二维位置敏感器件背景光消除的神经网络方法

Study on Background Light Elimination of Two-dimension Position Sensitive Detectors Based on Neural Networks

位置敏感器件 (position sensitive detectors,简称 PSD)是一种可直接对其光敏面上光斑位置进行检测的光电器件 ,常用于非接触高精度动态位移监测。 PSD器件使用中的一个关键问题是如何克服背景光的干扰 ,以提高检测的精度和可靠性。根据 PSD的原理及特征方程 ,分析了存在背景光时 PSD输出信号是非线性的。提出一种基于神经网络的 PSD背景光非线性修正方法。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。计算机仿真表明 。

The position sensitive detector(PSD)is a photo-electronic sensor which can detect the position of a light spot traveling over its surface, and convert the position of light spot to simple electric current signal. Based upon PSD,many types of precision detection instruments could be constructed. The most important problem to use the PSD is how to oversome the influence of background light action on the PSD,therefore to improve the precision and reliability of the instrument. Following the principle and feature equations of the PSD,it is found that the output signal of PSD is nonlinear when there exists background light.A method for background light compensation of position detector based on neural network is presented.In order to eliminate background light over a full range, the neural network is trained to properly represent the nonlinear mapping between sensor readings and their output accurately at different background light. It is revealed from the computer simulation results that the influence of background light can be eliminated effectively, and a desired linear relationship between the sensor input and the neural network output can be obtained.