Aircraft Engine Performance Model Identification using Artificial Neural Networks

This paper presents a methodology developed at the Laboratory of Applied Research in Active Controls, Avionics and AeroServoElasticiy (LARCASE) to identify a performance model of the engine powering the CRJ-700 regional jet aircraft from flight data using neural networks. To this end, a qualified virtual research simulator (VRESIM) was used to conduct several categories of flight tests and collect engine data under a wide range of operating conditions. The collected data were then used to create a comprehensive database for the training process. This process was performed using the Bayesian regularization algorithm available in the Matlab Neural Networks Toobox, and a study was carried out to estimate the optimal number of neurons in the network structure. Validation of the methodology was accomplished by comparing the prediction model with a series of flight data collected with the flight simulator for different flight conditions and different flight phases including takeoff, climb, cruise and descent. The results showed that the model was able to predict the engine performance in terms of fan speed, thrust and fuel flow with very good accuracy.