一种新型灰色预测模型在陀螺漂移预测中的应用研究  

Application of a New Grey Prediction Algorithm to the Gyroscope Drifting Tendency

作　　者：卢凯[1] 胡昌华[1] 

机构地区：[1]第二炮兵工程学院302教研室,陕西西安710025

出　　处：《系统仿真技术》2009年第3期176-181,共6页System Simulation Technology

摘　　要：针对某型导弹的陀螺漂移趋势预测问题,提出1种基于经验模态分解(EMD)的新型灰色支持向量回归预测模型。该模型通过运用经验模态分解算法将陀螺漂移数据趋势项和随机项进行分离,然后分别运用灰色GM(1,1)和支持向量回归算法对这2种数据进行预测,最后将预测结果进行重构得出最终的预测值。给出了这种算法的具体步骤并将其应用到某型导弹陀螺漂移的预测中,仿真试验结果表明这种预测模型的有效性和可行性。A new GM（ 1,1 ）-support vector regression（SVR） time series prediction model based on the Empirical Mode Decomposition （EMD） is proposed for the prediction of the gyroscope drifting tendency. The model separates the trend part and random part of the gyroscope drifting data by using the EMD algorithm. Then the trend part is predicted by the GM （ 1,1 ） model, the random part is predicted by the SVR forecasting algorithm. The final prediction result is the superimposition of the respective prediction by using the EMD reconstruction algorithm. The algorithm is presented in detail and used to predict the missile gyroscope tendency. Simulation results demonstrate that the proposed method is feasible and effective.

关 键 词：灰色预测 经验模态分解 支持向量回归 陀螺漂移 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]