International Journal of Unmanned Systems Engineering

ISSN: 2052-112X

 
  Research Article
IJUSEng - 2019, Vol. 7, No. 1, 24-48
http://dx.doi.org/10.14323/ijuseng.2019.3
 
Performing Diagnostics and Prognostics on Simulated Engine Failures Using Neural Networks

Owen Macmann *, Kelly Cohen *, Alireza Behbahani ** and Tim Seitz ***

* University of Cincinnati, Aerospace Engineering & Engineering Mechanics,
Cincinnati, USA.
** The Ohio State University, Mechanical and Aerospace Engineering, Columbus, USA.
*** Air Force Research Laboratory, Aerospace Systems Directorate,
Wright-Patterson AFB, USA.

Abstract: Macmann O, Cohen K, Behbahani A and Seitz T. (2019). Performing diagnostics and prognostics on simulated engine failures using Neural Networks. International Journal of Unmanned Systems Engineering. 7(1): 24-48. Good prognostic health management (PHM) solutions for jet engines remain elusive, owing partially to lack of run-to-failure data sets. A good PHM solution has the potential to improve on unscheduled maintenance by offering an accurate, real-time estimation of the engine’s current health state. Aero-engine simulations allow for generation of simulated data invaluable for data-driven PHM solutions. Simulated data can characteristically represent propagation of faults in an engine over time and present the results of that fault propagation in terms of realistically acquirable sensor data. A method of data set generation for jet engine degradation that incorporates multiple faults is described. The generated data sets can be used for training a combined diagnostic/prognostic solution. This work proposes a neural network-based prognostic system that uses diagnostic evaluations as additional tag data for a prognostic analysis. Self-organized maps are used to classify data. The classifications are added to the data as an additional input for a neural network designed to predict remaining usable life. This method performs unsupervised learning of a remaining usable life model. In testing, these methods were found to produce tools that could successfully perform diagnostic and prognostic analyses on turbine engine failure data. Diagnostic classification was found to achieve error rates of 2.7% and the prognostic step achieved an RMSE of 17.24, recommending these methods to further work. © IJUSEng

Keywords: Diagnostics, Engine health monitoring, Gas turbine engine, Prognostic health management, Remaining usable life.