Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 9, Issue 2, 2025

Application of Deep Learning in Mining Accident Prediction

Download as PDF

DOI: 10.23977/acss.2025.090204 | Downloads: 18 | Views: 513

Author(s)

Bin Li 1

Affiliation(s)

1 Yuanbaoshan Open-pit Coal Mine, Inner Mongolia Pingzhuang Coal Industry (Group) Co., Ltd., Chifeng City, 024076, Inner Mongolia, China

Corresponding Author

Bin Li

ABSTRACT

Accident prediction is crucial in the mining process, but existing methods have limitations in capturing the spatiotemporal correlation and dynamic changes of the mine environment, making it difficult to accurately predict the propagation path and impact range of accidents. To this end, this paper applies a graph neural network (GNN) model, constructs a graph structure based on the mine environment, and optimizes the accident propagation prediction algorithm to improve the accuracy and real-time performance of accident prediction. In view of the diversity of mine data, this paper constructs three main graph structures: sensor network graph (based on sensor data correlation), mine area topology graph (based on the interactive relationship between personnel, equipment and mine area units) and accident propagation path graph (based on accident trigger points and impact range). The edge weights of the sensor network graph are calculated by the Pearson correlation coefficient (PCC), the edge weights of the mining area topology graph are calculated by normalizing the number of interactions, and the edge weights of the accident propagation path graph are dynamically updated using the Gaussian decay model. In order to further improve the spatiotemporal modeling capabilities of accident prediction, this paper uses a spatiotemporal graph neural network (ST-GNN) combined with a graph convolutional network (GCN) for spatial information extraction, and a temporal convolutional network (TCN) for time series modeling. The experimental results show that the proposed GNN model has significantly improved the accident prediction accuracy, accident propagation path identification accuracy and response time. The accident prediction accuracy of ST-GNN (this study) is 92.3%, and the F1-score is 0.91, which is excellent. ST-GNN performs well in predicting accident propagation paths, can accurately capture the chain reaction of mine accidents, and provides strong support for mine safety management.

KEYWORDS

Mine Environment Modeling; Graph Neural Network; Accident Propagation Prediction; Spatiotemporal Graph Neural Network; Mining Safety Monitoring

CITE THIS PAPER

Bin Li, Application of Deep Learning in Mining Accident Prediction. Advances in Computer, Signals and Systems (2025) Vol. 9: 26-34. DOI: http://dx.doi.org/10.23977/acss.2025.090204.

REFERENCES

[1] Javaid A, Siddique M A, Reshi A A, et al. Coal mining accident causes classification using voting-based hybrid classifier (VHC)[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(10): 13211-13221.
[2] Ye Z, Shoufeng T, Ke S, et al. An evaluation of the mine water inrush based on the deep learning of ISMOTE[J. Natural Hazards, 2023, 117(2): 1475-1491.
[3] Ramos P M S, Macedo J B, Maior C B S, et al. Combining BERT with numerical variables to classify injury leave based on accident description[J]. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 2024, 238(5): 945-956.
[4] Masood M M, Verma T, Seervi V. Development of an algorithm for the prediction of slope failure in surface mines[J]. Journal of the Institution of Engineers (India): Series D, 2024, 105(2): 875-885.
[5] Trirat P, Yoon S, Lee J G. MG-TAR: Multi-view graph convolutional networks for traffic accident risk prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(4): 3779-3794.
[6]Tang K H D. Artificial intelligence in occupational health and safety risk Management of Construction, mining, and oil and gas sectors: advances and prospects[J]. J. Eng. Res. Rep, 2024, 26(6): 241-253.
[7] Youhua M O, Zhang P, Yishuo G U, et al. Exploration of predicting occupational injury severity based on LightGBM model and model interpretability method[J]. Journal of Environmental and Occupational Medicine, 2025, 42(2): 157-164.
[8] Bing Z, Wang X, Dong Z, et al. A novel edge computing architecture for intelligent coal mining system[J]. Wireless Networks, 2023, 29(4): 1545-1554.
[9] Hui L I U, Guiqin L I U, Dianyan N, et al. Mine water inrush prediction method based on VMD-DBN model[J]. Coal Geology & Exploration, 2023, 51(6): 13-21.
[10] Mostofi F, Toğan V. Predicting construction accident outcomes using graph convolutional and dual-edge safety networks[J]. Arabian Journal for Science and Engineering, 2024, 49(10): 13315-13332.
[11] Babaeian M, Sereshki F, Ataei M, et al. Application of soft computing, statistical and multi-criteria decision-making methods to develop a predictive equation for prediction of flyrock distance in open-pit mining[J]. Mining, 2023, 3(2): 304-333.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 38554
Visits: 697982

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.