论文部分内容阅读
光纤pH传感器的一个重要测试项目是pH～mV工作曲线.溶液pH值与传感器输出mV数之间的关系是非线性的,其曲线呈S形(或反S形),尚无法建立物理模型或者线性函数插值模型.为了克服上述困难,本文根据数学上曲线拟合的原理,利用神经的高度的非线性表达能力,建立了传感器工作曲线的神经网络插值模型.
An important test item of optical fiber pH sensor is the working curve of pH ~ mV.The relationship between the pH value of the solution and the number of mV of the sensor is nonlinear and the curve is S-shaped (or inverse S-shaped), the physical model can not be established yet or the linear Function interpolation model.In order to overcome the above difficulties, this paper established a neural network interpolation model of sensor working curve based on the principle of mathematical curve fitting and using the highly nonlinear expression ability of nerve.