基于多源信息融合的复杂系统安全监测及诊断方法研究
|
摘要
资源、环境、生态及重大工程等复杂系统所涌现出的安全问题对人类的生存安全和社会经济发展构成巨大的威胁,因此如何对这类复杂系统进行安全诊断与预测维护是一个极其重要而有意义的课题。在本文中,基于多源信息融合及智能计算理论,结合输变电系统及水电站坝体两个应用范例,建立适用于复杂系统安全监测及诊断的信息融合理论功能模型,对多源信息融合机理、智能诊断技术以及安全监测系统设计等进行了研究,为相关部门的灾害预测与防治提供支持。
取得的主要研究成果如下:
(1)在数据融合级异常值识别与突变特征提取研究中,结合某水电站坝体的形变监测具体应用,提出了基于BP神经网络的异常值识别算法。与现有的异常值识别算法相比较,该算法从监测量产生的物理机理模型出发,融合了多个传感器的监测数据,可以区别异常值中存在的野值和突变,而且对于孤立型和斑点型异常值均可较好的识别。
(2)在特征融合级复杂系统灾变条件特征提取研究中,结合某输变电系统覆冰监测的具体应用,提出了基于自组织图的复杂系统灾变条件特征提取算法,实现了在特征融合级对输电线覆冰的形成和增长的气象条件特征进行了提取,其结果有助于在决策融合级利用微观气象信息对输变电系统的安全态势进行估计。
(3)以某水电站坝体安全监测系统开发为应用背景,针对中小型电站及水库坝体安全监测的特点和需求,对传统的应用于大坝安全监测的软件系统结构进行适当的调整,设计了面向中小型水坝安全监测软件系统,对软件系统的调整使得开发周期和开发成本大为减少,较适用于中小型水坝的安全监测系统的设计和开发。
Complex systems, such as resource, environment, ecology and great engineering, have come forth many safety problems, which seriously threaten the subsistence and development of human being. So it is an important and significant problem that how to monitor and diagnose the safety of complex system. In this paper, based on multi-source information fusion and combined two complications about power transmission system and hydropower station dam safety monitoring, an information fusion functional model, which is suitable for complex systems safety monitoring and diagnosing, has been established. Research on multi-source information fusion mechanism, intelligence diagnosing technology and safety monitoring system designing, for which can provide theory and technology for disaster prediction and preventive treatment to related departments.
The achievements which have got are as follows:
(1)Practicing in the hydropower station dam displacement monitoring, an algorithm based on BP neural network is presented. Comparing with the existing outlier identifying algorithm, this algorithm take the advantage of the mechanism model of the dam monitoring data conformation, and fuse many data from sensors,it can identify outlier and mutation exist in unusual data and can well identify both patch-type outliers and isolated outliers.
(2)Practicing in the power transmission lines system monitoring, an algorithm based on Kohonen Self-Organizing Map is presented to extract the disaster features of the complex system. In feature fusion level, for power transmission lines icing and its increasing, the extract of the feature is achieved. The results are helpful for using meteorology features to estimate the safety situation of the power transmission lines system in decision-making level.
(3)On the background of developing a dam safety monitoring system, aiming at small-or-medium reservoirs safety monitoring feature and demands , adjust the traditional structure of software system which apply to the dam safety monitoring and design the safety monitoring system which is suitable for the small-or-medium reservoirs. Adjusting the software system makes the system development cycle short and cost decreased and it’s more suitable for small-or-medium reservoirs safety monitoring.
取得的主要研究成果如下:
(1)在数据融合级异常值识别与突变特征提取研究中,结合某水电站坝体的形变监测具体应用,提出了基于BP神经网络的异常值识别算法。与现有的异常值识别算法相比较,该算法从监测量产生的物理机理模型出发,融合了多个传感器的监测数据,可以区别异常值中存在的野值和突变,而且对于孤立型和斑点型异常值均可较好的识别。
(2)在特征融合级复杂系统灾变条件特征提取研究中,结合某输变电系统覆冰监测的具体应用,提出了基于自组织图的复杂系统灾变条件特征提取算法,实现了在特征融合级对输电线覆冰的形成和增长的气象条件特征进行了提取,其结果有助于在决策融合级利用微观气象信息对输变电系统的安全态势进行估计。
(3)以某水电站坝体安全监测系统开发为应用背景,针对中小型电站及水库坝体安全监测的特点和需求,对传统的应用于大坝安全监测的软件系统结构进行适当的调整,设计了面向中小型水坝安全监测软件系统,对软件系统的调整使得开发周期和开发成本大为减少,较适用于中小型水坝的安全监测系统的设计和开发。
Complex systems, such as resource, environment, ecology and great engineering, have come forth many safety problems, which seriously threaten the subsistence and development of human being. So it is an important and significant problem that how to monitor and diagnose the safety of complex system. In this paper, based on multi-source information fusion and combined two complications about power transmission system and hydropower station dam safety monitoring, an information fusion functional model, which is suitable for complex systems safety monitoring and diagnosing, has been established. Research on multi-source information fusion mechanism, intelligence diagnosing technology and safety monitoring system designing, for which can provide theory and technology for disaster prediction and preventive treatment to related departments.
The achievements which have got are as follows:
(1)Practicing in the hydropower station dam displacement monitoring, an algorithm based on BP neural network is presented. Comparing with the existing outlier identifying algorithm, this algorithm take the advantage of the mechanism model of the dam monitoring data conformation, and fuse many data from sensors,it can identify outlier and mutation exist in unusual data and can well identify both patch-type outliers and isolated outliers.
(2)Practicing in the power transmission lines system monitoring, an algorithm based on Kohonen Self-Organizing Map is presented to extract the disaster features of the complex system. In feature fusion level, for power transmission lines icing and its increasing, the extract of the feature is achieved. The results are helpful for using meteorology features to estimate the safety situation of the power transmission lines system in decision-making level.
(3)On the background of developing a dam safety monitoring system, aiming at small-or-medium reservoirs safety monitoring feature and demands , adjust the traditional structure of software system which apply to the dam safety monitoring and design the safety monitoring system which is suitable for the small-or-medium reservoirs. Adjusting the software system makes the system development cycle short and cost decreased and it’s more suitable for small-or-medium reservoirs safety monitoring.
引文
[1]张宗亮.超高面板堆石坝监测信息管理与安全评价理论方法研究[D].天津:天津大学,2008.
[2]林韩等.电网防灾减灾应急管理系统建设与应用[M].北京:国防工业出版社,2009.
[3]Paul A.Longley,Michael F.Goodchild,David J.Maguire,David W.Rhind.Geographical Information system(Volume 1) [M].北京:电子工业出版社,2004.
[4]李德仁.地球空间信息学及在陆地科学中的应用[J].自然杂志,2006,27(6).
[5]岳建平,方露,黎昵.变形监测理论与技术研究进展[J].测绘通报,2007,(7).
[6]李德仁,关泽群.空间信息系统的集成与实现[M].武汉:武汉测绘科技大学出版社, 2000.
[7]欧阳莹之.复杂系统理论基础[M].上海:上海科技教育出版社, 2002.
[8]向衍.高坝坝体与复杂坝基互馈的力学行为及其分析理论[D].南京:河海大学,2004.
[9]黄声亭,尹辉,蒋征.变形监测数据处理[M].武汉:武汉大学出版社,2003.
[10]Zhao Erfeng, Jin Yongqiang. Dam Deformation Monitoring Model and Forecast Based on Hierarchical Diagonal Neural Network. Proceedings of the 7th World Congress on Intelligent Controland Automation,2008.
[11]宋智宇.基于智能计算的大坝安全监测方法研究[D].大连:大连理工大学, 2007.
[12]Gertler J .Survey of model based failure detection and isolation in complex plants[J]. IEEE Control Systems Magazine, 1998.
[13]韩崇昭,朱洪艳,段战胜.多源信息融合[M].北京:清华大学出版社,2006.
[14]赵宗贵.信息融合技术现状、概念与结构模型[J].中国电子科学研究院学报,2006,1(4):305-312.
[15]徐波,于劲松,李行善.复杂系统的智能故障诊断[J].信息与控制,2004,33(1).
[16]孙庆先等.地理空间数据的尺度问题及其研究进展.地理与地理信息科学,2007,23(4).
[17]岳建平,田林亚.变形监测技术与应用[M].北京:国防工业出版社,2007.
[18]Fang HuaJing,Ye Hao,Zhong MaiYing.Fault diagnosis of networked control system,Annual Reviews in Control,2007,31(1):55～68.
[19] Zhengguo Xu Yindong Ji Donghua Zhou. A New Real-Time Reliability Prediction Method for Dynamic Systems Based on On-Line Fault Prediction [J]. IEEE Transactions on Reability,2009.Vol. 58,NO.3:523～538.
[20]中国科学技术协会主编.2007-2008控制科学与工程科学发展报告[M].北京:中国科技出版设,2007:116-121.
[21] Anon. The design, construction and performance of concrete faced rockfill dams[J]. International Journal on Hydropower and Dams, 2000,7(6):56～60.
[22] Yao Y Y.Granular computing.basic issues and possible solutions.In Proc.of the 5th Joint Conf.on Information Sciences,Volume I,Atlantic City,New Jersey,USA, February 27’March 3,2000
[23]Zadeh I.A. Fuzzy Logic Computing with Words[J].IEEE Trans.on Fuzzy Systems, 1996(2): 1O3-111.
[24]温熙森.模式识别与状态监控[M].北京:科学出版社,2007.
[25] Laurent Peyras, Paul Royet. Dam ageing diagnosis and risk analysis: Development of methods to support expert judgment[J]. Can. Geotech. J. 2006, 43(8):169～186.
[26] Anon. The design, construction and performance of concrete faced rockfill dams[J]. International Journal on Hydropower and Dams, 2000,7(6):56～60.
[27] Stopinski,Wojciech. Bedrock monitoring by means of the electric receptivity method during the construction and operation of the Czorsztyn-Niedzica dam[J]. Acta Geophysica Polonica,2003,51(2):215～226.
[28]Xinmiao Wu, Zhihong Qie, Hongquan Liu. Dam’s Safety Monitoring Statistical Model Optimization Basing on The GA and AIC. Proceedings of the 6th World Congress on Intelligent Controland Automation,2006,7856～7859.
[29] Virginia Gewin. Mapping Opportunies[J]. Nature, 2004,427:376-377.
[30]David L.Hall James Llinas.Handbook of Multisensor Data Fusion[M]. CRC Press LLC, 2001.
[31]何友,王国宏等.多传感器信息融合及应用[M].北京:电子工业出版社,2007.
[32]权太范等.信息融合神经网络-模糊推理理论与应用[M].北京:国防工业出版社,2001.
[33]王仲生.智能诊断与容错控制[M].西安:西北工业大学出版社,2005.
[34]林育梁.岩土与结构工程中不确定性问题及其分析方法[M].北京:科学出版社,2009.
[35]黄铭.数学模型与工程安全监测[M].上海:上海交通大学出版社,2008.
[36]王正明,易东云.测量数据建模与参数估计[M].长沙:国防科技大学出版社,1996.
[37]张文博,李凯,朱尤攀,等.光电稳定跟踪平台中微机电陀螺滤波方法研究[J].红外技术,2006,28(5):249-252.
[38]沈一鹰,冉启文,刘永坦.改进的格拉布斯准则在信号检测门限估值中的应用[J].哈尔滨工业大学学报,1999,31(3):111-113.
[39]卓宁.靶场外弹道数据处理中野值点剔出方法[J].测试技术学报,2008,22(4):313-317.
[40]梁桂兰,徐卫亚,谈小龙,刘大文,蔡德文.岩石高边坡安全监测数据的小波变换去噪处理[J].岩石力学与工程学报,2008,27,(9):1837-1844.
[41]刘成栋,马福恒,戴群.野值诊断技术在大坝安全监测资料分析中的应用[J].岩土工程学报,2008,30,(11):1726-1728.
[42]张婷,汪渤.连续型野值判别的新方法[J].东南大学学报(自然科学版),2005,35(增刊):621-623.
[43]苏怀智.大坝安全监控感智融合理论和方法及其应用研究[D].南京:河海大学,2002.
[44] Mallat S.A Theory of Multiresolution Signal Decomposition:The Wavelet Transform[J].IEEE Trans On Pattern Machine Intelligence,1989,11(7):674-693.
[45]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[46] Chen-Chia Chuang,Jin-Tsong Jengl. CPBUM neural networks for modeling with outliers and noise[J].Applied Soft Computing,2007,(7):957-967.
[47] C.C.Chuang,S.F.Su,C.C.Hsiao,The annealing robust backpropagation(ARBP) learning algorithm,IEEE Trans.Neural Networks,2000,5(11):1067-1077.
[48] Tsuking H.Extraction Rules for trained Neural Networks.IEEE Trans NN, 2000, 11(2):377-389.
[49]周宏仁,敬忠良,王培德.机动目标跟踪[M].北京:国防工业出版社,1991.
[50] JIANG Xin-liang, YI hui . Protection and icing of transmission lines. Beijing: China electric power press ,2002 .
[51] HUAN Xin-bo. Monitoring online and fault diagnosis of transmission lines. Beijing: China electric power press ,2008 .
[52] Lasse Makkonen. Modeling Power Line Icing in Freeing Precipitation.Atmospheric Research,46,131-142,1998.
[53] Irene Y.H. Gu, Unai Sistiaga, Sonja M. Berlijn, Intelligent video surveillance for detecting snow and Ice coverage on electrical insulators of power transmission lines Computer Analysis of Images and Patterns - 13th International Conference CAIP 2009.
[54] Zhang J. Improved on-line process fault diagnosis throughinformation fusion in multiple neuralnetworks. Computersand Chemical Engineering, 2006, 30(3): 558~571.
[55] Rajakarunakaran S, Venkat P, Devaraj D, Surya P R K.Articial neural network approach for fault detection in LPG transfer system. Applied Soft Computing, 2008, 8(1):740~748.
[56]Quteishat A, Lim C P. A modified fuzzy min-max neuralnetwork with rule extraction and its application to fault detection and classication. Applied Soft Computing, 2008,8(2): 985~995.
[57] Kohonen T, Simula O, Visa A. Engineering Applications of the Self-organizing Map. IEEE Trans Processor,84(10),1358~1384,1996.
[58] Rabee Rustum and Adebayo J. Adeloye. Replacing Outliers and Missing Values from Activated Sludge Data Using Kohonen Self-Organizing Map. Journal of Environmental Engineering, 909~916,2007.
[59]李永江.土石坝安全监测技术及安全监控理论研究进展[J].水利水电科技进展,2006, 26(5):73-77.
[60]李季,陆声鸿,郭晨.李家峡水电站大坝安全监测自动化系统[J].水力发电,2005,2005(6):63-65.
[61]王启宁,杜刚,姜景捷.基于ARM的海底大地电磁信号采集系统主控模块改进[J].计算机应用,2005,31(1):17-21.
[62]李学桥,陈晓雷,郭功兵,李淑君.基于ARM的远程数据采集系统的设计与实现[J].仪表技术与传感器,2004,2004(2):29-34.
[2]林韩等.电网防灾减灾应急管理系统建设与应用[M].北京:国防工业出版社,2009.
[3]Paul A.Longley,Michael F.Goodchild,David J.Maguire,David W.Rhind.Geographical Information system(Volume 1) [M].北京:电子工业出版社,2004.
[4]李德仁.地球空间信息学及在陆地科学中的应用[J].自然杂志,2006,27(6).
[5]岳建平,方露,黎昵.变形监测理论与技术研究进展[J].测绘通报,2007,(7).
[6]李德仁,关泽群.空间信息系统的集成与实现[M].武汉:武汉测绘科技大学出版社, 2000.
[7]欧阳莹之.复杂系统理论基础[M].上海:上海科技教育出版社, 2002.
[8]向衍.高坝坝体与复杂坝基互馈的力学行为及其分析理论[D].南京:河海大学,2004.
[9]黄声亭,尹辉,蒋征.变形监测数据处理[M].武汉:武汉大学出版社,2003.
[10]Zhao Erfeng, Jin Yongqiang. Dam Deformation Monitoring Model and Forecast Based on Hierarchical Diagonal Neural Network. Proceedings of the 7th World Congress on Intelligent Controland Automation,2008.
[11]宋智宇.基于智能计算的大坝安全监测方法研究[D].大连:大连理工大学, 2007.
[12]Gertler J .Survey of model based failure detection and isolation in complex plants[J]. IEEE Control Systems Magazine, 1998.
[13]韩崇昭,朱洪艳,段战胜.多源信息融合[M].北京:清华大学出版社,2006.
[14]赵宗贵.信息融合技术现状、概念与结构模型[J].中国电子科学研究院学报,2006,1(4):305-312.
[15]徐波,于劲松,李行善.复杂系统的智能故障诊断[J].信息与控制,2004,33(1).
[16]孙庆先等.地理空间数据的尺度问题及其研究进展.地理与地理信息科学,2007,23(4).
[17]岳建平,田林亚.变形监测技术与应用[M].北京:国防工业出版社,2007.
[18]Fang HuaJing,Ye Hao,Zhong MaiYing.Fault diagnosis of networked control system,Annual Reviews in Control,2007,31(1):55～68.
[19] Zhengguo Xu Yindong Ji Donghua Zhou. A New Real-Time Reliability Prediction Method for Dynamic Systems Based on On-Line Fault Prediction [J]. IEEE Transactions on Reability,2009.Vol. 58,NO.3:523～538.
[20]中国科学技术协会主编.2007-2008控制科学与工程科学发展报告[M].北京:中国科技出版设,2007:116-121.
[21] Anon. The design, construction and performance of concrete faced rockfill dams[J]. International Journal on Hydropower and Dams, 2000,7(6):56～60.
[22] Yao Y Y.Granular computing.basic issues and possible solutions.In Proc.of the 5th Joint Conf.on Information Sciences,Volume I,Atlantic City,New Jersey,USA, February 27’March 3,2000
[23]Zadeh I.A. Fuzzy Logic Computing with Words[J].IEEE Trans.on Fuzzy Systems, 1996(2): 1O3-111.
[24]温熙森.模式识别与状态监控[M].北京:科学出版社,2007.
[25] Laurent Peyras, Paul Royet. Dam ageing diagnosis and risk analysis: Development of methods to support expert judgment[J]. Can. Geotech. J. 2006, 43(8):169～186.
[26] Anon. The design, construction and performance of concrete faced rockfill dams[J]. International Journal on Hydropower and Dams, 2000,7(6):56～60.
[27] Stopinski,Wojciech. Bedrock monitoring by means of the electric receptivity method during the construction and operation of the Czorsztyn-Niedzica dam[J]. Acta Geophysica Polonica,2003,51(2):215～226.
[28]Xinmiao Wu, Zhihong Qie, Hongquan Liu. Dam’s Safety Monitoring Statistical Model Optimization Basing on The GA and AIC. Proceedings of the 6th World Congress on Intelligent Controland Automation,2006,7856～7859.
[29] Virginia Gewin. Mapping Opportunies[J]. Nature, 2004,427:376-377.
[30]David L.Hall James Llinas.Handbook of Multisensor Data Fusion[M]. CRC Press LLC, 2001.
[31]何友,王国宏等.多传感器信息融合及应用[M].北京:电子工业出版社,2007.
[32]权太范等.信息融合神经网络-模糊推理理论与应用[M].北京:国防工业出版社,2001.
[33]王仲生.智能诊断与容错控制[M].西安:西北工业大学出版社,2005.
[34]林育梁.岩土与结构工程中不确定性问题及其分析方法[M].北京:科学出版社,2009.
[35]黄铭.数学模型与工程安全监测[M].上海:上海交通大学出版社,2008.
[36]王正明,易东云.测量数据建模与参数估计[M].长沙:国防科技大学出版社,1996.
[37]张文博,李凯,朱尤攀,等.光电稳定跟踪平台中微机电陀螺滤波方法研究[J].红外技术,2006,28(5):249-252.
[38]沈一鹰,冉启文,刘永坦.改进的格拉布斯准则在信号检测门限估值中的应用[J].哈尔滨工业大学学报,1999,31(3):111-113.
[39]卓宁.靶场外弹道数据处理中野值点剔出方法[J].测试技术学报,2008,22(4):313-317.
[40]梁桂兰,徐卫亚,谈小龙,刘大文,蔡德文.岩石高边坡安全监测数据的小波变换去噪处理[J].岩石力学与工程学报,2008,27,(9):1837-1844.
[41]刘成栋,马福恒,戴群.野值诊断技术在大坝安全监测资料分析中的应用[J].岩土工程学报,2008,30,(11):1726-1728.
[42]张婷,汪渤.连续型野值判别的新方法[J].东南大学学报(自然科学版),2005,35(增刊):621-623.
[43]苏怀智.大坝安全监控感智融合理论和方法及其应用研究[D].南京:河海大学,2002.
[44] Mallat S.A Theory of Multiresolution Signal Decomposition:The Wavelet Transform[J].IEEE Trans On Pattern Machine Intelligence,1989,11(7):674-693.
[45]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[46] Chen-Chia Chuang,Jin-Tsong Jengl. CPBUM neural networks for modeling with outliers and noise[J].Applied Soft Computing,2007,(7):957-967.
[47] C.C.Chuang,S.F.Su,C.C.Hsiao,The annealing robust backpropagation(ARBP) learning algorithm,IEEE Trans.Neural Networks,2000,5(11):1067-1077.
[48] Tsuking H.Extraction Rules for trained Neural Networks.IEEE Trans NN, 2000, 11(2):377-389.
[49]周宏仁,敬忠良,王培德.机动目标跟踪[M].北京:国防工业出版社,1991.
[50] JIANG Xin-liang, YI hui . Protection and icing of transmission lines. Beijing: China electric power press ,2002 .
[51] HUAN Xin-bo. Monitoring online and fault diagnosis of transmission lines. Beijing: China electric power press ,2008 .
[52] Lasse Makkonen. Modeling Power Line Icing in Freeing Precipitation.Atmospheric Research,46,131-142,1998.
[53] Irene Y.H. Gu, Unai Sistiaga, Sonja M. Berlijn, Intelligent video surveillance for detecting snow and Ice coverage on electrical insulators of power transmission lines Computer Analysis of Images and Patterns - 13th International Conference CAIP 2009.
[54] Zhang J. Improved on-line process fault diagnosis throughinformation fusion in multiple neuralnetworks. Computersand Chemical Engineering, 2006, 30(3): 558~571.
[55] Rajakarunakaran S, Venkat P, Devaraj D, Surya P R K.Articial neural network approach for fault detection in LPG transfer system. Applied Soft Computing, 2008, 8(1):740~748.
[56]Quteishat A, Lim C P. A modified fuzzy min-max neuralnetwork with rule extraction and its application to fault detection and classication. Applied Soft Computing, 2008,8(2): 985~995.
[57] Kohonen T, Simula O, Visa A. Engineering Applications of the Self-organizing Map. IEEE Trans Processor,84(10),1358~1384,1996.
[58] Rabee Rustum and Adebayo J. Adeloye. Replacing Outliers and Missing Values from Activated Sludge Data Using Kohonen Self-Organizing Map. Journal of Environmental Engineering, 909~916,2007.
[59]李永江.土石坝安全监测技术及安全监控理论研究进展[J].水利水电科技进展,2006, 26(5):73-77.
[60]李季,陆声鸿,郭晨.李家峡水电站大坝安全监测自动化系统[J].水力发电,2005,2005(6):63-65.
[61]王启宁,杜刚,姜景捷.基于ARM的海底大地电磁信号采集系统主控模块改进[J].计算机应用,2005,31(1):17-21.
[62]李学桥,陈晓雷,郭功兵,李淑君.基于ARM的远程数据采集系统的设计与实现[J].仪表技术与传感器,2004,2004(2):29-34.