Journal of Rock Mechanics and Geotechnical Engineering最新文献

The decision-making method of tunnel boring machine (TBM) operating parameters has a significant guiding significance for TBM safe and efficient construction, and it has been one of the TBM tunneling research hotspots. For this purpose, this paper introduces an intelligent decision-making method of TBM operating parameters based on multiple constraints and objective optimization. First, linear cutting tests and numerical simulations are used to investigate the physical rules between different cutting parameters (penetration, cutter spacing, etc.) and rock compressive strength. Second, a dual-driven mapping of rock parameters and TBM operating parameters based on data mining and physical rules of rock breaking is established with high accuracy by combining rock-breaking rules and deep neural networks (DNNs). The decision-making method is established by dual-driven mapping, using the effective rock-breaking capacity and the rated value of mechanical parameters as constraints and the total excavation cost as the optimization objective. The best operational parameters can be obtained by searching for the revolutions per minute and penetration that correspond to the extremum of the constrained objective function. The practicability and effectiveness of the developed decision-making model is verified in the Second Water Source Channel of Hangzhou, China, resulting in the average penetration rate increasing by 11.3% and the total cost decreasing by 10%.

The unconfined compressive strength (UCS) of alkali-activated slag (AAS)-based cemented paste backfill (CPB) is influenced by multiple design parameters. However, the experimental methods are limited to understanding the relationships between a single design parameter and the UCS, independently of each other. Although machine learning (ML) methods have proven efficient in understanding relationships between multiple parameters and the UCS of ordinary Portland cement (OPC)-based CPB, there is a lack of ML research on AAS-based CPB. In this study, two ensemble ML methods, comprising gradient boosting regression (GBR) and random forest (RF), were built on a dataset collected from literature alongside two other single ML methods, support vector regression (SVR) and artificial neural network (ANN). The results revealed that the ensemble learning methods outperformed the single learning methods in predicting the UCS of AAS-based CPB. Relative importance analysis based on the best-performing model (GBR) indicated that curing time and water-to-binder ratio were the most critical input parameters in the model. Finally, the GBR model with the highest accuracy was proposed for the UCS predictions of AAS-based CPB.

A comparison between deep learning and standalone models in predicting the compaction parameters of soil is presented in this research. One hundred and ninety and fifty-three soil samples were randomly picked up from two hundred and forty-three soil samples to create training and validation datasets, respectively. The performance and accuracy of the models were measured by root mean square error (RMSE), coefficient of determination (R²), Pearson product-moment correlation coefficient (r), mean absolute error (MAE), variance accounted for (VAF), mean absolute percentage error (MAPE), weighted mean absolute percentage error (WMAPE), a20-index, index of scatter (IOS), and index of agreement (IOA). Comparisons between standalone models demonstrate that the model MD 29 in Gaussian process regression (GPR) and model MD 101 in support vector machine (SVM) can achieve over 96% of accuracy in predicting the optimum moisture content (OMC) and maximum dry density (MDD) of soil, and outperformed other standalone models. The comparison between deep learning models shows that the models MD 46 and MD 146 in long short-term memory (LSTM) predict OMC and MDD with higher accuracy than ANN models. However, the LSTM models outperformed the GPR models in predicting the compaction parameters. The sensitivity analysis illustrates that fine content (FC), specific gravity (SG), and liquid limit (LL) highly influence the prediction of compaction parameters.

Smartphones are usually packed with a large number of features. An increasing number of researchers are paying attention to the technological capabilities of smartphones, which is a new topic and research interest. This paper proposes a method using smartphones and digital photogrammetry to measure the discontinuity orientation of a rock mass. Smartphone photos satisfying a certain overlap rate provide an efficient method for generating point cloud models of rock outcrops based on image matching. Using the target and the generated point cloud model allows for determining actual geographic coordinates and the measurement of discontinuity orientations. The method proposed has been applied to two different study areas. The discontinuity orientations measured by the proposed method are compared with those measured by the manual method in two cases. The results show a good agreement, verifying the reliability and accuracy of the proposed method. The main contribution of this paper is to use knowledge of coordinate rotation to determine the actual geographic location of the model through a square target. The equipment used in this study is simple, and photogrammetric field surveys are easy to carry out.

The calculation of frost heaving with ice lens formation is still not standard for construction projects using artificial ground freezing (AGF). In fine-grained material, ice lenses may initiate and lead to significant heaving at the ground surface, which should be considered in advance. However, the complex processes during ice lens formation are still not fully understood and difficult to capture in a simple approach. In the past, the semi-analytical approach of Konrad and Morgenstern used one soil constant, the “segregation potential (SP)”. It has been mainly and most successfully applied to the heave calculation of natural-induced soil freezing in cold regions. Its application to AGF has been so far unsuccessful. To solve this, a new semi-analytical approach is presented in this paper. It includes AGF conditions such as bottom-up freezing, temperature gradients to reach great freezing velocities, and a distinction between two freezing states. One is the freezing-up state until a certain frost body thickness is reached (thermal transient state), and the other is a holding phase where the frost body thickness is kept constant (thermal quasi-steady state). To test its ability, the results are applied to another freezing direction, the top-down freezing. The new approach is validated using two different frost-susceptible soils and, in total, 50 frost heave tests. In the thermal transient region, where the SP is applicable, the two semi-analytical approaches are compared, showing improved performance of the current method by about 15%.