A foundation pit deformation space-time evolution prediction and support parameter reverse optimization system and method
By constructing a prior random field and Bayesian compressed sensing inversion, combined with a deep Gaussian process and covariance matrix adaptive evolution strategy, the foundation pit support parameters were optimized, solving the problem of uncontrollable deformation exceeding probability in complex strata and achieving improvements in safety and adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANCHANG TRANSPORTATION COLLEGE
- Filing Date
- 2026-05-09
- Publication Date
- 2026-07-24
AI Technical Summary
Existing technologies cannot quantify the impact of geological uncertainties on the deformation response of foundation pits under complex geological conditions with significant spatial variability in soil and rock parameters, resulting in an uncontrollable probability of deformation exceeding limits in actual construction when the combination of support parameters is combined.
By collecting sparse borehole geotechnical parameters and continuous in-situ test data, a prior random field is constructed. Bayesian compressed sensing is used for sparse observation inversion to generate a posterior probability distribution. A nonlinear mapping function is constructed using a deep Gaussian process, and an adaptive evolution strategy based on the covariance matrix is used for inverse search to optimize the support parameters.
It effectively characterizes the spatial variability of soil parameters, quantifies geological uncertainties, and the optimized combination of support parameters can meet the deformation control threshold with a high probability under abnormal geological conditions, thereby improving the safety and adaptability of foundation pit engineering and shortening the design cycle.
Smart Images

Figure CN122154049B_ABST