Prediction of Aero-Engine Wear Based on Genetic Algorithms and BP Neural Network

Abstract

A prediction model based on the genetic algorithms and back propagation (BP) network by using genetic algorithm to train back propagation neural network and optimize network structure was presented. The aero-engine wear was estimated by the optimized network. The result of this approach was poly-regression model, which was compared with that of the simple BP network as well as Poly-regression model. The results indicate that BP neural network based on the genetic algorithms is superior to the simple BP network and the poly-regression model.