摘要
根据桥梁挠度的各成分的特性,建立温度和温度挠度效应的非线性关系。为了提高温度挠度效应的拟合能力,提出多最小二乘支持向量机(M-LS-SVM)拟合模型,通过减聚类方法将输入空间划分为一些小的局部空间,在每个局部空间中用LS-SVM建立子模型。为解决子模型相互之间的严重相关问题,提高模型的精度和鲁棒性,各个子模型的预测输出通过主元递归(PCR)方法连接。实验和分析结果表明:该方法能分离挠度监测信号中的温度效应,为从长期监测信号中进行损伤识别提供基础数据。
According to the characteristics various components of bridge deflection,the non-linear relationship between temperature and temperature deflection effect was established.In order to improve the regressive ability to fit the temperature deflection effect, a multiple least square support vector machine （M-LS-SVM） regressive model was presented.The subtractive clustering was adopted to divide the input space into several sub-spaces,and sub-models were built by LS-SVM in each sub-space.In order to minimize the severe correlation among sub-models and to improve the accuracy and robustness of the model,the sub-models were combined by the method of principal components regression （PCR）.The experimental and analytical results show that the method can separate the temperature effect from monitoring signals of deflection and provide basis data for damage detection from long-term monitoring signals.
出处
《振动与冲击》
EI
CSCD
北大核心
2014年第1期71-76,88,共7页
Journal of Vibration and Shock
基金
国家自然科学基金面上项目(51078093)
广东省科技计划项目(2011B010300026)
关键词
多最小二乘支持向量机
温度
温度挠度效应
分离
multiple least square support vector machine
temperature
deflection temperature effect
separation
