Explore the vast range of titles available.

Because of the disasters associated with slope failure, the analysis and forecasting of slope stability for geotechnical engineers are crucial. In this work, in order to forecast the factor of safety (FOS) of the slopes, six machine learning techniques of Gaussian process regression (GPR), support vector regression, decision trees, long-short term memory, deep neural networks, and K-nearest neighbors were performed. A total of 327 slope cases in Iran with various geometric and shear strength parameters analyzed by PLAXIS software to evaluate their FOS were employed in the models. The K-fold (K = 5) cross-validation (CV) method was applied to evaluate the performance of models’ prediction. Finally, all the models produced acceptable results and almost close to each other. However, the GPR model with R2 = 0.8139, RMSE = 0.160893, and MAPE = 7.209772% was the most accurate model to predict slope stability. Also, the backward selection method was applied to evaluate the contribution of each parameter in the prediction problem. The results showed that all the features considered in this study have significant contributions to slope stability. However, features φ (friction angle) and γ (unit weight) were the most effective and least effective parameters on slope stability, respectively.

To accurately estimate the rock shear strength parameters of cohesion (C) and friction angle (φ), triaxial tests must be carried out at different stress levels so that a failure envelope can be obtained to be linearized. However, this involves a higher budget and time requirements that are often unavailable at the early stage of a project. To address this problem, faster and more inexpensive indirect techniques such as artificial intelligence algorithms are under development. This paper first aims to utilize four machine learning techniques of Gaussian process regression (GPR), support vector regression (SVR), decision trees (DT), and long-short term memory (LSTM) to develop a predictive model to estimate parameters C and φ. To this aim, 244 datasets are available in the RockData software for intact Sandstone, including three input parameters of uniaxial compressive strength (UCS), uniaxial tensile strength (UTS), and confining stress (σ3) are employed in the models. The dropout technique is used to overcome the overfitting problem in LSTM-based models. A comprehensive evaluation is adopted for the performance indices of the prediction models. In this step, the most accurate results are produced by the LSTM model (C: R2 = 0.9842; RMSE = 1.295; MAPE = 0.009/φ: R2 = 0.8543; RMSE = 1.857; MAPE = 1.4301). In the second step, we improve the performance of the proposed LSTM model by fine-tuning the LSTM hyper-parameters, using six metaheuristic algorithms of grey wolf optimization (GWO), particle swarm optimization (PSO), social spider optimization (SSO), sine cosine algorithm (SCA), multiverse optimization (MVO), and moth flame optimization (MFO). The developed models' prediction performance for predicting parameter C from high to low was PSO-LSTM, GWO-LSTM, MVO-LSTM, MFO-LSTM, SCA-LSTM SSO-LSTM, and LSTM with ranking scores of 34, 29, 24, 21, 14, 12, and 5, respectively. Also, the models' prediction performance for predicting parameter φ from high to low was PSO-LSTM, GWO-LSTM, MVO-LSTM, MFO-LSTM, SCA-LSTM SSO-LSTM, and LSTM with ranking scores of 34, 31, 23, 18, 15, 14, and 5, respectively. However, the most robust results are produced by the PSO-LSTM model. Finally, the results indicate that applying a metaheuristic algorithm to tune the hyper-parameters of the LSTM model can significantly improve the prediction results. In the last step, the mutual information test method is applied to sensitivity analysis of the input parameters to predict parameters C and φ. Finally, it is revealed that parameters σ3 and UCS have the highest and lowest impact on the parameters C and φ, respectively.HighlightsEmploying a large dataset consists of 244 data.Using six ML algorithms that most of them had not been tested before for this issue.Applying 5-fold CV to validate the results.Application of feature selection to find the most effective parameters on the water inflow into tunnels.Recognition of the best prediction method.

Tunnel boring machine (TBM) performance prediction in mechanized tunneling is an essential factor for selecting an appropriate excavation machine, tunnel design, and safe construction. To implement safe mechanized excavation, it is important to accurately assess and predict the range of machine driving parameters, especially the machine rate of penetration (ROP); this can reduce the cost of TBM repairs due to the abrasion of disc cutters and cutterhead and also has a positive effect on the post-construction period. This study focuses on predicting the ROP of TBMs passing through metamorphic rocks during deep excavation and under a complex geotechnical situation. For this purpose, three fuzzy-based models of the Mamdani fuzzy inference system (MFIS), adaptive neuro-fuzzy inference system (ANFIS), Takagi Sugeno fuzzy model (TSF), as well as linear and non-linear regression models were developed. Historical tunnels were used to compile 189 data points (151 for training and 37 for testing). In the dataset, three parameters, including uniaxial compressive strength (UCS), cutterhead rotational speed per minute (RPM), and thrust force (TF), were considered effective parameters on the TBM’s ROP. According to the findings, the suggested models provided satisfactory and consistent accuracy. Moreover, the results demonstrated that the forecasted values correlate rather well with the measured ones. The proposed algorithms can be considered for use in similar ground and tunneling conditions (metamorphic rocks with low-average strength). It is worth noting that this study has the potential to drastically cut down on tunneling uncertainties and makes fuzzy inference systems a robust algorithm for planning mechanized tunneling.HighlightsPrediction of TBM performance in complex geological conditions.Forecasting TBM performance in deep tunnels passing through metamorphic rocks.Presenting an empirical model for calculating the TBM performance based on statistical analysis.Detailed analysis of fuzzy-based techniques potential for TBM performance prediction.Examining the models’ accuracy with several loss functions and statistical indices.

One of the crucial tasks during the EPB shield tunnelling is estimating the optimum tunnel face pressure (FP), which ensures self-drilling safety, helps to reduce surface settlement and prevents the entire tunnel from collapsing. This study aims to propose an optimized and state-of-the-art machine learning model to predict the EPB-FP as accurately as possible. To this end, a support vector regression SVR model and six metaheuristic optimization algorithms of particle swarm optimization (PSO), grey wolf optimization (GWO), multiverse optimization (MVO), moth flame optimization (MFO), sine cosine algorithm (SCA), and social spider optimization (SSO) were developed to predict the FP in the EPB tunnelling. 250 data sets, including seven input parameters and one output parameter (FP) were utilized in the models obtained from the Tehran metro Line 3. Finally, the performance prediction of the models from high to low was SVR–PSO,SVR–GWO,SVR–MVO,SVR–MFO,SVR–SCA,SVR–SSO, and SVR with ranking scores of 55,49,45,39,37,30, and 21, respectively. Therefore, the SVR–PSO hybrid model produced the most accurate results and it was recommended to predict the FP in the EPB tunnelling. In addition, using the mutual information test, the surface load (SL) parameter was identified as the most influential parameter on the FP. This work’s significance is that it allows geotechnical engineers to accurately estimate the FP during the EPB tunnelling, which ensures the safety of the excavation itself, helps to minimize surface settlement, and ultimately prevents the collapse of the entire tunnel. Also, it can prevent the time-consuming and cost overruns that the FP may cause during the EPB tunnelling.HighlightsImprove the SVR ability through meta-heuristic optimization for low data.Develop six hybrid meta-heuristic algorithms to predict the tunnel face pressure.High accuracy in the prediction of face pressure during EPB tunnelling.Sensitivity analysis of the input parameters using mutual information testRecognition of the most robust model.

The waste generated by brick industries in many countries around the world is increasing significantly with the continuous expansion of urbanization and industrialization, and as a result, more environmental and financial problems are brought about. The waste material out of bricks production could be used as a stabilizing material for high-plasticity silt (MH) that has caused damage to different roads and buildings. This study aimed to investigate the effect of waste brick powder (WBP) on stabilizing high-plasticity silt and reduce the influence of WBP on the environment. An experimental study was performed to evaluate the effects of WBP on the geotechnical properties of MH soil. Atterberg limits, compaction characteristics, specific gravity, free swelling, unconfined compressive strength (UCS), California bearing ratio (CBR), and permeability were performed for natural and stabilized soil at different ratios (6%, 12%, 18%, 24%, and 30% by dry weight of the soil sample) of WBP. The test results showed that liquid limit, plastic limit, plasticity index, linear shrinkage, free swelling, and the coefficient of permeability are decreased by adding WBP, whereas specific gravity, maximum dry density, UCS, and CBR are increased by adding WBP.