基于子块集成神经网络法的PSD背景光补偿

提出一种基于神经网络高精度线性化子块网络集成插值实现光电位置敏感器件（PSD）背景光非线性补偿方法。利用神经网络具有逼近任意非线性函数的特点，通过训练，使神经网络建立在不同背景光下PSD输出与其标准值之间的非线性映射关系，实现PSD全程跟踪补偿。实验结果表明，该方法能有效地消除背景光的影响，在神经网络的输出端得到期望的线性输出。

Background Light Compensation of PSD on Sub-block Integration Neural Network Method

A method for nonlinear compensation of background light voltage of position sensitive detector(PSD) based on neural network high accuracy linearization sub-block network integration interpolation is presented.In order to background light compensation over a full range,the neural network is trained to properly represent the nonlinear mapping between sensor readings and their outputs accurately at different background light.The experimental results show that the influence of background light fluctuation can be eliminated effectively,and a desired linear relationship between the sensor input and the neural network output can be obtained.