多点监测自适应网内数据融合技术的研究及应用
|
摘要
多点监测无线传感网络中,由于节点能量有限和数目众多的特点导致网络的寿命受到限制。网络中数据包的无线收发消耗了节点的大部分能量,在无线传感网络内部的传感数据汇集过程中进行数据融合(网内数据融合)可以降低网络中数据传输量、降低网络整体功耗和提高网络寿命,但它又会带来额外的数据包延迟和监测精确度降低的副作用。
本文详述了无线传感网络体系结构及其协议标准,讨论了网内数据融合技术及其在多点监测系统中的应用,对数据融合技术、聚类分析思想和模糊集合理论进行了分析,针对经典模糊聚类算法步骤,给出一种改进的聚类中心初始化方法,通过算法仿真和对比分析证明其改进效果,并将改进的模糊聚类算法应用于数据融合中,设计了分层的网内数据融合结构和自适应参数调整的融合模型。
融合模型应用在无线多点监测系统中,随监测目标的变化自适应地调整网内融合的各参数,从而使监测的精确度自适应于监测目标的状态,系统在监测目标时降低数据的传输量、在监测目标异常时及时调整提高监测精确度,在大幅度降低网络整体功耗的同时又最大程度地减少因融合而产生的监测精度损失,使得监测系统能够及时准确的捕获每一次异常的发生,尤其适用于预警监测应用。论文最后通过分析煤矿自燃过程、自燃释放气体的浓度推测自燃状态的方法,针对煤矿自燃监测系统详细描述了模型的应用原型,设计了系统结构、各节点软件工作流程。
Due to the large number of nodes and limited energy, the multi-point monitoring wireless sensor networks usually have a limited network lifetime. Wireless network packets sending and receiving consume most of the node's energy. If aggregate data within the the wireless sensor network data collection(In-network Data Aggregation), it will reduce the amount of data transferred in the network, reducing the network's overall power consumption and increase network lifetime. But it will bring additional packet delay and monitoring accuracy reduces.
This paper detailed the wireless sensor network's architecture and protocol standards, discussed the in-network data aggregation and its techniques in the application of multi-point monitoring system, analyzed cluster analysis algorithms and fuzzy set theory ideas, discussed classical steps of the fuzzy c means clustering algorithm, given an improved method of cluster centers initialization, verify the effectiveness of the improved algorithms through comparative analysis, and applied the improved fuzzy c means clustering algorithm to data aggregation, given a design of the hierarchical in-network data aggregation structure and an adaptive parameter adjustment model.
Applied this system model to wireless multi-point monitoring system, it can adaptively adjust the aggregation parameters to the changing of monitoring goal in the network. It reduce the amount of data transfer when the system monitor the target, and increase monitoring precision degree when the monitoring target abnormal. It can reduce the overall network power consumption significantly and minimize the precision loss due to the data aggregation. And it can making the monitoring system to capture every unusual occurrence timely and accurate. At last, the paper analyzed the process of coal spontaneous combustion and the gases of coal spontaneous combustion, detailed the method of use gases to speculate the coal spontaneous combustion state, discribled the application of the prototype model, given a design of the system architecture and each node's software workflow.
本文详述了无线传感网络体系结构及其协议标准,讨论了网内数据融合技术及其在多点监测系统中的应用,对数据融合技术、聚类分析思想和模糊集合理论进行了分析,针对经典模糊聚类算法步骤,给出一种改进的聚类中心初始化方法,通过算法仿真和对比分析证明其改进效果,并将改进的模糊聚类算法应用于数据融合中,设计了分层的网内数据融合结构和自适应参数调整的融合模型。
融合模型应用在无线多点监测系统中,随监测目标的变化自适应地调整网内融合的各参数,从而使监测的精确度自适应于监测目标的状态,系统在监测目标时降低数据的传输量、在监测目标异常时及时调整提高监测精确度,在大幅度降低网络整体功耗的同时又最大程度地减少因融合而产生的监测精度损失,使得监测系统能够及时准确的捕获每一次异常的发生,尤其适用于预警监测应用。论文最后通过分析煤矿自燃过程、自燃释放气体的浓度推测自燃状态的方法,针对煤矿自燃监测系统详细描述了模型的应用原型,设计了系统结构、各节点软件工作流程。
Due to the large number of nodes and limited energy, the multi-point monitoring wireless sensor networks usually have a limited network lifetime. Wireless network packets sending and receiving consume most of the node's energy. If aggregate data within the the wireless sensor network data collection(In-network Data Aggregation), it will reduce the amount of data transferred in the network, reducing the network's overall power consumption and increase network lifetime. But it will bring additional packet delay and monitoring accuracy reduces.
This paper detailed the wireless sensor network's architecture and protocol standards, discussed the in-network data aggregation and its techniques in the application of multi-point monitoring system, analyzed cluster analysis algorithms and fuzzy set theory ideas, discussed classical steps of the fuzzy c means clustering algorithm, given an improved method of cluster centers initialization, verify the effectiveness of the improved algorithms through comparative analysis, and applied the improved fuzzy c means clustering algorithm to data aggregation, given a design of the hierarchical in-network data aggregation structure and an adaptive parameter adjustment model.
Applied this system model to wireless multi-point monitoring system, it can adaptively adjust the aggregation parameters to the changing of monitoring goal in the network. It reduce the amount of data transfer when the system monitor the target, and increase monitoring precision degree when the monitoring target abnormal. It can reduce the overall network power consumption significantly and minimize the precision loss due to the data aggregation. And it can making the monitoring system to capture every unusual occurrence timely and accurate. At last, the paper analyzed the process of coal spontaneous combustion and the gases of coal spontaneous combustion, detailed the method of use gases to speculate the coal spontaneous combustion state, discribled the application of the prototype model, given a design of the system architecture and each node's software workflow.
引文
[1]Hongli Xu, Liusheng Huang, Yindong Zhang, He Huang, Shenglong Jiang, Gang Liu.Energy-efficient cooperative data aggregation for wireless sensor networks.Journal of Parallel and Distributed Computing,2010,9:953
[2]屈剑锋.无线传感器网络数据融合与目标跟踪研究及其应用.重庆大学,2009：28
[3]Huifang Chen, Hiroshi Mineno, Tadanori Mizuno.Adaptive data aggregation scheme in clustered wireless sensor networks.Computer Communications,2008,15:3579-3585
[4]L Necchi, A Bonivento, L Lavagno, A Sangiovanni Vincentelli, L Vanzago.E2RINA:an Energy Efficient and Reliable In-Network Aggregation for Clustered Wireless Sensor Networks.Wireless Communications and Networking Conference,2007:3366～3370
[5]Soonmok Kwon, Jae Hoon Ko, Jeongkyu Kim, Cheeha Kim.Dynamic timeout for data aggregation in wireless sensor networks.Computer Networks,2011,3:650-664
[6]Pei Wang,Yuan He,Liusheng Huang.Near optimal scheduling of data aggregation in wireless sensor networks.Ad Hoc Networks,2011,13:1～9
[7]Suat Ozdemir,Yang Xiao.Secure data aggregation in wireless sensor networks.Computer Networks,2009,12:2022～2033
[8]Wen-Hwa Liao,Yucheng Kao,Chien-Ming Fan.Data aggregation in wireless sensornetworks using ant colony algorithm.Journal of Network and Computer Applications.2008,31:387～401
[9]陈正宇,杨庚,陈蕾,许建.无线传感器网络数据融合研究综述.计算机应用研究,2011(05)：1601～1602
[10]沈江,王粟,徐曼.多传感器动态数据融合自适应控制系统.组合机床与自动化加工技术,2006(12)：48～50
[11]柴毅,屈剑锋,郭茂耘,尹宏鹏.分布式传感器网络在线自适应数据融合算法研究.自动化及先进集成技术大会论文集(一),2007：129～134
[12]陈敏,王擘,李军华.无线传感器网络原理与实践.第1版.北京：化学工业出版社,2011
[13]赵腾.无线传感网节能技术研究.中小企业管理与科技(下旬刊),2011(7)：271
[14]Jennifer Yick,Biswanath Mukherjee,Dipak Ghosal.Wireless sensor network survey.Computer Networks,2008,12:2292
[15]Giuseppe Anastasi,Marco Conti,Mario Di Francesco,Andrea Passarella.Energy conservation in wireless sensor networks:A survey.Ad Hoc Networks,2009,3:537
[16]Julien Happich.Ambient electromagnetic energy harvesting drives small electronic devices.EE Times.http://www.eet-china.com/,2011
[17]Jelena Misic.ZigBee:A long way to go?.R&D/Technology,2007,3,:33
[18]Chao SHA, Ru-chuan WANG, Hai-ping HUANG, Li-juan SUN.Energy efficient clustering algorithm for data aggregation in wireless sensor networks.The Journal of China Universities of Posts and Telecommunications,2010,17:104～105
[19]Giuseppe Anastasi, Marco Conti, Mario Di Francesco, Andrea Passarella.Energy conservation in wireless sensor networks.Ad Hoc Networks,2009,3:537～539
[20]宋晓君,孙洪伟.多传感器数据融合技术方法探究.华章,2011(07)：282
[21]尚海昆K-means聚类算法的研究.华北电力大学(河北),2009：5
[22]胡晓庆.模糊聚类中若干问题的研究.南京航空航天大学,2011：5
[23]A B Goktepe,S Altun,A Sezer.Soil clustering by fuzzy c-means algorithm.Advances in Engineering Software,2005,10:692
[24]George E Tsekouras, Haralambos Sarimveis.A new approach for measuring the validity of the fuzzy c-means algorithm.Advances in Engineering Software,2004,9:568
[25]Z Hou, W Qian, S Huang, Q Hu, W L Nowinski.Regularized fuzzy c-means method for brain tissue clustering.Pattern Recognition Letters,2007,13:1789
[26]Jesus Lazaro, Jagoba Arias, Jose L Martin, Carlos Cuadrado, Armando Astarloa.Implementation of a modified Fuzzy C-Means clustering algorithm for real-time applications.Microprocessors and Microsystems,2005,8:376
[27]Chenglong Tang, Shigang Wang, Wei Xu.New fuzzy c-means clustering model based on the data weighted approach.Data & Knowledge Engineering,2010,9:881～900
[28]Jiayin Kang, Lequan Min, Qingxian Luan, Xiao Li, Jinzhu Liu.Novel modified fuzzy c-means algorithm with applications.Digital Signal Processing,2009,2:309～319
[29]Roelof K. Brouwer, Albert Groenwold.Modified fuzzy c-means for ordinal valued attributes with particle swarm for optimization.Fuzzy Sets and Systems,2010,13:1776～1777
[30]S R Kannan, S Ramathilagam, A Sathya, R Pandiyarajan. Effective fuzzy c-means based kernel function in segmenting medical images.Computers in Biology and Medicine, 2010,6:573
[31]张飞,王贵林,殷跃,孙江,孙家驹.煤自燃发火综合防治方法研究.煤,2011(1)：21
[32]孔宪法.煤矿监测监控系统应用的研究.华章,2011(09)：269
[33]罗海珠,梁运涛.煤自然发火预测预报技术的现状与展望.中国安全科学学报,2003,(03)：76
[34]阮殿旭,唐大放,张晓光,刘旭东.Zigbee技术无线传感器网络在煤矿井下环境监测中 的应用研究.煤矿机械,2008(6)：163
[35]王兰云,蒋曙光,邵昊,张卫清,邹力力,寇砾文.煤自燃过程中自氧化加速温度研究.煤炭学报,2011(06)：990
[36]马姗姗,钱建生,甄国清.煤矿安全监测层次型无线传感器网络拓扑结构设计.矿业安全与环保,2011(1)：34
[37]江海峰,甄阳清,傅毅.矿井无线传感器网络的网关设计.计算机工程,2009(3)：112
[38]邓军,李保霖,程方明,陈晓坤,靳玉萍.煤自燃特征信息的模糊聚类与模式识别.西安科技大学学报,2011(5)：505
[39]张辛亥,孙久政,陈晓坤,程方明,周金生,李庆军.基于指标气体的煤自燃预报人工神经网络专家系统研究.煤矿安全,2010(03)：10～11
[40]黄翰文,彭祥宇,刘学服,苏罗利.煤的自燃点及其影响因素考察.煤矿安全,2009(02)：65～66
[41]温冬伟,王平立,宋斌.基于W7100的以太网读卡器的设计与实现.电子设计工程,2011(9)：182
[42]WIZnet Co,Inc. Internet embedded MCU W7100A [EB/OL].www.wiznet.co.kr,2009
[2]屈剑锋.无线传感器网络数据融合与目标跟踪研究及其应用.重庆大学,2009：28
[3]Huifang Chen, Hiroshi Mineno, Tadanori Mizuno.Adaptive data aggregation scheme in clustered wireless sensor networks.Computer Communications,2008,15:3579-3585
[4]L Necchi, A Bonivento, L Lavagno, A Sangiovanni Vincentelli, L Vanzago.E2RINA:an Energy Efficient and Reliable In-Network Aggregation for Clustered Wireless Sensor Networks.Wireless Communications and Networking Conference,2007:3366～3370
[5]Soonmok Kwon, Jae Hoon Ko, Jeongkyu Kim, Cheeha Kim.Dynamic timeout for data aggregation in wireless sensor networks.Computer Networks,2011,3:650-664
[6]Pei Wang,Yuan He,Liusheng Huang.Near optimal scheduling of data aggregation in wireless sensor networks.Ad Hoc Networks,2011,13:1～9
[7]Suat Ozdemir,Yang Xiao.Secure data aggregation in wireless sensor networks.Computer Networks,2009,12:2022～2033
[8]Wen-Hwa Liao,Yucheng Kao,Chien-Ming Fan.Data aggregation in wireless sensornetworks using ant colony algorithm.Journal of Network and Computer Applications.2008,31:387～401
[9]陈正宇,杨庚,陈蕾,许建.无线传感器网络数据融合研究综述.计算机应用研究,2011(05)：1601～1602
[10]沈江,王粟,徐曼.多传感器动态数据融合自适应控制系统.组合机床与自动化加工技术,2006(12)：48～50
[11]柴毅,屈剑锋,郭茂耘,尹宏鹏.分布式传感器网络在线自适应数据融合算法研究.自动化及先进集成技术大会论文集(一),2007：129～134
[12]陈敏,王擘,李军华.无线传感器网络原理与实践.第1版.北京：化学工业出版社,2011
[13]赵腾.无线传感网节能技术研究.中小企业管理与科技(下旬刊),2011(7)：271
[14]Jennifer Yick,Biswanath Mukherjee,Dipak Ghosal.Wireless sensor network survey.Computer Networks,2008,12:2292
[15]Giuseppe Anastasi,Marco Conti,Mario Di Francesco,Andrea Passarella.Energy conservation in wireless sensor networks:A survey.Ad Hoc Networks,2009,3:537
[16]Julien Happich.Ambient electromagnetic energy harvesting drives small electronic devices.EE Times.http://www.eet-china.com/,2011
[17]Jelena Misic.ZigBee:A long way to go?.R&D/Technology,2007,3,:33
[18]Chao SHA, Ru-chuan WANG, Hai-ping HUANG, Li-juan SUN.Energy efficient clustering algorithm for data aggregation in wireless sensor networks.The Journal of China Universities of Posts and Telecommunications,2010,17:104～105
[19]Giuseppe Anastasi, Marco Conti, Mario Di Francesco, Andrea Passarella.Energy conservation in wireless sensor networks.Ad Hoc Networks,2009,3:537～539
[20]宋晓君,孙洪伟.多传感器数据融合技术方法探究.华章,2011(07)：282
[21]尚海昆K-means聚类算法的研究.华北电力大学(河北),2009：5
[22]胡晓庆.模糊聚类中若干问题的研究.南京航空航天大学,2011：5
[23]A B Goktepe,S Altun,A Sezer.Soil clustering by fuzzy c-means algorithm.Advances in Engineering Software,2005,10:692
[24]George E Tsekouras, Haralambos Sarimveis.A new approach for measuring the validity of the fuzzy c-means algorithm.Advances in Engineering Software,2004,9:568
[25]Z Hou, W Qian, S Huang, Q Hu, W L Nowinski.Regularized fuzzy c-means method for brain tissue clustering.Pattern Recognition Letters,2007,13:1789
[26]Jesus Lazaro, Jagoba Arias, Jose L Martin, Carlos Cuadrado, Armando Astarloa.Implementation of a modified Fuzzy C-Means clustering algorithm for real-time applications.Microprocessors and Microsystems,2005,8:376
[27]Chenglong Tang, Shigang Wang, Wei Xu.New fuzzy c-means clustering model based on the data weighted approach.Data & Knowledge Engineering,2010,9:881～900
[28]Jiayin Kang, Lequan Min, Qingxian Luan, Xiao Li, Jinzhu Liu.Novel modified fuzzy c-means algorithm with applications.Digital Signal Processing,2009,2:309～319
[29]Roelof K. Brouwer, Albert Groenwold.Modified fuzzy c-means for ordinal valued attributes with particle swarm for optimization.Fuzzy Sets and Systems,2010,13:1776～1777
[30]S R Kannan, S Ramathilagam, A Sathya, R Pandiyarajan. Effective fuzzy c-means based kernel function in segmenting medical images.Computers in Biology and Medicine, 2010,6:573
[31]张飞,王贵林,殷跃,孙江,孙家驹.煤自燃发火综合防治方法研究.煤,2011(1)：21
[32]孔宪法.煤矿监测监控系统应用的研究.华章,2011(09)：269
[33]罗海珠,梁运涛.煤自然发火预测预报技术的现状与展望.中国安全科学学报,2003,(03)：76
[34]阮殿旭,唐大放,张晓光,刘旭东.Zigbee技术无线传感器网络在煤矿井下环境监测中 的应用研究.煤矿机械,2008(6)：163
[35]王兰云,蒋曙光,邵昊,张卫清,邹力力,寇砾文.煤自燃过程中自氧化加速温度研究.煤炭学报,2011(06)：990
[36]马姗姗,钱建生,甄国清.煤矿安全监测层次型无线传感器网络拓扑结构设计.矿业安全与环保,2011(1)：34
[37]江海峰,甄阳清,傅毅.矿井无线传感器网络的网关设计.计算机工程,2009(3)：112
[38]邓军,李保霖,程方明,陈晓坤,靳玉萍.煤自燃特征信息的模糊聚类与模式识别.西安科技大学学报,2011(5)：505
[39]张辛亥,孙久政,陈晓坤,程方明,周金生,李庆军.基于指标气体的煤自燃预报人工神经网络专家系统研究.煤矿安全,2010(03)：10～11
[40]黄翰文,彭祥宇,刘学服,苏罗利.煤的自燃点及其影响因素考察.煤矿安全,2009(02)：65～66
[41]温冬伟,王平立,宋斌.基于W7100的以太网读卡器的设计与实现.电子设计工程,2011(9)：182
[42]WIZnet Co,Inc. Internet embedded MCU W7100A [EB/OL].www.wiznet.co.kr,2009