基于小波支撑矢量机的陀螺仪漂移预测  

Gyroscopic drift forecasting based on wavelet support vector machine

作　　者：陈伟[1] 胡昌华[1] 方华元[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》2006年第2期97-100,共4页Electronics Optics & Control

摘　　要：提出了基于小波支撑矢量机的导弹惯性器件故障预报方法。将子波核函数应用于支撑矢量机,得到小波支撑矢量机(WSVM)方法,用于某陀螺仪漂移时间序列预测中,预测精度优于基于传统核函数的支撑矢量机。通过仿真实验证明了算法的有效性和可行性。In this paper, a new method based on wavelet support vector machine（WSVM） is put forward for fault prediction of missile inertial device. The wavelet support machine is obtained with wavelet kernel function, which is then used in time series forecasting for a certain kind of gyro. The accuracy of the prediction resuit is better than that of the Supporter Vector Machine （SVM） based on traditional kernel function. The simulated experiment proves that the algorithm is valid and feasible.

关 键 词：子波核函数 小波支撑矢量机 惯性器件 故障预报 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] TJ76[兵器科学与技术—武器系统与运用工程]