检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:窦占树 崔丽珍[1] 罗海勇[2] 洪金祥 DOU Zhanshu;CUI Lizhen;LUO Haiyong;HONG Jinxiang(School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China)
机构地区:[1]内蒙古科技大学信息工程学院,内蒙古包头014010 [2]中国科学院计算技术研究所,北京100190
出 处:《无线电工程》2023年第3期714-720,共7页Radio Engineering
基 金:国家自然科学基金(61761038);内蒙古自然科学基金(2020MS06027)。
摘 要:井下无线通信环境的高动态变化会使定位模型精度降低,可将在线顺序极限学习机(Online Sequential Limit Learning Machine,OSELM)算法用于井下定位,利用在线学习能力实现对模型的实时更新,与批量式处理算法SVM和ELM相比,该算法能更有效地提高模型的定位精度。但在OSELM模型更新过程中,并没有对新增数据有效性进行考虑,针对这一问题,从新增数据时效性和采集新增数据参考点覆盖率2方面对OSELM算法进行改进,同时融合以上2个因素做融合性改进,用权重项表示新增数据对OSELM定位模型的更新程度。实验结果表明,在3 m误差距离范围内,经改进的OSELM算法均能有效提高定位模型精度,更好地改善因井下环境高动态变化导致模型精度降低的问题。The highly dynamic changes in downhole wireless communication environment can degrade the positioning model accuracy.The Online Sequential Limit Learning Machine(OSELM)algorithm can be used for downhole positioning to achieve real-time updating of the model using online learning capability,which can improve the positioning accuracy of the model more effectively as compared with batch-type processing algorithms such as SVM and ELM.However,the validity of the new data is not considered in the process of OSELM model updating.To address this problem,the OSELM algorithm is improved in terms of the timeliness of new data and the coverage of reference points for collecting the new data,and the above two factors are fused to make convergent improvements,and the weight term is used to indicate the degree of update of the new data on the OSELM positioning model.The experimental results show that the improved OSELM algorithm can effectively improve the positioning model accuracy within 3 m error distance,and better address the problem of model accuracy degradation due to highly dynamic changes in downhole environment.
关 键 词:WiFi井下定位 改进OSELM定位模型 高动态井下环境 增量式学习
分 类 号:TN92[电子电信—通信与信息系统]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.60