摘要
光电位置敏感器件(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,基于PSD可以构成多种非接触的高精度动态位移监测仪器。在PSD器件使用中的一个关键问题是如何克服温度的影响,以提高检测的精度和可靠性。分析了光电位置敏感器件(PSD)的温度特性,表明测量范围较宽时,传感器的输出易受环境温度的影响,并且成非线性。提出一种基于神经网络共轭梯度算法的光电位置敏感器件温度补偿方法.利用神经网络共轭梯度算法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环境温度下传感器输出与其实际感受的电压值之间的非线性映射关系,实现光电位置敏感器件温度补偿。实验结果表明,该方法不仅能有效地消除温度的影响,而且能在神经网络的输出端得到期望的线性输出。
The position sensitive detector (PSD) is 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 and contactless motion detection instruments could be constructed. The most important problem to use the PSD is how to overcome the influence of tempera: ture action on the PSD, therefore to improve the precision and reliable of the instrument. The output characteristic of PSD pressure senser is analyzed. It is found that the response of senser is non - linear and the senser suffers from the influence of over a wide measuring range. A method for temperature compensation of PSD senser voltage based on artificial conjugate gradient optimum algorithm for nerve network is presented in this paper. In order to realize temperature compensation over a full range, the neural network is trained to properly represent the nonlinear mapping between senser reading and their represent output accurately at different temperature It is revealed from the experiment result that not only the influence of temperature fluctuation can be eliminated effectively, but also a desired linear relationship between the senser input and the neural network output can be obtained.
出处
《长春理工大学学报(自然科学版)》
2007年第1期5-8,4,共5页
Journal of Changchun University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金项目(50174020)
黑龙江省教育厅基金项目(10551091)
关键词
光电位置敏感器件
温度
非线性
神经网络
共轭梯度算法
补偿
PSD senser
temperature
non- l inearity
neural network
conjugate gradientoptimum algorithm
compensation