Online fault diagnosis of mine ventilation system based on OCISVM

doi:10.16265/j.cnki.issn1003-3033.2022.10.1766

Abstract

Abstract:

In order to address the difficulty in obtaining failure samples of mine ventilation system and the lack of research on online detection to fill the blank in fault branch diagnosis based on real-time monitoring data of sensors, OC-SVM and IL method were combined to construct OCISVM model. Firstly, monitoring data of normal samples were used to construct classification hyperplane at offline phase. Then, at online detection stage, classification hyperplane was updated by introducing delta function according to incremental learning, and online fault branch diagnosis was achieved based on threshold criterion. Finally, the proposed model was applied to Dongshan coal mine ventilation system. The results show that the model's fault diagnosis accuracy can reach as high as 96.5% while running in milliseconds. Moreover, it demonstrates higher stability when dealing with unbalanced data.

Key words: mine ventilation system, one-class support vector machine (OC-SVM), incremental learning (IL), fault diagnosis, monitoring data

ZHAO Dan, SHEN Zhiyuan, LIU Xiaoqing. Online fault diagnosis of mine ventilation system based on OCISVM[J]. China Safety Science Journal, 2022, 32(10): 76-82.

Figures/Tables 6

Fig.1

Tab.1

Fig.2

Fig.3

Fig.4

Fig.5

References 19

[1]	SEMIN M A, LEVIN L Y. Stability of air flows in mine ventilation networks[J]. Process Safety and Environmental Protection, 2019, 124:167-171. doi: 10.1016/j.psep.2019.02.006
[2]	JIA Jinzhang, JIA Peng, LI Bin. Theoretical study on stability of mine ventilation network based on sensitivity analysis[J]. Energy Science & Engineering, 2020, 8(8):2823-2830.
[3]	龚晓燕, 冯华光, 薛河. 基于多元技术的矿井局部通风机故障检测与诊断研究[J]. 矿山机械, 2008, 36(15):27-30.
	GONG Xianyan, FENG Huaguang, XUE He. Fault detection and diagnosis research of mine local ventilator based on multivariate technology[J]. Mining & Processing Equipment, 2008, 36(15):27-30.
[4]	龚晓燕, 孙晓辉. 基于遗传算法的矿井局部通风故障诊断神经网络模型[J]. 煤矿安全, 2008, 39(5):35-38.
	GONG Xiaoyan, SUN Xiaohui. Neural network model for fault diagnosis of mine local ventilation based on genetic algorithm[J]. Safety in Coal Mines, 2008, 39(5):35-38.
[5]	CHANG Yanwei, WANG Yaocai, LIU Tao, et al. Fault diagnosis of a mine hoist using PCA and SVM techniques[J]. Journal of China University of Mining and Technology, 2008, 18(3):327-31. doi: 10.1016/S1006-1266(08)60069-3
[6]	赵丹, 潘竞涛. 改进灵敏度矩阵的矿井通风故障源诊断及传感器布置研究[J]. 中国安全科学学报, 2011, 21(2):78-84.
	ZHAO Dan, PAN Jingtao. Fault source diagnosis for mine ventilation based on improved sensitivity matrix and its wind speed[J]. China Safety Science Journal, 2011, 21(2) :78-84.
[7]	ZHAO Dan, ZHANG Hui, PAN Jingtao. Solving optimization of a mine gas sensor layout based on a hybrid GA-DBPSO algorithm[J]. IEEE Sensors Journal, 2019, 19(15):6400-6409. doi: 10.1109/JSEN.2019.2909277
[8]	刘剑, 郭欣, 邓立军, 等. 基于风量特征的矿井通风系统阻变型单故障源诊断[J]. 煤炭学报, 2018, 43(1):143-149.
	LIU Jian, GUO Xin, DENG Lijun, et al. Resistance variant single fault source diagnosis of mine ventilation system based on air volume characteristic[J]. Journal of China Coal Society, 2018, 43(1):143-149.
[9]	刘剑, 刘丽, 黄德, 等. 基于风量-风压复合特征的通风系统阻变型故障诊断[J]. 中国安全生产科学技术, 2020, 16(1):85-91.
	LIU Jian, LIU Li, HUANG De, et al. Resistance variant fault diagnosis of ventilation system based on composite features of air volume and air pressure[J]. Journal of Safety Science and Technology, 2020, 16(1):85-91.
[10]	周启超, 刘剑, 刘丽. 基于SVM的通风系统故障诊断惩罚系数与核函数系数优化研究[J]. 中国安全生产科学技术, 2019, 15(4):45-51.
	ZHOU Qichao, LIU Jian, LIU Li, et al. Research on fault diagnosis penalty coefficient and kernel function coefficient optimization of ventilation system based on SVM[J]. Journal of Safety Science and Technology, 2019, 15(4):45-51.
[11]	HUANG De, LIU Jian, DENG Lijun. A hybrid-encoding adaptive evolutionary strategy algorithm for windage alteration fault diagnosis[J]. Process Safety and Environmental Protection, 2020, 136:242-252. doi: 10.1016/j.psep.2020.01.037
[12]	黄德, 刘剑, 刘永, 等. 矿井通风阻变故障观测特征组合选择试验研究[J]. 煤炭学报, 2021, 46(12):3922-3933.
	HUANG De, LIU Jian, LIU Yong, et al. Experimental research on combination selection of observation feature of resistance variation fault in mine ventilation[J]. Journal of China Coal Society, 2021, 46(12):3922-3933.
[13]	刘剑, 尹昌胜, 黄德, 等. 矿井通风阻变型故障复合特征诊断无监督学习模型[J]. 煤炭学报, 2020, 45(9):3157-3165.
	LIU Jian, YIN Changsheng, HUANG De, et al. Unsupervised machine learning model for resistance variant fault diagnosis of mine ventilation system with composite features[J]. Journal of China Coal Society, 2020, 45(9):3157-3165.
[14]	骆正山, 田珮琦. RS-PSO-ELM下腐蚀管道失效压力预测[J]. 中国安全科学学报, 2021, 31(3):28-34. doi: 10.16265/j.cnki.issn1003-3033.2021.03.004
	LUO Zhengshan, TIAN Peiqi. Prediction of failure pressure of corrosion pipelines based on RS-PSO-ELM[J]. China Safety Science Journal, 2021, 31(3):28-34. doi: 10.16265/j.cnki.issn1003-3033.2021.03.004
[15]	TAX D M J, DUIN R P W. Support vector data description[J]. Machine Learning, 2004, 54(1):45-66. doi: 10.1023/B:MACH.0000008084.60811.49
[16]	MANSOUR M, NOUNOU M, NOUNOU H, et al. Kernel PCA based GLRT for nonlinear fault detection of chemical processes[J]. Journal of Loss Prevention in the Process Industries, 2016, 40:334-347. doi: 10.1016/j.jlp.2016.01.011
[17]	肖鹏, 谢行俊, 双海清, 等. 基于KPCA-CMGANN算法的瓦斯涌出量预测研究[J]. 中国安全科学学报, 2020, 30(5):39-47. doi: 10.16265/j.cnki.issn1003-3033.2020.05.007
	XIAO Peng, XIE Xingjun, SHUANG Haiqing, et al. Prediction of gas emission quantity based on KPCA-CMGANN algorithm[J]. China Safety Science Journal, 2020, 30(5):39-47. doi: 10.16265/j.cnki.issn1003-3033.2020.05.007
[18]	王洪波, 赵光宙, 齐东莲, 等. 一类支持向量机快速增量学习方法[J]. 浙江大学学报:工学版, 2012, 46(7):1327-1332.
	WANG Hongbo, ZHAO Guangzhou, QI Donglian, et al. Fast incremental learning method for one-class support vector machine[J]. Journal of Zhejiang University:Engineering Science, 2012, 46(7):1327-1332.
[19]	MARINA S, GUY L. A systematic analysis of performance measures for classification tasks[J]. Information Processing & Management, 2009, 45(4):427-437. doi: 10.1016/j.ipm.2009.03.002

方法	ACC	AUC	F₁	G-mean	训练时间/s	测试时间/s
CMA-ES	0.956	0.924	0.931	0.921	13.452	9.247
SVDD	0.835	0.915	0.724	0.732	14.324	10.089
PCA	0.812	0.905	0.811	0.814	9.782	9.236
OC-SVM	0.938	0.934	0.851	0.847	2.087	0.158
OCISVM	0.965	0.945	0.964	0.968	2.235	0.064