基于SAPSO-BP神经网络的井下自适应定位算法
|
摘要
针对基于传统BP神经网络的井下定位算法存在收敛速度慢、易形成局部极值、在煤矿井下强时变性电磁环境中定位误差大等问题,提出了一种基于模拟退火思想的粒子群优化算法加BP神经网络(SAPSO-BP)的井下自适应定位算法。采用SAPSO算法优化BP神经网络的初始权值和阈值,以加快训练收敛速度,使之到达全局最优;通过安装在井下巷道中的无线校准器采集目标点接收信号强度指示(RSSI)值,采用自适应动态校准方法对RSSI值进行实时校准,以减小强时变性电磁环境对定位精度的影响;最后利用SAPSO-BP神经网络估算出目标点位置坐标。实验结果表明,该算法的定位误差在2m内的置信概率为77.54%,平均误差为1.53m,定位性能优于未校准SAPSO-BP神经网络算法、PSO-BP神经网络算法、BP神经网络算法。
In view of problems of slow convergence,easy to form local extremum and large positioning error in strong time-varying electromagnetic environment of underground positioning algorithms based on traditional BP neural network,an underground adaptive positioning algorithm based on simulated annealing and particle swarm optimization and BP neural network(SAPSO-BP)was proposed.SAPSO algorithm is used to optimize the initial weight and threshold of BP neural network to accelerate training convergence speed and make it reach the global optimum.The target point RSSI value is collected by wireless calibrator installed in underground roadway and real-time calibrated by adaptive dynamic calibration method,in order to reduce influence of time-varying electromagnetic environment on positioning accuracy.Finally,the SAPSO-BP neural network is used to estimate position coordinates of target point.The experimental results show that confidence probability of positioning error within 2 mof the proposed algorithm is 77.54%,average error is 1.53 m,the positioning performance is better than uncalibrated SAPSO-BP neural network algorithm,PSO-BP neural network algorithm and BP neural network algorithm.
In view of problems of slow convergence,easy to form local extremum and large positioning error in strong time-varying electromagnetic environment of underground positioning algorithms based on traditional BP neural network,an underground adaptive positioning algorithm based on simulated annealing and particle swarm optimization and BP neural network(SAPSO-BP)was proposed.SAPSO algorithm is used to optimize the initial weight and threshold of BP neural network to accelerate training convergence speed and make it reach the global optimum.The target point RSSI value is collected by wireless calibrator installed in underground roadway and real-time calibrated by adaptive dynamic calibration method,in order to reduce influence of time-varying electromagnetic environment on positioning accuracy.Finally,the SAPSO-BP neural network is used to estimate position coordinates of target point.The experimental results show that confidence probability of positioning error within 2 mof the proposed algorithm is 77.54%,average error is 1.53 m,the positioning performance is better than uncalibrated SAPSO-BP neural network algorithm,PSO-BP neural network algorithm and BP neural network algorithm.
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]孙继平.2016年版《煤矿安全规程》监控与通信条款解析[J].工矿自动化,2016,42(5):1-8.SUN Jiping.Explanations for part of monitoring and communication of Coal Mine Safety Regulations of2016 Edition[J].Industry and Mine Automation,2016,42(5):1-8.
[3]张立亚.全矿井融合通信系统研究[J].工矿自动化,2018,44(3):12-16.ZHANG Liya. Research on mine integrated communication system[J].Industry and Mine Automation,2018,44(3):12-16.
[4]LIU Dawei,SHENG Bin,HOU Fen,et al.From wireless positioning to mobile positioning:an overview of recent advances[J].IEEE Systems Journal,2014,8(4):1249-1259.
[5]FANG Xuming,JIANG Zonghua,NAN Lei,et a1.Optimal weighted K-nearest neighbor algorithm for wireless sensor network fingerprint location in noisy environment[J].IET Communications,2018,12(10):1171-1177.
[6]蒋锐,杨震.基于质心迭代估计的无线传感器网络节点定位算法[J].物理学报,2016,65(3):9-17.JIANG Rui,YANG Zhen.An improved centroid localization algorithm based on iterative computation for wireless sensor network[J].Acta Physica Sinica,2016,65(3):9-17.
[7]邹自明,何文斌,杨小平.基于LMBP神经网络的无线室内定位方法[J].桂林理工大学学报,2018,38(3):574-578.ZOU Ziming,HE Wenbin,YANG Xiaoping.Wireless indoor positioning method based on LMBP neural network[J].Journal of Guilin University of Technology,2018,38(3):574-578.
[8]石晓伟.基于BP神经网络和改进质心算法的室内无线定位技术的研究[D].北京:北京工业大学,2012.
[9]张会清,石晓伟,邓贵华,等.基于BP神经网络和泰勒级数的室内定位算法研究[J].电子学报,2012,40(9):1876-1879.ZHANG Huiqing,SHI Xiaowei, DENG Guihua,et al.Research on indoor location technology based on back propagation neural network and Taylor series[J].Acta Electronica Sinica,2012,40(9):1876-1879.
[10]崔丽珍,许凡非,王巧利,等.基于PSO-BP神经网络的煤矿井下自适应定位算法[J].工矿自动化,2018,44(2):74-79.CUI Lizhen,XU Fanfei, WANG Qiaoli,et al.Underground adaptive positioning algorithm based on PSO-BP neural network[J].Industry and Mine Automation,2018,44(2):74-79.
[11]ZHANG Yanjun,XU Jinrui,FU Xinghu,et a1.Hybrid algorithm combining genetic algorithm with back propagation neural network for extracting the characteristics of multi-peak Brillouin scattering spectrum[J].Frontiers of Optoelectronics,2017,10(1):62-69.
[12]陈雯柏.人工神经网络原理与实践[M].西安:西安电子科技大学出版社,2016.
[13]XIONG Hailiang,PENG Meixuan,ZHU Kongfan,et a1.Efficient bias reduction approach of time-offlight-based wireless localization networks in NLOS states[J].IET Radar,Sonar &Navigation,2018,12(11):1353-1360.
[14]张亚明,史浩山,陈客松,等.一种改进的无线传感器网络优化定位算法[J].电子科技大学学报,2015,44(3):357-362.ZHANG Yaming,SHI Haoshan,CHEN Kesong,et al.An improved optimization localization algorithm in WSNs[J].Journal of University of Electronic Science and Technology of China,2015,44(3):357-362.
[15]专祥涛.最优化方法基础[M].武汉:武汉大学出版社,2018.
[16]宗群,秦新立,张博渊,等.基于DPSO-GT-SA算法的大规模UCAV协同任务分配[J].天津大学学报(自然科学与工程技术版),2018,51(10):1005-1014.ZONG Qun,QIN Xinli,ZHANG Boyuan,et al.Cooperative task allocation of large-scale UCAV based on DPSO-GT-SA algorithm[J].Journal of Tianjin University(Science and Technology),2018,51(10):1005-1014.
[17]张卿祎,王兴伟,黄敏.基于PSO和SA混合优化的智能容错QoS路由机制[J].东北大学学报(自然科学版),2017,38(3):325-330.ZHANG Qingyi,WANG Xingwei,HUANG Min.An intelligent fault-tolerant QoS routing mechanism based on PSO and SA hybrid optimization[J].Journal of Northeastern University(Natural Science),2017,38(3):325-330.
[18]姚建丽,胡红萍,白艳萍,等.应用SAPSO-BP神经网络的DOA估计方法[J].重庆理工大学学报(自然科学),2018,32(5):183-188.YAO Jianli,HU Hongping,BAI Yanping,et al.DOA estimation method based on SAPSO-BP neural network[J].Journal of Chongqing University of Technology(Natural Science),2018,32(5):183-188.
[19]刘海波,王和平,沈立顶.基于SAPSO优化灰色神经网络的空中目标威胁估计[J].西北工业大学学报,2016,34(1):25-32.LIU Haibo,WANG Heping,SHEN Liding.Target threat assessment using SAPSO and grey neural network[J].Journal of Northwestern Polytechnical University,2016,34(1):25-32.
[2]孙继平.2016年版《煤矿安全规程》监控与通信条款解析[J].工矿自动化,2016,42(5):1-8.SUN Jiping.Explanations for part of monitoring and communication of Coal Mine Safety Regulations of2016 Edition[J].Industry and Mine Automation,2016,42(5):1-8.
[3]张立亚.全矿井融合通信系统研究[J].工矿自动化,2018,44(3):12-16.ZHANG Liya. Research on mine integrated communication system[J].Industry and Mine Automation,2018,44(3):12-16.
[4]LIU Dawei,SHENG Bin,HOU Fen,et al.From wireless positioning to mobile positioning:an overview of recent advances[J].IEEE Systems Journal,2014,8(4):1249-1259.
[5]FANG Xuming,JIANG Zonghua,NAN Lei,et a1.Optimal weighted K-nearest neighbor algorithm for wireless sensor network fingerprint location in noisy environment[J].IET Communications,2018,12(10):1171-1177.
[6]蒋锐,杨震.基于质心迭代估计的无线传感器网络节点定位算法[J].物理学报,2016,65(3):9-17.JIANG Rui,YANG Zhen.An improved centroid localization algorithm based on iterative computation for wireless sensor network[J].Acta Physica Sinica,2016,65(3):9-17.
[7]邹自明,何文斌,杨小平.基于LMBP神经网络的无线室内定位方法[J].桂林理工大学学报,2018,38(3):574-578.ZOU Ziming,HE Wenbin,YANG Xiaoping.Wireless indoor positioning method based on LMBP neural network[J].Journal of Guilin University of Technology,2018,38(3):574-578.
[8]石晓伟.基于BP神经网络和改进质心算法的室内无线定位技术的研究[D].北京:北京工业大学,2012.
[9]张会清,石晓伟,邓贵华,等.基于BP神经网络和泰勒级数的室内定位算法研究[J].电子学报,2012,40(9):1876-1879.ZHANG Huiqing,SHI Xiaowei, DENG Guihua,et al.Research on indoor location technology based on back propagation neural network and Taylor series[J].Acta Electronica Sinica,2012,40(9):1876-1879.
[10]崔丽珍,许凡非,王巧利,等.基于PSO-BP神经网络的煤矿井下自适应定位算法[J].工矿自动化,2018,44(2):74-79.CUI Lizhen,XU Fanfei, WANG Qiaoli,et al.Underground adaptive positioning algorithm based on PSO-BP neural network[J].Industry and Mine Automation,2018,44(2):74-79.
[11]ZHANG Yanjun,XU Jinrui,FU Xinghu,et a1.Hybrid algorithm combining genetic algorithm with back propagation neural network for extracting the characteristics of multi-peak Brillouin scattering spectrum[J].Frontiers of Optoelectronics,2017,10(1):62-69.
[12]陈雯柏.人工神经网络原理与实践[M].西安:西安电子科技大学出版社,2016.
[13]XIONG Hailiang,PENG Meixuan,ZHU Kongfan,et a1.Efficient bias reduction approach of time-offlight-based wireless localization networks in NLOS states[J].IET Radar,Sonar &Navigation,2018,12(11):1353-1360.
[14]张亚明,史浩山,陈客松,等.一种改进的无线传感器网络优化定位算法[J].电子科技大学学报,2015,44(3):357-362.ZHANG Yaming,SHI Haoshan,CHEN Kesong,et al.An improved optimization localization algorithm in WSNs[J].Journal of University of Electronic Science and Technology of China,2015,44(3):357-362.
[15]专祥涛.最优化方法基础[M].武汉:武汉大学出版社,2018.
[16]宗群,秦新立,张博渊,等.基于DPSO-GT-SA算法的大规模UCAV协同任务分配[J].天津大学学报(自然科学与工程技术版),2018,51(10):1005-1014.ZONG Qun,QIN Xinli,ZHANG Boyuan,et al.Cooperative task allocation of large-scale UCAV based on DPSO-GT-SA algorithm[J].Journal of Tianjin University(Science and Technology),2018,51(10):1005-1014.
[17]张卿祎,王兴伟,黄敏.基于PSO和SA混合优化的智能容错QoS路由机制[J].东北大学学报(自然科学版),2017,38(3):325-330.ZHANG Qingyi,WANG Xingwei,HUANG Min.An intelligent fault-tolerant QoS routing mechanism based on PSO and SA hybrid optimization[J].Journal of Northeastern University(Natural Science),2017,38(3):325-330.
[18]姚建丽,胡红萍,白艳萍,等.应用SAPSO-BP神经网络的DOA估计方法[J].重庆理工大学学报(自然科学),2018,32(5):183-188.YAO Jianli,HU Hongping,BAI Yanping,et al.DOA estimation method based on SAPSO-BP neural network[J].Journal of Chongqing University of Technology(Natural Science),2018,32(5):183-188.
[19]刘海波,王和平,沈立顶.基于SAPSO优化灰色神经网络的空中目标威胁估计[J].西北工业大学学报,2016,34(1):25-32.LIU Haibo,WANG Heping,SHEN Liding.Target threat assessment using SAPSO and grey neural network[J].Journal of Northwestern Polytechnical University,2016,34(1):25-32.