Energy Evaluation of Triggering Soil Liquefaction Based on the Response Surface Method

Tang, X.; Yang, Qing

doi:10.3390/app9040694

Cited by 11 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, several researchers used ML algorithms and achieved efficient successes in different civil engineering and other sectors such as environmental [10], geotechnical [11][12][13][14][15][16][17][18], and other fields of science [19][20][21][22][23][24][25][26][27][28]. Numerous researchers have documented the behavior of the RFM.…”

Section: Introductionmentioning

confidence: 99%

Development of Prediction Models for Shear Strength of Rockfill Material Using Machine Learning Techniques

et al. 2021

View full text Add to dashboard Cite

Supervised machine learning and its algorithms are a developing trend in the prediction of rockfill material (RFM) mechanical properties. This study investigates supervised learning algorithms support vector machine (SVM), random forest (RF), AdaBoost, and k-nearest neighbor (KNN) for the prediction of the RFM shear strength. A total of 165 RFM case studies with 13 key material properties for rockfill characterization have been applied to construct and validate the models. The performance of the SVM, RF, AdaBoost, and KNN models are assessed using statistical parameters, including the coefficient of determination (R2), Nash–Sutcliffe efficiency (NSE) coefficient, root mean square error (RMSE), and ratio of the RMSE to the standard deviation of measured data (RSR). The applications for the abovementioned models for predicting the shear strength of RFM are compared and discussed. The analysis of the R2 together with NSE, RMSE, and RSR for the RFM shear strength data set demonstrates that the SVM achieved a better prediction performance with (R2 = 0.9655, NSE = 0.9639, RMSE = 0.1135, and RSR = 0.1899) succeeded by the RF model with (R2 = 0.9545, NSE = 0.9542, RMSE = 0.1279, and RSR = 0.2140), the AdaBoost model with (R2 = 0.9390, NSE = 0.9388, RMSE = 0.1478, and RSR = 0.2474), and the KNN with (R2 = 0.6233, NSE = 0.6180, RMSE = 0.3693, and RSR = 0.6181). Furthermore, the sensitivity analysis result shows that normal stress was the key parameter affecting the shear strength of RFM.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of Prediction Models for Shear Strength of Rockfill Material Using Machine Learning Techniques

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Ghorbani and Eslami (2021) used the evolutionary polynomial regression to train an energy-based evaluation model for the liquefaction of sand-clay mixtures using a dataset from shaking table experiments. Pirhadi, Tang, and Yang (2019) applied the response surface method (RSM) to develop six new strain energy models to estimate the capacity energy for soil liquefaction; besides, the effect of fine content was also studied. Pirhadi et al (2018) obtained a new equation for soil liquefaction evaluation in sandy soil, in which two new earthquake parameters: standardized cumulative absolute velocity and closest distance from the site to the rupture surface (CAV5 and rrup) were introduced.…”

Section: Introductionmentioning

confidence: 99%

The establishment of prediction model for soil liquefaction based on the seismic energy using the neural network

2022

View full text Add to dashboard Cite

In the development of the prediction model for soil liquefaction, compared to the stress-based method, the energy-based methods proposed and developed in recent years are closer to the essence of soil liquefaction which is about the energy dissipation. Therefore, considering the weak nonlinear relationship found by the previous research, the fuzzy neural network (FNN) and BP neural network (BPNN) were adopted to try to obtain a prediction model which is the most proper to this nonlinear relationship. Firstly, the database including 284 cases obtained from laboratory test was divided into three separate groups denoted as training, validation set and testing sets by the ratio of 5:1:1; then, the FNN model and BPNN model were iterated to determine the model parameter by referring to the variation of fitness value and relative error of validation set; at the same time, the optimization algorithm of genetic algorithm (GA) was adopted to BPNN to find the best coefficients; besides, the parameter of 𝐶 𝑐 and 𝐷 50 was respectively excluded from the database to test their influence degree according to the prediction error; finally, 6 prediction results of FNN and genetic algorithm BP neural network (GABP) were compared with the previously proposed models. The results showed that the relationship of capacity energy to the influencing parameters could not be fitted as a fully linear relationship; the FNN model can learn the role of 𝐶 𝑐 in affecting the capacity energy while the GABP model needs not to take it into account; the FNN and GABP model all fitted 2 a good weakly nonlinear relationship for the capacity energy, and the GABP model is a better prediction model for capacity energy so far.

show abstract

“…The computational burden can be reduced by using metamodels, also known as surrogate models, which approximate the behavior of complex models with simpler ones [28,29]. Methods such as polynomial response surface [30,31], response surface based multi-fidelity model [32], polynomial chaos expansion (PCE) [33,34], Gaussian process [35,36], Kriging [37,38], and neural network [39,40,41] are used to the creation of such metamodels. While the use of metamodels significantly reduces computational burden by approximating complex models with simpler ones, there are some critical drawbacks to this approach [42,43,44].…”

mentioning

confidence: 99%

Global Sensitivity Analysis of Structural Reliability Using Cliff Delta

Kala

2024

Preprint

View full text Add to dashboard Cite

This paper introduces innovative sensitivity indices based on Cliff's Delta for global sensitivity analysis of structural reliability. These indices build on Sobol's method, using binary outcomes (success or failure), but avoid the need to calculate failure probability Pf and the associated distributional assumptions of resistance R and load F. Cliff's Delta, originally for ordinal data, evaluates the dominance of resistance over load without specific assumptions. The mathematical formulations for computing Cliff's Delta between R and F quantify structural reliability by assessing the random realizations of R > F using a double-nested-loop approach. The derived sensitivity indices, based on the squared value of Cliff's Delta, exhibit properties analogous to those in Sobol's sensitivity analysis, including first-order, second-order, and higher-order indices. This provides a comprehensive framework for evaluating the contributions of input variables and their interactions on structural reliability. This method is particularly significant for FEM applications, where repeated simulations of R or F are computationally intensive. The double-nested-loop algorithm of Cliff's Delta maximizes the extraction of information about structural reliability from these simulations. However, the high computational demand of Cliff's Delta is a disadvantage. Future research should optimize computational demands, especially for small Pf, where the inner loop may often be unnecessary.

show abstract

Energy Evaluation of Triggering Soil Liquefaction Based on the Response Surface Method

Cited by 11 publications

References 46 publications

Development of Prediction Models for Shear Strength of Rockfill Material Using Machine Learning Techniques

Development of Prediction Models for Shear Strength of Rockfill Material Using Machine Learning Techniques

The establishment of prediction model for soil liquefaction based on the seismic energy using the neural network

Global Sensitivity Analysis of Structural Reliability Using Cliff Delta

Contact Info

Product

Resources

About