|本期目录/Table of Contents|

[1]张巍,李雨成,张欢,等.面向通风智能化的风速传感器结构化数据降噪方法对比*[J].中国安全生产科学技术,2021,17(8):70-76.[doi:10.11731/j.issn.1673-193x.2021.08.011]
 ZHANG Wei,LI Yucheng,ZHANG Huan,et al.Comparison of structured data noise reduction methods for airflow speed sensor of intelligent ventilation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(8):70-76.[doi:10.11731/j.issn.1673-193x.2021.08.011]
点击复制

面向通风智能化的风速传感器结构化数据降噪方法对比*
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8期
页码:
70-76
栏目:
职业安全卫生管理与技术
出版日期:
2021-08-31

文章信息/Info

Title:
Comparison of structured data noise reduction methods for airflow speed sensor of intelligent ventilation
文章编号:
1673-193X(2021)-08-0070-07
作者:
张巍李雨成张欢李俊桥张静李博伦
(太原理工大学 安全与应急管理工程学院,山西 太原 030032)
Author(s):
ZHANG Wei LI Yucheng ZHANG Huan LI Junqiao ZHANG Jing LI Bolun
(College of Safety and Emergency Management Engineering,Taiyuan University of Technology,Taiyuan Shanxi 030032,China)
关键词:
通风智能化结构化数据降噪模糊C均值聚类Rloess卷积滤波
Keywords:
intelligent ventilation structured data noise reduction fuzzy C-means clustering Rloess convolution filtering
分类号:
X936;TD76
DOI:
10.11731/j.issn.1673-193x.2021.08.011
文献标志码:
A
摘要:
为实现风网实时解算、系统优化调节等关键技术,需要去除监测数据噪声,得到结构清晰、纯度较高的通风数据。利用FCM,Rloess和S-G等平滑降噪算法对300组实测风速数据进行分析处理。结果表明:FCM算法处理过程变量引起噪声较为优越,但需提前给定分类数目;窗宽参数选7时,Rloess算法去除由状态变量引起的风速异常数据最优;在窗宽选5、次数为2时,S-G算法降噪和保持数据特性最佳;结合使用FCM-Rloess或FCM-SG算法可有效处理过程变量和状态变量引起的风速异常数据。研究结果可为矿井通风的异常诊断、灾变识别等研究提供合理的基础数据。
Abstract:
In order to realize the key technologies such as the real-time resolution of air network and the optimal adjustment of system,it is necessary to remove the noise of monitoring data and obtain the ventilation data with clear structure and high purity.The smoothing noise reduction algorithms such as FCM,Rloess and S-G were used to analyze and process 300 sets of measured airflow speed data.The results showed that the FCM algorithm was superior to process the noise caused by the process variables,but the number of classifications needed to be given in advance.When the window width parameter was selected as 7,the Rloess algorithm was optimal to remove the abnormal airflow speed data caused by the state variables.When the window width was 5 and the number of times was 2,the S-G algorithm had the best effect of noise reduction and data characteristics retention.The combination of FCM-Rloess or FCM-SG algorithm could effectively process the abnormal airflow speed data caused by the process variables and state variables.The research provides reasonable basic data for the abnormal diagnosis and disaster identification of mine ventilation.

参考文献/References:

[1]王仁涛,王成虎,宋凯.青岛地铁超浅埋段爆破振动监测数据特征研究[J].中国安全生产科学技术,2015,11(12):72-78. WANG Rentao,WANG Chenghu,SONG Kai.Study on characteristics of monitoring data for blasting vibration in the ultra-shallow buried section of Qingdao metro [J].Journal of Safety Science and Technology,2015,11(12):72-78.
[2]郝爽,李国良,冯建华,等.结构化数据清洗技术综述[J].清华大学学报(自然科学版),2018,58(12):1037-1050. HAO Shuang,LI Guoliang,FENG Jianhua,et al.Survey of structured data cleaning methods [J].Journal of Tsinghua University (Science & Technology),2018,58(12):1037-1050.
[3]付净,聂方超,荆德吉,等.数据挖掘在预测组织事故防控效果中的应用[J].中国安全生产科学技术,2020,16(10):152-157. FU Jing,NIE Fangchao,JING Deji,et al.Application of data mining in predicting prevention and control effect of organizational accidents [J].Journal of Safety Science and Technology,2020,16(10):152-157.
[4]王其军,程久龙.基于免疫神经网络模型的瓦斯浓度智能预测[J].煤炭学报,2008,33(6):665-669. WANG Qijun,CHENG Jiulong.Forecast of coal mine gas concentration based on the immune neural network model [J].Journal of China Coal Society,2008,33(6):665-669.
[5]付华,杨欣,高婷.基于SVR的瓦斯传感器故障诊断方法[J].传感器与微系统,2009,28(2):10-12. FU Hua,YANG Xin,GAO Ting.Method of gas sensor fault detection based on SVR[J].Transducer and MicrosystemTechnologies,2009,28(2):10-12.
[6]马明焕,王新浩,许晓辉,等.基于数据挖掘技术的事故隐患预警方法研究[J].中国安全生产科学技术,2017,13(7):11-17. MA Minghuan,WANG Xinhao,XU Xiaohui,et al.Research on early-warning method of potential safety hazard based on data mining techniques [J].Journal of Safety Science and Technology,2017,13(7):11-17.
[7]付华,梁明广,康海潮.基于主元分析和D-S证据理论的传感器故障诊断与应用[J].计算机应用研究,2011(4):1315-1317. FU Hua,LIANG Mingguang,KANG Haichao.Based on principal component analysis and D-S evidence theory and application of sensor fault diagnosis [J].Application Research of Computers,2011(4):1315-1317.
[8]王军号,孟祥瑞,吴宏伟.基于小波包与EKF-RBF神经网络辨识的瓦斯传感器故障诊断[J].煤炭学报,2011,36(5):867-872. WANG Junhao,MENG Xiangrui.WU Hongwei.Gas sensor fault diagnosis based on wavelet packet and EKF-RBF neural network identification [J].Journal of China Coal Society,2011,36(5):867-872.
[9]赵金宪,金鸿章.基于小波包和神经网络的瓦斯传感器故障诊断[J].传感器与微系统,2010,29(5):80-82. ZHAO Jinxian,JIN Hongzhang.Gas sensor fault diagnosis based on wavelet packet and neural network [J].Transducer and Microsystem Technologies,2010,29(5):80-82.
[10]黄序桢.基于监测数据的矿井通风仿真系统研究与应用[D].阜新:辽宁工程技术大学,2014.
[11]黄凯峰.煤矿安全监测监控系统瓦斯浓度异常信号辨识方法研究[D].淮南:安徽理工大学,2016.
[12]郭松,郭广礼,李怀展,等.基于降维模糊C均值聚类算法的采动场地稳定性评价[J].煤炭科学技术,2020,48(10):137-142. GUO Song,GUO Guangli,LI Huaizhan.et al.Stability evaluation of mining-induced goaf site based on dimensionality reduction fuzzy C-means algorithm [J].Coal Science and Technology,2020,48(10):137-142.
[13]李波,陈广平,于正兴.基于因果模糊聚类法预测覆岩裂隙带高度研究[J].中国安全生产科学技术,2013,9(11):25-29. LI Bo,CHEN Guangping,YU Zhengxing.Study on prediction of fracture zone height of overburden rock bosed on causality fuzzy clustering method [J].Journal of Safety Science and Technology,2013,9(11):25-29.
[14]佘玉萍.基于中位数的双MAD的离群值检测方法[J].廊坊师范学院学报(自然科学版),2016,16(2):25-27. SHE Yuping.Method fordetecting outliers based on double MAD from median [J].Journal of Langfang Teachers University (Natural Science Edition),2016,16(2):25-27.
[15]程传奇,郝向阳,刘松林.基于改进型MAD算法的地形辅助惯性导航[J].电子测量技术,2015,38(4):6-9. CHENG Chuanqi,HAO Xiangyang,LIU Songlin.Improved MAD algorithm for terrain aided inertial navigation [J] Electronic Measurement Technology,2015,38(4):6-9.
[16]吴迪,陈健,石满,等.基于Savitzky-Golay滤波算法的FY-2F地表温度产品时间序列重建 [J].国土资源遥感,2019,31(2):59-65. WU Di,CHEN Jian,SHI Man,et al.Reconstruction of land surface temperature time-series datasets of FY-2F based on Savitzky-Golay filter [J] Remote Sensing for Land and Resources,2019,31(2):59-65.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期: 2021-06-01
* 基金项目: 国家自然科学基金项目(51774168,52004170)
作者简介: 张巍,硕士研究生,主要研究方向为矿井火灾防治。
通信作者: 李雨成,博士,教授,主要研究方向为智能通风与粉尘防治、气体与粉尘爆炸。
更新日期/Last Update: 2021-09-08