Search

In this paper we consider the problem of restoration of a image contaminated by a mixture of Gaussian and impulse noises. We propose a new statistic called ROADGI which improves the well-known Rank-Ordered Absolute Differences (ROAD) statistic for detecting points contaminated with the impulse noise in this context. Combining ROADGI statistic with the method of weights optimization we obtain a new algorithm called Optimal Weights Mixed Filter (OWMF) to deal with the mixed noise. Our simulation results show that the proposed filter is effective for mixed noises, as well as for single impulse noise and for single Gaussian noise.

Rockburst is a kind of complex and catastrophic dynamic geological disaster in the development and utilization of underground space, which seriously threatens the safety of personnel and environment. Due to the suddenness in time and randomness in space, the prediction of rockburst becomes a great challenge. Microseismic monitoring is capable to continuously capture rock microfracture signals in real time, which offers an effective means for rockburst prediction. With the explosive growth of monitoring data, the conventional manual forecasting methods are laborious and time-consuming. Therefore, artificial intelligence was introduced to improve prediction efficiency. A novel tree-based algorithm was proposed. Its basic idea was to automatically recognize precursory microseismic sequences for the real-time prediction of rockburst intensity. The database consisting of 1500 microseismic events was analyzed. To establish precursory microseismic sequences, dimensionality reduction of the database was first implemented by t-SNE algorithm. Then, k-means clustering algorithm was employed for labelling 1500 microseismic events. Before that, canopy algorithm was adopted to determine the number of clusters. Finally, 300 precursory microseismic sequences were formed by the grouping rule. They were further partitioned into two parts through stratified sampling: 70% for training and 30% for validation. The validation results indicated that the precursor tree with pruning achieved a higher prediction accuracy of 98.9% than one without pruning on the validation set. And the increase was separately 12.2%, 9.2% and 28.6% on the whole validation set and each classes (low/moderate rockburst). In comparison with low rockburst, moderate rockburst was minority class. The improved accuracy on moderate rockburst suggested that pruning can enhance the recognition ability of precursor tree for the minority class. Additionally, two extra rockburst cases were collected from a diversion tunnel in northwestern China, which provided a complete workflow about how to apply the built precursor tree model to achieve field rockburst warning in engineering practice. The tree-based algorithm served as a new and promising way for the real-time rockburst prediction, which successfully integrated field microseismic monitoring and artificial intelligence. [ABSTRACT FROM AUTHOR]

Highlights • A Voronoi tessellation algorithm is incorporated to model the rock microstructure. • A modified contact model is adopted to simulate the intergranular cracking. • Numerical simulations are carried out to verify this new approach. • Grain-size effects on micro-mechanical parameters and REV size are studied. Abstract In this study, a two-dimensional Voronoi element based-numerical manifold method (VE-NMM) was developed as a new approach to investigate the micro- and macro- mechanical properties of intact rocks. The Voronoi technique was used to generate a polygonal grain assemblage to approximate the microstructure of sandstone samples from Gubei colliery of Huainan mining area in China. A modified contact model incorporating cohesion and tensile strength was adopted to interpret the interactions between rock grains. A series of laboratory tests, i.e. scanning electron microscope tests, uniaxial compression and Brazilian tests were carried out to obtain the microstructural information and macro-mechanical properties of the sandstone samples. To verify the proposed VE-NMM, simulations of Brazilian tensile splitting and uniaxial compressive tests were carried out and the results, in terms of strength, elastic constant and crack distribution, were compared to those of the laboratory tests. To investigate the effects of grain size on the micro-mechanical parameters and the representative elementary volume (REV) size, numerical uniaxial compression tests with different grain sizes (2mm, 3 mm and 4 mm) were conducted using the developed VE-NMM approach. Simulation results indicate that both the micro-mechanical parameters and the representative elementary volume size are heavily dependent on grain size. [ABSTRACT FROM AUTHOR]

We introduce an oracle filter for removing the Gaussian noise with weights depending on a similarity function. The usual Non-Local Means filter is obtained from this oracle filter by substituting the similarity function by an estimator based on similarity patches. When the sizes of the search win-dow are chosen appropriately, it is shown that the oracle filter converges with the optimal rate. The same optimal convergence rate is preserved when the similarity function has suitable errors-in measurements. We also provide a sta-tistical estimator of the similarity which converges at a convenient rate. Based on our convergence theorems, we propose some simple formulas for the choice of the parameters. Simulation results show that our choice of parameters im-proves the restoration quality of the filter compared with the usual choice of parameters in the original algorithm. [ABSTRACT FROM AUTHOR]

The numerical manifold method (NMM) simulates continuous and discontinuous problems in a unified framework; thus NMM has advantages in analysing crack propagation. However, calculation of the stress intensity factors (SIFs) when adopting the NMM requires additional procedures, such as the J-integral and the interaction integral. In this study, a hybrid crack element (HCE) method is incorporated into the NMM to directly obtain the SIFs; the new algorithm combines the merits of both the NMM and HCE method. In the proposed algorithm, the HCE is used in the crack-tip region while the NMM is applied in the remaining region. The SIFs at the crack-tip are calculated directly from the solution of the governing equation with less computational complexity relative to existing methods. The proposed algorithm does not require any changes to the initial mesh during crack propagation. It is verified by a few examples and the results show that the simulated crack propagation paths are in good agreement with the results from existing studies while the computational efficiency is improved due to the direct calculation of the SIFs and the consistency of the mesh system in the crack propagation process. [ABSTRACT FROM AUTHOR]

To resolve the image deconvolution problem, the total variation (TV) minimization approach has been proved to be very efficient. However, we observe that this approach has an over-minimizing TV effect in the sense that it gives a solution whose TV is usually smaller than that of the original image. This effect is due to the pre-pondering role of the TV in the corresponding minimization problem and prevents from finding the exact solution of the deconvolution problem when such a solution exists. We propose a modified version of the gradient descent algorithm, which leads to an exact solution of the deconvolution problem if it exists and to a satisfactory approximative solution if there is no exact one. The idea consists in introducing a control on the contribution of the TV in the classical gradient descent algorithm. The new algorithm has the advantage that the restored image has the TV closer to that of the original image, compared to the classical gradient descent approach. Numerical results show that our method is competitive compared to some recent ones. [ABSTRACT FROM AUTHOR]

• A novel rockburst prediction framework is raised based on microseismic monitoring and machine learning. • An integrated CNN-Adam-BO algorithm is proposed to recognize the microseismic sequence. • A field rockburst risk warning system is demonstrated. • Compared to BPNN, SVM, and two benchmark models, the CNN-Adam-BO model is the most superior. Rockburst is a dynamic geological disaster common during underground excavation, which significantly threatens the safety of personnel, equipment, and property. This paper proposes an integrated CNN-Adam-BO algorithm based on microseismic monitoring data to achieve real-time prediction of rockburst intensity. A total of 400 rockburst cases were collected from a water conveyance tunnel in northwestern China, including 100 no rockbursts, 252 low rockbursts, and 48 moderate rockbursts. During modeling, adaptive moment estimation optimization and Bayes optimization were separately used to tune the CNN network hyper-parameters (i.e., convolution kernels and bias) as well as dropout probability, and a parametric analysis was carried out to optimize the CNN structure and training parameters (i.e., the CNN architecture, the number of kernels in the convolutional layer, the number of neurons in the full connection layer, and the number of training epochs). To assess model performance, 2 global metrics (i.e., accuracy and Kappa) and 3 within-class metrics (i.e., precision, recall, and F 1 -score) were introduced. Additionally, a comparison analysis with other machine learning models, such as a back-propagation neural network, a support vector machine, and two CNN-based benchmark models, was conducted in regard to prediction ability and running speed. Results show that the CNN-Adam-BO model is the most superior, which achieved an accuracy of 91.67%, Kappa of 0.8392, F 1 -score of 0.8750, 0.9474, and 0.8333 (on no/low/moderate rockburst), and running time of 190.12 s. Taking 2 extra rockburst cases as examples, a complete workflow for how to apply the constructed model to construct a field rockburst risk warning system was illustrated. Further, the effect of data quality, especially data imbalance, on model performance was discussed, indicating that the synthetic minority oversampling technique is an effective way to eliminate data imbalance. Finally, superiority of the dimension enhancement method of the microseismic sequence described in this paper was verified via comparison with the continuous wavelet transform and cross wavelet transform. [ABSTRACT FROM AUTHOR]

This study introduces the three-dimensional combined finite-discrete element method (3D FDEM) to perform cracking analysis of segmental linings under extreme conditions. Considering the complex contact interactions of segments, this study first proposes a polar-based GPGPU-parallelized contact detection algorithm to handle memory issues confronted by existing FDEM algorithms. Initially, a spatial decomposition approach based on the polar coordinate system is implemented during the broad search phase. Each tetrahedral element is positioned within suitable search cells according to the axis-aligned bounding box. Subsequently, element pairs within each search cell are iteratively traversed, and potential contact pairs are identified using the judge cell criteria. After the broad search, a narrow search phase is executed to determine all real contacts. Following the above implementation, a load-structure model encompassing soil spring and external pressure calculations is then proposed. Based on the shape functions and coordinate transformation, the formulations of soil springs and external loads are derived and parallelized in the 3D FDEM framework. Three numerical tests are presented to validate the effectiveness of the proposed approach. Simulation results confirm the suitability of the proposed method for cracking analysis of segmental linings. Compared to the existing methods, it reduces GPU memory usage by 56 ∼ 76 % without extending time, which enhances the computational scale of 3D FDEM simulations. Furthermore, the proposed method is applied to two engineering scenarios, i.e., straight and curved segmental linings, both considering the absence and presence of contact defects between segments. The results show that contact defects can significantly reduce the resistance of the structural system comprising bolts and concrete segments for straight and curved scenarios. [ABSTRACT FROM AUTHOR]

• An ensemble model AdaBoost-CART is proposed to predict rock mass classification. • SMOTE is utilized to address the imbalance ratio of rock mass classifications. • The AdaBoost-CART model performs better than conventional machine learning methods. • The variable importance of the model is analyzed. The real-time acquisition of surrounding rock information is important for the efficient tunneling and hazard prevention in tunnel boring machines (TBMs). This study presents an ensemble learning model based on classification and regression tree (CART) and AdaBoost algorithm to predict the classification of surrounding rock mass. Statistical indicators (i.e., mean value and standard deviation) of TBM operational parameters were calculated and used as input variables, and the rock mass classification obtained by the hydropower classification (HC) method was used as output variable. To develop the model, a database was established, consisting of 3166 samples collected from the Songhua River Water Conveyance Tunnel. The synthetic minority over-sampling technique (SMOTE) was utilized to address the imbalance ratio of rock mass classifications in the database. The results of the testing set showed that the accuracy and F1-measure of AdaBoost-CART were 0.865 and 0.770, respectively, which are better than the results of the standard CART (0.753 and 0.629, respectively). The application of SMOTE improves the recall of minority classes. Compared with artificial neural networks, k-nearest neighbor, and support vector classifier, the developed AdaBoost-CART model achieves better performance. The variable importance was analyzed to distinguish key features; the results showed that rock mass boreability may not be a major consideration of the HC method. The presented model can provide significant guidance for the real-time acquisition of surrounding rock information during TBM tunneling. [ABSTRACT FROM AUTHOR]

One significant factor influencing geothermal energy exploitation is the variation of the mechanical properties of rock in high temperature environments. Since rock is typically a heterogeneous granular material, thermal fracturing frequently occurs in the rock when the ambient temperature changes, which can greatly influence the geothermal energy exploitation. A numerical method based on the numerical manifold method (NMM) is developed in this study to simulate the thermo-elastic fracturing of rocklike granular materials. The Voronoi tessellation is incorporated into the pre-processor of NMM to represent the grain structure. A contact-based heat transfer model is developed to reflect heat interaction among grains. Based on the model, the transient thermal conduction algorithm for granular materials is established. To simulate the cohesion effects among grains and the fracturing process between grains, a damage-based contact fracture model is developed to improve the contact algorithm of NMM. In the developed numerical method, the heat interaction among grains as well as the heat transfer inside each solid grain are both simulated. Additionally, as damage evolution and fracturing at grain interfaces are also considered, the developed numerical method is applicable to simulate the geothermal-related thermal fracturing process. [ABSTRACT FROM AUTHOR]