摘要(Abstract):
为了提高结构损伤定量和定位的准确率,提出基于移动主成分分析与集成学习的结构损伤识别方法;利用移动主成分分析对原始应变响应数据进行特征分析,得到包含损伤信息的第一、第二特征向量,将两者相结合所得的组合特征向量作为损伤指标输入集成学习模型,进行结构损伤程度和损伤位置预测;采用双跨平面梁的仿真应变监测数据,对所提出的结构损伤识别方法的有效性进行验证,对比分别以第一、第二、组合特征向量作为输入的分类模型的损伤定量和定位的准确率。结果表明:在一定强度的噪声条件下,组合特征向量能同时具备第一、第二特征向量的优点,并且能克服单个特征向量的局限,获得优异的损伤识别性能和抗噪性;在信噪比为40 dB的弱噪声情况下,将组合特征向量输入集成学习模型进行损伤定量和定位,准确率分别可达98.9%、 99.0%,在信噪比为10 dB的强噪声情况下准确率仍分别可达82.3%、 73.2%。
关键词(KeyWords): 结构健康监测;损伤识别;移动主成分分析;集成学习;组合特征向量
基金项目(Foundation): 国家自然科学基金项目(11972162);; 中国博士后科学基金项目(2021M700886)
作者(Author): 周颖,刘泽佳,张舸,周立成,刘逸平,汤立群,蒋震宇,杨宝
DOI: 10.13349/j.cnki.jdxbn.20221103.002
参考文献(References):
[1] 刘沐宇,袁卫国.桥梁无损检测技术的研究现状与发展[J].中外公路,2002,22(6):34-37.
[2] 李惠,鲍跃全,李顺龙,等.结构健康监测数据科学与工程[J].工程力学,2015,32(8):1-7.
[3] YAN A M,KERSCHEN G,DE BOE P,et al.Structural damage diagnosis under varying environmental conditions:part II:local PCA for non-linear cases[J].Mechanical Systems and Signal Processing,2005,19(4):865-880.
[4] POSENATO D,LANATA F,INAUDI D,et al.Model-free data interpretation for continuous monitoring of complex structures[J].Advanced Engineering Informatics,2008,22(1):135-144.
[5] CAVADAS F,SMITH I F C,FIGUEIRAS J.Damage detection using data-driven methods applied to moving-load responses[J].Mechanical Systems and Signal Processing,2013,39(1/2):409-425.
[6] LAORY I,TRINH T N,SMITH I F C.Evaluating two model-free data interpretation methods for measurements that are influenced by temperature[J].Advanced Engineering Informatics,2011,25(3):495-506.
[7] ZHANG G,TANG L,LIU Z,et al.Machine-learning-based damage identification methods with features derived from moving principal component analysis[J].Mechanics of Advanced Materials and Structures,2020,27(21):1789-1802.
[8] ZHU Y,NI Y Q,JIN H,et al.A temperature-driven MPCA method for structural anomaly detection[J].Engineering Structures,2019,190:447-458.
[9] 聂振华,杨卫星,程良彦,等.联合移动主成分分析与传递熵的桥梁损伤识别方法[J].振动工程学报,2020,33(5):1062-1072.
[10] POSENATO D,KRIPAKARAN P,INAUDI D,et al.Methodologies for model-free data interpretation of civil engineering structures[J].Computers & Structures,2010,88(7/8):467-482.
[11] COVER T,HART P.Nearest neighbor pattern classification[J].IEEE Transactions on Information Theory,1953,13(1):21-27.
[12] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.
[13] FRIEDMAN J H.Greedy function approximation:a gradient boosting machine[J].Annals of Statistics,2001,29(5):1189-1232.
[14] CHEN T Q,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//KDD’ 16:The 22nd ACM SIGKDD:International Conference on Knowledge Discovery and Data Mining,August 13-17,2016,San Francisco,CA,USA.New York:ACM,2016:785-794.