Aero-engines Anomaly Detection using an Unsupervised Fisher Autoencoder

TL;DR

This paper introduces an unsupervised Fisher autoencoder leveraging Fisher divergence for robust aero-engine anomaly detection, improving accuracy and reducing false alarms in noisy, multivariate sensor data.

Contribution

It proposes a novel Fisher autoencoder with Gaussian mixture prior for enhanced anomaly detection in aero-engines, addressing model uncertainty and data noise.

Findings

Improved anomaly detection accuracy on CMAPSS dataset

Reduced false alarms compared to existing methods

Effective in noisy and unbalanced data scenarios

Abstract

Reliable aero-engine anomaly detection is crucial for ensuring aircraft safety and operational efficiency. This research explores the application of the Fisher autoencoder as an unsupervised deep learning method for detecting anomalies in aero-engine multivariate sensor data, using a Gaussian mixture as the prior distribution of the latent space. The proposed method aims to minimize the Fisher divergence between the true and the modeled data distribution in order to train an autoencoder that can capture the normal patterns of aero-engine behavior. The Fisher divergence is robust to model uncertainty, meaning it can handle noisy or incomplete data. The Fisher autoencoder also has well-defined latent space regions, which makes it more generalizable and regularized for various types of aero-engines as well as facilitates diagnostic purposes. The proposed approach improves the accuracy of anomaly detection and reduces false alarms. Simulations using the CMAPSS dataset demonstrate the model's efficacy in achieving timely anomaly detection, even in the case of an unbalanced dataset.