中国光学, 2018, 11 (6): 1024, 网络出版: 2019-01-10
基于小波神经网络的光纤陀螺误差补偿方法
A fiber optic gyro error compensation method based on wavelet neural network
光纤陀螺 小波神经网络 小波分析 误差补偿 趋势项提取 fiber optic gyro wavelet neural network wavelet analysis error compensation trend term extraction
摘要
为了提高光纤陀螺的测量精度, 提出了一种基于小波神经网络的误差补偿方法。首先使用小波分析中的Mallat分解算法提取出陀螺信号中的主趋势项, 对其误差余项进行重构。然后将重构信号作为小波神经网络的目标输出, 将原始陀螺信号作为训练样本。为了提高小波神经网络的训练速度同时防止其陷入局部极小值, 采用增加动量因子和自适应调整学习速率的方法来改进训练方法。训练后建立的神经网络模型对光纤陀螺误差具有良好的估计能力。结果表明, 经过小波神经网络方法补偿后, 光纤陀螺的输出精度达到了0019 4°/s, 光纤陀螺的测量性能得到了提高。
Abstract
In order to improve the measurement accuracy of fiber optic gyroscope, an error compensation method based on wavelet neural network(WNN) is proposed. Firstly, the main trend term in the gyro signal is extracted by the Mallat decomposition algorithm in wavelet analysis, and the error residuals are reconstructed. The reconstructed signal is then used as the target output of the wavelet neural network, and the original gyro signal is used as the training input. In order to improve the training speed of the WNN and prevent it from falling into local minimum values, the method of increasing the momentum factor and adaptively adjusting the learning rate is used. The neural network model established after training has a good ability to estimate the fiber optic gyro error. The final result shows that after the compensation by the WNN method, the output precision of the fiber optic gyroscope reaches 00194°/s, which improves the measurement performance of the fiber optic gyroscope.
骞微著, 杨立保. 基于小波神经网络的光纤陀螺误差补偿方法[J]. 中国光学, 2018, 11(6): 1024. QIAN Wei-zhu, YANG Li-bao. A fiber optic gyro error compensation method based on wavelet neural network[J]. Chinese Optics, 2018, 11(6): 1024.