基于数据融合的张弦桁架多位置损伤识别与抗噪性分析

Multi-position damage identification and anti-noise analysis of cable-stayed arch-truss based on data fusion

为提高张弦桁架多位置损伤识别的准确性,将数据融合方法与损伤识别指标相结合,采用D-S证据矩阵理论融合叠加曲率模态改变率和模态柔度差曲率两项指标的损伤识别结果,提出了张弦桁架多损伤的单次融合和两阶段融合识别方法。以某实际工程缩尺简化得到的张弦桁架作为研究对象,设计了两种不同的多损伤工况,通过有限元分析获取了结构损伤前后的前三阶模态数据,并进行了损伤识别分析。结果表明:基于数据融合的多损伤识别方法能够准确地识别张弦桁架多损伤,其能够综合两种单指标的识别结果,降低甚至消除非损伤位置的干扰,有效解决了单指标识别精度低、不能全面反映损伤位置的问题;两阶段融合方法通过两次融合逐步降低了非损伤位置的干扰,识别效果优于单次融合方法。此外,分析中考虑了不同水平噪声对张弦桁架多损伤识别的影响,结果表明:基于数据融合的多损伤识别方法具有较好的抗噪能力,能够降低噪声和非损伤位置的干扰,且两阶段融合方法的抗噪能力优于单次融合方法。

In order to improve the accuracy of multi-position damage identification of cable-stayed arch-truss,the data fusion method and damage identification index was combined. D-S evidence matrix theory was used to fuse the identification results of superposition curvature mode and modal flexibility difference curvature,and the single fusion and two-stage fusion recognition methods for multi-position damage of cable-stayed arch-truss were proposed. Two kinds of multi-position damage conditions were designed for a cable-stayed arch-truss which is simplified by the scale reduction of an actual project. The first-three modal data before and after the structural damage were obtained through the finite element analysis,and the damage identification analysis was carried out. The results show that the multiposition damage identification method based on data fusion can realize accurate judgment of the multiple damaged position. It can integrate the identification results of the two damage identification indexes,reduce or even eliminate the interference of the non-damage position. It can effectively solve the problem of low accuracy and inability to fully reflect the damage position of single damage identification index. The two-stage fusion method gradually reduces the interference of the non-damaged position through two fusions,and the recognition effect is better than single fusion method. Besides,the influence of different levels of noise on the multi-position damage identification of cable-stayed arch-truss was considered. The results show that the multi-position damage identification method based on data fusion has good anti-noise ability,which can reduce the interference of noise and non-damaged position,and the anti-noise ability of the two-stage fusion method is better than that of the single fusion method.