基于神经网络的加速度计静态误差系数标定

Static Error Coefficients' Calibration of Accelerometer Based on Neural Network

利用具有强自学习性、自适应能力及非线性变换特性的神经网络方法 ,构造加速度计静态函数型神经网络模型 ,并用于对加速度计静态误差系数的标定。试验证明 ,利用该方法标定的系数结果具有高精度性 。

The mathematic model of accelerometer with neural network which has the characteristic of self-learning, self-adapting, nonlinear transformation is established and is used to calibrate the static coefficients of the accelerometer. It is proved that the calibrated values are exactly enough to compensate the accelerometer's output.