基于BP神经网络的两参数区域对流层延迟模型
|
摘要
为了提高区域对流层延迟模型的精度,利用BP神经算法构建两参数区域对流层延迟新模型。基于河南省部分CORS基准站的数据,将穿刺面作为研究面,基于BP神经网络模型、平面拟合模型、二次曲面拟合模型分别建立两参数区域对流层延迟模型,并设计了3种不同的建模方案,以验证模型的精度。实验结果表明,BP神经网络模型的对流层延迟精度达到mm级,明显优于其他2种模型,BP神经网络模型和平面拟合模型不仅适用于区域内,同样适用于区域外,证实了新模型的有效性。
In order to improve the accuracy of regional tropospheric delay model,using BP neural algorithm to construct a new region tropospheric delay model in two-parameter. Based on data from the part of CORS benchmark station in henan province,the puncture surface as the research area,based on the BP neural network model,plane fitting model,the quadric surface fitting model,a two-parameter regional tropospheric delay model is established,and three different modeling schemes are designed to verify the accuracy of the model. The experimental results show that tropospheric delay accuracy of BP neural network model reaches mm level,which is obviously better than the other two models,BP neural network model and plane fitting model not only apply to the region,the same applies outside the region.Confirmed the validity of the new model.
In order to improve the accuracy of regional tropospheric delay model,using BP neural algorithm to construct a new region tropospheric delay model in two-parameter. Based on data from the part of CORS benchmark station in henan province,the puncture surface as the research area,based on the BP neural network model,plane fitting model,the quadric surface fitting model,a two-parameter regional tropospheric delay model is established,and three different modeling schemes are designed to verify the accuracy of the model. The experimental results show that tropospheric delay accuracy of BP neural network model reaches mm level,which is obviously better than the other two models,BP neural network model and plane fitting model not only apply to the region,the same applies outside the region.Confirmed the validity of the new model.
引文
[1]王斐,吴晓莉,等.不同Klobuchar模型参数的性能比较[J].测绘学报,2014,43(11):1151-1157.
[2]吉绪发,卢辰龙. GPS多路径误差滤波方法比较研究[J].测绘通报,2015,(04):10-13.
[3] H. S. Hopfield,“Two-quartic tropospheric refractivity profile for correcting satellite data,” J. Geophys. Res.1969,74(18):4487–4499.
[4] J. Saastamoinen,“Atmospheric correction for the troposphere and stratosphere in radio ranging of satellite” in Proceedings Int. Sympos. on the Use of Artificial Satellite(Washington,DC,1971),247–251.
[5]陈瑞琼,刘娅,李孝辉,等.卫星导航系统中对流层改正模型分析[J].测绘通报,2015,(03):12-15.
[6] Collins J P. Assessment and Development of a Tropospheric Delay Model for Aircraft Users of the Global Positioning System[R]. Technical Report University of New Brunswick,Frederiction,Canad,1999.
[7]赵铁成,韩曜旭,等.GPS定位系统中几种对流层模型的探讨[J].全球定位系统,2011,36(1):46-52.
[8]戴吾蛟,陈招华,等.区域精密对流层延迟建模[J].武汉大学学报(信息科学版),2011,36(04):392-396.
[9] Noboru Takeichi,etal.Tropospheric delay correction with dense GPS network in L1-SAIF augementation[J].GPS Solution,2010,14:185-192.
[10]谢建涛,郝金明,等.一种改进的网络RTK对流层延迟误差线性内插模型[J].大地测量与地球动力学,2013,33(6):90-93.
[11]张小红,朱锋,等.区域CORS网络增强PPP天顶对流层延迟内插建模阴[J].武汉大学学报.信息科学版,2012,38(6):679-683.
[12]丁茂华,胡伍生.一种优化的基于神经网络的经验ZTD模型[J].测绘通报,2017,(01):22-25.
[13]赵坤娟.区域电离层延迟误差改正方法研究[D].中国科学院研究生院(国家授时中心),2014.
[14]周鹏.基于CORS数据的电离层延迟模型研究[D].中国矿业大学,2014.
[15]赵岩.区域对流层延迟建模分析[D].中南大学,2013.
[16]李剑锋,王永前,等.预测模型在对流层延迟计算中的应用研究[J].测绘科学技术学报,2015,32(05):450-454.
[17]刘彩虹.BP神经网络学习算法的研究[D].重庆师范大学,2008.
[18]尹为松,陶庭叶,等.遗传算法优化的GPS对流层延迟内插算法[J].测绘科学,2016,41(01):180-184.
[2]吉绪发,卢辰龙. GPS多路径误差滤波方法比较研究[J].测绘通报,2015,(04):10-13.
[3] H. S. Hopfield,“Two-quartic tropospheric refractivity profile for correcting satellite data,” J. Geophys. Res.1969,74(18):4487–4499.
[4] J. Saastamoinen,“Atmospheric correction for the troposphere and stratosphere in radio ranging of satellite” in Proceedings Int. Sympos. on the Use of Artificial Satellite(Washington,DC,1971),247–251.
[5]陈瑞琼,刘娅,李孝辉,等.卫星导航系统中对流层改正模型分析[J].测绘通报,2015,(03):12-15.
[6] Collins J P. Assessment and Development of a Tropospheric Delay Model for Aircraft Users of the Global Positioning System[R]. Technical Report University of New Brunswick,Frederiction,Canad,1999.
[7]赵铁成,韩曜旭,等.GPS定位系统中几种对流层模型的探讨[J].全球定位系统,2011,36(1):46-52.
[8]戴吾蛟,陈招华,等.区域精密对流层延迟建模[J].武汉大学学报(信息科学版),2011,36(04):392-396.
[9] Noboru Takeichi,etal.Tropospheric delay correction with dense GPS network in L1-SAIF augementation[J].GPS Solution,2010,14:185-192.
[10]谢建涛,郝金明,等.一种改进的网络RTK对流层延迟误差线性内插模型[J].大地测量与地球动力学,2013,33(6):90-93.
[11]张小红,朱锋,等.区域CORS网络增强PPP天顶对流层延迟内插建模阴[J].武汉大学学报.信息科学版,2012,38(6):679-683.
[12]丁茂华,胡伍生.一种优化的基于神经网络的经验ZTD模型[J].测绘通报,2017,(01):22-25.
[13]赵坤娟.区域电离层延迟误差改正方法研究[D].中国科学院研究生院(国家授时中心),2014.
[14]周鹏.基于CORS数据的电离层延迟模型研究[D].中国矿业大学,2014.
[15]赵岩.区域对流层延迟建模分析[D].中南大学,2013.
[16]李剑锋,王永前,等.预测模型在对流层延迟计算中的应用研究[J].测绘科学技术学报,2015,32(05):450-454.
[17]刘彩虹.BP神经网络学习算法的研究[D].重庆师范大学,2008.
[18]尹为松,陶庭叶,等.遗传算法优化的GPS对流层延迟内插算法[J].测绘科学,2016,41(01):180-184.