Prediction method of surface deformation due to construction based on least square support vector machine
A technology of support vector machine and least squares, which is applied in the prediction of surface deformation caused by construction and the prediction of shield construction, can solve the problems of oversimplification and poor engineering application effect, and achieve the effect of low calculation cost and high efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] Please refer to the attached figure 1 As shown, the present invention is a method for predicting surface deformation caused by construction based on least squares support vector machine, which includes the following steps:
[0024] (1) Collect sample data for surface deformation prediction
[0025] Eight variables are taken as the input variables, including the buried depth of the tunnel, the standard penetration value of the overburden of the vault, the pressure of the soil bin, the propulsion speed, the thrust, the torque, the rotating speed of the cutterhead, and the amount of grouting, and the two variables of the maximum deformation value of the surface and the width of the settlement trough are used as the output. Variables, arrange the values of the above-mentioned variables on different test sections to form a sample data set; wherein, the sample data is specifically the data of the shield tunneling (initial) excavation stage;
[0026] (2), establish a traini...
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