摘要
为了精准监测降雨量大小、分析天气及气候实时变化,设计一种基于全连接神经网络的红外漫反射光学雨量计,通过雨量计测量降雨频率反演出降雨强度。雨量计由光电模块和MCU模块等组成,光电模块的红外发射端发射固定频率光信号,光信号通过雨滴时产生漫反射现象,红外接收端采集回波信号并进行放大采样,同时人工记录该时刻降雨强度。利用全连接神经网络算法拟合采样信号频率和降雨强度间的映射关系。实验结果拟合度达到0.962,该雨量计灵敏度高、速度快,可广泛应用于气象、交通等领域。
In order to accurately monitor the rainfall and analyze the real-time changes of weather and climate,this paper designs an infrared diffuse reflection optical rain gauge based on fully connected neural network,and measures the rainfall frequency to reflect the rainfall intensity through the rain gauge. The rain gauge is composed of a photoelectric module and an MCU module. The infrared emitting end of the photoelectric module emits a fixed frequency optical signal,and the optical signal generates a diffuse reflection phenomenon when passing the raindrop,and the infrared receiving end collects the echo signal and performs amplification sampling,and simultaneously records the moment manually. Rainfall intensity. The fully connected neural network algorithm is used to fit the mapping relationship between the sampling signal frequency and the rainfall intensity. The fitting result of the experiment reaches0.962. The rain gauge has high sensitivity and high speed and can be widely used in meteorology,transportation and other fields.
作者
郎亚军
行鸿彦
LANG Yajun;XING Hongyan(Collaborative Innovation Center for Meteorological Disaster Prediction and Evaluation,Nanjing University of Information Science and Technology,Nanjing 210044,China;Jiangsu Key Laboratory of Meteorological Detection and Information Processing,Nanjing University of Information Science and Technology,Nanjing 210044,China)
出处
《传感技术学报》
CAS
CSCD
北大核心
2019年第3期476-480,共5页
Chinese Journal of Sensors and Actuators
基金
国家自然科学基金项目(61671248
41605121)
江苏省重点研发计划项目(BE2018719)
江苏省"信息与通信工程"优势学科计划项目
关键词
雨量计
红外
漫反射
神经网络
rain gauge
infrared
diffuse reflection
Neural Networks
