Applied Sciences

Research

17 pages, 1715 KiB

Open AccessArticle

Urban Quarry Ground Vibration Forecasting: A Matrix Factorization Approach

by Hajime Ikeda, Masato Takeuchi, Elsa Pansilvania, Brian Bino Sinaice, Hisatoshi Toriya, Tsuyoshi Adachi and Youhei Kawamura

Appl. Sci. 2023, 13(23), 12674; https://doi.org/10.3390/app132312674 - 25 Nov 2023

Viewed by 1353

Abstract

Blasting is routinely carried out in urban quarry sites. Residents or houses around quarry sites are affected by the ground vibrations induced by blasting. Peak Particle Velocity (PPV) is used as a metric to measure ground vibration intensity. Therefore, many prediction models of [...] Read more.

Blasting is routinely carried out in urban quarry sites. Residents or houses around quarry sites are affected by the ground vibrations induced by blasting. Peak Particle Velocity (PPV) is used as a metric to measure ground vibration intensity. Therefore, many prediction models of PPV using experimental methods, statistical methods, and Artificial Neural Networks (ANNs) have been proposed to mitigate this effect. However, prediction models using experimental and statistical methods have a tendency of poor prediction accuracy. In addition, while prediction models using ANNs can produce a highly accurate prediction results, a large amount of measured data is necessarily collected. In an urban quarry site where the number of blastings is limited, it is difficult to collect a lot of measured data. In this study, a new PPV prediction method using Weighted Non-negative Matrix Factorization (WNMF) is proposed. WNMF is a method that approximates a non-negative matrix (including missing data) to the product of two low-dimensional matrices and predicts the missing data. In addition, WNMF is one of the unsupervised learning methods, so it can predict PPV regardless of the amount of data. In this study, PPV was predicted using measured data from 100 sites at the Mikurahana quarry site in Japan. As a result, the proposed method showed higher accuracy when using measured data at 60 sites rather than 100 sites, and the root mean square error for PPV prediction decreased from 0.1759 (100 points) to 0.1378 (60 points). Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

18 pages, 14875 KiB

Open AccessArticle

Deep Learning-Based Estimation of Muckpile Fragmentation Using Simulated 3D Point Cloud Data

by Hajime Ikeda, Taiga Sato, Kohei Yoshino, Hisatoshi Toriya, Hyongdoo Jang, Tsuyoshi Adachi, Itaru Kitahara and Youhei Kawamura

Appl. Sci. 2023, 13(19), 10985; https://doi.org/10.3390/app131910985 - 5 Oct 2023

Cited by 5 | Viewed by 2010

Abstract

This research introduces an innovative technique for estimating the particle size distribution of muckpiles, a determinant significantly affecting the efficiency of mining operations. By employing deep learning and simulation methodologies, this study enhances the precision and efficiency of these vital estimations. Utilizing photogrammetry [...] Read more.

This research introduces an innovative technique for estimating the particle size distribution of muckpiles, a determinant significantly affecting the efficiency of mining operations. By employing deep learning and simulation methodologies, this study enhances the precision and efficiency of these vital estimations. Utilizing photogrammetry from multi-view images, the 3D point cloud of a muckpile is meticulously reconstructed. Following this, the particle size distribution is estimated through deep learning methods. The point cloud is partitioned into various segments, and each segment’s distinguishing features are carefully extracted. A shared multilayer perceptron processes these features, outputting scores that, when consolidated, provide a comprehensive estimation of the particle size distribution. Addressing the prevalent issue of limited training data, this study utilizes simulation to generate muckpiles and consequently fabricates an expansive dataset. This dataset comprises 3D point clouds and corresponding particle size distributions. The combination of simulation and deep learning not only improves the accuracy of particle size distribution estimation but also significantly enhances the efficiency, thereby contributing substantially to mining operations. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

11 pages, 4463 KiB

Open AccessArticle

Experimental Study of Three-Dimensional Time Domain of Water Evaporation from Goaf

by Chuanbo Cui, Zhipeng Jiao, Yuying Zhou, Shuguang Jiang, Yanwei Yuan, Jiangjiang Li and Zhiqiang Song

Appl. Sci. 2023, 13(13), 7932; https://doi.org/10.3390/app13137932 - 6 Jul 2023

Viewed by 1074

Abstract

Previous theories on coal spontaneous combustion (CSC) prevention and control mostly focused on how to improve the CSC-inhibiting effect instead of the failure of the inhibitors. Due to the influence of air leakage in the goaf, the inhibitors and the water in the [...] Read more.

Previous theories on coal spontaneous combustion (CSC) prevention and control mostly focused on how to improve the CSC-inhibiting effect instead of the failure of the inhibitors. Due to the influence of air leakage in the goaf, the inhibitors and the water in the coal evaporate continuously, thus making the effect of the inhibitors to inhibit coal spontaneous combustion weakened or even null. Due to the complex environment inside the goaf, it is difficult for personnel to enter and collect data such as coal moisture. Therefore, a three-dimensional model of the mining area was built to study the changes in coal moisture inside the goaf under different air leakage conditions. The analysis of the experimental results shows that the larger the air leakage volume is, the faster the moisture evaporates inside the goaf. The moisture of the coal body was reduced from 30% to about 5% in 15, 11 and 7 days when the air leakage was 0.02, 0.03 and 0.04 m³/s, respectively. The law of moisture evaporation at different times and locations in the mining area was also studied and it was found that the evaporation of moisture from the coal body in the mining area was location- and time-dependent. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

12 pages, 4759 KiB

Open AccessArticle

Influence of Discontinuous Linear Deformation on the Values of Continuous Deformations of a Mining Area and a Building Induced by an Exploitation of Hard Coal Seam

by Justyna Orwat

Appl. Sci. 2023, 13(6), 3549; https://doi.org/10.3390/app13063549 - 10 Mar 2023

Cited by 4 | Viewed by 1362

Abstract

In this article, the impact of a ground step on a residential building and a mining terrain has been presented. Influence of a discontinuous linear deformation by the changes of the inclination and curvatures’ values (continuous deformations) has been observed. Discontinuous and continuous [...] Read more.

In this article, the impact of a ground step on a residential building and a mining terrain has been presented. Influence of a discontinuous linear deformation by the changes of the inclination and curvatures’ values (continuous deformations) has been observed. Discontinuous and continuous deformations have been caused by an exploitation of the 405/1 hard coal seam, located at a depth of 550 m. Extraction was carried out with the use of the longwall system to the south of the building. A discontinuous linear deformation occurred parallel to a north wall of the building and had a height of 0.2 m. The inclination and curvatures’ values have been calculated on the basis of the results of the geodesic surveys. Vertical displacements and horizontal distances between the measuring points in the ground and on the building’s walls have been measured. Points in two perpendicular directions (parallel and perpendicular to a ground step) have been stabilized. The observational network consisted of 12 points (3 points in each direction, in the ground and on the walls). Research has shown that inclinations and curvatures have different values on a terrain’s surface and in buildings, which means that a deformation process takes place in a different way in the ground and a building. The obtained results indicate that an occurrence of a discontinuous linear deformation near the building reduces the values of inclinations and curvatures of a terrain surface and a building in a parallel direction to its longitudinal axis, and it increases the values of the continuous deformations in the direction perpendicular to it. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

12 pages, 3615 KiB

Open AccessArticle

Effect of Secondary Oxidation of Pre-Oxidized Coal on Early Warning Value for Spontaneous Combustion of Coal

by Chaowei Guo, Shuguang Jiang, Hao Shao, Zhengyan Wu and Marc Bascompta

Appl. Sci. 2023, 13(5), 3154; https://doi.org/10.3390/app13053154 - 1 Mar 2023

Cited by 11 | Viewed by 2142

Abstract

The indicative ability of a gas indicator for the spontaneous combustion of coal is affected by the secondary oxidation of oxidized coal, from old goafs, entering a new goaf through air leakages. This phenomenon can affect the accuracy of early warning systems regarding [...] Read more.

The indicative ability of a gas indicator for the spontaneous combustion of coal is affected by the secondary oxidation of oxidized coal, from old goafs, entering a new goaf through air leakages. This phenomenon can affect the accuracy of early warning systems regarding the spontaneous combustion of coal in a goaf. In this research, three kinds of coal were selected to carry out a spontaneous combustion simulation experiment in which a temperature-programmed experimental device was used to analyze the behavior of the index gas towards raw coal and oxidized coal, for which the latter was oxidized at 70 °C, 90 °C, 130 °C, and 150 °C. The results show that the chain alkane ratio in the secondary oxidation process and the trends of oxygen, CO, and C₂H₄ concentrations are the same as those in the primary oxidation process. On the other hand, the temperature at which C₂H₄ initially appears, during secondary oxidation, is lower than in primary oxidation. The CO produced in the early stage of secondary oxidation is greater than the CO produced, at the same temperature, in primary oxidation. In this regard, the usage of C₂H₄ concentration as an indicator with which to judge the occurrence of the spontaneous combustion of coal would allow for an earlier response. In the secondary oxidation process, the temperature of the extreme value of the alkene ratio appears higher than in primary oxidation. The presence of a higher pre-oxidation temperature and a higher proportion of secondary oxidation gas will affect an indicator’s judgement when the primary oxidation enters the severe oxidation stage. The gas produced by secondary oxidation will affect the early warning of the spontaneous combustion of coal in the coal mine goaf, which should be considered in the establishment of an early warning system. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

21 pages, 5186 KiB

Open AccessArticle

Application of Bayesian Neural Network (BNN) for the Prediction of Blast-Induced Ground Vibration

by Yewuhalashet Fissha, Hajime Ikeda, Hisatoshi Toriya, Tsuyoshi Adachi and Youhei Kawamura

Appl. Sci. 2023, 13(5), 3128; https://doi.org/10.3390/app13053128 - 28 Feb 2023

Cited by 25 | Viewed by 4757

Abstract

Rock blasting is one of the most common and cost-effective excavation techniques. However, rock blasting has various negative environmental effects, such as air overpressure, fly rock, and ground vibration. Ground vibration is the most hazardous of these inevitable impacts since it has a [...] Read more.

Rock blasting is one of the most common and cost-effective excavation techniques. However, rock blasting has various negative environmental effects, such as air overpressure, fly rock, and ground vibration. Ground vibration is the most hazardous of these inevitable impacts since it has a negative impact not only on the environment of the surrounding area but also on the human population and the rock itself. The PPV is the most critical base parameter practice for understanding, evaluating, and predicting ground vibration in terms of vibration velocity. This study aims to predict the blast-induced ground vibration of the Mikurahana quarry, using Bayesian neural network (BNN) and four machine learning techniques, namely, gradient boosting, k-neighbors, decision tree, and random forest. The proposed models were developed using eight input parameters, one output, and one hundred blasting datasets. The assessment of the suitability of one model in comparison to the others was conducted by using different performance evaluation metrics, such as R, RMSE, and MSE. Hence, this study compared the performances of the BNN model with four machine learning regression analyses, and found that the result from the BNN was superior, with a lower error: R = 0.94, RMSE = 0.17, and MSE = 0.03. Finally, after the evaluation of the models, SHAP was performed to describe the importance of the models’ features and to avoid the black box issue. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

16 pages, 2535 KiB

Open AccessArticle

Optimization of BP Neural Network Model for Rockburst Prediction under Multiple Influence Factors

by Chao Wang, Jianhui Xu, Yuefeng Li, Tuanhui Wang and Qiwei Wang

Appl. Sci. 2023, 13(4), 2741; https://doi.org/10.3390/app13042741 - 20 Feb 2023

Cited by 8 | Viewed by 2693

Abstract

Rockbursts are serious threats to the safe production of mining, resulting in great casualties and property losses. The accurate prediction of rockburst is an important premise that influences the safety and health of miners. As a classical machine learning algorithm, the back propagation [...] Read more.

Rockbursts are serious threats to the safe production of mining, resulting in great casualties and property losses. The accurate prediction of rockburst is an important premise that influences the safety and health of miners. As a classical machine learning algorithm, the back propagation (BP) neural network has been widely used in rockburst prediction. However, there are few reports about the influence study of different training sample sizes, optimization algorithms and index dimensionless methods on the prediction accuracy of BP neural network models. Therefore, 100 groups of typical rockburst engineering samples were collected locally and abroad, and considering the relevance, scientificity and quantifiability of the prediction indexes, the ratio of the maximum tangential stress of surrounding rock to the rock uniaxial compressive strength (σ_θ/σ_c), the ratio of the rock uniaxial compressive strength to the rock uniaxial tensile strength (σ_c/σ_t) and the elastic energy index (W_et) were chosen as the prediction indexes. When the number of samples was 40, 70 and 100, sixty improved BP models were established based on the standard gradient descent algorithm and four optimization algorithms (momentum gradient descent algorithm, quasi-Newton algorithm, conjugate gradient algorithm, Levenberg–Marquardt algorithm) and four index dimensionless methods (unified extreme value processing method, differentiated extreme value processing method, data averaging processing method, normalized processing method). The prediction performances of each improved model were compared with those of standard BP models. The comparative study results indicate that the sample size, optimization algorithm and dimensionless method have different effects on the prediction accuracy of BP models, which are described as follows: (1) The prediction accuracy value A of the BP model increases with the addition of sample size. The average value A_ave of twenty improved models under three kinds of sample sizes increases from A_ave (40) = 69.7% to A_ave (100) = 75.3%, with a maximal value A_max from A_max (40) = 85.0% to A_max (100) = 97.0%. (2) The value A and comprehensive accuracy value C of the BP model based on four optimization algorithms are generally higher than those of the standard BP model. (3) The improved BP model based on the unified extreme value processing method combined with the Levenberg–Marquardt algorithm has the highest value A_max (100) = 97.0% and value C = 194, and the prediction results of five engineering cases are completely consistent with the actual situation at the site, so this is the best BP neural network model selected in this paper. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

17 pages, 15396 KiB

Open AccessArticle

Experimental Analysis of Pressure Relief Effect of Surrounding Rock in High-Stress Roadways under Different Drilling Parameters

by Ping Wang, Yongzhi Jiang, Peng Li, Jinlian Zhou and Ze Zhou

Appl. Sci. 2023, 13(4), 2511; https://doi.org/10.3390/app13042511 - 15 Feb 2023

Cited by 7 | Viewed by 1733

Abstract

Drilling to relieve pressure is a simple and efficient solution to prevent impact ground pressure for the engineering problem of the high risk of impact on the surrounding rock of high stress roads, and choosing suitable drilling parameters is the key to it. [...] Read more.

Drilling to relieve pressure is a simple and efficient solution to prevent impact ground pressure for the engineering problem of the high risk of impact on the surrounding rock of high stress roads, and choosing suitable drilling parameters is the key to it. The unloading law of borehole diameter, depth, and spacing was investigated using a combination of indoor tests, numerical simulations, and theoretical analysis. The characteristics of crack extension and plastic zone changes of the three were analyzed, and the relationship between boreholes and elastic strain energy was derived by developing a hole mechanics model. The findings indicate that as drilling radius and depth are increased, peak strength and the elastic strain energy stored in front of the peak decrease, the plastic zone around the hole and the main control crack on the surface of the block expand more obviously, and the vertical stress at the top and bottom of the hole decrease, and the peak stress increases with the depth of the hole. The plastic zone surrounding the hole is attached to one another more easily the closer the drilling spacing is. The test block is changed from independent damage to penetrating damage when the drilling spacing is less than or equal to 3.286 cm. However, the pressure release effect does not necessarily improve with narrower drilling spacing. The plastic zone radius and the elastic strain energy held in the rock body are linked to each other linearly and quadratically, respectively, by the drilling radius. The joint pressure relief of several holes should be prioritized when drilling pressure is relieved, and then the hole’s diameter should be increased, and, finally, the hole’s depth should be increased. A reference for engineering applications is provided by this. Full article

(This article belongs to the Special Issue Mining Safety: Challenges & Prevention)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Mining Safety: Challenges & Prevention

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI