Fast and efficient determination of the mechanicalparameters of surrounding rock masses is vitally important to the calculation and evaluation of the stability of surrounding rock masses in tunnel engineering. In thi...
详细信息
Fast and efficient determination of the mechanicalparameters of surrounding rock masses is vitally important to the calculation and evaluation of the stability of surrounding rock masses in tunnel engineering. In this paper, a displacement back-analysis (DBA) model is proposed to identify the mechanicalparameters based on support vector regression (SVR) optimized by multi-strategy artificial fish swarm algorithm (MAFSA). The MAFSA adopts the differential evolution strategy, the particle swarm optimization strategy, the adaptive step size and phased vision strategy on the basis of artificial fish swarm algorithm (AFSA) to enhance the global search capability and improve convergence speed and optimization accuracy. Then, the kernel width and the penalty parameter of SVR are optimized by MAFSA, forming into MAFSA-SVR. Meanwhile, the training and testing samples for MAFSA-SVR are constructed by orthogonal design and forward calculation by FLAC(3D) code. Finally, the DBA model is established based on MAFSA-SVR and applied to the mechanical parameter inversion of surrounding rock masses in the Heshi tunnel with the following conclusion: the relative errors of all the mechanicalparameters are less than 8% between the inversed values of the DBA model based on MAFSA-SVR and the actual values. The method proposed in this paper could provide an efficient tool for the mechanical parameter inversion of the tunnel surrounding rock masses.
Concrete dam mechanicalparameter identification remains a significant focus in dam engineering research. However, conventional inversion methods based on finite element modeling encounter challenges such as computati...
详细信息
Concrete dam mechanicalparameter identification remains a significant focus in dam engineering research. However, conventional inversion methods based on finite element modeling encounter challenges such as computational complexity and prolonged processing times. To address these issues and enhance computational efficiency and accuracy, we propose a novel fast and high-precision inversion method for concrete dam parameters combining ensemble learning and a multi-strategy improved meta-heuristic optimizer. Initially, hydrostatic component is extracted from measured displacement data, followed by the construction of a finite element model for the gravity dam. parameter sample sets are generated via the Latin hypercube sampling, and the corresponding hydrostatic displacement is obtained by substituting these sets into the finite element model (FEM). Subsequently, a correlation between the parameters and multi-point hydrostatic component is established by LGBM, replacing the direct finite element method. Finally, a fitness function is formulated between the surrogate model output and measured hydrostatic displacement, and meta-heuristic optimizer is employed to search for the optimal parameters. Engineering case studies verify the efficiency of the proposed method. Results demonstrate the consistency between the surrogate model and FEM calculations. Compared with other optimizers and surrogate models, proposed method exhibits faster convergence, higher accuracy, and reduced inversion time. The findings highlight that our optimized inversion method significantly enhances computational efficiency while maintaining accuracy, offering a straightforward and practical solution for real-world engineering applications.
To address the problem in which the mechanicalparameters of a dam's body and foundation are affected by a complex environment and changes during the service period, this study proposes an arch dam mechanical para...
详细信息
To address the problem in which the mechanicalparameters of a dam's body and foundation are affected by a complex environment and changes during the service period, this study proposes an arch dam mechanical parameter inversion technique based on the sensitivity analysis of the Morris method and the Hooke-Jeeves algorithm. First, a Kriging mathematical model that reflects the nonlinear mapping relationship between the radial displacement of an arch dam and the mechanicalparameters of an arch dam's body and foundation is established. The sensitivity of the mechanicalparameters of an arch dam and its foundation to the radial displacement of an arch dam is analyzed on the basis of the Morris method, and the mechanicalparameters to be inverted are determined. Second, an optimization mathematical model based on the Kriging mathematical model is proposed to calculate the mechanicalparameters of a dam's body and foundation and the inversion of the displacement of an arch dam. The inversion problem of the mechanicalparameters of a dam's body and foundation is transformed into an optimization problem of the objective function. Finally, the Hooke-Jeeves algorithm is used to optimize the objective function, and the mechanicalparameters of a dam's body and foundation are inversely obtained. The case study shows that the relative errors of the mechanicalparameters of the arch dam retrieved using the proposed method are all within 10%. Results indicate that the proposed parameter identification method is reasonable and effective. It provides a new idea for the parameterinversion of other hydraulic structures.
暂无评论