基于STM32架构与朴素贝叶斯预测模型的微型气象站系统设计  

Design of Micro Weather Station System Based on STM32 and Naive Bayesian Prediction Model

作　　者：程玉怀 黄星明 颜轶涵 王一 CHENG Yuhuai;HUANG Xingming;YAN Yihan;WANG Yi(College of Big Data and Information Engineering,Guizhou University,Guizhou 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵州550025

出　　处：《电子技术（上海）》2023年第4期19-21,共3页Electronic Technology

基　　金：贵州省教育厅高等学校青年科技人才成长计划(黔教合KY[2022]141号);贵州大学“SRT计划”项目(贵大SRT字(2021)039号)。

摘　　要：阐述一种具备数据实时采集、短时气象信息预测功能,支持云端协作计算的微型气象站系统的设计。该系统在硬件上采用STM32微控制器作为主控单元,驱动气象传感器采集数据,并通过4G移动通信技术将气象数据上传至云端服务器;在系统算法设计上,利用了朴素贝叶斯预测模型作基础气象预报。同时,基于预测区域的气象历史资料,建立BP神经网络预测模型对基础的预报结果作融合、修正。系统预测结果与实测值误差降低,预报精度相对提高65.14%。This paper expounds the design of a micro weather station system with real-time data collection,short-term weather information prediction and cloud collaborative computing.The system uses STM32 microcontroller as the main control unit to drive the weather sensor to collect data and upload the weather data to the cloud server through 4G mobile communication technology;in the system algorithm design,a plain Bayesian prediction model is used for basic weather forecasting.In the meantime,based on the meteorological historical data of the prediction area,a BP neural network prediction model is established to integrate and modify the basic prediction results.The system prediction results and the actual measured value error is reduced,and the forecast accuracy is relatively improved by 65.14%.

关 键 词：朴素贝叶斯 BP神经网络 短时天气预报 STM32 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP368.1[自动化与计算机技术—控制科学与工程] TP212