Abstract
Reliable and stable mine monitoring systems are efficient tools for preventing mine accidents. Roadway faults due to deformation, destruction, or damper situation transformation can cause changes in airflow resistance. The airflow quantities of other branches also change. This phenomenon is called ventilation system failure. It is of great significance to determine the network topology location of ventilation system failure according to the changes in air volume perceived by the wind speed sensor. This paper proposes a method of building a sensitivity 0–1 matrix by improving the sensitivity matrix and then establishing a roadway faulty scope library. Taking the Daming coal mine as the experimental object, the improved SVM method was applied to diagnose the fault location in the roadway fault scope library. The experimental results demonstrate that: the improved method is effective and feasible for fault diagnosis of the mine ventilation system. After the fault roadway scope library is established, the sample training time is shortened by 66.5%, and the fault location diagnosis accuracy rate is increased by 13.95%. The proposed method has the best performance in ACU, F1, and G-mean. The research results can provide the theoretical basis and implementation technology for intelligent mine ventilation.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Torano J, Torno S, Menendez M, Gent M, Velasco J (2009) Models of methane behavior in auxiliary ventilation of underground coal mining. Coal Geol 80(1):35–43
Rusiński E, Moczko P, Odyjas P, Pitrusiak D (2014) Investigation of vibrations of a main centrifugal fan used in mine ventilation. Arch Civil Mechanic Eng 14(4):569–279
Semin MA, Levin LY (2019) Stability of air flows in mine ventilation networks. Process Saf Environ Prot 124:167–171
Yan X, Jia M (2018) A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing. Neurocomputing 313:47–64
Soldevila A, Ferandez-Cant R, Blesa M (2017) Leak localization in water distribution networks using Bayesian classifiers. J Process Control 55:1–9
Mohammed M, Ghani MA (2018) Genetic case-based reasoning for improved mobile phone faults diagnosis. Comput Electric Eng 71:212–222
Zhao H, Lia Z (2019) Neighborhood preserving neural network for fault detection. Neural Netw 109:6–18
Guo D, Zhong M, Ji H (2018) A hybrid feature model and deep learning based fault diagnosis for unmanned aerial vehicle sensors. Neurocomputing 319:155–163
Helbing G, Ritter M (2018) Deep learning for fault detection in wind turbines. Renew Sustain Energy Rev 98:189–198
Zhang Y, Li X, Gao L (2018) A new subset based deep feature learning method for intelligent fault diagnosis of bearing. Expert Syst Appl 110:125–142
Jensen TN, Puig V, Romera J (2018) Leakage localization in water distribution using data- driven models and sensitivity analysis. IFAC- Papers Online 51(24):736–741
Zhang LY, Hang XX, Zhang J (2019) Fault diagnosis method for active power distribution network based on D-PMU measurement information. Proceed SCU-EPSA 31(10):145–150
Jia Z, Ho SC, Li Y (2019) Multi point hoop strain measurement based pipeline leakage localization with an optimized support vector regression approach. J Loss Prev Process Ind 62:1026–1039
Kim D, Shin S, Choi G (2017) Diagnosis of partial block-age in water pipeline using support vector machine with fault-characteristic peaks in frequency domain. Canadian J Civil Eng 44(9):707–714
Xiao Q, Li J, Bai Z (2016) A small leak detection method based on VMD adaptive de-noising and ambiguity correlation classification intended for natural gas pipelines. Sensors 16(12):16
Wang W, Shen L, Wang B (2017) Failure probability analysis of the urban buried gas pipelines using Bayesian networks. Process Saf Environ Prot 111:678–686
Leng L, Huang Y (2008) Fault diagnosis of mine ventilator base on multi sensor information integration. Coal Sci Technol 6:72–74
Huang L (2008) Fault diagnosis expert system of local ventilation in coal mine based on web. Xian University Of Science And Technology, Xian
Jia JZ, Jia P, Li B (2020) Theoretical study on stability of mine ventilation network based on sensitivity analysis. Energy Sci Eng 00:1–8
Zhao D, Liu J, Pan J (2011) A renovated network-based intelligent diagnosis mining-ventilation expertise system. J Saf Environ 1(4):206–210
Liu J, Guo X, Deng L (2018) Resistance variant single fault source diagnosis of mine ventilation system based on air volume characteristic. J China Coal Soc 43(1):143–149
Wang C, Wu C (2007) Mine ventilation and its system reliability. Chemical Industry Press, Beijing
Ma H, Jia J, Yu F (2001) Stability of airflow in complicated network. J Liaoning Technic Univ 5:64–68
Zhao D (2011) Study of fault source diagnosis technology for mine ventilation system based on network analysis. Liaoning Technical University, Fuxin
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhao, D., Shen, Z. Study on Roadway Fault Diagnosis of the Mine Ventilation System Based on Improved SVM. Mining, Metallurgy & Exploration 39, 983–992 (2022). https://doi.org/10.1007/s42461-022-00595-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42461-022-00595-z