基于聚类和K近邻算法的井下人员定位算法
|
摘要
针对现有基于指纹模的井下定位算法存在的计算量大、实时性低、定位精度较低的问题,提出了基于聚类和K近邻算法的井下人员定位算法。用二分k-means聚类算法对采集的RSSI数据进行分类,建立离线指纹数据库;无线移动终端和动态修正器实时采集RSSI值,分别存储到在线定位数据库和动态修正数据库;根据待测点和动态修正器的离线数据和实时数据,采用软硬件动态修正加权K近邻算法计算权重值,结合离线指纹数据库中待测点的物理位置信息估算其实时位置。实验分析结果表明,所提定位算法的最小标准误差为0.46m,最大标准误差为3.26m,平均误差为1.62m。对比分析结果表明,与未进行聚类分析的算法相比,本文算法的精度更高,实时性更好;与未动态修正权重值的算法相比,本文算法的运算时间略有增加,但定位精度提高了37.21%。
In view of problems of large amount of calculation,low real-time performance and low positioning accuracy of existing fingerprint-based underground positioning algorithm,underground personnel positioning algorithm based on clustering and K-nearest neighbor algorithm was proposed.Bisecting k-means clustering algorithm is used to classify collected RSSI data to establish an offline fingerprint database.Real time RSSI values are collected by wireless mobile terminal and dynamic corrector and stored in online positioning database and dynamic correction database respectively.According to offline data and real-time data,weight value is calculated using software and hardware dynamic correction weighted K-nearest neighbor algorithm,and real-time position is estimated by combining the physical location information of the point to be measured in the offline fingerprint database.The example analysis results show that the minimum standard error of the proposed positioning algorithm is 0.46 m,the maximum standard error is 3.26 m,and the average error is 1.62 m.The results of comparative analysis show that the proposed algorithm has higher precision and better real-time performance than the algorithm without clustering analysis.Compared with the algorithm without dynamic correction ofweights,the computation time of the proposed algorithm is slightly increased,but the positioning accuracy is increased by 37.21%.
In view of problems of large amount of calculation,low real-time performance and low positioning accuracy of existing fingerprint-based underground positioning algorithm,underground personnel positioning algorithm based on clustering and K-nearest neighbor algorithm was proposed.Bisecting k-means clustering algorithm is used to classify collected RSSI data to establish an offline fingerprint database.Real time RSSI values are collected by wireless mobile terminal and dynamic corrector and stored in online positioning database and dynamic correction database respectively.According to offline data and real-time data,weight value is calculated using software and hardware dynamic correction weighted K-nearest neighbor algorithm,and real-time position is estimated by combining the physical location information of the point to be measured in the offline fingerprint database.The example analysis results show that the minimum standard error of the proposed positioning algorithm is 0.46 m,the maximum standard error is 3.26 m,and the average error is 1.62 m.The results of comparative analysis show that the proposed algorithm has higher precision and better real-time performance than the algorithm without clustering analysis.Compared with the algorithm without dynamic correction ofweights,the computation time of the proposed algorithm is slightly increased,but the positioning accuracy is increased by 37.21%.
引文
[1]孙继平.煤矿信息化自动化新技术与发展[J].煤炭科学技术,2016,44(1):19-23.SUN Jiping.New technology and development of mine informatization and automation[J].Coal Science and Technology,2016,44(1):19-23.
[2]闫雷兵,陆音,张业荣.基于改进最小二乘算法的TDOA/AOA定位方法[J].电波科学学报,2016,31(2):394-400.YAN Leibing,LU Yin,ZHANG Yerong.Improved least-squares algorithm for TDOA/AOA-based localization[J].Chinese Journal of Radio Science,2016,31(2):394-400.
[3]孙继平,蒋恩松.基于WiFi信号二次扩频的矿井TOA测距方法[J].工矿自动化,2017,43(10):53-58.SUN Jiping,JIANG Ensong.Mine TOA ranging method based on re-spread spectrum to WiFi signal[J].Industry and Mine Automation,2017,43(10):53-58.
[4]孙哲星,孙继平.异步测时矿井人员精确定位方法[J].煤炭学报,2018,43(5):1464-1470.SUN Zhexing,SUN Jiping.Underground coal mine accurate personnel positioning method based on asynchronous time-measuring[J].Journal of China Coal Society,2018,43(5):1464-1470.
[5]FANG Xuming,JIANG Zonghua,NAN Lei,et al.Optimal weighted K-nearest neighbor algorithm for wireless sensor network fingerprint location in noisy environment[J].IET Communications,2018,12(10):1171-1177.
[6]孙哲星.基于时间测距的矿井人员定位方法研究[J].工矿自动化,2018,44(4):30-33.SUN Zhexing.Research on mine personnel positioning method based on time range[J].Industry and Mine Automation,2018,44(4):30-33.
[7]钱志鸿,孙大洋,LEUNG Victor.无线网络定位综述[J].计算机学报,2016,39(6):1237-1256.QIAN Zhihong,SUN Dayang,LEUNG Victor.Asurvey on localization model in wireless networks[J].Chinese Journal of Computers,2016,39(6):1237-1256.
[8]尚俊龙,胡建华,邓红卫.基于加权三边测算的井下人员精确定位研究[J].中国安全科学学报,2011,21(2):126-130.SHANG Junlong,HU Jianhua,DENG Hongwei.Accurate positioning of mine staff based on measurement of weighted trilateration[J].China Safety Science Journal,2011,21(2):126-130.
[9]赵彤,李先圣,张雷,等.煤矿井下节点合作加权质心定位算法[J].工矿自动化,2018,44(8):32-38.ZHAO Tong,LI Xiansheng,ZHANG Lei,et al.Weighted centroid localization algorithm based on node cooperation in coal mine underground[J].Industry and Mine Automation,2018,44(8):32-38.
[10]王永星,华钢,徐永刚,等.基于信号传输模型的指纹井下目标定位算法[J].中国科技论文,2015,10(20):2463-2466.WANG Yongxing,HUA Gang,XU Yonggang,et al.Localization algorithm of coal mine miner based on the signal transmission model fingerprint[J].China Sciencepaper,2015,10(20):2463-2466.
[11]董建平,杨诚,陆小丽.基于WiFi的井下指纹模定位算法[J].工矿自动化,2014,40(10):87-89.DONG Jianping,YANG Cheng,LU Xiaoli.Underground fingerprint module positioning algorithm based on WiFi[J].Industry and Mine Automation,2014,40(10):87-89.
[12]张宪超.数据聚类[M].北京:科学出版社,2017.
[13]陈平华,陈传瑜.基于满二叉树的二分K-means聚类并行推荐算法[J].计算机工程与科学,2015,37(8):1450-1457.CHEN Pinghua,CHEN Chuanyu.A bisecting K-means clustering parallel recommendation algorithm based on full binary tree[J].Computer Engineering&Science,2015,37(8):1450-1457.
[14]杨慧琳,黄智刚,刘久文,等.基于核模糊C均值指纹库管理的WIFI室内定位方法[J].浙江大学学报(工学版),2016,50(6):1126-1133.YANG Huilin,HUANG Zhigang,LIU Jiuwen,et al.WIFI fingerprinting localization based on kernel fuzzy C-means II clustering[J].Journal of Zhejiang University(Engineering Science),2016,50(6):1126-1133.
[15]XUE Weixing,YU Kegen,HUA Xianghong,et a1.APs'virtual positions based reference point clustering and physical distance based weighting for indoor WiFi positioning[J].IEEE Internet of Things Journal,2018,5(4):3031-3042.
[16]石欣,印爱民,张琦.基于K最近邻分类的无线传感器网络定位算法[J].仪器仪表学报,2014,35(10):2238-2247.SHI Xin,YIN Aimin,ZHANG Qi.Localization in wireless sensor networks based on K-nearest neighbor[J].Chinese Journal of Scientific Instrument,2014,35(10):2238-2247.
[17]田洪亮,钱志鸿,梁潇,等.离散度WKNN位置指纹Wi-Fi定位算法[J].哈尔滨工业大学学报,2017,49(5):94-99.TIAN Hongliang,QIAN Zhihong,LIANG Xiao,et al.Discrete degree WKNN location fingerprinting algorithm based on Wi-Fi[J].Journal of Harbin Institute of Technology,2017,49(5):94-99.
[18]莫树培.煤矿井下配电系统电容电流的测量方法研究[J].煤炭技术,2014,33(9):209-211.MO Shupei.Research on measuring method of capacitive current of distribution system in coal mine[J].Coal Technology,2014,33(9):209-211.
[19]王怡婷,郭红.基于层次聚类的WiFi室内位置指纹定位算法[J].福州大学学报(自然科学版),2017,45(1):8-15.WANG Yiting,GUO Hong.WiFi indoor position fingerprinting localization algorithm based on hierarchical clustering[J].Journal of Fuzhou University(Natural Science Edition),2017,45(1):8-15.
[20]莫树培.悬臂式掘进机截齿截割模型构建及受力分析[J].煤矿机械,2015,36(1):113-115.MO Shupei.Force analysis and modeling of cutting pick of boom roadheader[J].Coal Mine Machinery,2015,36(1):113-115.
[21]孙利民,张书钦,李志,等.无线传感器网络理论及应用[M].北京:清华大学出版社,2018.
[22]孙继平,李晨鑫.基于TOA技术的煤矿井下人员定位精度评价方法[J].煤炭科学技术,2014,42(3):66-68.SUN Jiping,LI Chenxin.Evaluation method of positioning accuracy for mine underground personnel based on TOA technology[J].Coal Science and Technology,2014,42(3):66-68.
[2]闫雷兵,陆音,张业荣.基于改进最小二乘算法的TDOA/AOA定位方法[J].电波科学学报,2016,31(2):394-400.YAN Leibing,LU Yin,ZHANG Yerong.Improved least-squares algorithm for TDOA/AOA-based localization[J].Chinese Journal of Radio Science,2016,31(2):394-400.
[3]孙继平,蒋恩松.基于WiFi信号二次扩频的矿井TOA测距方法[J].工矿自动化,2017,43(10):53-58.SUN Jiping,JIANG Ensong.Mine TOA ranging method based on re-spread spectrum to WiFi signal[J].Industry and Mine Automation,2017,43(10):53-58.
[4]孙哲星,孙继平.异步测时矿井人员精确定位方法[J].煤炭学报,2018,43(5):1464-1470.SUN Zhexing,SUN Jiping.Underground coal mine accurate personnel positioning method based on asynchronous time-measuring[J].Journal of China Coal Society,2018,43(5):1464-1470.
[5]FANG Xuming,JIANG Zonghua,NAN Lei,et al.Optimal weighted K-nearest neighbor algorithm for wireless sensor network fingerprint location in noisy environment[J].IET Communications,2018,12(10):1171-1177.
[6]孙哲星.基于时间测距的矿井人员定位方法研究[J].工矿自动化,2018,44(4):30-33.SUN Zhexing.Research on mine personnel positioning method based on time range[J].Industry and Mine Automation,2018,44(4):30-33.
[7]钱志鸿,孙大洋,LEUNG Victor.无线网络定位综述[J].计算机学报,2016,39(6):1237-1256.QIAN Zhihong,SUN Dayang,LEUNG Victor.Asurvey on localization model in wireless networks[J].Chinese Journal of Computers,2016,39(6):1237-1256.
[8]尚俊龙,胡建华,邓红卫.基于加权三边测算的井下人员精确定位研究[J].中国安全科学学报,2011,21(2):126-130.SHANG Junlong,HU Jianhua,DENG Hongwei.Accurate positioning of mine staff based on measurement of weighted trilateration[J].China Safety Science Journal,2011,21(2):126-130.
[9]赵彤,李先圣,张雷,等.煤矿井下节点合作加权质心定位算法[J].工矿自动化,2018,44(8):32-38.ZHAO Tong,LI Xiansheng,ZHANG Lei,et al.Weighted centroid localization algorithm based on node cooperation in coal mine underground[J].Industry and Mine Automation,2018,44(8):32-38.
[10]王永星,华钢,徐永刚,等.基于信号传输模型的指纹井下目标定位算法[J].中国科技论文,2015,10(20):2463-2466.WANG Yongxing,HUA Gang,XU Yonggang,et al.Localization algorithm of coal mine miner based on the signal transmission model fingerprint[J].China Sciencepaper,2015,10(20):2463-2466.
[11]董建平,杨诚,陆小丽.基于WiFi的井下指纹模定位算法[J].工矿自动化,2014,40(10):87-89.DONG Jianping,YANG Cheng,LU Xiaoli.Underground fingerprint module positioning algorithm based on WiFi[J].Industry and Mine Automation,2014,40(10):87-89.
[12]张宪超.数据聚类[M].北京:科学出版社,2017.
[13]陈平华,陈传瑜.基于满二叉树的二分K-means聚类并行推荐算法[J].计算机工程与科学,2015,37(8):1450-1457.CHEN Pinghua,CHEN Chuanyu.A bisecting K-means clustering parallel recommendation algorithm based on full binary tree[J].Computer Engineering&Science,2015,37(8):1450-1457.
[14]杨慧琳,黄智刚,刘久文,等.基于核模糊C均值指纹库管理的WIFI室内定位方法[J].浙江大学学报(工学版),2016,50(6):1126-1133.YANG Huilin,HUANG Zhigang,LIU Jiuwen,et al.WIFI fingerprinting localization based on kernel fuzzy C-means II clustering[J].Journal of Zhejiang University(Engineering Science),2016,50(6):1126-1133.
[15]XUE Weixing,YU Kegen,HUA Xianghong,et a1.APs'virtual positions based reference point clustering and physical distance based weighting for indoor WiFi positioning[J].IEEE Internet of Things Journal,2018,5(4):3031-3042.
[16]石欣,印爱民,张琦.基于K最近邻分类的无线传感器网络定位算法[J].仪器仪表学报,2014,35(10):2238-2247.SHI Xin,YIN Aimin,ZHANG Qi.Localization in wireless sensor networks based on K-nearest neighbor[J].Chinese Journal of Scientific Instrument,2014,35(10):2238-2247.
[17]田洪亮,钱志鸿,梁潇,等.离散度WKNN位置指纹Wi-Fi定位算法[J].哈尔滨工业大学学报,2017,49(5):94-99.TIAN Hongliang,QIAN Zhihong,LIANG Xiao,et al.Discrete degree WKNN location fingerprinting algorithm based on Wi-Fi[J].Journal of Harbin Institute of Technology,2017,49(5):94-99.
[18]莫树培.煤矿井下配电系统电容电流的测量方法研究[J].煤炭技术,2014,33(9):209-211.MO Shupei.Research on measuring method of capacitive current of distribution system in coal mine[J].Coal Technology,2014,33(9):209-211.
[19]王怡婷,郭红.基于层次聚类的WiFi室内位置指纹定位算法[J].福州大学学报(自然科学版),2017,45(1):8-15.WANG Yiting,GUO Hong.WiFi indoor position fingerprinting localization algorithm based on hierarchical clustering[J].Journal of Fuzhou University(Natural Science Edition),2017,45(1):8-15.
[20]莫树培.悬臂式掘进机截齿截割模型构建及受力分析[J].煤矿机械,2015,36(1):113-115.MO Shupei.Force analysis and modeling of cutting pick of boom roadheader[J].Coal Mine Machinery,2015,36(1):113-115.
[21]孙利民,张书钦,李志,等.无线传感器网络理论及应用[M].北京:清华大学出版社,2018.
[22]孙继平,李晨鑫.基于TOA技术的煤矿井下人员定位精度评价方法[J].煤炭科学技术,2014,42(3):66-68.SUN Jiping,LI Chenxin.Evaluation method of positioning accuracy for mine underground personnel based on TOA technology[J].Coal Science and Technology,2014,42(3):66-68.