基于神经网络算法的一维PSD非线性修正

Non-linear correction of one-dimension PSD on neural network optimizations

分析了PSD(positionsensitivedetctor)的非线性成因,并根据PSD的非线性特点,提出一种基于神经网络的PSD非线性补偿方法,利用神经网络具有逼近任意非线性函数的特点,通过训练使神经网络建立在PSD输出与其理想值之间的非线性映射关系,实现PSD非线性补偿.从而使PSD的非线性区获得了与线性区近似的线性度.实验结果表明,该方法能有效地消除非线性的影响,在神经网络的输出端得到期望的线性输出.

The causes of non-1inearity of PSD are analyzed in this paper. A method for non-linear compensation of PSD based on artificial neural network is presented. In order to non-linear compensation over a full range, the neural network is trained to properly represent the nonlinear mapping between sensor reading and their represent output accuratelyIt is revealed from the experiment result that not only the influence of non-linear fluctuation can be eliminated effectively, but also a desired linear relationship between the sensor input and the neural network output can be obtained.