A federated data fusion-based prognostic model for applications with multi-stream incomplete signals

Abstract

Most prognostic methods require a decent amount of data for model training. In reality, however, the amount of historical data owned by a single organization might be small or not large enough to train a reliable prognostic model. To address this challenge, this article proposes a federated prognostic model that allows multiple users to jointly construct a failure time prediction model using their multi-stream, high-dimensional, and incomplete data while keeping each user’s data local and confidential. The prognostic model first employs multivariate functional principal component analysis to fuse the multi-stream degradation signals. Then, the fused features coupled with the times-to-failure are utilized to build a (log)-location-scale regression model for failure prediction. To estimate parameters using distributed datasets and keep the data privacy of all participants, we propose a new federated algorithm for feature extraction. Numerical studies indicate that the performance of the proposed model is the same as that of classic non-federated prognostic models and is better than that of the models constructed by each user itself.

Keywords:

• Federated learning
• federated data fusion
• remaining useful life

Data availability statement

The data that support the findings of this study are openly available in NASA Prognostics Center of Excellence Data Set Repository at https://www.nasa.gov/content/prognostics-center-of-excellence-data-set-repository.

Additional information

Notes on contributors

Madi Arabi

Madi Arabi received her BS degree in Industrial Engineering from Sharif University of Technology Tehran, Iran, in 2019 and an M.S. degree in Operation Research from North Carolina State University, Raleigh, in 2023. Currently, she is working toward her PhD degree in Industrial and System Engineering at the Edward P. Fitts Department of Industrial and Systems Engineering, North Carolina State University, Raleigh. Her research interests are focused on data analytics on high-dimensional signals, including developing optimization and machine learning tools for image-streams and multi-streams data, She is most passionate about physics-informed models for applications in system monitoring, diagnostics, and prognostics. She is a member of IISE and INFORMS.

Xiaolei Fang

Xiaolei Fang earned his PhD degree in Industrial Engineering from the H. Milton Stewart School of Industrial and Systems Engineering at the Georgia Institute of Technology, Atlanta, GA, USA, in 2018. He is currently an Associate Professor in the Edward P. Fitts Department of Industrial and Systems Engineering at North Carolina State University, Raleigh, NC, USA. His research interests are in industrial data analytics, focusing on High-Dimensional and Big Data applications across energy, manufacturing, and service sectors. Specifically, his work addresses analytical, computational, scalability, and privacy challenges in developing statistical and optimization methods for analyzing vast complex data structures for real-time asset management and optimization.