时变模糊神经网络及其在航空发动机排气温度预测中的应用

Time-varying fuzzy neural network and its application in prediction of exhaust gas temperature

为了提高气路参数偏差值预测精度,首先建立了时变模糊推理系统;同时,为了解决模糊推理系统因参数众多而难以实际应用的问题,建立了时变模糊神经网络,并给出了该网络的学习算法。采用Mackey-Glass时间序列对时变模糊神经网络的预测精度进行验证,并将其应用到发动机排气温度偏差值预测中。应用实例表明,时变模糊神经网络能更好地预测排气温度偏差值的变化趋势,为发动机预诊断提供支持。

To obtain a better accuracy, the time-varying fuzzy inference system theory was established, and a time-va- rying fuzzy neural network was created to solve the problem that the application was hard realized by too much pa- rameters of the fuzzy inference system. The learning algorithm of the network structure was also designed. Mackey- Glass chaotic time series prediction was used to prove the network prediction accuracy, and the time-varying fuzzy inference system theory was used to predict the exhaust gas temperature deviation. The result showed that the bet- ter variation trend was predicted by proposed network, which could provide support for pre-diagnosis of aero-en- gine.