Federated learning framework for collaborative remaining useful life prognostics: an aircraft engine case study

TL;DR

This paper develops a federated learning framework for aircraft engine prognostics, enabling multiple airlines to collaboratively train a RUL prediction model without sharing sensitive data, and introduces robust aggregation methods to handle noisy sensor data.

Contribution

It proposes a novel federated learning approach with decentralized validation and robust aggregation techniques for RUL prognostics in aircraft engines, addressing data privacy and noise challenges.

Findings

Federated learning improves RUL prediction accuracy for most airlines.

Robust aggregation methods enhance model resilience to noisy data.

Collaborative models outperform individual airline models in RUL estimation.

Abstract

Complex systems such as aircraft engines are continuously monitored by sensors. In predictive aircraft maintenance, the collected sensor measurements are used to estimate the health condition and the Remaining Useful Life (RUL) of such systems. However, a major challenge when developing prognostics is the limited number of run-to-failure data samples. This challenge could be overcome if multiple airlines would share their run-to-failure data samples such that sufficient learning can be achieved. Due to privacy concerns, however, airlines are reluctant to share their data in a centralized setting. In this paper, a collaborative federated learning framework is therefore developed instead. Here, several airlines cooperate to train a collective RUL prognostic machine learning model, without the need to centrally share their data. For this, a decentralized validation procedure is proposed to validate the prognostics model without sharing any data. Moreover, sensor data is often noisy and of low quality. This paper therefore proposes four novel methods to aggregate the parameters of the global prognostic model. These methods enhance the robustness of the FL framework against noisy data. The proposed framework is illustrated for training a collaborative RUL prognostic model for aircraft engines, using the N-CMAPSS dataset. Here, six airlines are considered, that collaborate in the FL framework to train a collective RUL prognostic model for their aircraft's engines. When comparing the proposed FL framework with the case where each airline independently develops their own prognostic model, the results show that FL leads to more accurate RUL prognostics for five out of the six airlines. Moreover, the novel robust aggregation methods render the FL framework robust to noisy data samples.