SDAE cleaning model of wind speed monitoring data in the Mine Monitoring System

• Autorzy: Zhao Dan , Shen Zhiyuan , Song Zihao , Xie Lina

Identyfikatory

DOI

10.24425/ams.2023.146178

• Języki publikacji: EN

Abstrakty

EN

The effective utilisation of monitoring data of the coal mine is the core of realising intelligent mine. The complex and challenging underground environment, coupled with unstable sensors, can result in “dirty” data in monitoring information. A reliable data cleaning method is necessary to figure out how to extract high-quality information from large monitoring data sets while minimising data redundancy. Based on this, a cleaning method for sensor monitoring data based on stacked denoising autoencoders (SDAE) is proposed. The sample data of the ventilation system under normal conditions are trained by the SDAE algorithm and the upper limit of reconstruction errors is obtained by Kernel density estimation (KDE). The Apriori algorithm is used to study the correlation between monitoring data time series. By comparing reconstruction errors and error duration of test data with the upper limit of reconstruction error and tolerance time, cooperating with the correlation rule, the “dirty” data is resolved. The method is tested in the Dongshan coal mine. The experimental results show that the proposed method can not only identify the dirty data but retain the faulty information. The research provides effective basic data for fault diagnosis and disaster warning.

Słowa kluczowe

EN

intelligent ventilation; monitoring data; data cleaning; association rules; stacked denoising autoencoder

PL

inteligentna wentylacja; monitoring danych; czyszczenie danych

• Wydawca: Instytut Mechaniki Górotworu PAN
• Czasopismo: Archives of Mining Sciences
• Rocznik: 2023
• Tom: Vol. 68, no. 2
• Strony: 251--266
• Opis fizyczny: Bibliogr. 21 poz., rys., tab., wykr.

Twórcy

autor

Zhao Dan

• Liaoning Technical University, College of Safety Science & Engineering, Fuxin 123000, China

• https://orcid.org/0000-0002-5609-7978

autor

Shen Zhiyuan

• Liaoning Technical University, College of Safety Science & Engineering, Fuxin 123000, China

• https://orcid.org/0000-0001-8021-9034

autor

Song Zihao

• Liaoning Technical University, College of Safety Science & Engineering, Fuxin 123000, China

• https://orcid.org/0000-0001-9399-2616

autor

Xie Lina

• Shenyang Institute of Technology, Shenyang 110000, China

• https://orcid.org/0000-0003-1507-294X

Bibliografia

• [1] M.A. Semin, L.Y. Levin, Stability of air flows in mine ventilation networks. Process. Saf. Environmen. Prot. 124, 167-171(2019). DOI: https://doi.org/10.1016/j.psep.2019.02.006.
• [2] J.W. Cheng, S.Q. Yang, Data mining applications in evaluating mine ventilation system. Safety. Sci. 50 (4), 918-955 (2012). DOI: https://doi.org/10.1016/j.ssci.2011.08.003.
• [3] G.F. Wang, Y.X. Xu, H.W. Ren, Intelligent and ecological coal mining as well as clean utilization technology inChina: Review and prospects. J. Int. J. Mining. Sci. Tec. 29 (2), 161-169 (2019). DOI:https://doi.org/10.1016/j.ijmst.2018.06.005.
• [4] L. Muduli, D.P. Mishra, P.K. Jana, Application of wireless sensor network for environmental monitoring in underground coal mines: A systematic review. J. Netw. Comput. Appl. 106, 48-67 (2018). DOI: https://doi.org/10.1016/j.jnca.2017.12.022.
• [5] W.H. Wang, K.L. Shen, B.B. Wang, Failure probability analysis of the urban buried gas pipelines using Bayesian networks. Process. Saf. Environmen. Prot. 111, 678-686 (2017). DOI: https://doi.org/10.1016/j.psep.2017.08.040.
• [6] D. Huang, J. Liu, L.J. Deng, A hybrid-encoding adaptive evolutionary strategy algorithm for windage alteration fault diagnosis. Process. Saf. Environmen. Prot. 136, 242-252 (2020). DOI: https://doi.org/10.1016/j.psep.2020.01.037.
• [7] Z.N. Gao, F. Yang, S.B. Hu, et al., Pseudo-fluctuation data cleaning for state estimation of new energy power system. High. Voltage. Eng. 48 (06), 2366-2377 (2022). DOI: https://doi.org/10.13336/j.1003-6520.hve.20210591.
• [8] Y.J. Yan, G.H. Sheng, Y.F. Chen, et al., Cleaning method for big data of power transmission and transformation equipment state based on time sequence analysis. High. Voltage. Eng. 39 (7), 138-144 (2015). DOI: https://doi.org/10.7500/AEPS20140111003.
• [9] G.E. Hinton, R.R. Salakhutdinov, Reducing the dimensionality of data with neural networks. Science 313, 504-507 (2006). DOI: https://doi.org/10.1126/science.1127647.
• [10] Y. Bengio, Learning deep architectures for AI. Found. Trends. Mac. Lear. 2 (1), 1-127 (2009). DOI: http://dx.doi.org/10.1561/2200000006.
• [11] P. Vicent, H. Larochlle, Y. Bengio, et al., Extracting and composing robust features with denoising autoencoders. C. //25th International Conference on Machine Learning, June 5-9. Helsinki, Finland: 1096-1103 (2008). DOI: https://doi.org/10.1145/1390156.1390294.
• [12] P. Vicent, H. Larochlle, I. Lajoie, et al., Stacked denoising antoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11 (12), 3371-3408 (2010).
• [13] F. Xu, F.F. Yang, Z.C. Fei, et al., Life prediction of lithium-ion batteries based on stacked denoising autoencoders. Reliab. Eng. Sys. Safe. 208: 107396 (2021). DOI: https://doi.org/10.1016/j.ress.2020.107396.
• [14] J.J. Dai, H. Song, G.H. Sheng, et al., Cleaning method for status monitoring data of power equipment based on stacked denoising autoencoders. J. Ieee Access. 5, 22863-22870 (2017). DOI: https://doi.org/10.1109/ACCESS.2017.2740968.
• [15] J.J. Dai, H. Song, Cleaning method for status data of power transmission and transformation equipment base on tacked denoising autoencoders. Automation of Electric Power Systems 41 (12), 224-230 (2017). DOI: https://doi.org/10.7500/AEPS2016201003.
• [16] M. Kozielski, M. Sikora, Ł. Wróbel, Data on methane concentration collected by underground coal mine sensors. Data in Brief. 39, 107457 (2021). DOI: https://doi.org/10.1016/j.dib.2021.107457.
• [17] D. Ślęzak, M. Grzegorowski, A.Januszet, et al., A framework for learning and embedding multi-sensor forecasting models into a decision support system: A case study of methane concentration in coal mines. Inform. Sciences 451, 112-133 (2018). DOI: https://doi.org/10.1016/j.ins.2018.04.026.
• [18] D. Huang, J. Liu, L.J. Deng, et al., An adaptive Kalman filter for online monitoring of mine wind speed. Arch. Min. Sci. 64 (4), 813-827 (2019). DOI: https://doi.org/10.24425/ams.2019.131068.
• [19] W. Zhang, Y.C. Li, H, Zhang, et al., Comparison of structured data noise reduction methods for airflow speed sensor of intelligent ventilation. Journal of Safety Science and Technology 17 (08). 70-76 (2021). DOI: https://doi.org/10.11731/j.issn.1673-193x.2021.08.011.
• [20] S.J. Qu, Real-time date processing method of wind speed sensor in roadway. Safety in Coal Mines 48 (02), 163-166 (2017). DOI: https://doi.org/10.13347/j.cnki.mkaq.2017.02.044.
• [21] S. Węglarczyk, Kernel density estimation and its application [C]//ITM Web of Conferences. EDP Sciences 23, 00037 (2018). DOI: https://doi.org/10.1051/itmconf/20182300037.