Bridge damage identification method based on neural network
A neural network and damage recognition technology, applied in biological neural network models, character and pattern recognition, special data processing applications, etc., can solve the problem of low damage recognition accuracy, and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0193] Embodiment 1 of the present invention: the bridge damage identification method based on neural network, comprises the following steps:
[0194] S1, constructing sample data: use the general finite element calculation software ANSYS to establish a solid finite element model of the whole bridge, obtain the simulated strain data of the bridge in good condition and under different damage conditions, and use the strain change rate as the sample data of the BP neural network; The strain rate of change is: Among them, ε uj is the strain data of the jth position in the undamaged condition, ε sj is the strain data of the jth position under the damage condition; the described acquisition of the simulated strain data under the intact and different damage conditions of the bridge includes: using ANSYS software to analyze the model, and utilizing the Block Lanczos method to extract the natural frequency under the undamaged condition The modal shape of frequency and frequency, sel...
Embodiment 2
[0200] Embodiment 2: the bridge damage identification method based on neural network, comprises the following steps:
[0201] S1, Constructing sample data: Using the finite element method to build a bridge model refers to using the general finite element calculation software ANSYS to build a solid finite element model of the whole bridge; use ANSYS software to analyze the model, and use the Block Lanczos method to extract the inherent Frequency and frequency mode shape, select the damage location according to the size of the modal displacement in the mode shape and the installation position of the actual bridge sensor; use the method of reducing the elastic modulus to simulate different degrees of damage at different positions, that is, the damage location Different degrees of damage can be obtained by modifying the elastic modulus of the material at the location; then use the *get command in the APDL language to extract the strain data of different degrees of damage at differe...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com