基于支持向量机的大型输电铁塔损伤识别方法研究
|
摘要
输电铁塔在电力的传输上占有重要地位,一旦发生损伤破坏将造成严重的经济损失.模态曲率改变率这一参数具有良好的损伤定位能力,通过对某500kV输电铁塔的损伤位置识别,即使是在诸如1%等微小损伤条件下,仍能取得良好的效果.作为一种新兴的机器学习算法,支持向量机在损伤识别中已显示出其回归能力的优越性.本文提出了利用最小二乘支持向量机进行大型输电铁塔的损伤程度识别方法,通过对某500kV输电铁塔的损伤程度进行识别,发现该方法在较少的样本条件下,亦能非常逼近目标值,具有精确的损伤程度识别能力.
Transmission tower occupies an important position in the event of transmission of electricity.The failure of transmission tower would pose serious economic losses.As a damage identification parameter,variation ratio of curvature mode has a great ability to damage location.In the field of damage location identification on transmission tower of 500kV, variation ratio of curvature mode achieved good results even in the condition of tiny damage such as 1%.Support vector machine,as new machine learning algorithm,has shown its superiority of the ability of regression in the fields of damage identification.In this paper,the method of least squares support vector machine was applied to study on the damage extent identification of transmission tower of 500kV.It was found that this method could extremely approach the targets even under the condition of little sample and it had accurate ability of damage extent identification.
Transmission tower occupies an important position in the event of transmission of electricity.The failure of transmission tower would pose serious economic losses.As a damage identification parameter,variation ratio of curvature mode has a great ability to damage location.In the field of damage location identification on transmission tower of 500kV, variation ratio of curvature mode achieved good results even in the condition of tiny damage such as 1%.Support vector machine,as new machine learning algorithm,has shown its superiority of the ability of regression in the fields of damage identification.In this paper,the method of least squares support vector machine was applied to study on the damage extent identification of transmission tower of 500kV.It was found that this method could extremely approach the targets even under the condition of little sample and it had accurate ability of damage extent identification.
引文
[1]郭慧勇,李正良.基于模态应变能与频率信息修正的结构多损伤识别研究[J].应用基础与工程科学学报, 2008,16(5):719-725 Guo Huiyong,Li Zhengliang.An improved information method based on modal strain energy and frequency for structural multiple damage identification[J].Journal of Basic Science and Engineering,2008,16(5):719-725
[2]Alberto Escobar J,Jesu's Sosa J,Roberto Go'mez.Structural damage detection using the transformation matrix[J]. Computers and Structures,2005,83(4/5):357-368
[3]Fang X,Luo H,Tang J.Structural damage detection using neural network with learning rate improvement[J]. Computers and Structures,2005,83(25/26):2150-2161
[4]Jong Jae Lee,Jong Won Lee,Jin Hak Yia,et al.Neural networks-based damage detection for bridges considering errors in baseline finite element models[J].Journal of Sound and Vibration,2005,280(3-5):555-578
[5]刘春城,徐健,刘向阳,等.基于神经网络的大型输电铁塔损伤识别研究[J].华东电力,2009,37(2):257-260 Liu Chuncheng,Xu Jian,Liu Xiangyang,et al.Damage identification of electricity transmission towers based on neural network[J].East China Electric Power,2009,37(2):257-260
[6]娄文娟,林宝龙.基于小波变换的大型输电铁塔损伤位置识别[J].工程力学,2006,23(增刊Ⅰ):157-162 Lou Wenjuan,Lin Baolong.Wavelet transform based method for detecting damge lodation of electricity transmission towers[J].Engineering Mechanics,2006,23(supplementⅠ):157-162
[7]高柏峰,李慧剑,刘艳霞.格构式塔结构刚度突变处损伤识别方法[J].应用基础与工程科学学报,2009,17 (2):309-316 Gao Baifeng,Li Huijian,Liu Yanxia.Damage identification for stiffness mutation position of lattice tower structure [J].Journal of Basic Science and Engineering,2009,17(2):309-316
[8]冯立芳.小波和神经网络相结合的结构损伤识别方法[D].杭州:浙江大学,2006 Feng Lifang.The method combining wavelet and neural network to identify structure damage[D].Hangzhou:Zhejiang University,2006
[9]Vapnik V.张学工译.统计学习理论的本质[M].北京:清华大学出版社,2004 Vapnik V.Zhang Xuegong translation.The nature of statistical learning theory[M].Beijing:Tsinghua University Press,2004
[10]苏怀智,温志萍,吴中如.基于SVM理论的大坝安全预警模型研究[J].应用基础与工程科学学报,2009,17 (1):40-48 Su Huaizhi,Wen Zhiping,Wu Zhongru.An early-warning model of dam safety based on SVM theory[J].Journal of Basic Science and Engineering,2009,17(1):40-48
[11]李忠献,齐怀展,朱劲松.基于模态曲率法的大跨度斜拉桥损伤识别[J].地震工程与工程振动,2007,27(4): 122-126 Li Zhongxian,Qi Huaizhan,Zhu Jinsong.Damage identification for long-span cable-stayed bridge baaed on medal curvature method[J].Journal of Earthquake Engineering and Engineering Vibration,2007,27(4):122-126
[12]王成强,陈怀海,姜双燕,等.基于转角模态曲率的损伤识别研究[J].海军航空工程学院学报,2009,24(3): 251-254 Wang Chengqiang,Chen Huaihai,Jiang Shuangyan,et al.Research on the damage identification based on rotational mode shape curvature[J].loumal of naval Aeronautical Engineering Institute,2009,24(3):251-254
[13]Nello Cristianini,John Shawe-Taylor.An introduction to support vector machines and other kernel-based learning methods[M].Cambridge University Press,2000
[14]金伟良,袁雪霞.基于LS-SVM的结构可靠度响应面分析方法[J].浙江大学学报(工学版),2007,1:44-47 Jin Weiliang,Yuan Xuexia.Response surface method based on LS-SVM for structural rehability analysis[J].Journal of Zhejiang University(Engineering Science),2007,1:44-47
[15]Fletcher R.Practical method of optimization,John Wiley and Sons:Chichester and New York,1987
[16]刘龙,孟光.基于曲率模态和支持向量机的结构损伤位置两步识别方法[J].工程力学,2006,23(增刊I):35- 39 Liu Long,Meng Guang.A Two-step approach to identification damage location based on curvature modal parameters and support vector machine[J].Engineering Mechanics,2006,23(supplement I):35-39
[2]Alberto Escobar J,Jesu's Sosa J,Roberto Go'mez.Structural damage detection using the transformation matrix[J]. Computers and Structures,2005,83(4/5):357-368
[3]Fang X,Luo H,Tang J.Structural damage detection using neural network with learning rate improvement[J]. Computers and Structures,2005,83(25/26):2150-2161
[4]Jong Jae Lee,Jong Won Lee,Jin Hak Yia,et al.Neural networks-based damage detection for bridges considering errors in baseline finite element models[J].Journal of Sound and Vibration,2005,280(3-5):555-578
[5]刘春城,徐健,刘向阳,等.基于神经网络的大型输电铁塔损伤识别研究[J].华东电力,2009,37(2):257-260 Liu Chuncheng,Xu Jian,Liu Xiangyang,et al.Damage identification of electricity transmission towers based on neural network[J].East China Electric Power,2009,37(2):257-260
[6]娄文娟,林宝龙.基于小波变换的大型输电铁塔损伤位置识别[J].工程力学,2006,23(增刊Ⅰ):157-162 Lou Wenjuan,Lin Baolong.Wavelet transform based method for detecting damge lodation of electricity transmission towers[J].Engineering Mechanics,2006,23(supplementⅠ):157-162
[7]高柏峰,李慧剑,刘艳霞.格构式塔结构刚度突变处损伤识别方法[J].应用基础与工程科学学报,2009,17 (2):309-316 Gao Baifeng,Li Huijian,Liu Yanxia.Damage identification for stiffness mutation position of lattice tower structure [J].Journal of Basic Science and Engineering,2009,17(2):309-316
[8]冯立芳.小波和神经网络相结合的结构损伤识别方法[D].杭州:浙江大学,2006 Feng Lifang.The method combining wavelet and neural network to identify structure damage[D].Hangzhou:Zhejiang University,2006
[9]Vapnik V.张学工译.统计学习理论的本质[M].北京:清华大学出版社,2004 Vapnik V.Zhang Xuegong translation.The nature of statistical learning theory[M].Beijing:Tsinghua University Press,2004
[10]苏怀智,温志萍,吴中如.基于SVM理论的大坝安全预警模型研究[J].应用基础与工程科学学报,2009,17 (1):40-48 Su Huaizhi,Wen Zhiping,Wu Zhongru.An early-warning model of dam safety based on SVM theory[J].Journal of Basic Science and Engineering,2009,17(1):40-48
[11]李忠献,齐怀展,朱劲松.基于模态曲率法的大跨度斜拉桥损伤识别[J].地震工程与工程振动,2007,27(4): 122-126 Li Zhongxian,Qi Huaizhan,Zhu Jinsong.Damage identification for long-span cable-stayed bridge baaed on medal curvature method[J].Journal of Earthquake Engineering and Engineering Vibration,2007,27(4):122-126
[12]王成强,陈怀海,姜双燕,等.基于转角模态曲率的损伤识别研究[J].海军航空工程学院学报,2009,24(3): 251-254 Wang Chengqiang,Chen Huaihai,Jiang Shuangyan,et al.Research on the damage identification based on rotational mode shape curvature[J].loumal of naval Aeronautical Engineering Institute,2009,24(3):251-254
[13]Nello Cristianini,John Shawe-Taylor.An introduction to support vector machines and other kernel-based learning methods[M].Cambridge University Press,2000
[14]金伟良,袁雪霞.基于LS-SVM的结构可靠度响应面分析方法[J].浙江大学学报(工学版),2007,1:44-47 Jin Weiliang,Yuan Xuexia.Response surface method based on LS-SVM for structural rehability analysis[J].Journal of Zhejiang University(Engineering Science),2007,1:44-47
[15]Fletcher R.Practical method of optimization,John Wiley and Sons:Chichester and New York,1987
[16]刘龙,孟光.基于曲率模态和支持向量机的结构损伤位置两步识别方法[J].工程力学,2006,23(增刊I):35- 39 Liu Long,Meng Guang.A Two-step approach to identification damage location based on curvature modal parameters and support vector machine[J].Engineering Mechanics,2006,23(supplement I):35-39
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