|本期目录/Table of Contents|

[1]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].中国安全生产科学技术,2019,15(4):45-51.[doi:10.11731/j.issn.1673-193x.2019.04.007]
　ZHOU Qichao,LIU Jian,LIU Li,et al.Research on fault fiagnosis 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.[doi:10.11731/j.issn.1673-193x.2019.04.007]
点击复制

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
分享到：

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

卷:
15
期数:
2019年4期
页码:
45-51
栏目:
学术论著
出版日期:
2019-04-30

文章信息/Info

Title:
Research on fault fiagnosis penalty coefficient and kernel function coefficient optimization of ventilation system based on SVM
文章编号:
1673-193X(2019)-03-0045-07
作者:
周启超1; 2; 刘剑1; 2; 刘丽1; 2; 黄德1; 2; 邓立军1; 2; 蒋清华1
（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）
Author(s):
ZHOU Qichao1; 2;  LIU Jian1; 2;  LIU Li1; 2;  HUANG De1; 2;  DENG Lijun1; 2;  JIANG Qinghua1
(1.College of Safety Science and Engineering, Liaoning Technical University, Huludao Liaonig 125105, China;2.Key Laboratory of Mine Thermomotive Disaster and Prevention，Ministry of Education，Liaoning Technical University, Huludao Liaonig 125105, China)
关键词:
支持向量机; 遗传算法; 参数优化; 通风系统故障诊断
Keywords:
support vector machine; genetic algorithm; parameter optimization; fault diagnosis of ventilation system
分类号:
X936
DOI:
10.11731/j.issn.1673-193x.2019.04.007
文献标志码:
A
摘要:
使用支持向量机（SVM）方法对矿井通风系统进行故障诊断，存在惩罚系数（c）和核函数系数（g），通过人工方法选取效率低、难以达到较高准确率并且出现过拟合的问题。为了提高矿井通风故障诊断的效率、准确率，同时避免过拟合现象，提出了一种改进遗传算法（GA），在故障诊断过程中对支持向量机的c，g参数进行优化。经过多组试验分析，研究结果表明：用遗传算法优化的SVM矿井通风故障诊断系统相比于未优化系统的故障诊断准确率有所提升，参数未优化前故障诊断的准确率为60%，优化后的准确率为97.894 7%，并且优化参数经过大数据样本验证，未出现过拟合现象，证明了本文提出方法的有效性。
Abstract:
The support vector machine (SVM) method is used to diagnose the mine ventilation system. There are problems of the penalty coefficient (c) and the kernel function coefficient (g) being low efficiency by manual method, difficult to achieve high accuracy and overfitting. In order to improve the efficiency and accuracy of mine ventilation fault diagnosis and avoid overfitting, an improved genetic algorithm (GA) is proposed to optimize the c and g parameters of SVM in the fault diagnosis process. After several sets of experiments, the results show that the accuracy of the fault diagnosis of the SVM mine ventilation fault diagnosis system optimized by genetic algorithm is improved compared with that of the unoptimized system. The accuracy of fault diagnosis before the parameters optimization is 60%. The optimized accuracy rate is 97.894 7%, and the optimization parameters are verified by big data samples. There is no overfitting phenomenon, which proves the effectiveness of the proposed method.

参考文献/References:

［1］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. Diagnosing single fault source diagnosis of mine ventilation system based on air volume characteristics［J］. Journal of China Coal Society, 2018, 43(1): 143-149.
［2］魏宁,孙亚胜男,邓立军,等.基于SVM的矿井通风阻力系数影响因素分析与预测［J］.中国安全生产科学技术,2018,14(4):39-44. WEI Ning,SUN Yasheng,DENG Lijun,et al.Analysis and prediction of influencing factors of mine ventilation resistance coefficient based on SVM［J］.China Safety Science and Technology,2018,14(4):39-44.
［3］李凤,易俊,王文和,等.基于SVM的CO_2驱油藏输油管道脆弱性评价研究［J］.中国安全生产科学技术,2015,11(8):157-163. LI Feng,YI Jun,WANG Wenhe,et al. Study on vulnerability evaluation of oil pipeline of CO_2 flooding reservoir based on SVM［J］.China Safety Science and Technology,2015,11(8):157-163.
［4］张明丽,姚继涛.基于支持向量机建筑施工安全预警模型的研究［J］.中国安全生产科学技术,2011,7(3):58-60. ZHANG Mingli,YAO Jitao.Study on construction safety early warning model based on support vector machine［J］.China Safety Science and Technology,2011,7(3):58-60.
［5］施式亮,李润求,罗文柯.基于EMD-PSO-SVM的煤矿瓦斯涌出量预测方法及应用［J］.中国安全科学学报,2014,24(7):43-49. SHI Shiliang,LI Runqiu,LUO Wenke.A method for forecasting coal mine gas emission based on EMD-PSO-SVM and its application［J］.China Safety Science Journal,2014,24(7):43-49.
［6］陈华舟,陈福,许丽莉,等.基于网格搜索的参数优化方法用于鱼粉灰分的近红外LSSVM定量分析［J］.分析科学学报,2016,32(2):198-202. CHEN Huazhou,CHEN Fu,XU Lili,et al.A quantitative analysis ofnear infrared LSSVM for fish ash by using parameter pptimization method based on grid search［J］.Journal of Analytical Science,2016,32(2):198-202.
［7］高雷阜,赵世杰,高晶.人工鱼群算法在SVM参数优化选择中的应用［J］.计算机工程与应用,2013,49(23):86-90. GAO Leifu,ZHAO Shijie,GAO Jing.Application of artificial fish swarm algorithm in SVM parameter optimization selection［J］.Computer Engineering and Applications,2013,49(23):86-90.
［8］王玉鑫,李东生,高杨.基于改进型花朵授粉算法的SVM参数优化［J］.火力与指挥控制,2018,43(10):8-13. WANG Yuxin,LI Dongsheng,GAO Yang.SVM parameter optimization based on improved flower pollination algorithm［J］.Fire Control & Command Control,2018,43(10):8-13.
［9］邱正,钱玉良,张云,等.基于人工蜂群算法优化支持向量机的燃气轮机故障诊断［J］.热能动力工程,2018,33(9):39-43,57. QIU Zheng,QIAN Yuliang,ZHANG Yun,et al. Gas turbine fault diagnosis based on artificial bee colony algorithm optimized support vector machine［J］. Thermal Power Engineering,2018,33(9):39-43,57.
［10］肖海军,卢常景,何凡.基于鸟群算法的SVM参数选择［J］.中南民族大学学报(自然科学版),2017,36(3):90-94. XIAO Haijun,LU Changjing,HE Fan.SVM parameter selection based on bird group algorithm［J］.Journal of South-Central University for Nationalities(Natural Science Edition),2017,36(3):90-94.
［11］ENACHE A C，SGARCIU V. Anomaly intrusions detection based on support vector machines with bat algorithm［C］//System Theory，Control and Computing （ICSTCC），2014 18th International Conference. IEEE，2014：856- 861.
［12］段艳艳.基于支持向量机的矿井风温预测［D］.西安:西安科技大学,2013.
［13］孙玲.一种支持向量机参数选择方法的研究及应用［D］.杭州：杭州电子科技大学,2017.
［14］颜晓娟,龚仁喜,张千锋.优化遗传算法寻优的SVM在短期风速预测中的应用［J］.电力系统保护与控制,2016,44(9):38-42. Yan Xiaojuan,Gong Renxi,Zhang Qianfeng.Application of SVM optimized by genetic algorithm for short-term wind speed prediction［J］.Power System Protection and Control,2016,44(09):38-42.
［15］张欢欢.基于支持向量机的矿井巷道摩擦阻力系数预测研究［D］.西安:西安科技大学,2017.
［16］周明,孙树栋.遗传算法原理及应用［M］.北京:国防工业出版社,1999.
［17］宋莹.基于GA的通风网络图优化绘制算法研究［D］.葫芦岛:辽宁工程技术大学,2013.
［18］邓立军.矿井通风阻力系数反演研究［D］.葫芦岛:辽宁工程技术大学,2014.

相似文献/References:

[1]金珠,马小平.基于核校准和SVM的煤矿安全组织管理因素分析[J].中国安全生产科学技术,2011,7(3):16.
　JIN Zhu,MA Xiao-ping.Analysis of organizational administrative factors in coal mine safety based on kernel alignment and SVM[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(4):16.
[2]张明丽,姚继涛.基于支持向量机建筑施工安全预警模型的研究[J].中国安全生产科学技术,2011,7(3):58.
　ZNANG Ming-li,YAO Ji-tao.Study on Warning model of construction safety based on SVM[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(4):58.
[3]吴云,王鹏,胡小娟,等.基于遗传-BP算法的煤矿安全监控系统测试研究[J].中国安全生产科学技术,2011,7(6):72.
　WU Yun,WANG Peng,HU Xiao-juan,et al.Test Case Study of Coal Mine Safety Monitoring System Based on Genetic-BP Algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(4):72.
[4]杨惠,陈利平,谢传欣,等.烃类及其衍生物闪点、沸点的定量构效关系[J].中国安全生产科学技术,2011,7(9):68.
　YANG Hui,CHEN Li-ping,XIE Chuan-xin,et al.QSPR study for predicting flash points and boiling points of hydrocarbon and their derivatives[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(4):68.
[5]杨力,陆红娟,张鑫,等.多类支持向量机在煤矿安全评价中的应用研究[J].中国安全生产科学技术,2012,8(4):111.
　YANG Li,LU Hong juan,ZHANG Xin,et al.Application research of multiclass support vector machines in coal mine safety evaluation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(4):111.
[6]甘旭升,端木京顺,高建国.基于相关向量机的飞行安全评价方法[J].中国安全生产科学技术,2012,8(12):143.
　GAN Xu sheng,DUANMU Jing shun,GAO Jian guo.Flight safety evaluation method based on relevance vector machine[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(4):143.
[7]甘旭升,端木京顺,丛伟,等.基于支持向量机的飞行安全隐患危险性评价[J].中国安全生产科学技术,2010,6(3):206.
　GAN Xu-sheng,DUANMU Jing-shun,CONG Wei,et al.Fatalness assessment of flight safety hidden danger based on support vector machine[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(4):206.
[8]陈莹,蒋军成,潘勇,等.混合液体火灾爆炸危险性——闪点预测与实验研究[J].中国安全生产科学技术,2010,6(2):8.
　CHEN Ying,JIANG Jun-cheng,PAN Yong,et al.Fire and Explosion risk of mixture——flash point prediction and experimental study[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(4):8.
[9]姚舜才,朱红青,沈静,等.支持向量机多重分类救生舱环境评价研究[J].中国安全生产科学技术,2013,9(4):44.[doi:10.11731/j.issn.1673-193x.2013.04.008]
　YAO Shun cai,ZHU Hong qing,et al.Study on dynamic environment assessment for coal refuge chamber based on support vector machine multiclassification[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(4):44.[doi:10.11731/j.issn.1673-193x.2013.04.008]
[10]袁朋伟,宋守信,董晓庆.基于灰色神经网络优化组合模型的火灾预测研究[J].中国安全生产科学技术,2014,10(3):119.[doi:10.11731/j.issn.1673-193x.2014.03.020]
　YUAN Peng wei,SONG Shou xin,DONG Xiao qing.Study on fire accident prediction based on optimized grey neural network combination model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(4):119.[doi:10.11731/j.issn.1673-193x.2014.03.020]
[11]张钦礼,陈秋松,王新民,等.全尾砂絮凝沉降参数GA-SVM优化预测模型研究[J].中国安全生产科学技术,2014,10(5):24.[doi:10.11731/j.issn.1673-193x.2014.05.004]
　ZHANG Qinli,CHEN Qiusong,WANG Xinming,et al.Study on GA_SVM optimal prediction model on flocculating sedimentation parameter of unclassified tailings[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(4):24.[doi:10.11731/j.issn.1673-193x.2014.05.004]

备注/Memo

备注/Memo:
收稿日期： 2019-02-26；数字出版日期：2019-04-29
基金项目： 国家自然科学基金项目（51774169）；国家重点研发计划项目（2017YFC0804401）
作者简介： 周启超，硕士研究生，主要研究方向为智能矿山。
通信作者： 刘剑，博士，教授，主要研究方向为矿井通风与防灭火工作。
更新日期/Last Update: 2019-05-09