基于神经网络的传感器非线性误差校正

Nonlinear Errors Correction Of Sensors Based On Neural Network

介绍了用神经网络校正传感器系统非线性误差的原理和方法,提出了一种基于RBF神经网络的传感器非线性校正模型及其算法,并与采用BP神经网络校正非线性误差进行了比较,并给出一个仿真实验,实验结果表明:采用RBF神经网络的传感器非线性校正精度和网络训练速度均大大优于BP神经网络,能满足实用要求。

The principles and methods for correcting the nonlinear errors of the sensor system based on a neural network are introduced. A nonlinear errors correction model and algorithm of sensor based on RBF neural network are brought forward, and be compared with those of the correction method based on BP neural network.. A emulation experiment is given and the results show that the data correcting precision by a RBF neural network is much better than that by a BP neural network, and the speed is also much faster. This approach is valuable for practical application.