Elman型神经网络在液体火箭发动机故障预测中的应用

提出一种将Elman神经网络应用于液体火箭发动机故障预测的模型,并进行了多参数多步预测。仿真计算结果表明,较传统的静态BP网络预测模型,该模型结构简单,动态特性好,对于液体火箭发动机重要参数的预测效果较好,收敛速度快且精度高,具有较好的非线性时序预测能力,说明其在液体火箭发动机的故障预测中应用的可行性。

Application of Elman Neural Network on Liquid Rocket Engine Fault Prediction

A fault prediction model of liquid rocket engine(LRE) is provided by applying Elman neural network and multi-parameters with multi-steps prediction has been done in this paper.It is proved by simulation results that this model has a good performance in non-linear time series prediction for some important parameters of LRE.Compared to traditional static model,it is more efficient and accurate.Also it has simple configuration and wonderful dynamic characteristic.The result shows Elman neural network is feasib...