Application of Parameter Inversion of HSS Model Based on BP Neural Network Optimized by Genetic Algorithm in Foundation Pit Engineering
Open Access
Abstract
The hardening soil model with small-strain stiffness (HSS model) is widely applied in deep foundation pit engineering in coastal soft-soil areas, yet it is characterized by a multitude of parameters that are relatively cumbersome to acquire. In this study, we incorporate a genetic algorithm and a back-propagation neural network (BPNN) model into an inversion analysis for HSS model parameters, with the objective of facilitating a more streamlined and accurate determination of these parameters in practical engineering. Utilizing horizontal displacement monitoring data from retaining structures, combined with local engineering, both a BPNN model and a BPNN optimized by a genetic algorithm (GA-BPNN) model were established to invert the stiffness modulus parameters of the HSS model for typical strata. Subsequently, numerical simulations were conducted based on the inverted parameters to analyze the deformation characteristics of the retaining structures. The performances of the BPNN and GA-BPNN models were evaluated using statistical metrics, including R2, MAE, MSE, WI, VAF, RAE, RRSE, and MAPE. The results demonstrate that the GA-BPNN model achieves significantly lower prediction errors, higher fitting accuracy, and predictive performance compared to the BPNN model. Based on the parameters inverted by the GA-BPNN model, the average compression modulus , the reference tangent stiffness modulus , the reference secant stiffness modulus , and the reference unloading–reloading stiffness modulus for gravelly cohesive soil were determined as and ; for fully weathered granite, and . Numerical simulations conducted with these stiffness modulus parameters show excellent agreement with monitoring data, effectively describing the deformation characteristics of the retaining structures. In situations where relevant mechanical tests are unavailable, the application of the GA-BPNN model for the inversion analysis of HSS model parameters is both rational and effective, offering a reference for similar engineering projects.
Keywords
Funding Information
- Sichuan Provincial Natural Science Foundation Project (2024NSFSC0975)
This publication has 11 references indexed in Scilit:
- Exploring the Potential of Machine Learning in Stochastic Reliability Modelling for Reinforced Soil FoundationsBuildings, 2024
- Application of soil parameter inversion method based on BP neural network in foundation pit deformation predictionApplied Geophysics, 2023
- Smart prediction of liquefaction-induced lateral spreadingJournal of Rock Mechanics and Geotechnical Engineering, 2023
- Analysis on intelligent deformation prediction of deep foundation pits with internal support based on optical fiber monitoring and the HSS modelFrontiers in Materials, 2023
- Prediction of the Mechanical Properties of Basalt Fiber Reinforced High-Performance Concrete Using Machine Learning TechniquesMaterials, 2022
- Comprehensive preference learning and feature validity for designing energy-efficient residential buildings using machine learning paradigmsApplied Soft Computing, 2019
- Predicting compressive strength of lightweight foamed concrete using extreme learning machine modelAdvances in Engineering Software, 2018
- Small‐strain stiffness in geotechnical analysesBautechnik, 2009
- The strength and dilatancy of sandsGéotechnique, 1986
- Soil moduli and damping factors for dynamic response analysisJournal of Terramechanics, 1972