Intelligent Diagnostics for Aircraft Hydraulic Equipment

In aviation industry, unscheduled maintenance costs may vary in a large range depending on several factors, such as specific aircraft system, operational environment and aircraft usage and maintenance policy. These costs will become more noteworthy in the next decade, due to the positive growing of worldwide fleet and the introduction of more technologically advanced aircraft. The new implemented technologies will bring new challenges in the Maintenance, Repair and Overhaul (MRO) companies, both because of the rising number of new technologies and high volume of well-established devices, such as Electro-Hydraulic Servo Actuators for primary flight control. Failures in aircraft hydraulic systems deeply influence the overall failure rate and so the relative maintenance costs. For this reason, overhaul procedures for these components still represents a profitable market share for all MRO stakeholders. Innovative solutions able to facilitate maintenance operations can lead to large cost savings. This paper proposes new methodologies and features of the Intelligent Diagnostic system which is being developed in partnership with Lufthansa Technik (LHT). The implementation of this innovative procedure is built on a set of failure detection algorithms, based on Machine Learning techniques. This development requires first to bring together the results from different parallel research activities: Identification of critical components from historical data; Designing and testing automatic and adaptable procedure for first faults detection; High-fidelity mathematical modeling of considered test units, for deeper physics analysis of possible failures; Implementation of Machine Learning reasoner, able to process experimental and simulated data.

[1]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[2]  A. Bernieri,et al.  A neural network approach for identification and fault diagnosis on dynamic systems , 1993 .

[3]  George Vachtsevanos,et al.  Prognostics and Health Management of an Electro-Hydraulic Servo Actuator , 2015 .

[4]  F. Lampl,et al.  Hydraulic Control Systems for Longwall Shield Supports in Coal Mines , 1980 .

[5]  Bin Yao,et al.  Fault Detection of an Electro-Hydraulic Cylinder Using Adaptive Robust Observers , 2004 .

[6]  Leonard J. Martini,et al.  Practical Seal Design , 1984 .

[7]  C.S. Byington,et al.  Data-driven neural network methodology to remaining life predictions for aircraft actuator components , 2004, 2004 IEEE Aerospace Conference Proceedings (IEEE Cat. No.04TH8720).

[8]  Nariman Sepehri,et al.  Diagnosis of process valve actuator faults using a multilayer neural network , 2003 .

[9]  E Urata,et al.  Influence of unequal air-gap thickness in servo valve torque motors , 2007 .

[10]  Duc Truong Pham,et al.  Fault classification of fluid power systems using a dynamics feature extraction technique and neural networks , 1998 .

[11]  Phillip Burrell,et al.  Case-Based Reasoning System and Artificial Neural Networks: A Review , 2001, Neural Computing & Applications.

[12]  Umberto Soverini,et al.  Identification of ARX and ARARX Models in the Presence of Input and Output Noises , 2010, Eur. J. Control.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Clifford R. Burrows,et al.  Fault diagnosis of a hydraulic actuator circuit using neural networks—an output vector space classification approach , 1997 .

[15]  Per-Olof Gutman,et al.  New models for backlash and gear play , 1997 .

[16]  George Vachtsevanos,et al.  Windings Fault Detection and Prognosis in Electro-Mechanical Flight Control Actuators Operating in Active-Active Configuration , 2020 .

[17]  M. Sorli,et al.  High Fidelity Model of a Ball Screw Drive for a Flight Control Servoactuator , 2017 .

[18]  Sriram Narasimhan,et al.  Combining Model-Based and Feature-Driven Diagnosis Approaches - A Case Study on Electromechanical Actuators , 2010 .

[19]  Andrea Mornacchi.  Design and development of prognostic and health management system for fly-by-wire primary flight control , 2016 .

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.