PCA Methods and Evidence Based Filtering for Robust Aircraft Sensor Fault Diagnosis

TL;DR

This paper applies PCA techniques and evidence-based filtering to improve fault diagnosis and estimation for aircraft sensors, demonstrating enhanced false alarm reduction and diagnostic accuracy in experimental tests.

Contribution

It introduces an evidence-based inference mechanism combined with PCA methods for improved fault diagnosis and estimation in aircraft sensors.

Findings

Evidence Based Filtering reduces false alarms effectively.

PCA-based methods enable accurate fault isolation and estimation.

Experimental validation on aircraft sensor data confirms improved performance.

Abstract

In this paper PCA and D-PCA techniques are applied for the design of a Data Driven diagnostic Fault Isolation (FI) and Fault Estimation (FE) scheme for 18 primary sensors of a semi-autonomous aircraft. Specifically, Contributions-based, and Reconstruction-based Contributions approaches have been considered. To improve FI performance an inference mechanism derived from evidence-based decision making theory has been proposed. A detailed FI and FE study is presented for the True Airspeed sensor based on experimental data. Evidence Based Filtering (EBF) showed to be very effective particularly in reducing false alarms.