基于RBF神经网络的加速度传感器动态补偿研究

提出一种应用径向基函数(RBF)神经网络进行加速度传感器动态性能补偿方法.介绍动态补偿原理以及算法,并将其与BP神经网络法和系统辨识法进行比较.该方法利用加速度传感器的动态标定数据,采用RBF神经网络搜索和优化补偿模型参数.结果表明,这种补偿模型误差小,比用系统辨识法有良好的鲁棒性、能实现在线软补偿,比用BP神经网络有更快的训练速度.

Study on Dynamic Compensation Method Based on RBF Neural Network for Accelerometer

The dynamic compensation model based on RBF neural network is proposed for accelerometer.The compensation principle and algorithms are introduced.This paper also presents the comparison of the compensation results.In this method,a dynamic compensation model can be set up according to measurement data of dynamic response of accelerometer without knowing its dynamic model.The dynamic compensation model parameters are trained by RBF neural network.The results show that the proposed new dynamic compensation method has high precision,and strong robustness,and on-line compensation compared with system identifying method and fast training speed compared with BP neural network.