基于多维度手段的构件滞回曲线预测方法、终端及介质
By constructing a dataset and training an intelligent proxy model using multi-dimensional methods, the problems of large initial stiffness prediction error and low computational efficiency of DS-SCB were solved. This enabled high-fidelity dynamic response tracking and performance evaluation of displacement amplification mechanisms, thereby improving structural safety and seismic performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEFEI UNIV OF TECH
- Filing Date
- 2026-05-18
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional analytical models have large errors in predicting the initial stiffness of displacement-enlarged slope friction self-resetting braces (DS-SCB), low numerical simulation efficiency, and lack of physical self-consistency in purely data-driven models. This makes it impossible to accurately balance displacement control and floor acceleration response during the design phase, thus affecting structural safety.
Using multi-dimensional methods, a simulated dataset is constructed by combining numerical simulation with a parameterized sampling strategy. An intelligent data proxy model is trained to capture the nonlinear characteristics of initial slip and progressive contact caused by manufacturing errors. Ridge regression algorithm is introduced for linear smoothing weighting and residual repair. By combining the mechanical equilibrium and deformation coordination relationship, the hysteresis curves are reconstructed over the entire displacement range.
It improves the accuracy and computational efficiency of the initial stiffness prediction of DS-SCB components, enhances the reliability of dynamic energy dissipation tracking and overall seismic performance assessment, significantly reduces the deviation between theoretical values and actual mechanical behavior, and provides a more valuable basis for performance assessment.
Smart Images
Figure CN122197662B_ABST