Federated Learning on Trusted Data for Distributed PHM Data Analysis

Abstract

Prognostics and health management (PHM) on systems such as vehicles and marine vessels are sometimes held back by complexities relating to data ownership and intellectual property rights. This is particularly true when multiple Original Equipment Manufacturers (OEMs) deliver components or sub-systems to a customer while having an interest in monitoring and maintenance of said component or sub-system. Further, the collection of PHM data from a fleet which may be non-uniform and spread across the globe with varying degrees of connectivity can be challenging from a bandwidth and cybersecurity point of view. Federated learning may address some of these challenges and open up new opportunities for how to approach PHM on a global and nonuniform fleet of components or systems. In this article we present FedChain, an approach for federated learning enabled by blockchain geared towards standardization for increased adoption. We discuss how a Docker based infrastructure for data collection, storage and analysis in combination with a methodology for tamperproofing PHM data can be a powerful substrate for bringing standardization, trust and transparency to federated learning implementations of PHM algorithms. We also demonstrate a basic blockchain enabled federated learning experiment and discuss the feasibility of applying FedChain from the perspectives of model performance, data privacy and security, tamper proofing and verifiability, and robustness.