一种基于联合神经网络的地震超材料预测设计方法
By employing a combined neural network-based earthquake metamaterial prediction and design method, utilizing the finite element method and deep learning models, the nonlinearity problem in earthquake metamaterial design was solved, generating low-frequency wide-bandgap materials, and achieving precise control of seismic waves and improved time efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING UNIV OF TECH
- Filing Date
- 2024-07-05
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to effectively control low-frequency seismic waves, and the highly nonlinear design of seismic metamaterials makes precise control of seismic waves difficult.
A seismic metamaterial prediction and design method based on joint neural networks is adopted. By using the finite element method and deep learning model, low-frequency wide-bandgap seismic metamaterials are generated, including the cascade training of UAE and DFN models. Combined with material parameter assignment and dispersion curve analysis, the reverse design of seismic metamaterials is realized.
It significantly shortens the design time, generates low-frequency, wide-bandgap seismic metamaterials that can effectively attenuate seismic waves, and has high design accuracy. The interdisciplinary approach has great potential in the design of seismic metamaterials.
Smart Images
Figure CN118692608B_ABST