA) framework designed to process multi-sensor data from complex systems, providing both RUL predictions and interpretable insights into system degradation life cycles. FLARE is applied to various simulation datasets shared by National Aeronautics and Space Administration (NASA), and the degradation trajectories of the aircraft engine sensors are adaptively modeled with Multivariate Functional Principal Component Analysis (MFPCA). While the results indicate that the proposed method predicts RUL competitively compared to other methods in the literature, it also demonstrates how multivariate Functional Data Analysis is useful for interpretability in prognostic studies within multi-sensor environments.
Keywords:
Condition Monitoring
Functional Data Analysis (FDA)
Multivariate Functional Principal Component Analysis (MFPCA)
Prognostic Health Management (PHM)
Remaining Useful Life (RUL)
Journal
A
IF:
1.5
Papers:
66
Citations:
1.3K