CESSNA Citation X Engine Model Identification using Neural Networks and Extended Great Deluge Algorithms
Journal Title: INCAS BULLETIN - Year 2019, Vol 11, Issue 2
Abstract
Accurate numerical engine model is an enabling factor in aircraft performance evaluation and improvement. In this work, nonlinear engine input-output relationships are learned and predicted by two cascading multilayer feedforward neural networks. Machine learning approaches necessitate a great amount of data to achieve efficiency. To satisfy this operational requirement, 441,000 flight cases are designed for a Cessna Citation X turbofan engine using a Level D Research Aircraft Flight Simulator designed and manufactured by CAE Inc. For each flight case, cruise phase data comprising Mach number, altitude, throttle level angle, low-pressure compressor speed, high-pressure compressor speed, engine net thrust and engine fuel flow are recorded. These data are then organized into subsets for training and validation purposes. Each neural network configuration is obtained by means of the Extended Great Deluge algorithm. The latter is also responsible for coordinating neural network training and learning error computation. Analyses based on computer experiments showed a mean relative prediction error upper bound of 4% is achievable for engine output parameters for all cruise phase flight cases.
Authors and Affiliations
Mahdi ZAAG, Ruxandra Mihaela BOTEZ, Tony WONG
Keywords
Related Articles
- EP ID EP585308
- DOI 10.13111/2066-8201.2019.11.2.16
- Views 69
- Downloads 0
Preliminary Design of a LSA Aircraft Using Wind Tunnel Tests
This paper presents preliminary results concerning the design and aerodynamic calculations of a light sport aircraft (LSA). These were performed for a new lightweight, low cost, low fuel consumption and long-range aircra...
Lamb Waves Tunning On Aluminium Plates for Structure Health Monitoring
The method for defects detection inside the mechanical structures, namely aerospace structures, using the Lamb waves is widespread because of its benefits: it is nondestructive, may reveal the presence and size of defect...
Drag coefficient modelling in the context of small launcher optimisation
The purpose of this paper is to present a fast mathematical model that can be used to quickly asses the drag coefficient for generic launcher configurations. The tool developed based on this mathematical model can be use...
Using genetic algorithms to optimize airfoils in incompressible regime
Aerodynamic optimization is a very actual problem in aircraft design and airfoils are basic two-dimensional shape forming cross sections of wings. Traditionally, the airfoil geometry if defined by a very large number of...
On the synthesis of the pilot optimal control model
The study continues some work of the authors, this time performing a synthesis of optimal control model of the human pilot in systems with input delay, by removing the Padé or Hess approximations characterizing the pilot...