State-of-the-art review of soft computing applications in underground excavations

Zhang, Wengang; Zhang, Runhong; Wu, Chongzhi; Goh, Anthony Teck Chee; Lacasse, Suzanne; Liu, Zhongqiang; Liu, Hanlong

doi:10.1016/j.gsf.2019.12.003

Cited by 370 publications

(87 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Soft computing analysis is preferred by engineers recently by considering the complex, nonlinear responses of engineering applications in soil or rocks (Zhang et al [26]). As a hybrid soft computing method, ANFIS method was used in different engineering areas by a great number of investigators (such as Jang and Sun, [13], Rezazadeh et al [22], Mishra and Mohanty, [19], Mathur et al [17], Petkovic et al [21]).…”

Section: Anfis Modelingmentioning

confidence: 99%

Investigation of the effect of impact direction on Schmidt rebound values by multivariate regression and neuro-fuzzy model

Karakul

2020

SN Appl. Sci.

View full text Add to dashboard Cite

Schmidt hammer test is a nondestructive test used in rock characterization and estimation of mechanical properties of rocks. It is an important advantage that the experiment can be carried out for different impact directions. However, a normalization should be performed on the test results because of variation of effect of gravitational forces on rebound value. On the other hand, some weak, highly porous and weathered rocks have different energy absorbance levels that may not confirm the assumption of normalization formula of the suggested method. So, in this study it is aimed to examine the prediction performance of suggested normalization formulation for weak and highly porous rocks. For this purpose, Schmidt hammer tests for five different impact directions were performed on eight different rock types. The test results indicated that, in general, the rebound values obtained for an impact direction other than horizontal can be converted to the rebound value of horizontal impact direction with a high accuracy by using suggested normalization formula and/or chart. However, existence of some exception was also determined for weak and highly porous rock types. Multivariate regression analyses and adaptive-neuro-fuzzy inference system (ANFIS) were used to explain the variation of ratio between the normalized and tested rebound values for rock types used in this study. The results obtained from statistical and soft computing methods showed that the ratio between the normalized and tested rebound values is predictable and higher for weak and highly porous rock types.

show abstract

Section: Anfis Modelingmentioning

confidence: 99%

Investigation of the effect of impact direction on Schmidt rebound values by multivariate regression and neuro-fuzzy model

Karakul

2020

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…In recent years, China's engineering construction has developed rapidly, especially for deep foundation pit projects, caused by the need of large-scale public facilities and lots of exploitation of underground spaces [1][2][3][4][5][6][7][8][9]. However, the settlement of the foundation pit is affected by many factors, such as the excavation rate, the real-time excavation depth, changes in groundwater level, internal friction angle, soil weight, and number of supports [10][11][12][13][14]. Thus, the prediction of the foundation pit settlements and deformation is difficult and inaccurate [15].…”

Section: Introductionmentioning

confidence: 99%

“…Meanwhile, in the preview study, the amount of training data is extremely insufficient, in which the amount of training data is often less than 20 sets, and the amount of prediction data is usually less than 10 sets [12,40,43,57,58]. It is mainly because the units of training data and prediction data are often set as month and week [40].…”

Section: Introductionmentioning

confidence: 99%

“…It is mainly because the units of training data and prediction data are often set as month and week [40]. Not only that, time is often set as the only input parameter [12,57,58]. However, the settlement of the foundation pit is influenced by many factors, such as the internal friction angle, cohesion, bulk density, Poisson's ratio, void ratio, changes of real-time water level, permeability coefficient, the number of supports, and real-time excavation depth.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of GA-BP Neural Network Optimized by Grey Verhulst Model around Settlement Prediction of Foundation Pit

Liu

Wang

et al. 2021

Geofluids

View full text Add to dashboard Cite

Due to the limitation in the prediction of the foundation pit settlement, this paper proposed a new methodology which takes advantage of the grey Verhulst model and a genetic algorithm. In the previous study, excavation times are often the only factor to predict the settlement, which is mainly because the correspondence between real-time excavation depth and the excavation time is hard to determine. To solve this issue, the supporting times are precisely recorded and the excavation depth rate can be obtained through the excavation time length and excavation depth between two adjacent supports. After the correspondence between real-time excavation depth and the excavation time is obtained, the internal friction angle, cohesion, bulk density, Poisson’s ratio, void ratio, water level changes, permeability coefficient, number of supports, and excavation depth, which can influence the settlement, are taken to be considered in this study. For the application of the methodology, the settlement monitoring point of D4, which is near the bridge pier of the highway, is studied in this paper. The predicted values of the BP neural network, GA-BP neural network, BP neural network optimized by the grey Verhulst model, and GA-BP neural network optimized by the grey Verhulst model are detailed compared with the measured values. And the evaluation indexes of RMSE, MAE, MSE, MAPE, and R 2 are calculated for these models. The results show that the grey Verhulst model can greatly improve the consistency between predicted values and measured values, while the accuracy and resolution is still low. The genetic algorithm (GA) can greatly improve the accuracy of the predicted values, while the GA-BP neural network shows low reflection to the fluctuation of measured values. The GA-BP neural network optimized by the grey Verhulst model, which has taken the advantages of GA and the grey Verhulst model, has extremely high accuracy and well consistency with the measured values.

show abstract

“…They have proved the ability, accuracy, and computational efficiency of the soft computing method as a satisfactory alternative to the limit equilibrium method. In another related work, Zhang et al (2020b) comprehensively studied the application of ANN, multivariate adaptive regression splines, and some other soft computing methods in underground excavations modeling to provide an overview of the features relevant to the process and operation of the soft computing methods, the merits and disadvantages of these methods. They have mentioned that ANFIS, alongside the other ANN type models, is one of the most interesting research aspects of geotechnical engineering.…”

Section: Introductionmentioning

confidence: 99%

Development of a new empirical model and adaptive neuro-fuzzy inference systems in predicting unconfined compressive strength of weathered granite grade III

Moosavi

Mohammadi

2021

Bull Eng Geol Environ

View full text Add to dashboard Cite

The present paper has developed a new multivariate linear regression and adaptive neuro-fuzzy inference processing to predict UCS for weathered granite grade III based on simple input data from point load index, Schmidt rebound hardness, and P wave velocity. Data from 85 rock core samples of this granite type have been selected. By using multivariate regression analysis, three models with two independent variables and one model with three independent variables have been developed. Furthermore, another model has been obtained by using a neuro-fuzzy logic analysis. The root means square error, RMSE, coefficient of determination, R 2 , and the mean absolute percentage error, MAPE, were used as the evaluation criteria of the accuracy of the models. The results have indicated that the regression-based and neuro-fuzzy models are effective, but the accuracy of the neurofuzzy model is in good agreement with the realistic data from the direct test.

show abstract

State-of-the-art review of soft computing applications in underground excavations

Cited by 370 publications

References 90 publications

Investigation of the effect of impact direction on Schmidt rebound values by multivariate regression and neuro-fuzzy model

Investigation of the effect of impact direction on Schmidt rebound values by multivariate regression and neuro-fuzzy model

Application of GA-BP Neural Network Optimized by Grey Verhulst Model around Settlement Prediction of Foundation Pit

Development of a new empirical model and adaptive neuro-fuzzy inference systems in predicting unconfined compressive strength of weathered granite grade III

Contact Info

Product

Resources

About