A Model-Based Anomaly Detection Approach for Analyzing Streaming Aircraft Engine Measurement Data

This paper presents a model-based anomaly detection architecture designed for analyzing streaming transient aircraft engine measurement data. The technique calculates and monitors residuals between sensed engine outputs and model predicted outputs for anomaly detection purposes. Pivotal to the performance of this technique is the ability to construct a model that accurately reflects the nominal operating performance of the engine. The dynamic model applied in the architecture is a piecewise linear design comprising steady-state trim points and dynamic state space matrices. A simple curve-fitting technique for updating the model trim point information based on steadystate information extracted from available nominal engine measurement data is presented. Results from the application of the model-based approach for processing actual engine test data are shown. These include both nominal fault-free test case data and seeded fault test case data. The results indicate that the updates applied to improve the model trim point information also improve anomaly detection performance. Recommendations for follow-on enhancements to the technique are also presented and discussed.

[1]  Nasa.  An Integrated Architecture for On-Board Aircraft: Engine Performance Trend Monitoring and Gas Path Fault Diagnostics , 2010 .

[2]  Brook Park,et al.  Constructing an Efficient Self-Tuning Aircraft Engine Model for Control and Health Management Applications , 2012, Annual Conference of the PHM Society.

[3]  Graham C. Goodwin,et al.  Fault Detection and Diagnosis in Gas Turbines , 1990 .

[4]  Asok Ray,et al.  Anomaly detection in flight recorder data: A dynamic data-driven approach , 2013, 2013 American Control Conference.

[5]  K. Mathioudakis,et al.  On-Line Aircraft Engine Diagnostic Using a Soft-Constrained Kalman Filter , 2004 .

[6]  George W. Gallops,et al.  Real-time estimation of gas turbine engine damage using a control-based Kalman filter algorithm , 1991 .

[7]  Stephen P. Boyd,et al.  Detecting Aircraft Performance Anomalies from Cruise Flight Data , 2010 .

[8]  Pierre Dewallef,et al.  ON-LINE TRANSIENT ENGINE DIAGNOSTICS IN A KALMAN FILTERING FRAMEWORK , 2005 .

[9]  Dimitry M. Gorinevsky,et al.  Aircraft anomaly detection using performance models trained on fleet data , 2012, 2012 Conference on Intelligent Data Understanding.

[10]  Donald L. Simon,et al.  Implementation of an Integrated On-Board Aircraft Engine Diagnostic Architecture , 2011 .

[11]  Ranjan Ganguli,et al.  Trend Shift Detection in Jet Engine Gas Path Measurements Using Cascaded Recursive Median Filter With Gradient and Laplacian Edge Detector , 2004 .

[12]  Thomas M. Lavelle,et al.  A High-Fidelity Simulation of a Generic Commercial Aircraft Engine and Controller , 2010 .

[13]  Donald L. Simon,et al.  Enhanced Self Tuning On-Board Real-Time Model (eSTORM) for Aircraft Engine Performance Health Tracking , 2008 .