WK-LS-SVM结构损伤模式识别方法的性能分析
|
摘要
基于小波核函数最小二乘支持向量机方法(WK-LS-SVM)的研究成果,对WK-LS-SVM方法的抗噪声能力和适用性进行了分析。对10层框架结构的25种损伤工况进行了数值模拟,结果表明WK-LS-SVM方法具有良好的抗噪声能力。对不同结构相同损伤等级的自振频率进行分析,发现两者的自振频率变化率具有相似性,因此用某结构参数训练的支持向量机识别结构参数与之差异不大的结构的损伤情况,其识别误差小。因此实际工程中用简化估计的结构参数来识别损伤能满足工程精度要求。
Based on the achievement in research on wavelet kernel funclion-least square-support vector machine(WK-LS-SVM) method,the anti-noise capability and adaptability of the method were analyzed.In this paper,25 typical damage conditions in a ten-storey frame structure were simulated.The results show that WK-LS SVM has a good anti-noise capacity.Further,the natural frequencies of different structures with same damage level were examined.The similarity of the change rate of natural frequencies was discovered.It shows that using supported vector machine trained with certain structural parameters to identify the damage level of similar structures is feasible and the induced error is small.Hence,identifying damage level of structure with simplified structure parameter estimation in practical engineering can satisfy engineering accuracy demand.
Based on the achievement in research on wavelet kernel funclion-least square-support vector machine(WK-LS-SVM) method,the anti-noise capability and adaptability of the method were analyzed.In this paper,25 typical damage conditions in a ten-storey frame structure were simulated.The results show that WK-LS SVM has a good anti-noise capacity.Further,the natural frequencies of different structures with same damage level were examined.The similarity of the change rate of natural frequencies was discovered.It shows that using supported vector machine trained with certain structural parameters to identify the damage level of similar structures is feasible and the induced error is small.Hence,identifying damage level of structure with simplified structure parameter estimation in practical engineering can satisfy engineering accuracy demand.
引文
[1]王术新,姜哲.基于结构振动损伤识别技术的研究现状及进展[J].振动与冲击,2004,23(4):99-102.Wang Shuxin,Jiang zhe.Present developing situation and research advances in the field of structural damage detection[J].Journal of Vibrationand Shock,2004,23(4):99-102.
[2]LiY,Mau ST.Learning from recorded earthquakemotion of buildings[J].Journal of structural Engineering,1997,123(1):62-69.
[3]尚久铨.从地震记录识别结构参数[J].世界地震工程,1989(3):18-27.SHANG Jiuquan.Identification of structural parameters from earthquake record[J].Orld Earthquake Engineering,1989(3):18-27.
[4]CATBAS F N,BROWN D L,AKTAN A E.Use of Modal Flexibility for Damage Detection and Condition Assessment:Case Studies and Demonstra-tions on Large Structures[J].Journal of Structural Engineer-ing,2006,132(11):1699-1712.
[5]邰扣霞,丁大钧.中国桥梁建设新飞跃[J].建筑科学与工程学报,2006,23(2):30-40.TAI Kou-xia,DING Da-jun.New Leaps in Construc-tion of Bridges in China[J].Journal of Architecture and Civil Engineering,2006,23(2):30-40.
[6]KIM J T,STUBBS N.Improved Damage Identifica-tion Method Based on Modal Information[J].Journalof Sound and Vibration,2002,252(2):223-238.
[7]姜绍飞,杨博,党永勤.易损性分析在结构抗震及健康监测中的应用[J].建筑科学与工程学报,2008,25(2):15-23.JIANG Shao-fei,YANG Bo,DANG Yong-qin.Appli-cation of Vulnerability Analysis in Structural Seism and Health Monitoring[J].Journalof Architecture and Civil Engineering,2008,25(2):15-23.
[8]赵昕,贾京,郑毅敏.基于BP神经网络的大跨高空连廊应变监测数据恢复[J].建筑科学与工程学报,2009,26(1):101-106.ZHAOXin,JIA Jing,ZHENG Yi-min.Strain Monito-ring Data Restoring of Large-span Steel Skybridge Based on BP Neural Network[J].Journal ofArchitec-ture and Civil Engineering,2009,26(1):101-106.
[9]张茂雨,陈联盟,杨克家,陈跃.结构损伤模式识别与试验分析[J].自然灾害学报,2010,19(4):89-94.ZHANG Maoyu,CHEN Lianmeng,YANG Kejia,CHEN Yue.Pattern identification and test analysis of structural damage[J].Journal of NaturalDisasters,2009,26(1):101-106.
[10]张茂雨.支持向量机方法在结构损伤识别中的应用[D].上海:同济大学,2007.ZHANG Maoyu.The Application of Support Vector Machine Method to Structural Damage Identification[D].Shanghai:Tongji University,2007.
[2]LiY,Mau ST.Learning from recorded earthquakemotion of buildings[J].Journal of structural Engineering,1997,123(1):62-69.
[3]尚久铨.从地震记录识别结构参数[J].世界地震工程,1989(3):18-27.SHANG Jiuquan.Identification of structural parameters from earthquake record[J].Orld Earthquake Engineering,1989(3):18-27.
[4]CATBAS F N,BROWN D L,AKTAN A E.Use of Modal Flexibility for Damage Detection and Condition Assessment:Case Studies and Demonstra-tions on Large Structures[J].Journal of Structural Engineer-ing,2006,132(11):1699-1712.
[5]邰扣霞,丁大钧.中国桥梁建设新飞跃[J].建筑科学与工程学报,2006,23(2):30-40.TAI Kou-xia,DING Da-jun.New Leaps in Construc-tion of Bridges in China[J].Journal of Architecture and Civil Engineering,2006,23(2):30-40.
[6]KIM J T,STUBBS N.Improved Damage Identifica-tion Method Based on Modal Information[J].Journalof Sound and Vibration,2002,252(2):223-238.
[7]姜绍飞,杨博,党永勤.易损性分析在结构抗震及健康监测中的应用[J].建筑科学与工程学报,2008,25(2):15-23.JIANG Shao-fei,YANG Bo,DANG Yong-qin.Appli-cation of Vulnerability Analysis in Structural Seism and Health Monitoring[J].Journalof Architecture and Civil Engineering,2008,25(2):15-23.
[8]赵昕,贾京,郑毅敏.基于BP神经网络的大跨高空连廊应变监测数据恢复[J].建筑科学与工程学报,2009,26(1):101-106.ZHAOXin,JIA Jing,ZHENG Yi-min.Strain Monito-ring Data Restoring of Large-span Steel Skybridge Based on BP Neural Network[J].Journal ofArchitec-ture and Civil Engineering,2009,26(1):101-106.
[9]张茂雨,陈联盟,杨克家,陈跃.结构损伤模式识别与试验分析[J].自然灾害学报,2010,19(4):89-94.ZHANG Maoyu,CHEN Lianmeng,YANG Kejia,CHEN Yue.Pattern identification and test analysis of structural damage[J].Journal of NaturalDisasters,2009,26(1):101-106.
[10]张茂雨.支持向量机方法在结构损伤识别中的应用[D].上海:同济大学,2007.ZHANG Maoyu.The Application of Support Vector Machine Method to Structural Damage Identification[D].Shanghai:Tongji University,2007.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心