摘要
根据光电位置敏感器件的原理和光点位置方程分析了PSD的非线性成因,并根据PSD的非线性特点,提出用神经网络的共轭梯度算法对PSD的非线性进行补偿·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,通过神经网络建立PSD实际输出与其理想值之间的非线性映射关系,实现光电位置敏感器件非线性补偿·计算机仿真表明,该方法不仅能有效地消除非线性的影响,而且在神经网络的输出端得到期望的线性输出·从而使PSD的B区获得了与A区近似的线性度,故在不增加成本,不改变测量设备复杂度的情况下,扩大了测量范围,提高了B区的测量准确度及数据的置信度·
?The causes of non1inearity of Position Sensitive Detector were analyzed. A conjugate gradient optimum algorithm for neural network is provided to correct the nonlinearity of PSD after precalibration. In order to supply the nonlinear compensation over a full range, the neural network was properly trained to represent the nonlinear mapping between sensor reading and their represent output accurately. Simulation result shows 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.The correction leads to prominent improvement of linearity of Barea, and the usable area of PSD is thus extended. The reliability of data is also improved without increasing the complexity of hardware by the method.
出处
《东北大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2003年第5期507-509,共3页
Journal of Northeastern University(Natural Science)
基金
国家自然科学基金资助项目(50174020)
关键词
光电位置敏感器件
补偿
非线性修正
神经网络
共轭梯度法
PSD
compensation
correction of non-linearity
neural network
conjugate gradient optimum algorithm
