【摘要】 针对室内环境舒适度及安全性监测需求,设计并实现了一种基于多传感器的室内环境监测系统。在分析并比较反向传播(BP)神经网络、径向基函数(RBF)神经网络、支持向量机(SVM)、遗传算法优化的BP神经网络在此应用中的性能与误差的基础上,在Android端实现了ISO国际标准的PMV热舒适度算法及有害气体浓度预警算法,从而实现室内空气质量的各参数的实时监测,并能更好地预测火灾等高危险灾害。此系统可全面反映室内的空气质量,让居民能更有针对性地改善自己的居住环境。更多还原

【Abstract】 To meet the requirements of indoor environmental comfort level and safety monitoring,design and implement an multi-sensor system for indoor environment monitoring. On the basis of analyzing and comparing performance and error of the back propagation( BP) neural network,the RBF neural network,the SVM and the genetic algorithm optimized BP neural network in this application,the algorithms for ISO PMV thermal comfort level and harmful gas early warning are implemented on Android devices,thus the real-time monitoring of the indoor air quality parameters can be achieved,and high risk disasters such as fire can be predicted better. The proposed system can deliver comprehensively information of the indoor air quality to the residents,thus they can improve their living environment accordingly.更多还原