基于ARIMA和RBF网络组合预测的惯性器件故障预报  

Fault prediction of inertial component based on combined forecasting of ARIMA and RBF neural network

作　　者：吕瑛洁[1] 胡昌华[1] 李国华[1] 张伟[1] 

机构地区：[1]第二炮兵工程学院,陕西西安710025

出　　处：《电光与控制》2005年第4期32-34,共3页Electronics Optics & Control

基　　金：国家自然科学基金重点课题(69931040);国防预研课题(103010201)资助。

摘　　要：提出了一种基于ARIMA和RBF网络进行组合预测的方法,该方法综合运用ARIMA良好的线性拟合能力和RBF网络强大的非线性映射功能,将两种预测模型有机地组合在一起,综合各自优点,以期有效改善模型的拟合能力,获得最优预测效果。论文将该方法应用于某飞行器惯性器件的故障预报当中并进行了仿真实验。结果表明,这种方法相对于单项模型的预测具有更高的精度,对于复杂时间序列的分析和预测有很好的应用价值,在故障预报中具有广泛的应用前景。A new method of combined predicting based on ARIMA forecast and RBF network is put forward in this paper. The ARIMA forecasting model has perfect linear fitting capability, and artificial neural network possesses the characteristics of strong nonlinear fitting. The two methods are combined together in order to integrate their own advantages, improve the fitting capability of the model and obtain the optimum predicting effect. The prediction performances of the method are tested by simulated experiment for a certain type of inertial component. The result shows that the combined model has better accuracy and it is an effective method for the fault prediction of inertialcomponent.

关 键 词：组合预测 故障预报 ARIMA RBF神经网络 惯性器件 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TP393[自动化与计算机技术—计算机应用技术]