Skip to main content
SpringerLink
Log in

Method for Quickly Identifying Mine Water Inrush Using Convolutional Neural Network in Coal Mine Safety Mining

  • Published:
Wireless Personal Communications Aims and scope Submit manuscript

Abstract

In the early stage of water inrush prevention, accurate and rapid identification of water source is required to play an early warning role in water inrush prevention and control. The AF structure is a multi-layer network model between the shallow layer and the deep layer, which can reduce the original spectral data to 2 dimensions. In order to make the dimensionality reduction model sparse, a convolutional neural network layer is added to the traditional AF algorithm. First, the unsupervised learning algorithm is used to reduce the dimension of the original spectral data, so as to reduce the influence of redundant information in the spectral data on clustering. The identification of coal mine water source type runs through the early prediction and later treatment of water inrush prevention and control. Secondly, a mine inrush water source identification model of support vector machine and convolutional neural network is constructed. On this basis, an improved frog jump optimization algorithm for mine inrush water source identification is proposed to solve the local optimal solution problem caused by the randomness of initial weight setting of convolutional neural network. Compared with convolution and neural network, the recognition rate of the optimized leapfrog optimization algorithm is improved. Finally, the model is optimized from the aspects of performance fluctuation, function singleness and constraint of training mode, and combined with the demand of water source identification. The optimized model has the characteristics of anti-interference, functional expansibility and online identification, etc., and its effectiveness is verified by standard data set, which is extended to the water source spectral data, so as to assist the prevention and control of coal mine water in burst disaster. According to the experiment, the dimensionality reduction model with the addition of the convolutional neural network layer has a faster convergence rate. The recognition rate of spectral data based on DBN method is 91.07% s and recognition rate of 99.02%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Abbreviations

AF:

Asset framework

DBN:

Deep belief network

PCA:

Principle component analysis

REDOX:

Oxidation–reduction reaction

DBSCAN:

Density-based spatial clustering of applications with noise

DOM:

Document object model

SFLA:

Shuffled frog-leaping algorithm

ELM:

Extreme learning machine

SLFN:

Single hidden-layer feed forward neural networks

RELM:

Regularised extreme learning machine

MVO:

Multi-verse optimizer

AE-RELM:

Auto encoder- Regularised extreme learning machine

References

  1. Hu, F., Zhou, M., & Yan, P. (2019). Identification of mine water inrush using laser-induced fluorescence spectroscopy combined with one-dimensional convolutional neural network. RSC Advances, 9(14), 7673–7679.

    Article  Google Scholar 

  2. Huang, L., Li, J., & Hao, H. (2018). Micro-seismic event detection and location in underground mines by using Convolutional Neural Networks (CNN) and deep learning. Tunnelling and Underground Space Technology, 81, 265–276.

    Article  Google Scholar 

  3. Bowen, C., Zhiguo, J., & Haopeng, Z. (2017). Airport detection using end-to-end convolutional neural network with hard example mining. Remote Sensing, 9(11), 1198–1205.

    Article  Google Scholar 

  4. Kitagawa, J., Enomoto, K., & Toda, M. (2017). Classification method for bottom sediment from seabed image using convolutional neural network. Journal of the Japan Society for Precision Engineering, 83(12), 1172–1177.

    Article  Google Scholar 

  5. Kohiyama, M., Oka, K., & Yamashita, T. (2020). Detection method of unlearned pattern using support vector machine in damage classification based on deep neural network. Structural Control and Health Monitoring, 2020(4), e2552–e2559.

    Google Scholar 

  6. Zabidi, A., Yassin, I. M., & Hassan, H. A. (2018). Detection of asphyxia in infants using deep learning Convolutional Neural Network (CNN) trained on Mel Frequency Cepstrum Coefficient (MFCC) features extracted from cry sounds. Journal of Fundamental & Applied Sciences, 9(3S), 768–775.

    Article  Google Scholar 

  7. Jia, H., Pan, D., & Yuan, Y. (2015). Using a BP neural network for rapid assessment of populations with difficulties accessing drinking water because of drought. Human and Ecological Risk Assessment, 21(1–2), 100–116.

    Article  Google Scholar 

  8. Li, Y., Niu, G., & Zhang, X. (2017). Improved ESN neural network model for mine water inrush identification. Journal of Chongqing University, 40(12), 87–96.

    Google Scholar 

  9. Mokh, S., El Hawari, K., & Nassar, R. (2015). Optimization of a solid-phase extraction method for the determination of 12 aminoglycosides in water samples using LC–ESI–MS/MS. Chromatographia, 78(9–10), 631–640.

    Article  Google Scholar 

  10. Soares, D. O. B. S., Beinner, M. A., & Silva, J. B. B. (2015). Direct method for determination of Al, Cd, Cu, and Pb in beers in situ digested by GF AAS using permanent modifiers. Biological Trace Element Research, 167(1), 155–163.

    Article  Google Scholar 

  11. Reid, E., King, A., & Mathieson, A. (2015). Identifying reasons for delays in acute hospitals using the day-of-care survey method. Clinical Medicine, 15(2), 117–120.

    Article  Google Scholar 

  12. Ridgway, S., & Wajrak, M. (2019). Development of an in-field method for the detection of barium in various water samples using differential pulse anodic stripping voltammetry. International Journal of Electrochemistry, 2019, 1–7.

    Article  Google Scholar 

  13. Chung, Y. M., Lou, S. L., & Tsai, P. Z. (2019). A novel statistical analysis method using neural network classifier for sleep Apnea identification. Journal of Medical Imaging and Health Informatics, 9(9), 1796–1800.

    Article  Google Scholar 

  14. Tiantian, W., Dewu, J., & Jian, Y. (2019). Assessing mine water quality using a hierarchy fuzzy variable sets method: A case study in the Guojiawan mining area, Shaanxi Province China. Environmental Geology, 78(8), 2641–26413.

    Google Scholar 

  15. Wang, S., Cuomo, S., & Mei, G. (2019). Efficient method for identifying influential vertices in dynamic networks using the strategy of local detection and updating. Future Generation Computer Systems, 91(2), 10–24.

    Article  Google Scholar 

  16. Nagasato, D., Tabuchi, H., & Ohsugi, H. (2018). Deep neural network-based method for detecting central retinal vein occlusion using ultrawide-field fundus ophthalmoscopy. Journal of Ophthalmology, 2018, 1–6.

    Article  Google Scholar 

  17. Alves-Ribeiro, F. A., Costa-Silva, D. R., & Escórcio-Dourado, C. S. (2017). Masse detection in mammographic images using texture feature extraction and neural networks. Journal of Computational and Theoretical Nanoscience, 14(4), 2064–2068.

    Article  Google Scholar 

  18. Zhou, Q., Herrera, J., & Hidalgo, A. (2018). The numerical analysis of fault-induced mine water inrush using the extended finite element method and fracture mechanics. Mine Water and the Environment, 37(1), 21–31.

    Article  Google Scholar 

  19. Xu, D., Peng, S., & Xiang, S. (2016). The effects of caving of a coal mine’s immediate roof on floor strata failure and water inrush. Mine Water and the Environment, 35(3), 337–349.

    Article  Google Scholar 

  20. Wu, J., Xu, S., & Zhou, R. (2016). Scenario analysis of mine water inrush hazard using Bayesian networks. Safety Science, 89, 231–239.

    Article  Google Scholar 

  21. Yan, P. C., Zhou, M. R., & Liu, Q. M. (2016). Research on the source identification of mine water inrush based on LIF technology and SIMCA algorithm. Spectroscopy and Spectral Analysis, 36(1), 243–247.

    Google Scholar 

  22. Xu, D., Peng, S., & Xiang, S. (2016). The effects of caving of a coal Mine’s immediate roof on floor strata failure and water inrush. Mine Water & Environment, 35(3), 337–349.

    Article  Google Scholar 

  23. Xu, D., Peng, S., & Xiang, S. (2015). The effects of caving of a coal Mine’s immediate roof on floor strata failure and water inrush. Mine Water & the Environment, 35(3), 1–13.

    Google Scholar 

  24. Zhang, S., Guo, W., & Li, Y. (2017). Experimental simulation of fault water inrush channel evolution in a coal mine floor. Mine Water & the Environment, 36(3), 21–29.

    Article  Google Scholar 

  25. Wu, Q., Liu, Y., & Zhou, W. (2015). Evaluation of water inrush vulnerability from aquifers overlying coal seams in the menkeqing coal mine, China. Mine Water and Environment, 34(3), 258–269.

    Article  Google Scholar 

  26. Hu, Y., Sun, J., & Liu, W. (2019). The evolution and prevention of water inrush due to fault activation at working face No. 632 in the Hengyuan coal mine. Mine Water and Environment, 38(1), 93–103.

    Article  Google Scholar 

  27. Zhang, S., Guo, W., & Li, Y. (2017). Experimental simulation of water-inrush disaster from the floor of mine and its mechanism investigation. Arabian Journal of Geoences, 10(22), 503–512.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Safety Science & Engineering, Liaoning Technical University, Fuxin, Liaoning, China

    Bo Fang

Authors
  1. Bo Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bo Fang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fang, B. Method for Quickly Identifying Mine Water Inrush Using Convolutional Neural Network in Coal Mine Safety Mining. Wireless Pers Commun 127, 945–962 (2022). https://doi.org/10.1007/s11277-021-08452-w

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11277-021-08452-w

Keywords

Search

Navigation