[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.1
2.8
Journals
Processes
Special Issues
Security Intelligent Monitoring and Big Data Utilization in Coal Mining...
share announcement

Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Process Control and Monitoring".

Deadline for manuscript submissions: 25 October 2024 | Viewed by 4911

Special Issue Editors

Dr. Yuanyuan Pu

E-Mail Website
Guest Editor
School of Resource and Safety Engineering, Chongqing University, Chongqing 400044, China
Interests: rock signaling and coal-rock dynamic disaster; big data and data-driven methods in mines
Dr. Sitao Zhu

E-Mail Website
Guest Editor
School of Civil and Resource a Engineering, University of Science and Technology Beijing, Beijing, China
Interests: rock dynamics; microseismic monitoring; rockburst and mine earthquake disaster prevention
Dr. Xinglong Zhao

E-Mail Website
Guest Editor
State Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources, China University of Mining & Technology, Xuzhou, China
Interests: rock mechanics; hydraulic fracturing; stress disturbance; fracture propagation
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The coal mining process involves extensive movements of rock and coal masses. Such activities lead to significant alterations in geostress and tectonic stress, paving the way for various mining-induced dynamic disasters, including bursts of rock/coal, roof collapses, and gas outbursts. These incidents pose severe threats to the safety of mining operations. Consequently, various mining safety monitoring techniques, such as microseismic and electromagnetic monitoring, have been developed to oversee changes in the state of coal and surrounding rocks. These methods produce a vast array of data in diverse structures and formats. The effective processing, analysis, and utilization of these data are vital for enhancing mining safety by predicting and preventing dynamic disasters. Traditional data processing and analysis techniques, however, struggle with the complexity and nonlinear relationships inherent in monitoring data. In contrast, the recent surge in intelligent operations across society and everyday life has led to an abundance of data generation. Advances in data storage, transmission, and processing technologies (e.g., the advent of distributed file systems like HDFS, and the development of sophisticated machine learning models) have elevated data to a crucial resource for scientific research. Data-driven approaches, recognized as the fourth scientific paradigm—supplementing the traditional triad of experimentation, theory, and computation—hold significant promise. They are particularly valuable when conventional methods fail to resolve complex issues, allowing for insights to be gleaned directly from the data itself.

This Special Issue aims to develop security intelligent monitoring and big data utilization theories and technologies in the coal mining process. The topics of interest for this Special Issue include, but are not limited to, the following:

  • Novel field monitoring theories and engineering applications in mining;
  • Monitoring system optimization and improvement;
  • Monitoring data processing and analysis;
  • Prediction of mining disasters based on data-driven methods.

Dr. Yuanyuan Pu
Dr. Sitao Zhu
Dr. Xinglong Zhao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • intelligent monitoring
  • data processing and analysis
  • monitroing system optimization
  • microseismic monitoring
  • big data technology

Published Papers (8 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 7227 KiB  
Article
The Changing of Micromechanical Properties of Coal after Water Immersion: The Insight from Nanoindentation Test
by Wei Xiong, Qing Ye, Yuling Tan, Zhenzhen Jia and Guanglei Cui
Processes 2024, 12(8), 1636; https://doi.org/10.3390/pr12081636 - 3 Aug 2024
Viewed by 311
Abstract
The application of the hydrodynamic method has enhanced the extraction of coal bed methane (CBM). In this method, fracturing fluid rapidly penetrates the coal reservoir, altering its intrinsic pore structure and microscopic mechanical properties. These changes impact the properties of the coal reservoir [...] Read more.
The application of the hydrodynamic method has enhanced the extraction of coal bed methane (CBM). In this method, fracturing fluid rapidly penetrates the coal reservoir, altering its intrinsic pore structure and microscopic mechanical properties. These changes impact the properties of the coal reservoir and CBM depletion. It is, therefore, crucial to explore how these micro-characteristics evolve following water invasion. In this context, using nanoindentation tests, the microscopic characteristics of three coal samples were measured under dry conditions and at water saturations corresponding to 44% and 75% relative humidity. The influence of water immersion on the pore structure was also assessed using mercury injection experiments. Moreover, cluster analysis was used to categorize the extensive measured data into three sub-components: fractures (large pores), inertinite, and vitrinite, to investigate the impact of water saturation on microscopic properties. The findings indicate that cluster analysis is well-suited to these data, showing excellent agreement with porosity and maceral tests. The relationship between the elastic modulus and hardness of dry and wet coal samples varies across the sub-components. There is a notable dependency in the case of vitrinite, whereas water content tends to reduce this dependency. It is also found that water content negatively affects elastic modulus and hardness and reduces the anisotropy ratio. The mechanical properties of inertinite are highly responsive to water immersion, whereas vitrinite exhibits lesser sensitivity. The softening mechanisms of coal when immersed in water, such as calcite phase dissolution, swelling stress fracturing, and weakening of macerals, are identified. This study offers new perspectives on the impact of moisture on the alteration of micromechanical properties in coal. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Water invasion process during water hydraulic fracturing and the induced variation of micro-properties. (<b>a</b>) Illustration of hydraulic fracturing; (<b>b</b>) water invasion process; (<b>c</b>) basic component of coal; (<b>d</b>) changing of representative mineral; and (<b>e</b>) unsolved issue—how do the micro-mechanical properties of macerals change?</p> Full article ">Figure 2
<p>Experiment process for nano-indentation test. (<b>a</b>) Sealed moisture equilibration chamber schematic; (<b>b</b>) KLA iMicro nano-indentation instrument; and (<b>c</b>) load and indentation depth relationship curve.</p> Full article ">Figure 3
<p>Sample surface at microscopic scale. (<b>a</b>) Flat surface and (<b>b</b>) defective surface.</p> Full article ">Figure 4
<p>Pore size distribution: (<b>a</b>) logarithmic coordinates and (<b>b</b>) linear coordinates.</p> Full article ">Figure 5
<p>Nano-indentation test results for dry sample.</p> Full article ">Figure 6
<p>Nano-indentation test results for the sample with 44% humidity.</p> Full article ">Figure 7
<p>Nano-indentation test results for the sample with 75% humidity.</p> Full article ">Figure 8
<p>Clustering analysis of dry sample in both (<b>a</b>) vertical and (<b>b</b>) horizontal bedding direction.</p> Full article ">Figure 9
<p>Clustering analysis of a sample with 44% humidity in (<b>a</b>) vertical and (<b>b</b>) horizontal bedding direction.</p> Full article ">Figure 10
<p>Clustering analysis of a sample with 75% humidity in (<b>a</b>) vertical and (<b>b</b>) horizontal bedding direction.</p> Full article ">Figure 11
<p>Comparison of proportion determined by the cluster analysis and maceral test.</p> Full article ">Figure 12
<p>Properties of fracture component before and after water immersion. (<b>a</b>) Horizontal bedding direction and (<b>b</b>) vertical bedding direction.</p> Full article ">Figure 13
<p>Properties of vitrinite component before and after water immersion. (<b>a</b>) Horizontal bedding direction and (<b>b</b>) vertical bedding direction.</p> Full article ">Figure 14
<p>Properties of inertinite component before and after water immersion. (<b>a</b>) Horizontal bedding direction and (<b>b</b>) vertical bedding direction.</p> Full article ">Figure 15
<p>Measured data before and after water immersion. (<b>a</b>) Horizontal bedding direction and (<b>b</b>) vertical bedding direction.</p> Full article ">Figure 16
<p>Properties of coal sample before and after water immersion. (<b>a</b>) Horizontal bedding direction and (<b>b</b>) vertical bedding direction.</p> Full article ">
21 pages, 13107 KiB  
Article
Mechanism and Prevention of Rock Burst in a Wide Coal Pillar under the Superposition of Dynamic and Static Loads
by Bangyou Jiang, Yanan Xu, Wenshuai Li, Shitan Gu and Mingjun Ding
Processes 2024, 12(8), 1634; https://doi.org/10.3390/pr12081634 - 3 Aug 2024
Viewed by 349
Abstract
To address the frequent occurrence of rock burst disasters in areas with wide coal pillars during mining in the western mining area of China, the wide coal pillar area of the Tingnan coal mine in Shanxi Province was used as the research background. [...] Read more.
To address the frequent occurrence of rock burst disasters in areas with wide coal pillars during mining in the western mining area of China, the wide coal pillar area of the Tingnan coal mine in Shanxi Province was used as the research background. Theoretical analysis, numerical simulation, and field tests were used to establish the mechanical criterion and the energy criterion for the dynamic instability of wide coal pillars. The process and mechanism of wide coal pillar dynamic instability under dynamic and static load disturbances were revealed, and a wide coal pillar rock burst prevention and control scheme was proposed. The results indicated that when the load above a coal pillar reached the stress failure index and the energy failure index was met, the coal pillar reached the critical conditions for rock burst. With increasing static load, the stress, energy, and range of the plastic zone all showed increasing trends on both sides of the coal pillar. Under a given dynamic load, the stress and plastic zone range of the coal pillar significantly increased compared to those without a dynamic load. Under a given static load, the greater the dynamic load, the more likely the coal pillar was to undergo dynamic instability. The evolution of coal pillar dynamic instability was divided into three stages: energy accumulation, local instability, and dynamic instability. When the critical stress and energy conditions for coal pillar dynamic instability are exceeded, rock burst will occur. To reduce the static and dynamic loads of coal pillars, a rock burst prevention and control scheme of energy release and load reduction was proposed and applied onsite. The monitoring results showed that this control plan effectively reduced the stress of the coal pillar and the dynamic load generated by the fracture of the overlying rock layer, indicating safe mining in this area of wide coal pillars. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>The area where a rock burst occurred in the 207 working face in the Tingnan coal mine.</p> Full article ">Figure 2
<p>Borehole stratigraphy of 207 working face in the Tingnan coal mine.</p> Full article ">Figure 3
<p>Numerical calculation model of roof–coal pillar.</p> Full article ">Figure 4
<p>Mechanical response contour maps of coal pillar under different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 5
<p>Mechanical response curves of coal pillar under different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 6
<p>Mechanical response contour maps of coal pillar under a given dynamic load (10 MPa) and different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 7
<p>Mechanical response curves of coal pillar under given dynamic load (10 MPa) and different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 7 Cont.
<p>Mechanical response curves of coal pillar under given dynamic load (10 MPa) and different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 8
<p>Mechanical response contour maps of coal pillar under a given static load (9 MPa) and different dynamic loads (5 MPa, 10 MPa, 15 MPa, and 20 MPa).</p> Full article ">Figure 8 Cont.
<p>Mechanical response contour maps of coal pillar under a given static load (9 MPa) and different dynamic loads (5 MPa, 10 MPa, 15 MPa, and 20 MPa).</p> Full article ">Figure 9
<p>Mechanical response curves of coal pillar under a given static load (9 MPa) and different dynamic loads (5 MPa, 10 MPa, 15 MPa, and 20 MPa).</p> Full article ">Figure 9 Cont.
<p>Mechanical response curves of coal pillar under a given static load (9 MPa) and different dynamic loads (5 MPa, 10 MPa, 15 MPa, and 20 MPa).</p> Full article ">Figure 10
<p>Stress failure index of coal pillars under a given dynamic load (10 MPa) and different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 11
<p>Energy failure index of the coal pillar under a given dynamic load (10 MPa) and different static loads (5 MPa, 8 MPa, 12 MPa, and 15 MPa).</p> Full article ">Figure 12
<p>Stress failure index of coal pillars under a given static load (9 MPa) and different dynamic loads (5 MPa, 10 MPa, 15 MPa, and 20 MPa).</p> Full article ">Figure 13
<p>Energy failure index of coal pillars under a given static load (9 MPa) and different dynamic loads (5 MPa, 10 MPa, 15 MPa, and 20 MPa).</p> Full article ">Figure 14
<p>Mechanical response of a coal pillar before and after dynamic loads are applied.</p> Full article ">Figure 15
<p>Evolution process of coal pillar dynamic instability.</p> Full article ">Figure 16
<p>Layout plan of the 3409 working face in the Tingnan coal mine.</p> Full article ">Figure 17
<p>Stratigraphic diagram of the ZK5-4 borehole (partial) of the 3409 working face in the Tingnan coal mine.</p> Full article ">Figure 18
<p>Layout diagram of the shallow and deep blasting holes around coal pillar of the 3409 working face in the Tingnan coal mine.</p> Full article ">Figure 19
<p>Schematic diagram of plane view of drilling hole around the coal pillar of the 3409 working face in the Tingnan coal mine.</p> Full article ">Figure 20
<p>Microseismic monitoring data during mining around the coal pillar of the 3409 working face in the Tingnan coal mine.</p> Full article ">Figure 21
<p>Stress monitoring data collected during the mining period around the coal pillar of the 3409 working face in the Tingnan coal mine.</p> Full article ">
17 pages, 11091 KiB  
Article
Research on Wave Velocity Disparity Characteristics between Impact and Outburst Coal Seams and Tomography of Hazardous Zones
by Zhixin Fang, Qiang Liu, Liming Qiu, Zhanbiao Yang, Zhaohui Cao, Guifeng Wang, Zehua Niu and Yingjie Zhao
Processes 2024, 12(8), 1558; https://doi.org/10.3390/pr12081558 - 25 Jul 2024
Viewed by 311
Abstract
To investigate the variations in wave velocity fields between impact and outburst coal seams, we analyzed the fluctuations in wave velocity under loading conditions for both coal types. A comprehensive methodology was developed to correct coal wave velocities in response to stress and [...] Read more.
To investigate the variations in wave velocity fields between impact and outburst coal seams, we analyzed the fluctuations in wave velocity under loading conditions for both coal types. A comprehensive methodology was developed to correct coal wave velocities in response to stress and gas presence, which was then applied to field assessments of hazardous regions. Our findings reveal significant differences in wave velocity alterations between impact and outburst coal seams during loading-induced failure. Gas pressure exhibits a negative correlation with wave velocity in outburst coal (correlation coefficient R2 = 0.86), whereas wave velocity in impact coal demonstrates a positive correlation with stress (R2 = 0.63). A robust methodology for correcting coal wave velocities in response to stress and gas presence was established to enable more accurate measurement of wave velocity changes. In field applications, seismic wave computed tomography identified stress anomalies that closelycorresponded with geological structures and mining operations, effectively pinpointing hazardous zones. The abnormal wave velocity coefficient ranges for outburst coal seams and impact coal seams are −0.6 to 0.25 and −0.35 to 0.16, respectively, which correspond well with the field stress distribution. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Flowchart.</p> Full article ">Figure 2
<p>Experiment system.</p> Full article ">Figure 3
<p>Schematic diagram of wave speed testing.</p> Full article ">Figure 4
<p>The variation law of outburst coal wave velocity with gas pressure.</p> Full article ">Figure 5
<p>The variation law of shock coal wave velocity with stress.</p> Full article ">Figure 6
<p>Comprehensive stress–gas coal body wave velocity changes.</p> Full article ">Figure 7
<p>Schematic diagram of detection principle.</p> Full article ">Figure 8
<p>Position of working face and distribution of sensors.</p> Full article ">Figure 9
<p>Comparison diagram of the upper and lower parts of the 11,224 working face well.</p> Full article ">Figure 10
<p>CT results of the original wave velocity field in the 11,224 working face. (<b>a</b>) Before correction; (<b>b</b>) Revised.</p> Full article ">Figure 11
<p>Abnormality coefficient <span class="html-italic">A</span><sub>n</sub> of original wave velocity in working face 11,224. (<b>a</b>) Before correction; (<b>b</b>) Revised.</p> Full article ">Figure 12
<p>Differences in wave velocity anomaly coefficients before and after correction.</p> Full article ">Figure 13
<p>Revised abnormal index V<sub>G</sub> of wave velocity gradient change.</p> Full article ">Figure 14
<p>Comparative analysis of abnormal wave velocity values.</p> Full article ">Figure 15
<p>Inversion results of abnormal wave velocity values before impact coal seam mining. (<b>a</b>) Wave velocity anomaly coefficient; (<b>b</b>) Abnormal coefficient of wave velocity gradient.</p> Full article ">Figure 16
<p>Inversion results of coal seam wave velocity anomaly value during mining of impacted coal seam. (<b>a</b>) Wave velocity anomaly coefficient; (<b>b</b>) Abnormal coefficient of wave velocity gradient.</p> Full article ">Figure 17
<p>Inversion results of abnormal coal seam wave velocity after impact coal seam mining (after mining). (<b>a</b>) Wave velocity anomaly coefficient; (<b>b</b>) Abnormal coefficient of wave velocity gradient.</p> Full article ">
19 pages, 12450 KiB  
Article
Study on the Application of Finite Difference in Geological Mine Fault Groups: A Case Study
by Jianbo Yuan, Chao Wang, Zhigang Liu, Jingchao Lyu, Yajun Lu, Wuchao You and Jiazheng Yan
Processes 2024, 12(6), 1162; https://doi.org/10.3390/pr12061162 - 5 Jun 2024
Viewed by 480
Abstract
Fault structures can cause a bad mining environment and increase the stress of surrounding coal pillar faults. The study investigates the stress evolution characteristics within fault structure groups and their surrounding coal pillars and explores the extent to which these fault structure groups [...] Read more.
Fault structures can cause a bad mining environment and increase the stress of surrounding coal pillar faults. The study investigates the stress evolution characteristics within fault structure groups and their surrounding coal pillars and explores the extent to which these fault structure groups influence the stress distribution in coal pillars. Based on three-dimensional modeling technology, a transparent geological model of the geological environment of fault structure groups was constructed and finite difference software was used to generate a numerical simulation model. Two survey lines and four survey points were arranged to analyze the stress distribution of a coal pillar fault. The results show that the fault structure groups have obvious stress barrier effects. There is a 35 m stress reduction zone in the hanging wall of the fault and a 30 m stress increase zone in the footwall of the fault. Both FL-1 and FL-3 faults have a stress barrier effect in the hanging wall. The obvious stress increases in the footwall of the fault are 37.7 MPa and 33.5 MPa, respectively. The stress of the FL-2 fault as a whole appears to be a more obvious superposition at the end of mining, and the peak stress reaches 41.5 MPa. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Location and plan of Xinglongzhuang coal mine.</p> Full article ">Figure 2
<p>Layout of 1313 working face.</p> Full article ">Figure 3
<p>Two-dimensional plan and three-dimensional transparent geological model.</p> Full article ">Figure 4
<p>Optimized model of coal seam.</p> Full article ">Figure 5
<p>Model construction process and overall model.</p> Full article ">Figure 6
<p>Numerical model and local amplification diagram.</p> Full article ">Figure 7
<p>Faults model.</p> Full article ">Figure 8
<p>Schematic diagram of normal fault principal stress state.</p> Full article ">Figure 9
<p>Mechanical diagram of fault model.</p> Full article ">Figure 10
<p>Schematic diagram of abutment stress at the end of mining.</p> Full article ">Figure 11
<p>Spatial structure and initial stress of coal seam.</p> Full article ">Figure 12
<p>Layout of survey lines and survey points.</p> Full article ">Figure 13
<p>Vertical stress diagram of survey points.</p> Full article ">Figure 14
<p>Vertical stress cloud slice diagram of survey lines.</p> Full article ">Figure 15
<p>Vertical stress diagram of the A survey line.</p> Full article ">Figure 16
<p>Vertical stress diagram of B survey line.</p> Full article ">Figure 17
<p>Tailgate roadway-2 excavation microseismic data distribution.</p> Full article ">Figure 17 Cont.
<p>Tailgate roadway-2 excavation microseismic data distribution.</p> Full article ">Figure 18
<p>Microseismic data distribution diagram during working face mining.</p> Full article ">
13 pages, 8192 KiB  
Article
Classification of Microseismic Signals Using Machine Learning
by Ziyang Chen, Yi Cui, Yuanyuan Pu, Yichao Rui, Jie Chen, Deren Mengli and Bin Yu
Processes 2024, 12(6), 1135; https://doi.org/10.3390/pr12061135 - 31 May 2024
Viewed by 333
Abstract
The classification of microseismic signals represents a fundamental preprocessing step in microseismic monitoring and early warning. A microseismic signal source rock classification method based on a convolutional neural network is proposed. First, the characteristic parameters of the microseismic signals are extracted, and a [...] Read more.
The classification of microseismic signals represents a fundamental preprocessing step in microseismic monitoring and early warning. A microseismic signal source rock classification method based on a convolutional neural network is proposed. First, the characteristic parameters of the microseismic signals are extracted, and a convolutional neural network is constructed for the analysis of these parameters; then, the mapping relationship model between the characteristic parameters of the microseismic signals and the rock class is established. The feasibility of the proposed method in differentiating acoustic emission signals under different load conditions is verified by using acoustic emission data from laboratory uniaxial compression tests, Brazilian splitting tests, and shear tests. In the three distinct laboratory experiments, the proposed method achieved a source rock classification accuracy of greater than 90% for acoustic emission signals. The proposed and verified method provides a new basis for the preprocessing of microseismic signals. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Workflow source rock type identification for real microseismic signals.</p> Full article ">Figure 2
<p>Uniaxial compression acoustic emission signal experiments. (<b>a</b>) Test sample, (<b>b</b>) mechanical loading system, (<b>c</b>) acoustic emission monitoring system.</p> Full article ">Figure 3
<p>Shear failure acoustic emission signal experiments. (<b>a</b>) Test sample, (<b>b</b>) mechanical loading system.</p> Full article ">Figure 4
<p>Tensile failure acoustic emission signal experiments. (<b>a</b>) Test sample, (<b>b</b>) mechanical loading system.</p> Full article ">Figure 5
<p>Overview of common microseismic signal parameters used for rock type identifying. (<b>a</b>) Time domain characteristic parameter; (<b>b</b>) Frequncy domain characteristic parameter; (<b>c</b>) One-dimensional eigenparameter matrix; <span class="html-italic">x</span><sub>1</sub>~<span class="html-italic">x</span><sub>10</sub> is the value of the feature parameter, T is the rock type of the damage source corresponding to the microseismic signal.</p> Full article ">Figure 6
<p>Network structure and parameter composition of T_Net.</p> Full article ">Figure 7
<p>Training framework and hyperparameter setting of rock class recognition model for microseismic signals.</p> Full article ">Figure 8
<p>The loss and accuracy variation for model training and validating under uniaxial compression failure mode. (<b>a</b>) Training and Validation accuracy during model training; (<b>b</b>) Training and Validation loss during model training.</p> Full article ">Figure 9
<p>Test results of the model under uniaxial compression failure mode. S stands for sandstone, M stands for mudstone, C stands for coal. (<b>a</b>) Test set data identification result confusion matrix; (<b>b</b>) Training set data and test set recognition accuracy.</p> Full article ">Figure 10
<p>The loss and accuracy variation for model training and validating under shear failure mode. (<b>a</b>) Training and Validation accuracy during model training; (<b>b</b>) Training and Validation loss during model training.</p> Full article ">Figure 11
<p>Test results of the model under shear failure mode. S stands for sandstone, M stands for mudstone, C stands for coal. (<b>a</b>) Test set data identification result confusion matrix; (<b>b</b>) Training set data and test set recognition accuracy.</p> Full article ">Figure 12
<p>The loss and accuracy variation for model training and validating under tensile failure mode. (<b>a</b>) Training and Validation accuracy during model training; (<b>b</b>) Training and Validation loss during model training.</p> Full article ">Figure 13
<p>Test results of the model under tensile failure mode. S stands for sandstone, M stands for mudstone, C stands for coal. (<b>a</b>) Test set data identification result confusion matrix; (<b>b</b>) Training set data and test set recognition accuracy.</p> Full article ">
23 pages, 5192 KiB  
Article
Method and Validation of Coal Mine Gas Concentration Prediction by Integrating PSO Algorithm and LSTM Network
by Guangyu Yang, Quanjie Zhu, Dacang Wang, Yu Feng, Xuexi Chen and Qingsong Li
Processes 2024, 12(5), 898; https://doi.org/10.3390/pr12050898 - 28 Apr 2024
Cited by 1 | Viewed by 690
Abstract
Gas concentration monitoring is an effective method for predicting gas disasters in mines. In response to the shortcomings of low efficiency and accuracy in conventional gas concentration prediction, a new method for gas concentration prediction based on Particle Swarm Optimization and Long Short-Term [...] Read more.
Gas concentration monitoring is an effective method for predicting gas disasters in mines. In response to the shortcomings of low efficiency and accuracy in conventional gas concentration prediction, a new method for gas concentration prediction based on Particle Swarm Optimization and Long Short-Term Memory Network (PSO-LSTM) is proposed. First, the principle of the PSO-LSTM fusion model is analyzed, and the PSO-LSTM gas concentration analysis and prediction model is constructed. Second, the gas concentration data are normalized and preprocessed. The PSO algorithm is utilized to optimize the training set of the LSTM model, facilitating the selection of the training data set for the LSTM model. Finally, the MAE, RMSE, and coefficient of determination R2 evaluation indicators are proposed to verify and analyze the prediction results. Gas concentration prediction comparison and verification research was conducted using gas concentration data measured in a mine as the sample data. The experimental results show that: (1) The maximum RMSE predicted using the PSO-LSTM model is 0.0029, and the minimum RMSE is 0.0010 when the sample size changes. This verifies the reliability of the prediction effect of the PSO-LSTM model. (2) The predictive performance of all models ranks as follows: PSO-LSTM > SVR-LSTM > LSTM > PSO-GRU. Comparative analysis with the LSTM model demonstrates that the PSO-LSTM model is more effective in predicting gas concentration, further confirming the superiority of this model in gas concentration prediction. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Typical gas concentration data one.</p> Full article ">Figure 2
<p>Typical gas concentration data two.</p> Full article ">Figure 3
<p>Structure diagram of PSO-LSTM model.</p> Full article ">Figure 4
<p>Raw time series with missing values.</p> Full article ">Figure 5
<p>Gap-filled data series.</p> Full article ">Figure 6
<p>Flow chart of PSO-LSTM model.</p> Full article ">Figure 7
<p>Convergence curve of the optimal fitness process.</p> Full article ">Figure 8
<p>Analysis of the effect of training sets with different monitoring data lengths on the pre-diction results: (<b>a</b>) 6 h; (<b>b</b>) 12 h; (<b>c</b>) 24 h; (<b>d</b>) 48 h.</p> Full article ">Figure 9
<p>Prediction results of sample data of gas concentration in Sample Two.</p> Full article ">Figure 10
<p>Training set, test set, validation set gas concentration prediction results.</p> Full article ">Figure 11
<p>Training set, validation set loss rate obtained from cross-validation.</p> Full article ">Figure 12
<p>Changes in evaluation indicators during cross-validation.</p> Full article ">Figure 13
<p>Gas concentration prediction results of Case 1.</p> Full article ">Figure 14
<p>Gas concentration prediction results of Case 2.</p> Full article ">Figure 15
<p>Comparison of the prediction performance of several typical algorithms.</p> Full article ">Figure 15 Cont.
<p>Comparison of the prediction performance of several typical algorithms.</p> Full article ">
16 pages, 2616 KiB  
Article
Improving Computer Vision-Based Wildfire Smoke Detection by Combining SE-ResNet with SVM
by Xin Wang, Jinxin Wang, Linlin Chen and Yinan Zhang
Processes 2024, 12(4), 747; https://doi.org/10.3390/pr12040747 - 7 Apr 2024
Viewed by 1045
Abstract
Wildfire is one of the most critical natural disasters that poses a serious threat to human lives as well as ecosystems. One issue hindering a high accuracy of computer vision-based wildfire detection is the potential for water mists and clouds to be marked [...] Read more.
Wildfire is one of the most critical natural disasters that poses a serious threat to human lives as well as ecosystems. One issue hindering a high accuracy of computer vision-based wildfire detection is the potential for water mists and clouds to be marked as wildfire smoke due to the similar appearance in images, leading to an unacceptable high false alarm rate in real-world wildfire early warning cases. This paper proposes a novel hybrid wildfire smoke detection approach by combining the multi-layer ResNet architecture with SVM to extract the smoke image dynamic and static characteristics, respectively. The ResNet model is improved via the SE attention mechanism and fully convolutional network as SE-ResNet. A fusion decision procedure is proposed for wildfire early warning. The proposed detection method was tested on open datasets and achieved an accuracy of 98.99%. The comparisons with AlexNet, VGG-16, GoogleNet, SE-ResNet-50 and SVM further illustrate the improvements. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Framework of proposed approach.</p> Full article ">Figure 2
<p>Residual learning in ResNet.</p> Full article ">Figure 3
<p>Network architecture of ResNet-50.</p> Full article ">Figure 4
<p>Feature pyramid network for wildfire smoke detection.</p> Full article ">Figure 5
<p>Procedure for HOG features vector extraction.</p> Full article ">Figure 6
<p>Image samples: (<b>a</b>) real wildfire smoke; (<b>b</b>) water mists; (<b>c</b>) clouds.</p> Full article ">Figure 7
<p>Image segmentation using SE-ResNet: (<b>a</b>) wildfire smoke and (<b>b</b>) false segmentation of water mists and clouds.</p> Full article ">
14 pages, 11041 KiB  
Article
The Distribution Law of Ground Stress Field in Yingcheng Coal Mine Based on Rhino Surface Modeling
by Zhi Tang, Zhiwei Wu, Dunwei Jia and Jinguo Lv
Processes 2024, 12(4), 668; https://doi.org/10.3390/pr12040668 - 27 Mar 2024
Viewed by 684
Abstract
The distribution law of the ground stress field is of great significance in guiding the design of coal mine roadway alignment, determining the parameters of roadway support, and preventing and controlling the impact of ground pressure in coal mines. A geostress inversion method [...] Read more.
The distribution law of the ground stress field is of great significance in guiding the design of coal mine roadway alignment, determining the parameters of roadway support, and preventing and controlling the impact of ground pressure in coal mines. A geostress inversion method combining Rhino surface modeling and FLAC3D 6.0 numerical simulation software is proposed. Based on the geological data of the coal mine and the results of on-site measurements, a three-dimensional geological model of Yingcheng Coal Mine is established for the geostress inversion, and the distribution law of the geostress field in Yingcheng Coal Mine is obtained. Research shows the following: (1) The horizontal maximum principal stress values of the Yingcheng Mine are between 33.9 and 35.3 MPa, the horizontal minimum principal stress values are between 23.6 and 25.4 MPa, and the direction of the horizontal maximum principal stress is roughly in the southwest to west direction; (2) the three-way principal stress magnitude relationship is σH > σv > σh, indicating that the horizontal stress dominates in the study area, which belongs to the slip-type stress state; (3) The maximum principal stress of No. 3 coal seam is 33.1–34.8 MPa, the middle principal stress is 27.5–29.2 MPa, and the minimum principal stress is 17.3–22.9 MPa. Due to the influence of topography and burial depth, there is a phenomenon of stress concentration in some areas. By comparing the inversion values with the measured values, the accuracy of the geostress inversion is high, and the initial geostress inversion method based on Rhino surface modeling accurately inverts the geostress distribution pattern of the Yingcheng coal mine. Full article
(This article belongs to the Special Issue Security Intelligent Monitoring and Big Data Utilization in Coal Mining Process)
►▼ Show Figures

Figure 1

Figure 1
<p>Arrangement of boreholes for ground stress measurements in the field.</p> Full article ">Figure 2
<p>Strain–displacement graph during stress relief of drilled hole: (<b>a</b>) Drilling ZK01; (<b>b</b>) Drilling ZK02; (<b>c</b>) Drilling ZK03.</p> Full article ">Figure 3
<p>Geological borehole fitted rock surface.</p> Full article ">Figure 4
<p>Three-dimensional geological model constructed by Rhino software.</p> Full article ">Figure 5
<p>FLAC3D three-dimensional geological model and boundary range.</p> Full article ">Figure 6
<p>The maximum principal stress cloud diagram of the −900 m horizontal elevation plane.</p> Full article ">Figure 7
<p>Maximum principal stress cloud of No. 3 coal seam.</p> Full article ">Figure 8
<p>Intermediate principal stress cloud of No. 3 coal seam.</p> Full article ">Figure 9
<p>Minimum principal stress cloud of the No. 3 coal seam.</p> Full article ">Figure 10
<p>Comparison of measured and calculated ground stress values: (<b>a</b>) Comparison of measured and calculated values for measurement point ZK01; (<b>b</b>) comparison of measured and calculated values for measurement point ZK02; (<b>c</b>) comparison of measured and calculated values for measurement point ZK03.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-8
Back to TopTop