基于IA-BP神经网络的UWB室内定位系统
|
摘要
复杂的室内环境给定位系统带来非视距误差和多径干扰,消除或降低误差成为超宽带(UWB)室内定位研究的热点。提出一种基于IA-BP神经网络的UWB室内定位方法,将BP神经网络训练的误差值作为免疫算法计算亲和度的抗原,通过免疫算法寻得BP神经网络的最优权值和阈值,避免BP神经网络收敛速度较慢和容易陷入局部最优值的问题,达到定位误差较小的目的。仿真实验结果表明,IA-BP神经网络训练100个样本输出的最大归一化误差不超过0.02,以3个锚点构成的定位场景中,待定位节点的仿真输出轨迹与实际运动轨迹基本吻合。
The complex indoor environment brings non-visual range error and multipath interference to the localization system, How to eliminate or reduce error becomes a hot spot in research to UWB indoor localization. A UWB indoor localization method based on IA-BP neural network is proposed, Which is that the error of training by BP neural network is as the antigen of calculating affinity to immune algorithm,the optimal weight and threshold of BP neural network are obtained through immune algorithm, so as to avoid the problem of slow convergence and getting into easily local optimal value of BP neural network, then get the minimum localization error. Simulation results show that the maximum error from training to 100 samples by IA-BP neural network was not more than 0.02, In the positioning scene composed of three anchors, the simulation output trajectory of the undetermined bit node was basically consistent with the actual motion trajectory.
The complex indoor environment brings non-visual range error and multipath interference to the localization system, How to eliminate or reduce error becomes a hot spot in research to UWB indoor localization. A UWB indoor localization method based on IA-BP neural network is proposed, Which is that the error of training by BP neural network is as the antigen of calculating affinity to immune algorithm,the optimal weight and threshold of BP neural network are obtained through immune algorithm, so as to avoid the problem of slow convergence and getting into easily local optimal value of BP neural network, then get the minimum localization error. Simulation results show that the maximum error from training to 100 samples by IA-BP neural network was not more than 0.02, In the positioning scene composed of three anchors, the simulation output trajectory of the undetermined bit node was basically consistent with the actual motion trajectory.
引文
[1] 卞佳兴,朱荣,陈玄.基于改进双向测距—到达时间差定位算法的超宽带定位系统[J]. 计算机应用,2017,37(9):2496-2500,2511.
[2] 王磊,李鹏涛,贾宗璞.基于全质心-Taylor的UWB室内定位算法[J].传感器与微系统,2017,36(6):146-149.
[3] 闫保芳,毛庆洲.一种基于卡尔曼滤波的超宽带室内定位算法[J].传感器与微系统, 2017,36(10):137-140,143.
[4] 张桀,沈重.联合TDOA改进算法和卡尔曼滤波的UWB室内定位研究[J].现代电子技术, 2016,39(13):1-5.
[5] 张然,宋来亮,冉龙俊.非视距环境下基于粒子群的超宽带定位算法[J]. 传感器与微系统, 2017,36(9):117-120,124.
[6] 连宗凯,袁飞,祁伟.改进K均值聚类BP神经网络超宽带室内定位方法[J].现代计算机(专业版),2017(21):16-20.
[7] 阳熊.基于超宽带的定位技术研究与应用[D].成都:电子科技大学,2015.
[8] 赵义飞,高锦宏,刘亚平,等.基于蚁群优化神经网络的故障诊断[J].北京信息科技大学学报(自然科学版),2010,25(2):45-48.
[9] 赵章明,冯径,施恩,等.带启发信息的蚁群神经网络训练算法[J].计算机科学, 2017,44(11):284-288,296.
[10] 冯舒怡.基于免疫算法的TSP问题求解[D].天津:天津大学,2016.
[11] 李晴,何怡刚,包伟.免疫蚂蚁算法优化的RBF网络用于模拟电路故障诊断[J].仪器仪表学报,2010,31(6):1255-1261.
[12] 朱永龙.基于UWB的室内定位算法研究与应用[D].济南:山东大学,2014.
[13] 毛永毅,张颖.非视距传播环境下的AOA定位跟踪算法[J].计算机应用,2011,31(2):317-319.
[14] 崔荣一,洪炳熔.关于三层前馈神经网络隐层构建问题的研究[J].计算机研究与发展,2004(4):524-530.
[15] 何拥军,曾文权,曾文英.基于BP神经网络的多传感器数据融合技术优化[J].微型机与应用,2011,30(22):52-54,58.
[2] 王磊,李鹏涛,贾宗璞.基于全质心-Taylor的UWB室内定位算法[J].传感器与微系统,2017,36(6):146-149.
[3] 闫保芳,毛庆洲.一种基于卡尔曼滤波的超宽带室内定位算法[J].传感器与微系统, 2017,36(10):137-140,143.
[4] 张桀,沈重.联合TDOA改进算法和卡尔曼滤波的UWB室内定位研究[J].现代电子技术, 2016,39(13):1-5.
[5] 张然,宋来亮,冉龙俊.非视距环境下基于粒子群的超宽带定位算法[J]. 传感器与微系统, 2017,36(9):117-120,124.
[6] 连宗凯,袁飞,祁伟.改进K均值聚类BP神经网络超宽带室内定位方法[J].现代计算机(专业版),2017(21):16-20.
[7] 阳熊.基于超宽带的定位技术研究与应用[D].成都:电子科技大学,2015.
[8] 赵义飞,高锦宏,刘亚平,等.基于蚁群优化神经网络的故障诊断[J].北京信息科技大学学报(自然科学版),2010,25(2):45-48.
[9] 赵章明,冯径,施恩,等.带启发信息的蚁群神经网络训练算法[J].计算机科学, 2017,44(11):284-288,296.
[10] 冯舒怡.基于免疫算法的TSP问题求解[D].天津:天津大学,2016.
[11] 李晴,何怡刚,包伟.免疫蚂蚁算法优化的RBF网络用于模拟电路故障诊断[J].仪器仪表学报,2010,31(6):1255-1261.
[12] 朱永龙.基于UWB的室内定位算法研究与应用[D].济南:山东大学,2014.
[13] 毛永毅,张颖.非视距传播环境下的AOA定位跟踪算法[J].计算机应用,2011,31(2):317-319.
[14] 崔荣一,洪炳熔.关于三层前馈神经网络隐层构建问题的研究[J].计算机研究与发展,2004(4):524-530.
[15] 何拥军,曾文权,曾文英.基于BP神经网络的多传感器数据融合技术优化[J].微型机与应用,2011,30(22):52-54,58.