摘要
文中提出基于回归神经网络的城市夜景照明联动感知控制方法,满足城市夜景照明用电需求的同时节省能耗。建立Elman神经网络模型,以气象时间、环境亮度、天气状态以及人车流量等动态因素作为模型选取输入数据,使用差值法排除异常数据并经归一化处理后,输出控制值,完成城市夜景照明联动感知控制。结果表明,文中方法控制下的城市照明系统可根据环境亮度进行自适应调整;无人车通过时照度降低,但不熄灭,减少电流频繁通断对照明材料的伤害;满足城市夜景照明用电需求的同时可最大程度节省能耗。
This paper proposes a linkage perceptual control method of urban night scene lighting based on Recurrent Neural Network(RNN)to meet the power demand of urban night scene lighting and save energy consumption at the same time.The Elman neural network model is established,and the dynamic factors such as meteorological time,environmental brightness,weather state and passenger and vehicle flow are taken as the model to select input data.The difference method is used to eliminate the abnormal data,and the control value is output after normalization,so as to complete the linkage dynamic control of urban night scene lighting.The results show that the urban lighting system controlled by this method can adjust adaptively according to the ambient brightness.When the unmanned vehicle passes through,the illumination decreases but does not go out,so as to reduce the damage to lighting materials caused by frequent current on and off,which can meet the power demand of urban night lighting and save energy consumption to the greatest extent.
作者
赵志海
ZHAO Zhi-hai(Zhuhai Hengqin New Area Emergency Management Bureau,Zhuhai 519031,Guangdong Province,China)
出处
《信息技术》
2023年第3期51-56,共6页
Information Technology
基金
广东省物业城市APP(四期)开发项目(P-20190928-004077)。
关键词
回归神经网络
夜景照明
联动感知控制
环境亮度
人车流量
Regression Neural Network
night lighting
linkage perception control
ambient brightness
passenger and vehicle flow