Mixed-Input Bayesian Optimization Method for Structural Damage Diagnosis
Mixed-Input Bayesian Optimization Method for Structural Damage Diagnosis
复制标题
结构损伤诊断的混合输入贝叶斯优化方法
DOI：
10.1109/tr.2022.3179602
复制
发表时间：
2023-06
影响因子：
5.9
通讯作者：
Congfang Huang;Jaesung Lee;Yang Zhang;Shiyu Zhou;Jiong Tang
中科院分区：
文献类型：
--
作者：
Congfang Huang;Jaesung Lee;Yang Zhang;Shiyu Zhou;Jiong Tang
结构健康监测对于保证工程系统的耐久性和可靠性具有重要意义。在这篇文章中，我们介绍了贝叶斯优化方法使用多输出高斯过程来解决结构故障诊断问题。该方法利用结构的高保真度有限元模型（FE）和来自结构的阻抗/导纳测量来识别损伤的位置和严重程度。该方法采用多输出高斯过程作为有限元全模型的代理模型，并采用Thompson抽样方法指导贝叶斯优化中的结构损伤搜索，提高了损伤诊断的准确性。给出了详细的算法，并对算法的收敛性进行了分析.将该方法应用于模拟合成函数，与传统的混合输入优化方法相比，取得了更好的性能和更快的收敛速度。然后，我们将我们的方法应用于一个真实的世界的结构损伤识别问题，使用测量的压电导纳数据，并说明所提出的方法的有效性。
Structural health monitoring (SHM) is of significant importance in the operation of engineering systems to ensure the durability and reliability. In this article, we introduce a Bayesian optimization method using a multioutput Gaussian process to solve the structural fault diagnosis problem. This method utilizes a high fidelity finite element model (FE) of the structure and the impedance/admittance measurements from the structure to identify the location and severity of the damage. The method improves the accuracy of the damage diagnosis by adopting a multioutput Gaussian process as the surrogate model for the full FE model and Thompson sampling approach is used to guide the search for the structural damage in the Bayesian optimization. The detailed algorithms are presented, and the convergence analysis of the method is conducted. We apply our proposed method on simulated synthetic functions and it achieves better performance and higher convergence speed than the traditional mixed input optimization methods. We then apply our method on a real world structural damage identification problem using measured piezoelectric admittance data and illustrate the effectiveness of the proposed method.