GA-WNN在飞机引气系统故障预测的研究

Research of Wavelet Neural Network Based on Genetic Algorithm in Aircraft Bleed System Fault Prediction

飞机的引气系统的正常运行对飞机的安全起着至关重要的作用,而引气系统的关键参数变化表现为非线性特性,提高了引气系统故障预测的难度.首先建立故障监控模型,然后根据故障预测的非线性特性,提出一种基于遗传算法的小波神经网络故障预测模型.模型结合遗传算法全局优化搜索能力和小波神经网络良好局部特性,避免BP神经网络缺陷.最后通过MATLAB仿真,验证故障预测模型的准确性.上述模型对飞机引气系统故障预测提高预测精度具有重要意义.

The normal operation of aircraft bleed system plays an important role in the safety of the aircraft. And the key parameters of bleed system are nonlinear characteristics. Firstly, this paper built a fault monitoring model, and then built the fault prediction model of wavelet neural network(WNN) based on Genetic Algorithm(GA) for the nonlinear characteristics of the bleed system fault prediction. The model combines the global optimization searching performance of GA and the partial character of WNN to avoid the defects of BP WNN. Finally a simulation model was set up to verify the accuracy of fault prediction model with MATLAB. The model is vital significance for improving the accuracy for the bleed system fault prediction of civil aviation aircraft.