Improved ga-bpnn-based soft soil shield tunnel stability prediction method
By improving the GA-BPNN model and combining orthogonal experiments and finite element numerical simulation, the accuracy and efficiency problems of parameter inversion and stability prediction for soft soil shield tunnels were solved, achieving efficient parameter updating and prediction and ensuring construction safety.
CN120354704BActive Publication Date: 2026-06-09CHINA RAILWAY NO 2 ENG GROUP CO LTD +4
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA RAILWAY NO 2 ENG GROUP CO LTD
- Filing Date
- 2025-03-19
- Publication Date
- 2026-06-09
AI Technical Summary
Technical Problem
Existing technologies cannot effectively solve the accuracy and efficiency problems of parameter inversion and stability prediction for shield tunnels in soft soil, and they also consume a lot of computational resources.
Method used
An improved genetic algorithm and backpropagation neural network (GA-BPNN) model are used, combined with orthogonal experimental design and finite element numerical simulation, to update formation parameters through inversion analysis, thereby improving the accuracy of parameter inversion and prediction.
Benefits of technology
It significantly improves the accuracy and efficiency of parameter inversion and stability prediction for soft soil shield tunnels, providing theoretical and practical support for construction safety.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN120354704B_ABST
Abstract
The application belongs to the technical field of soft soil shield tunnel stability prediction, and specifically discloses a soft soil shield tunnel stability prediction method based on improved GA-BPNN, which comprises the following steps: determining initial stratum parameters, and generating multiple sets of stratum parameter combinations by using an orthogonal test method; inputting the multiple sets of stratum parameter combinations into a finite element model to output tunnel settlement under different parameter combinations, and then constructing an improved GA-BPNN model; performing inversion analysis on the stratum parameters based on actual monitoring data and the improved GA-BPNN model to obtain updated stratum parameters; and predicting the settlement of the soft soil shield tunnel based on the updated stratum parameters and the improved GA-BPNN model, and evaluating the long-term stability of the soft soil shield tunnel according to the prediction result. The application solves the problems that the prior art cannot guarantee the accuracy and efficiency of parameter inversion and stability prediction of the soft soil shield tunnel, and the large consumption of computing resources.
Need to check novelty before this filing date? Find Prior Art