|本期目录/Table of Contents|

[1]倪景峰,乐晓瑞,常立峰,等.基于决策树的矿井通风阻变型故障诊断及传感器优化布置*[J].中国安全生产科学技术,2021,17(2):34-39.[doi:10.11731/j.issn.1673-193x.2021.02.005]
　NI Jingfeng,LE Xiaorui,CHANG Lifeng,et al.Resistance variant fault diagnosis and optimized layout of sensors for mine ventilation based on decision tree[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(2):34-39.[doi:10.11731/j.issn.1673-193x.2021.02.005]
点击复制

基于决策树的矿井通风阻变型故障诊断及传感器优化布置*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
17
期数:
2021年2期
页码:
34-39
栏目:
学术论著
出版日期:
2021-02-28

文章信息/Info

Title:
Resistance variant fault diagnosis and optimized layout of sensors for mine ventilation based on decision tree
文章编号:
1673-193X(2021)-02-0034-06
作者:
倪景峰; 乐晓瑞; 常立峰; 邓立军
（1.辽宁工程技术大学 安全科学与工程学院，辽宁 葫芦岛 125105；
2.辽宁工程技术大学 矿山热动力灾害与防治教育部重点实验室，辽宁 葫芦岛 125105；
3.山西瑞通路桥新技术有限公司，山西 太原 030000）
Author(s):
NI Jingfeng;  LE Xiaorui;  CHANG Lifeng;  DENG Lijun
(1.College of Safety Science and Engineering,Liaoning Technical University,Huludao Liaoning 125105,China;
2.Key Laboratory of Mine Thermal Dynamics and Prevention,Ministry of Education,Liaoning Technical University,Huludao Liaoning 125105,China;
3.Shanxi Ruitong Road Bridge New Technology Co.,Ltd.,Taiyuan Shanxi 030000,China)
关键词:
通风网络; 阻变型故障; 决策树; 故障诊断; 嵌入式; 传感器布置
Keywords:
ventilation network;  resistance variable fault;  decision tree;  fault diagnosis;  embedded approach;  sensor layout
分类号:
X936
DOI:
10.11731/j.issn.1673-193x.2021.02.005
文献标志码:
A
摘要:
为实现矿井通风阻变型故障智能诊断，解决风速传感器优化布置与诊断模型不匹配的问题，提出基于决策树的矿井通风故障位置分类判断、故障量回归预测及嵌入式风速传感器优化布置一体化方法；以唐安矿为例对上述方法进行验证。结果表明:矿井通风空间数据集无量纲化能提高故障诊断准确率、提升模型收敛速度，剪枝能提高模型泛化能力；以基尼系数为嵌入式传感器优化布置选择标准，其模型故障诊断准确率更高，当风速传感器数量为15时，故障诊断准确率为84.5%，继续增加风速传感器数量故障诊断准确率提升较小。人工智能诊断技术的应用具有较大的经济和社会效益，是智慧矿山的重要研究方向之一。
Abstract:
In order to realize the intelligent diagnosis on the resistance variable fault of mine ventilation and solve the problem that the optimized layout of wind speed sensors was difficult to match the diagnosis model,an integrated method of the classification and judgment on mine ventilation fault location,the regressive prediction of fault quantity and the optimized layout of embedded wind speed sensors based on the decision tree was put forward,and the verification was carried out by taking Tang’an mine as an example.The results showed that the nondimensionalization of mine ventilation space data set could improve the accuracy of fault diagnosis and convergence speed of model,and the pruning processing could improve the generalization ability of model.The Gini coefficient was used as the selection standard for optimized layout of embedded sensors,and the diagnosis accuracy of model was higher.When the number of wind speed sensors was fifteen,the accuracy of fault diagnosis was 84.5%,and the improvement of accuracy was smaller when increasing the number of wind speed sensors continuously.The application of artificial intelligence diagnosis technology has great economic and social benefits,and it is one of the important research directions of intelligent mines.

参考文献/References:

［1］曹允钦.基于云平台的煤矿安全动态诊断系统［J］.中国安全生产科学技术,2016，12(S1):290-295. CAO Yunqin.Dynamic diagnosis system of coal mine safety based on cloud platform［J］.Journal of Safety Science and Technology,2016，12(S1):290-295.
［2］刘红岩,陈剑,陈国青.数据挖掘中的数据分类算法综述［J］.清华大学学报(自然科学版),2002(6):727-730. LIU Hongyan,CHEN Jian,CHEN Guoqing,Review of classification algorithms for data mining［J］.Journal of Tsinghua University(Science and Techonlogy),2002(6):727-730.
［3］王子京,刘毓.决策树ID3新属性选择方法［J］.现代电子技术,2018,41(23):9-12. WANG Zijing,LIU Yu.A new attribute selection method of ID3 algorithm for decision tree［J］.Modern Electronics Technique,2018,41(23):9-12.
［4］周志华.机器学习［M］.北京：清华大学出版社，2019.
［5］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.
［6］郭欣.基于SVM的矿井通风系统故障诊断研究［D］.葫芦岛：辽宁工程技术大学，2018.
［7］姚志强.基于深度置信网络的管网泄漏故障诊断方法研究［J］.中国安全生产科学技术,2018,14(4):101-106. YAO Zhiqiang.Study on fault diagnosis method of pipelines leakage based on deep belief network［J］.Journal of Safety Science and Technology,2018,14(4):101-106.
［8］刘伟,周心权,谭文辉,等.用分区法优化布置火源探测传感器的研究用分区法优化布置火源探测传感器的研究［J］.煤炭工程师,1998(4):5-7,52. LIU Wei,ZHOU Xinquan,TAN Wenhui,et al.Study on the optimum arrangement of fire source detection sensors by zoning method ［J］.Coal Engineer,1998(4):5-7,52.
［9］孙继平,唐亮,陈伟.基于监测覆盖范围的瓦斯传感器无盲区布置［J］.煤炭学报,2008,33(8):946-950. SUN Jiping,TANG Liang,CHEN Wei.No-blind-zone placement of gas sensor based on monitoring coverage［J］.Journal of China Coal Society,2008,33(8):946-950.
［10］赵丹，陈帅，潘竞涛.基于FTA的矿井监控预警诊断知识表示及推理机制［J］.中国安全生产科学技术，2015，11(6):38-43. ZHAO Dan,CHEN Shuai,PAN Jingtao.Knowledge representation and reasoning mechanism of mine monitoring and early warning diag-nosis based on FTA［J］.Journal of Safety Science and Technology,2015,11(6):38-43.
［11］潘竞涛，赵丹，李宗翔，等.大明矿通风系统故障诊断及风速传感器的布置［J］.煤炭学报，2013,38（1）:154-158. PAN Jingtao,ZHAO Dan,LI Zongxiang,et al.Fault source diagnosis for ventilation system and air velocity transducer placement in Daming Mine［J］.Journal of China Coal Society,2013,38 (1):154-158.
［12］刘剑,蒋清华,刘丽,等.矿井通风系统阻变型故障诊断及风速传感器位置优化研究［J/OL］.煤炭学报:1-8［2021-02-05］.https://doi.org/10.13225/j.cnki.jccs.2019.1768.
［13］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.
［14］居银银.基于决策树和最佳特征选择的神经网络钓鱼网站检测研究［D］.合肥：安徽大学,2020.
［15］张先迪，李正良.图论及其应用［M］.北京：高等教育出版社，2019.
［16］倪景峰.矿井通风系统可视化研究［D］.葫芦岛：辽宁工程技术大学，2004.
［17］周启超，刘剑，刘丽，等.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］.中国安全生产科学术，2019，15(4):45-51. ZHOU Qichao,LIU Jian,LIU Li,et al.Study on optimization of pen-alty coefficient and kernel function coefficient of ventilation systemfault diagnosis based on SVM［J］.Journal of Safety Science and Technology,2019,15(4):45-51.
［18］SU C,JU S G,LIU Y G,et al.Improving random forest and rotation forest for highly imbalanced datasets［J］.Intelligent Data Analysis,2015,19（6）：1409-1432.
［19］贾涛.基于McDiarmid不等式的决策树分类方法研究与应用［D］.银川：北方民族大学,2019.
［20］李国和,王峰,郑阳,等.基于决策树生成及剪枝的数据集优化及其应用［J］.计算机工程与设计,2018,39(1):205-211. LI Guohe,WANG Feng,ZHENG Yang,et al.Optimization of data set and its application based on construction and pruning of decision tree［J］.Computer Engineering and Design,2018,39(1):205-211.
［21］王黎明.决策树学习及其剪枝算法研究［D］.武汉：武汉理工大学,2007.

相似文献/References:

[1]彭家兰,王海宁,彭斌,等.矿井通风三维仿真系统及其应用研究[J].中国安全生产科学技术,2014,10(1):124.[doi:10.11731/j.issn.1673-193x.2014.01.021]
　PENG Jia lan,WANG Hai ning,PENG Bin,et al.Study on threedimensional simulation and optimization system of mine ventilation network and its application in metal mines[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(2):124.[doi:10.11731/j.issn.1673-193x.2014.01.021]
[2]韩靖,蒋曙光,王媛媛,等.通风网络分支风量与风机频率及变频 灵敏度的关系研究[J].中国安全生产科学技术,2016,12(5):26.[doi:10.11731/j.issn.1673-193x.2016.05.005]
　HAN Jing,JIANG Shuguang,WANG Yuanyuan,et al.Study on relationship between air volume among branches of ventilation network with fan frequency and frequency conversion sensitivity[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(2):26.[doi:10.11731/j.issn.1673-193x.2016.05.005]
[3]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.[doi:10.11731/j.issn.1673-193x.2020.01.014]
　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(2):85.[doi:10.11731/j.issn.1673-193x.2020.01.014]
[4]王文,孙三祥,何世洋.隧道救援站通风网络优化设计及人员疏散研究*[J].中国安全生产科学技术,2020,16(8):57.[doi:10.11731/j.issn.1673-193x.2020.08.009]
　WANG Wen,SUN Sanxiang,HE Shiyang.Study on optimization design of ventilation network and personnel evacuation in tunnel rescue station[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(2):57.[doi:10.11731/j.issn.1673-193x.2020.08.009]
[5]李杰,严晓楠,叶绪谦,等.特长公路隧道全射流火灾通风网络解算研究*[J].中国安全生产科学技术,2021,17(2):20.[doi:10.11731/j.issn.1673-193x.2021.02.003]
　LI Jie,YAN Xiaonan,YE Xuqian,et al.Research on resolving of full jet fire ventilation network for extralong highway tunnel[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(2):20.[doi:10.11731/j.issn.1673-193x.2021.02.003]
[6]尚文天,邓立军,刘剑.基于有上下界风量约束的矿井风量极值流算法研究*[J].中国安全生产科学技术,2022,18(2):106.[doi:10.11731/j.issn.1673-193x.2022.02.016]
　SHANG Wentian,DENG Lijun,LIU Jian.Research on extreme flow algorithm of mine air volume based on upper and lower bound air volume constraints[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(2):106.[doi:10.11731/j.issn.1673-193x.2022.02.016]
[7]倪景峰,李振,乐晓瑞,等.基于随机森林的阻变型通风网络故障诊断方法*[J].中国安全生产科学技术,2022,18(4):34.[doi:10.11731/j.issn.1673-193x.2022.04.005]
　NI Jingfeng,LI Zhen,LE Xiaorui,et al.Resistance variant fault diagnosis method of ventilation network based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(2):34.[doi:10.11731/j.issn.1673-193x.2022.04.005]

备注/Memo

备注/Memo:
收稿日期： 2020-09-26
* 基金项目： 国家自然科学基金项目（51904143）
作者简介： 倪景峰，博士，教授，主要研究方向为通风网络解算。
更新日期/Last Update: 2021-03-11