A shallow foundation bearing capacity calculation method fusing machine learning and non-local algorithm
By integrating machine learning and nonlocal algorithms, combined with finite element simulation and triaxial experiments, the influence range and softening rate parameters are calibrated, solving the deviation problem in bearing capacity calculation in traditional methods, and realizing efficient and low-cost bearing capacity prediction.
Patent Information
- Application Number
- CN202510556486.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-29
- Publication Date
- 2026-02-17
- Estimated Expiration
- 2045-04-29
AI Technical Summary
Traditional geotechnical engineering methods for calculating the bearing capacity of shallow foundations are based on the theory of elastic half-space, which leads to large deviations between the calculated results and the actual situation. Furthermore, the values of nonlocal algorithm parameters affect the residual state of the load-displacement curve, making it impossible to obtain reasonable predicted values of the foundation bearing capacity.
By integrating machine learning and nonlocal algorithms, the influence range and softening rate control parameters are calibrated through indoor triaxial experiments. Machine learning technology is used to enhance efficiency and achieve efficient inversion of nonlocal parameters. Combined with finite element simulation, reasonable load-bearing capacity prediction values are obtained.
It solves the problem of the influence of nonlocal parameter values, realizes efficient and low-cost bearing capacity prediction, takes into account the bearing capacity prediction of hardened foundation soil, and reduces manpower and economic costs.