基于优化神经网络的隧道照明控制系统研究  

Tunnel Lighting Control System Research Based on PSO-BP

作　　者：陈鸿星[1] 

机构地区：[1]江西师范大学数学与信息科学学院,南昌330022

出　　处：《计算机测量与控制》2013年第12期3247-3249,共3页Computer Measurement &Control

摘　　要：高速公路中的隧道属于特殊路段,内外环境的差别会造成司机的暗适应与明适应的视觉问题,给行车带来安全隐患;提出一种基于优化神经网络的隧道照明控制系统,根据洞外的亮度、车速、车流量等参数构造神经网络控制模型,以灯具的不同功率为网络输出,神经网络的系数与阈值通过粒子群优化进行更新,防止神经网络陷入局部最小,以ARM7微控制器为核心构造硬件模块,实际的系统测试证明,这种方法可以建立准确率较高的隧道照明控制模型,具有很强的实用价值。The highway tunnel belongs to special sections, inside and outside environment difference can cause the driver＇s dark adapta- tion and light adaptation of visual problems, to bring traffic safety hidden trouble. This paper puts forward a neural network based on the op- timization of the tunnel lighting control system, according to the hole, speed, and the brightness of the traffic structure parameters such as neural network control model to lamps and lanterns of different power for the network output, neural network coefficient and threshold value through the particle swarm optimization to update and prevent neural network into local minimum, with ARM7 micro controller as the core structure hardware module, the actual system test proves that this method can build in the diagnosis of tunnel lighting control model, and has great practical value.

关 键 词：隧道照明 神经网络 粒子群优化 ARM7 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]