Ehsan Momeni

Prediction of the unconfined compressive strength of soft rocks: a PSO-based ANN approach

Many studies have shown that artificial neural networks (ANNs) are useful for predicting the unconfined compressive strength (UCS) of rocks. However, ANNs do have some deficiencies: they can get trapped in local minima and they have a slow learning rate. It is widely accepted that optimization algorithms such as particle swarm optimization (PSO) can improve ANN performance. This study investigated the application of a hybrid PSO-based ANN model to the prediction of rock UCS. To prepare a dataset for the predictive model, extensive laboratory tests (i.e., 160 tests in total) were conducted on 40 soft rock sample sets (mostly shale) presenting various weathering grades that were obtained from different excavation sites in Johor, Malaysia. The laboratory tests included the UCS test and other basic rock index tests (the Brazilian tensile strength test, point load index test, and ultrasonic test). When developing the predictive model of UCS, the results of the basic rock tests as well as the bulk densities of the samples were used as input parameters, while the UCS was set as the output of the predictive model. The value account for (VAF), root mean squared error (RMSE), and adjusted R2 (coefficient of determination) were utilized to check the performances of the predictive models. The high performance indices of the proposed model highlight the superiority of the PSO-based ANN model for UCS prediction.

Feasibility of ANFIS model for prediction of ground vibrations resulting from quarry blasting

One of the most significant environmental issues of blasting operations is ground vibration, which can cause damage to the surrounding residents and structures. Hence, it is a major concern to predict and subsequently control the ground vibration due to blasting. This paper presents two artificial intelligence techniques, namely, adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network for the prediction of ground vibration in quarry blasting site. For this purpose, blasting parameters as well as ground vibrations of 109 blasting operations were measured in ISB granite quarry, Johor, Malaysia. Moreover, an empirical equation was also proposed based on the measured data. Several AI-based models were trained and tested using the measured data to determine the optimum models. Each model involved two inputs (maximum charge per delay and distance from the blast-face) and one output (ground vibration). To control capacity performances of the predictive models, the values of root mean squared error (RMSE), value account for (VAF), and coefficient of determination (R2) were computed for each model. It was found that the ANFIS model can provide better performance capacity in predicting ground vibration in comparison with other predictive techniques. The values of 0.973, 0.987 and 97.345 for R2, RMSE and VAF, respectively, reveal that the ANFIS model is capable to predict ground vibration with high degree of accuracy.

Prediction of the strength and elasticity modulus of granite through an expert artificial neural network

The uniaxial compressive strength (UCS) and Young’s modulus (E) are important parameters in designing solutions to rock engineering problems. However, determination of these properties in the laboratory is expensive and time consuming. Therefore, many attempts have been made to estimate these properties indirectly by defining various correlations. These correlations often relate UCS and E to some basic rock index tests. Nevertheless, in this study, using an artificial neural network (ANN) enhanced with the imperialist competitive algorithm (ICA), a hybrid model is developed for predicting the UCS and E of granite samples. The samples used in this study were taken from the face of the Pahang–Selangor raw water transfer tunnel in Malaysia. To train the aforementioned model, the results of the laboratory tests, including porosity (n), P wave velocity (VP), point load strength index (Is(50)) and the Schmidt hammer rebound number (Rn), were used as model inputs. For the sake of comparison, the performance of the hybrid model was checked against a conventional ANN predictive model with similar architecture. Value account for (VAF), root mean square error (RMSE) and coefficient of determination (R2) were used to control the capacity performance of the predictive models. The performance indices obtained using the ICA-ANN approach show that the proposed model can predict UCS and E with a high degree of accuracy. The results of sensitivity analysis reveal that VP is the most influential parameter, compared to the other input parameters, on UCS and E.

Rock strength estimation: a PSO-based BP approach

Application of back-propagation (BP) artificial neural network (ANN) as an accurate, practical and quick tool in indirect estimation of uniaxial compressive strength (UCS) of rocks has recently been highlighted in the literature. This is mainly due to difficulty in direct determination of UCS in laboratory as preparing the core samples for this test is troublesome and time-consuming. However, ANN technique has some limitations such as getting trapped in local minima. These limitations can be minimized by combining the ANNs with robust optimization algorithms like particle swarm optimization (PSO). This paper gives insight into development of a hybrid PSO–BP predictive model of UCS. For this reason, dataset comprising the results of 228 laboratory tests including dry density, moisture content, P wave velocity, point load index test, slake durability index and UCS was prepared. These tests were conducted on 38 sandstone samples which were taken from two excavation sites in Malaysia. Findings showed that PSO–BP model performs well in predicting UCS. Nevertheless, to compare the prediction performance of the PSO–BP model, the UCS is predicted using ANN-based PSO and BP models. The correlation coefficient, R, values equal to 0.988 and 0.999 for training and testing datasets, respectively, suggest that the PSO–BP model outperforms the other predictive models.

Performance prediction of tunnel boring machine through developing a gene expression programming equation

The prediction of tunnel boring machine (TBM) performance in a specified rock mass condition is crucial for any mechanical tunneling project. TBM performance prediction in accurate may reduce the risks related to high capital costs and scheduling for tunneling. This paper presents a new model/equation based on gene expression programming (GEP) to estimate performance of TBM by means of the penetration rate (PR). To achieve the aim of the study, the Pahang–Selangor Raw Water Transfer tunnel in Malaysia was investigated and the data related to field observations and laboratory tests were used in modelling of PR of TBM. A database (1286 datasets in total) comprising 7 model inputs related to rock (mass and material) properties and machine characteristics and 1 output (PR) was prepared to use in GEP modelling. To evaluate capability of the developed GEP equation, a multiple regression (MR) model was also proposed. A comparison between the obtained results has been done using several performance indices and the best equations of GEP and MR were selected. System results for the developed GEP equation based on coefficient of determination (R2) were obtained as 0.855 and 0.829 for training and testing datasets, respectively, while these values were achieved as 0.795 and 0.789 for the developed MR equation. Concluding remark is that the GEP equation is superior in comparison with the MR equation and it can be introduced as a new equation in the field of TBM performance prediction.

Uplift Resistance of Buried Pipelines Enhanced by Geogrid

Failure of an oil or gas pipeline due to low uplift resistance of soil has serious economic and environmental consequences; hence, increasing the uplift resistance through soil reinforcement is of interest. The main purpose of this paper is to investigate the possible use of geogrid to enhance the uplift resistance of buried pipelines. For this reason, 11 small-scale laboratory tests were performed. The tests were conducted to investigate the effect of pipe diameter, burial depth, as well as length and number of geogrid layers on the uplift resistance of sandy soils. The experimental results suggest that although pipe diameter and burial depth are directly related to uplift resistance, the direct effect of geogrid incorporation is more pronounced. While Peak Uplift Resistance (PUR) is of interest, findings indicate that the number of geogrid layers does not have a pivotal influence on PUR. In addition, for verification purpose, the PUR of 11 laboratory tests were back analyzed numerically using finite element software PLAXIS 3D TUNNEL. The findings show that numerical and experimental results are in good agreement.

Bearing capacity of shallow foundation's prediction through hybrid artificial neural networks

The utilization of Artificial Neural Network (ANN) for bearing capacity estimation has some disadvantages such as getting trapped in local minima and slow rate of learning. Recent developments of optimization algorithms such as Particle Swarm Optimization (PSO) have made it possible to overcome ANN drawbacks and improve its efficiency. This paper presents a unified approach of ANN based on PSO algorithm to predict bearing capacity of shallow foundations in granular soils. To generate the network, numbers of 40 datasets including the recorded cases of full-scale axial compression load test on shallow foundations in granular soils were collected from literatures. Each dataset refers to a set of 6 inputs consisted of footing length and width, embedded depth of the footing, average vertical effective stress of the soil, friction angle of the soil, and ground water level as well as one output consisted of the ultimate axial bearing capacity. Several sensitivity analyses were conducted to determine the optimum parameters of PSO algorithm and the network architecture was determined following the trial and error method. The results demonstrate that the presented model predicts the bearing capacity of shallow foundations with high degree of accuracy.

Prediction of bearing capacity of thin-walled foundation: a simulation approach

In the recent past years, utilization of intelligent models for solving geotechnical problems has received considerable attention. This paper highlights the feasibility of adaptive neuro-fuzzy inference system (ANFIS) for predicting the bearing capacity of thin-walled foundations. For this reason, a data set comprising nearly 150 recorded cases of footing load tests was compiled from literature. Footing width, wall length-to-footing width ratio, internal friction angle, and unit weight of soil were set as inputs of the predictive model of bearing capacity. In addition, a pre-developed artificial neural network (ANN) model was utilized to estimate the bearing capacity of thin-walled foundations. The results recommend the workability of ANFIS in predicting the bearing capacity of thin-walled foundation. The coefficient of determination (R2) results of 0.933 and 0.875, and root mean square error (RMSE) results of 0.075 and 0.048 for training and testing data sets show higher accuracy and efficiency level of ANFIS in estimating bearing capacity of thin-walled spread foundations compared to the ANN model (R2 = 0.710, RMSE = 0.512 for train, R2 = 0.420, RMSE = 0.529 for test). Overall, findings of the study suggest utilization of ANFIS, as a feasible and quick tool, for predicting the bearing capacity of thin-walled spread foundations, though further study is still recommended to enhance the reliability of the proposed model.

The Influence of Bituminous Coating on Uplift Resistance of Short Pile Foundations in Sand

Bituminous coatings can be used to reduce negative skin friction on pile. The present study investigates the other applications and the effectiveness of heated coating withelastic and visco-elastic-plastic behavior on the skin friction at soil-pile interface. Aseries of small scale physical modeling tests of short pile foundations under pullout load was carried out to study the effects of adhesive coating materials on the short pile foundation interaction. The results indicated that heated bituminous materials can significantly affect the pull-out capacity of short pile foundations.