基于本征正交分解和卡尔曼滤波的结构损伤识别  

Structural damage identification based on proper orthogonal decomposition and Kalman filter

作　　者：杨少冲[1] 姚远 张凯 宋康宁 刘家亮 靳佳林 马连华 方有亮[1] YANG Shaochong;YAO Yuan;ZHANG Kai;SONG Kangning;LIU Jialiang;JIN Jialin;MA Lianhua;FANG Youliang(College of Civil Engineering and Architecture,Hebei University,Baoding 071002,China;School of Quality and Technical Supervision,Hebei University,Baoding 071002,China)

机构地区：[1]河北大学建筑工程学院,河北保定071002 [2]河北大学质量技术监督学院,河北保定071002

出　　处：《振动与冲击》2023年第18期304-312,共9页Journal of Vibration and Shock

基　　金：国家自然科学基金(12172117)。

摘　　要：目前已有损伤识别方法难以实现对结构的实时、准确地健康监测,针对这一问题发展了一种基于本征正交分解(proper orthogonal decomposition,POD)与卡尔曼滤波(Kalman filter,KF)相结合的POD-KF方法,对动载荷作用下的结构损伤识别进行了研究。该方法利用KF方法在线更新降阶模型的子空间,解决未知载荷作用下多自由度结构动力分析计算量大且难以收敛的问题,仅利用结构响应实时跟踪损伤的演化并对其进行定位,不需要耗时的再训练阶段;并以六层剪切型框架为例开展了数值模拟研究,验证了所发展理论与数值算法的有效性,结果表明所提出的方法在减少计算量的同时,能够保证较高的精度,有效地识别出剪切型建筑结构损伤的位置和严重程度,且能够有效抑制响应信号中的噪声,同时在处理微小损伤时仍具有较高的精度。At present,existing damage identification methods are still difficult to realize real-time and accurate health monitoring of structures.To solve this problem,a POD-KF method based on proper orthogonal decomposition(POD)and Kalman filter(KF)was developed.The structural damage identification method under dynamic loading was studied.In the method,Kalman filter was used to update on line the subspace of the reduced order model to solve the problems of large computation and low convergency in the dynamic analysis of multiple degrees of freedom structures under unknown loads.Only the response of the structure was used to track the evolution of the damage and locate it in real time,without the time-consuming retraining phase.The effectiveness of the proposed theory and the proposed algorithm was verified by the numerical simulation of a six-story shear frame structure.The results show that the proposed method can not only reduce the amount of calculation,but also guarantee high accuracy,effectively identify the location and severity of damage in the shear frame structure and effectively suppress the noise in the response signal.At the same time,it still has high precision in dealing with the case of slight degree of damage.

关 键 词：损伤识别 本征正交分解 卡尔曼滤波 数据驱动 健康监测 

分 类 号：TU312.3[建筑科学—结构工程]