强制通风温度传感器辐射误差修正与网站设计

Radiation error correction of forced ventilation temperature sensor and website design

为降低太阳辐射误差,提高测温精准度,设计一款用于地面气象观测的强制通风温度传感器防辐射罩。以太阳辐射强度、风速、下垫面反射率作为影响参数,利用计算流体动力学(CFD)方法计算出不同环境因素下的辐射误差。借助BP神经网络算法拟合仿真结果,得到辐射误差值修正方程。分析训练输出与样本输出,两者的绝对误差仅在[-0.002 5,0.002 5],可见BP神经网络的预测精度达到理想范围。最后设计一个基于B/S结构的查询网站,用户可通过该网站付费下载修正前后的历史温度数据以及历史温度曲线。

In order to reduce the solar radiation error and improve the temperature measurement accuracy,a radiation shield of the forced ventilation temperature sensor for ground meteorological observation is designed in this paper. The solar radiation intensity,wind speed and underlying surface reflectivity are taken as the influencing parameters to calculate the radiation error at different environmental factors by means of the computational fluid dynamics(CFD) method. The BP neural network algorithm is used to fit the simulation results,and then obtain the correction equation of the radiation error value. The training output and the sample output are analyzed,and the absolute error between the two is only [-0.002 5,0.002 5]. It can be seen that the prediction accuracy of the BP neural network reaches the ideal range. A query website based on B/S structure is designed,by which users can pay to the website to download the historical temperature data and historical temperature curves before and after the correction.