In this paper, an enhanced backtracking search algorithm (so-called MBSA-LS) for parameter identification is proposed with two modifications: (a) modifying the mutation of original backtracking search algorithm (BSA) considering the contribution of current best individual for accelerating convergence speed and (b) novelly incorporating an efficient differential evolution (DE) as local search for improving the quality of population. The proposed MBSA-LS is first validated with better performance than the original BSA and some other typical state-of-the-art optimization algorithms on a benchmark of soil parameter identification in terms of effectiveness, efficiency, and robustness. Then, the efficiency of the MBSA-LS is further illustrated by two representative cases: identifying soil parameters from both laboratory tests and field measurements. All comparisons demonstrate that the proposed MBSA-LS algorithm can give accurate results in a short time. Finally, to conveniently solve the problems of parameter identification, a practical tool ErosOpt for parameter identification is developed by integrating the proposed MBSA-LS and some other efficient algorithms for readers to conduct the parameter identification using optimisation algorithms. 相似文献
Acta Geotechnica - Parameter identification using Bayesian approach with Markov Chain Monte Carlo (MCMC) has been verified only for certain conventional simple constitutive models up to now. This... 相似文献
Different critical state-related formulas, for the critical state line and the critical state-dependent interlocking effect, have been proposed in constitutive modeling of granular material during last decades, which rises up a confusion on how to select an appropriate model in the geotechnical applications. This paper aims to discuss the selection of these critical state-related formulas and parameters identification. Three formulas of critical state line together with two formulas of critical state-dependent interlocking effect are combined to propose six elasto-plastic models. Drained and undrained triaxial tests on four different granular materials are selected for simulations. In order to eliminate artificial errors, a new hybrid genetic algorithm-based intelligent method is proposed and used to identify parameters and estimate simulations with minimum errors for each granular material and each model. Then, the performance of each CSL and each state parameter is evaluated using two information criteria. Furthermore, the performance was evaluated by simulating three footing tests using finite-element analysis in which the models are implemented. All comparisons demonstrate the incorporation of nonlinear critical state line combined with the state parameter e/ec in constitutive modeling can result in relatively more satisfied simulated results. 相似文献
Soft structured clays usually exhibit complex behaviors, which can lead to difficulties in the determination of parameters and high testing costs. This paper aims to propose an efficient optimization method for identifying the parameters of advanced constitutive model for soft structured clays from only limited conventional triaxial tests. First, a new real-coded genetic algorithm (RCGA) is proposed by combining two new crossover and mutation operators for improving the performance of optimization. A newly developed elastic–viscoplastic model accounting for anisotropy, destructuration and creep features is enhanced with the cross-anisotropy of elasticity and is adopted for test simulations during optimization. Laboratory tests on soft Wenzhou marine clay are selected, with three of them being used as objectives for optimization and others for validation. The optimization process, using the new RCGA with a uniform sampling initialization method, is carried out to obtain the soil parameters. A classic genetic algorithm (NSGA-II)-based optimization is also conducted and compared to the RCGA for estimating the performance of the new RCGA. Finally, the optimal parameters are validated by comparing with other measurements and test simulations on the same clay. All comparisons demonstrate that a reliable solution can be obtained by the new RCGA optimization combined with the appropriate soil model, which is practically useful with a reduction in testing costs. 相似文献
Acta Geotechnica - This study systematically presents the application of machine learning (ML) algorithms for constructing a constitutive model for soils. A genetic algorithm is integrated with ML... 相似文献
Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.The performance of five commonly used machine learning(ML)algorithms,i.e.back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),random forest(RF)and evolutionary polynomial regression(EPR)in predicting Cc is comprehensively investigated.A database with a total number of 311 datasets including three input variables,i.e.initial void ratio e0,liquid limit water content wL,plasticity index Ip,and one output variable Cc is first established.Genetic algorithm(GA)is used to optimize the hyper-parameters in five ML algorithms,and the average prediction error for the 10-fold cross-validation(CV)sets is set as thefitness function in the GA for enhancing the robustness of ML models.The results indicate that ML models outperform empirical prediction formulations with lower prediction error.RF yields the lowest error followed by BPNN,ELM,EPR and SVM.If the ranges of input variables in the database are large enough,BPNN and RF models are recommended to predict Cc.Furthermore,if the distribution of input variables is continuous,RF model is the best one.Otherwise,EPR model is recommended if the ranges of input variables are small.The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation. 相似文献
Current studies have focused on selecting constitutive models using optimization methods or selecting simple formulas or models using Bayesian methods. In contrast, this paper deals with the challenge to propose an effective Bayesian-based selection method for advanced soil models accounting for the soil uncertainty. Four representative critical state-based advanced sand models are chosen as database of constitutive model. Triaxial tests on Hostun sand are selected as training and testing data. The Bayesian method is enhanced based on transitional Markov chain Monte Carlo method, whereby the generalization ability for each model is simultaneously evaluated, for the model selection. The most plausible/suitable model in terms of predictive ability, generalization ability, and model complexity is selected using training data. The performance of the method is then validated by testing data. Finally, a series of drained triaxial tests on Karlsruhe sand is used for further evaluating the performance. 相似文献
Current multi-objective evolutionary polynomial regression (EPR) methodology has difficulties on decision-making of optimal EPR model. This paper proposes an intelligent multi-objective optimization-based EPR technique with multi-step automatic model selection procedure. A newly developed multi-objective differential evolution algorithm (MODE) is adopted to improve the optimization performance. The proposed EPR process is composed of two stages: (1) intelligent roughing model selection and (2) model delicacy identification. In the first stage, besides two objectives (model accuracy and model complexity), the model robustness measured by robustness ratio is considered as an additional objective in the multi-objective optimization. In the second stage, a new indicator named selection index is proposed and incorporated to find the optimal model. After intelligent roughing selection and delicacy identification, the optimal EPR model is obtained considering the combined effects of correlation coefficient, size of polynomial terms, number of involved variables, robustness ratio and monotonicity. To show the practicality of the proposed EPR technique, three illustrative cases helpful for geotechnical design are presented: (a) modelling of compressibility, (b) modelling of undrained shear strength and (c) modelling of hydraulic conductivity. For each case, a practical formula with better performance in comparison with various existing empirical equations is finally provided. All results demonstrate that the proposed intelligent MODE-based EPR technique is efficient and effective.
Modelling cyclic behaviour of granular soils under both drained and undrained conditions with a good performance is still a challenge. This study presents a new way of modelling the cyclic behaviour of granular materials using deep learning. To capture the continuous cyclic behaviour in time dimension, the long short-term memory (LSTM) neural network is adopted, which is characterised by the prediction of sequential data, meaning that it provides a novel means of predicting the continuous behaviour of soils under various loading paths. Synthetic datasets of cyclic loading under drained and undrained conditions generated by an advanced soil constitutive model are first employed to explore an appropriate framework for the LSTM-based model. Then the LSTM-based model is used to estimate the cyclic behaviour of real sands, ie, the Toyoura sand under the undrained condition and the Fontainebleau sand under both undrained and drained conditions. The estimates are compared with actual experimental results, which indicates that the LSTM-based model can simultaneously simulate the cyclic behaviour of sand under both drained and undrained conditions, ie, (a) the cyclic mobility mechanism, the degradation of effective stress and large deformation under the undrained condition, and (b) shear strain accumulation and densification under the drained condition. 相似文献