A Substructure-based Model Updating Method to Damage Detection for Large-scale Structures

The health monitoring and damage detection of structures are major scientific issues that the civil engineering discipline, which made great achievements in the 20th century, has bequeathed to the 21st century. Despite the installation of health monitoring systems in many large structures, implementing damage detection through finite element model updating is often time-consuming or even infeasible due to the size of the model and the presence of numerous uncertain parameters. To address this issue, this paper proposes a substructure-based model updating method. The entire structure is divided into substructures with reduced degrees of freedom, allowing for the simplification of the motion equation by employing only a small number of low-order modes from each substructure. Consequently, the analysis scale of the structure is effectively reduced. The discarded higher modes are compensated by residual modes to ensure the accuracy of structural response and sensitivity. Subsequently, a damage identification program substructurebased model updating is developed, which is applied to component mode synthesis and damage identification for large structures. By precisely detecting damage in critical areas, accurate diagnosis and evaluation of the global structural safety are achieved. The results validate the implementation, computational efficiency, and accuracy of the proposed substructure-based model updating method. This approach shifts the focus from model updating of the entire structure to model updating of substructures, with the aim of fundamentally resolving the technical challenge of accurate damage detection of large and complex structures. Furthermore, it provides theoretical support for the practical application of damage detection in large civil structures.