Deep Learning-Based Acoustic Emission Source Localization in Heterogeneous Rock Media without Prior Wave Velocity Information DOI
Yi Cui, Jie Chen,

Ziyang Chen

et al.

Measurement Science and Technology, Journal Year: 2024, Volume and Issue: 36(1), P. 016011 - 016011

Published: Oct. 21, 2024

Abstract Acoustic emission (AE) source localization is crucial for monitoring but often relies on prior information, such as wave velocity and arrival time. This study introduces a novel method locating AE sources in rocks without addressing challenges posed by heterogeneous sensor arrays. Experiments involving pencil led break (PLB) tests sandstone cubes collected waveforms their coordinates. A ResNet-50 based deep learning model was developed to correlate the time-frequency spectra of with PLB locations, expressed spatial Gaussian distributions. The model, achieved 79% prediction accuracy complex environments. While there room improvement training data quantity diversity, results validate model’s effectiveness, particularly coal mines tunnel engineering.

Language: Английский

Bibliometric analysis and review of mine ventilation literature published between 2010 and 2023 DOI Creative Commons

Yan Xue,

Jinmiao Wang, Jun Xiao

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(4), P. e26133 - e26133

Published: Feb. 1, 2024

To provide scholars with a quick understanding of the current status, research hotspots, and future trends in field mine ventilation, this paper conducted visualized bibliometric analysis comprehensive review ventilation-related literature from 2010 to 2023 using CiteSpace. A thorough publication time, co-authorship, co-citation, keywords, topics was carried out. Based on this, through systematic reading summarization, ventilation were organized, analyzed, classified. The results indicate that went three stages: stable development, slow growth, rapid ascent. Nie Wen China Univ Min & Technol most prolific authors institutions ventilation. had highest number publications during 2010–2023, while Canada Poland exhibited centrality, signifying their key roles domain. Deep intelligent emerged as hotspots mainstream future. multiple hazard coupling studies represents direction needs develop. Numerical simulation techniques should not be limited static analysis, dynamic is focal area interest.

Language: Английский

Citations

18

Comparative study on blasting simulation vibration reduction and field vibration reduction experiment of adjacent oil pipeline DOI Creative Commons

Y. Chen,

Ruichong Zhang,

Lifang Liang

et al.

Frontiers in Earth Science, Journal Year: 2025, Volume and Issue: 12

Published: Jan. 9, 2025

Introduction Yongxing Tunnel No.1’s complex geology near a buried oil pipeline on the Guizhou-Nanning high-speed route poses blasting risks. Prioritizing safety, efforts focus minimizing vibration impacts. Methods Research uses numerical simulations and field tests to analyze three delay times spacing charge materials for reduction. Results Optimal is 30 ms, yielding 0.52 cm/s velocity, 20%-29% lower than 28 ms 32 ms. Soil most effective spacer, achieving 0.46 cm/s, 30.30%-22.03% water air. Field align with simulations. Discussion Findings provide reference optimal reduction safe construction under similar conditions.

Language: Английский

Citations

0

A fast and reliable crack measurement approach based on perspective projection simulation models and UAV imaging for dam and levee inspections DOI
Xianwei Wang, Yidan Wang, Yuli Wang

et al.

Survey Review, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 12

Published: April 7, 2025

Language: Английский

Citations

0

Partition feature extraction of hyperspectral images for in situ intelligent lithology identification DOI Creative Commons
Zhenhao Xu, Shan Li, Peng Lin

et al.

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0

Landslide Susceptibility Assessment by Using Publicly‐Available Remote Sensing and Geospatial Data to Assist Risk Management and Geological Safety: A Case Study of the Wugongshan Area, South China DOI
Zeyu Yang,

Ruonan Jia,

Kai Liu

et al.

Transactions in GIS, Journal Year: 2025, Volume and Issue: 29(2)

Published: April 1, 2025

ABSTRACT The Wugongshan area has undergone complex geological evolution since Neoproterozoic, creating a wealth of natural relics that support tourism development, but also triggering frequent landslides threaten local sustainability. However, the primary factors remain unclear. Based on 692 historical in this area, eight potentially related to were selected for susceptibility assessment, including elevation, slope, aspect, lithology, distance fault, water system, transportation and Normalized Difference Vegetation Index. They are then applied with information quantity model value‐logistic regression coupled model, respectively, assess generate risk zoning maps ArcGIS platform. accuracy values two models 0.787 0.786, suggesting reliable assessment result. validation results suggest is better at dealing larger datasets environments. Elevation, system mainly responsible Wugongshan. framework developed by using public data relevant improving quality geohazard prevention safety other similar areas worldwide.

Language: Английский

Citations

0

Current Status and Outlook of Roadbed Slope Stability Research: Study Based on Knowledge Mapping Bibliometric Network Analysis DOI Open Access
Jiawei Chen, Chengyu Xie, Wentao Zhang

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(9), P. 4176 - 4176

Published: May 6, 2025

Landslide hazards on roadbed slopes pose significant safety risks, leading to casualties, property losses, and environmental damage. With the rapid expansion of global railway highway construction, slope stability has become a critical research focus. However, systematic reviews prospective studies based bibliometric analysis in this field remain limited; such lack is likely lead lag theoretical development field. To address gap, study analyzes 453 papers from 2014 2023 using Web Science (WOS) core collection tools like VOSviewer, CiteSpace, Bibliometrix R. This focuses following: (i) Visualizing trends through knowledge graphs, covering document quantity, authors, countries, keywords. (ii) The objectives, methods, specific objects, conditions literature are categorized discussed, limitations numerical simulation other shortcomings pointed out. (iii) Future directions, focusing actual working utilizing advanced flexible subroutine functions simulate complex with multi-physical coupling, discussed ensure accuracy sustainability road construction development. paper can help scholars comprehensively quickly understand status hotspots research, view providing support for future exploration.

Language: Английский

Citations

0

Numerical Simulation of Dam-Break Flood Routing in Pumped Storage Power Stations with Multi-Conditions and Disaster Impact Analysis DOI

Baojun Guan,

Jingming Hou,

Jiahao Lv

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: 39(2), P. 741 - 757

Published: Dec. 20, 2024

Language: Английский

Citations

3

Enhancing Microseismic Signal Classification in Metal Mines Using Transformer-Based Deep Learning DOI Open Access
Pingan Peng, Lei Ru, Jinmiao Wang

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(20), P. 14959 - 14959

Published: Oct. 17, 2023

As microseismic monitoring technology gains widespread application in mine risk pre-warning, the demand for automatic data processing has become increasingly evident. One crucial requirement that emerged is classification of signals. To address this, we propose a Transformer-based method signal classification, leveraging global feature extraction capability Transformer model. Firstly, original waveform were framed, windowed, and feature-extracted to obtain 16 × matrix, serving as primary input subsequent models. Then, verified performance model compared with five models, including VGG16, ResNet18, ResNet34, SVM, KNN. The experimental results demonstrate effectiveness model, which outperforms previous methods terms accuracy, precision, recall, F1 score. In addition, comprehensive analysis was performed investigate impact model’s parameters importance on outcomes, provides valuable reference further enhancing performance.

Language: Английский

Citations

6

A Review on Mine Fire Prevention Technology and Theory Based on Bibliometric Analysis DOI Open Access
Dongping Shi, Xun Liu,

Liwen He

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(24), P. 16639 - 16639

Published: Dec. 7, 2023

Of all mine disasters, fires are very threatening to safety and often lead the most serious consequences. Research on fire prevention technology theory has experienced significant growth is attracting escalating academic interest attention. However, dedicated literature reviews this topic scarce. For purpose of uncovering research characteristics trends theory, paper employs bibliometric analysis using Web Science Core Collection database. This study presents a detailed relevant articles published between 2010 2022. An assessment influences journals, countries, institutions, authors was conducted through citation analysis. Furthermore, describes co-authorship networks among different authors. Lastly, review techniques theories researched during period carried out keyword clustering Four main topics in were identified: “mine control technology”, occurrence mechanism”, prediction monitoring technology”. Additionally, spontaneous combustion its underlying mechanisms may represent potential focus for future research. These findings contribute providing solid foundation endeavors field prevention.

Language: Английский

Citations

3

Classification of Microseismic Signals Using Machine Learning DOI Open Access
Ziyang Chen,

Yi Cui,

Yuanyuan Pu

et al.

Processes, Journal Year: 2024, Volume and Issue: 12(6), P. 1135 - 1135

Published: May 31, 2024

The classification of microseismic signals represents a fundamental preprocessing step in monitoring and early warning. A signal source rock method based on convolutional neural network is proposed. First, the characteristic parameters are extracted, constructed for analysis these parameters; then, mapping relationship model between class established. feasibility proposed differentiating acoustic emission under different load conditions verified by using data from laboratory uniaxial compression tests, Brazilian splitting shear tests. In three distinct experiments, achieved accuracy greater than 90% signals. provides new basis

Language: Английский

Citations

0