基于PSO-RBF神经网络的光纤陀螺温度补偿及实现

Fiber optic gyroscope temperature compensation and implementation based on PSO-RBF neural network

摘要:

光纤陀螺零偏输出会受温度影响制约其性能,为降低光纤陀螺因温度效应产生的零偏漂移,从而提升精度,基于粒子群算法的RBF神经网络模型(PSO-RBF)建立光纤陀螺的温度补偿模型,并对三轴光纤陀螺在-40~+60℃的变温环境下,进行温度补偿试验。试验结果显示,该模型在变温情况下将光纤陀螺的全过程零偏漂移减少了85%以上,与传统多项式模型以及未经优化的RBF模型比较,其预测稳定性和补偿效果更好

Abstract:

In order to reduce the bias drift of the fiber optic gyroscope due to the temperature effect and improve the accuracy, the temperature compensation model of the fiber optic gyroscope was established based on the RBF neural network model based on particle swarm optimization (PSO-RBF), and the temperature compensation test was carried out on the three-axis fiber gyroscope in the temperature environment of -40~+60°C. The experimental results show that the model reduces the bias drift of the whole process of the fiber optic gyroscope by more than 85% under the condition of variable temperature, and its prediction stability and compensation effect are better than the traditional polynomial model and the unoptimized RBF model.