Airborne Electro-Mechanical Actuator Test Stand for Development of Prognostic Health Management Systems

With the advent of the next generation of aerospace systems equipped with fly-by-wire controls, electromechanical actuators (EMA) are quickly becoming components critical to safety of aerospace vehicles. Being relatively new to the field, however, EMA lack the knowledge base compared to what is accumulated for the more traditional actuator types, especially when it comes to fault detection and prognosis. Scarcity of health monitoring data from fielded systems and prohibitive costs of carrying out real flight tests create the need to build high-fidelity system models and design affordable yet realistic experimental setups. The objective of this work is to build an EMA test stand that, unlike current laboratory stands typically weighing in excess of one metric ton, is portable enough to be easily placed aboard a wide variety of aircraft. This stand, named the FLEA (for Fl yable Electromechanical Actuator test stand), allows testing EMA fault detection and prognosis technologies in flight environment, thus substantially increasing their technology readiness level – all without the expense of dedicated flights, as the stand is designed to function as a non-intrusive secondary payload. No aircraft modifications are required and data can be collected during any available flight opportunity: pilot currency flights, ferry flights, or flights dedicated to other experiments. The stand is currently equipped with a prototype version of NASA Ames developed prognostic health management system with models aimed at detecting and tracking several fault types. At this point the team has completed test flights of the stand on US Air Force C-17 aircraft and US Army UH-60 helicopters and more experiments, both laboratory and airborne, are planned for the coming months.

[1]  S. C. Jensen,et al.  Flight test experience with an electromechanical actuator on the F-18 Systems Research Aircraft , 2000, 19th DASC. 19th Digital Avionics Systems Conference. Proceedings (Cat. No.00CH37126).

[2]  R. Rosenberg,et al.  System Dynamics: Modeling and Simulation of Mechatronic Systems , 2006 .

[3]  Carl S. Byington,et al.  Experimental Data Collection and Modeling for Nominal and Fault Conditions on Electro-Mechanical Actuators , 2009 .

[4]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[5]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[6]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[7]  Carl S. Byington,et al.  Experimental and analytical development of health management for Electro-Mechanical Actuators , 2009, 2009 IEEE Aerospace conference.

[8]  Timo Sorsa,et al.  APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN PROCESS FAULT DIAGNOSIS , 1992 .

[9]  Pieter J. Mosterman,et al.  Diagnosis of continuous valued systems in transient operating regions , 1999, IEEE Trans. Syst. Man Cybern. Part A.

[10]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[11]  Heikki N. Koivo,et al.  Application of artificial neural networks in process fault diagnosis , 1991, Autom..

[12]  Abhinav Saxena,et al.  A diagnostic approach for electro-mechanical actuators in aerospace systems , 2009, 2009 IEEE Aerospace conference.

[13]  K. Mardia,et al.  Maximum likelihood estimation of models for residual covariance in spatial regression , 1984 .

[14]  E. Balaban,et al.  Modeling, Detection, and Disambiguation of Sensor Faults for Aerospace Applications , 2009, IEEE Sensors Journal.

[15]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .