环形激光陀螺的神经网络消噪

RLG Noise Elimination by Neural Network

分别应用BP神经网络和DRNN网络对处于静止和运动状态下的环形激光陀螺输出信号中的噪声进行了消除,并应用Allan方差方法对消噪前后的陀螺信号进行了对比分析。结果表明使用神经网络对RLG进行消噪是可行的,而DRNN网络作为一种动态网络,其去噪效果及陀螺初始启动时的信号跟踪能力要优于静态BP网络。使用神经网络去噪的方法对研究环形激光陀螺的误差补偿及快速启动是有实际意义的。

BP networks and DRNN networks are used to eliminate the noise of Ring Laser Gyro in static or in dynamic state. The method of Allan variance is used to analysis the gyro data before and after noise elimination. The results show that neural networks can be used to eliminate the noise of gyro. Dynamic network is prior to static networks in noise elimination and gyro initial signal tracking. The method is meaningful to the research of RLG error compensation and fast start.