矿用粉尘检测系统的算法研究
|
摘要
矿井中对粉尘浓度进行大范围内的检测,运用了无线传感器网络,针对网络耗能大、寿命有限及精度低等问题,对经典蚁群算法进行改进,使用其对反向传播(BP)神经网络进行优化,然后应用在无线传感器网络中进行数据融合。由于系统采集到的电压信号波动较大,采用滑动平均滤波算法进行处理,实验结果表明该算法能去除冗余数据,进而减少网络数据通信量,提高系统实时性,降低能耗,延长寿命,提高了系统精确度。
In the mine,the dust concentration is detected in a wide range,and the wireless sensor network is used. The classical ant colony algorithm is improved for the problems of large energy consumption,limited life time and low precision,and the back propagation(BP) nerve is used. The network is optimized and then applied to the wireless sensor network for data fusion. Because the voltage signal collected by the system fluctuates greatly,the moving average filtering algorithm is used for processing. The experimental results show that the algorithm can remove redundant data,thereby reduce the network data traffic,improve real-time performance of the system,reduce energy consumption,extend life and improve the accuracy of the system.
In the mine,the dust concentration is detected in a wide range,and the wireless sensor network is used. The classical ant colony algorithm is improved for the problems of large energy consumption,limited life time and low precision,and the back propagation(BP) nerve is used. The network is optimized and then applied to the wireless sensor network for data fusion. Because the voltage signal collected by the system fluctuates greatly,the moving average filtering algorithm is used for processing. The experimental results show that the algorithm can remove redundant data,thereby reduce the network data traffic,improve real-time performance of the system,reduce energy consumption,extend life and improve the accuracy of the system.
引文
[1]葛艳香,张全柱,邓永红.煤矿多功能智能传感器技术研究[J].华北科技学院学报,2016,13(6):35-39.
[2]李兆祥.无线传感器网络数据融合的算法研究[D].武汉:武汉理工大学,2011.
[3]张艳蕊.基于改进蚁群算法的BP神经网络优化的研究与应用[D].沈阳:东北大学,2013.
[4]王文华,徐光年,徐绍军,等.基于改进的蚁群算法的配电网虚拟测量技术研究[J].计算机与数字工程,2018,46(9):1708-1712.
[5]赵亚光.基于蚁群算法和BP神经网络的WSN数据融合算法研究[D].昆明:云南大学,2013.
[6]余修武,刘琴,李向阳,等.基于改进蚁群的BP神经网络WSN数据融合算法[J].北京邮电大学学报,2018,41(4):91-96.
[7]沙娓娓,刘增力.基于改进蚁群算法的无线传感器网络的路由优化[J].软件,2018,39(1):01-04.
[8] Li Shi,Liu Mengyao,Xia Li. WSN Data fusion approach based on improved BP algorithm and clustering protocol[C]//Control and Decision Conference. Qingdao:IEEE,2015:1450-1454.
[9]张组成.电容式触摸屏噪声特性分析与实时滤波算法研究[D].北京:北京交通大学,2018.
[2]李兆祥.无线传感器网络数据融合的算法研究[D].武汉:武汉理工大学,2011.
[3]张艳蕊.基于改进蚁群算法的BP神经网络优化的研究与应用[D].沈阳:东北大学,2013.
[4]王文华,徐光年,徐绍军,等.基于改进的蚁群算法的配电网虚拟测量技术研究[J].计算机与数字工程,2018,46(9):1708-1712.
[5]赵亚光.基于蚁群算法和BP神经网络的WSN数据融合算法研究[D].昆明:云南大学,2013.
[6]余修武,刘琴,李向阳,等.基于改进蚁群的BP神经网络WSN数据融合算法[J].北京邮电大学学报,2018,41(4):91-96.
[7]沙娓娓,刘增力.基于改进蚁群算法的无线传感器网络的路由优化[J].软件,2018,39(1):01-04.
[8] Li Shi,Liu Mengyao,Xia Li. WSN Data fusion approach based on improved BP algorithm and clustering protocol[C]//Control and Decision Conference. Qingdao:IEEE,2015:1450-1454.
[9]张组成.电容式触摸屏噪声特性分析与实时滤波算法研究[D].北京:北京交通大学,2018.