Anomaly Detection Based on Indicators Aggregation

TL;DR

This paper presents a methodology for anomaly detection that combines expert-designed binary indicators with feature selection and Naive Bayes classification to identify and interpret anomalies in engine monitoring data.

Contribution

It introduces a general approach leveraging expert knowledge to generate and select interpretable binary indicators for anomaly classification in engine health monitoring.

Findings

Effective classification of simulated engine anomalies

Indicators selected improve interpretability and detection accuracy

Method applicable to real-world engine monitoring scenarios

Abstract

Automatic anomaly detection is a major issue in various areas. Beyond mere detection, the identification of the source of the problem that produced the anomaly is also essential. This is particularly the case in aircraft engine health monitoring where detecting early signs of failure (anomalies) and helping the engine owner to implement efficiently the adapted maintenance operations (fixing the source of the anomaly) are of crucial importance to reduce the costs attached to unscheduled maintenance. This paper introduces a general methodology that aims at classifying monitoring signals into normal ones and several classes of abnormal ones. The main idea is to leverage expert knowledge by generating a very large number of binary indicators. Each indicator corresponds to a fully parametrized anomaly detector built from parametric anomaly scores designed by experts. A feature selection method is used to keep only the most discriminant indicators which are used at inputs of a Naive Bayes classifier. This give an interpretable classifier based on interpretable anomaly detectors whose parameters have been optimized indirectly by the selection process. The proposed methodology is evaluated on simulated data designed to reproduce some of the anomaly types observed in real world engines.