Earthquake destructive power prediction device and method based on recurrent neural network
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TSINGHUA UNIV
- Publication Date
- 2020-02-11
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of civil structural engineering and the technical field of disaster prevention and reduction, in particular to a device and method for predicting earthquake destructive force based on a cyclic neural network. Background technique
[0002] Earthquake disaster is an important security threat faced by buildings and one of the most serious casualties among various natural disasters. It is a factor that must be considered in building design and organizing personnel evacuation. When an earthquake disaster comes, it is of great significance to accurately and timely understand the earthquake damage suffered by the target area for organizing personnel evacuation and rescue and disaster relief. At present, there are two main ways to obtain earthquake destructive power: one is through field investigation or nonlinear time-history analysis, which is accurate but inefficient, and does not meet the real-time requirements of emergen...