AI Site Liquefaction Evaluation Using Dominant Frequency Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for site seismic performance evaluation do not effectively consider the decline and recovery of site performance during and after an earthquake, and the pre-existing methods fail to accurately predict the site performance, and the pre-existing methods fail to accurately predict the site performance during and after an earthquake.
Innovation Solution
A rapid evaluation method using artificial intelligence to analyze seismic data from seismic stations, establishing a historical database, and using a neural network model to predict site seismic liquefaction hazards, including dominant frequency prediction and damage assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If on-site surveys are adopted for evaluation of site seismic liquefaction hazards, then the evaluation can be conducted, but the investigations are carried out after the earthquake and cannot reflect real-time changes in site properties
Solution Approach 1:
The patent collects and processes seismic data from seismic stations in real-time before and during earthquakes, establishing a database of site response characteristics in advance. This preliminary action enables the system to evaluate site seismic liquefaction hazards proactively rather than reactively after earthquakes occur, resolving the timing limitation of traditional post-earthquake survey methods
Solution Approach 2:
The patent implements a feedback mechanism where seismic data from seismic stations is continuously monitored and used to update the evaluation model. The system compares real-time seismic responses with historical data to detect changes in site properties, providing continuous feedback on site condition evolution and enabling dynamic adjustment of hazard assessments
2Productivity
If empirical models are established to evaluate earthquake hazards based on historical earthquake surveys, then the evaluation can be performed, but the data points contain wide variety of soil properties and the evaluation outcome is often conservative and does not reflect actual site conditions
Solution Approach 1:
The patent transitions from using broad empirical models with diverse soil properties to site-specific evaluation based on seismic data from local seismic stations. By analyzing the actual seismic response characteristics of each specific site, the system captures local soil property variations and site conditions, eliminating the conservatism inherent in generalized empirical approaches
Solution Approach 2:
The patent replaces traditional empirical evaluation methods with an artificial intelligence-based system that processes seismic data. This substitution uses machine learning algorithms to analyze complex seismic signals and predict site seismic liquefaction hazards, achieving higher accuracy and efficiency compared to conventional empirical models
3Device complexity
If pre-existing on-site survey results are used as the basis for evaluation, then the evaluation process is simplified, but the method fails to consider the decline and recovery of site performance during and after earthquakes
Solution Approach 1:
The patent implements continuous monitoring of site performance through real-time seismic data collection from seismic stations. The system continuously evaluates site conditions before, during, and after earthquakes, capturing the dynamic decline and recovery of site performance. This continuous action replaces static pre-existing survey data, ensuring reliable assessment of evolving site conditions without requiring complex manual re-surveying
Data Source
AI summary
Disclosed in the present disclosure is a fast evaluation method of site seismic liquefaction hazard based on artificial intelligence algorithm: establishing a historical seismic and site information database, the database including a demand input module, a web crawler module, a data processing module, and a database module connected in sequence; a neural network model performs prediction to acquire a post-earthquake site dominant frequency; and, on the basis of the post-earthquake site dominant frequency, acquiring a site earthquake damage degree and seismic performance parameters. The present disclosure solves the problem of fast evaluating post-earthquake site earthquake damage and site seismic performance parameters, and can rapidly evaluate the site liquefaction or softening earthquake damage degree and site seismic performance parameters in given earthquake conditions.