高采样频率的矿井电火花图像识别及抗干扰方法研究

李小伟; 王建业

doi:10.13272/j.issn.1671-251x.18145

高采样频率的矿井电火花图像识别及抗干扰方法研究

doi: 10.13272/j.issn.1671-251x.18145

中国矿业大学(北京) 人工智能学院, 北京　100083

基金项目: 国家重点研发计划资助项目（2016YFC0801800）。

详细信息

作者简介:
李小伟（1991—），男，河南商丘人，博士研究生，研究方向为矿井监视与监测，E-mail:844051159@qq.com

中图分类号: TD67
计量
- 文章访问数: 579
- HTML全文浏览量: 58
- PDF下载量: 19
- 被引次数: 0
出版历程
- 收稿日期: 2023-08-07
- 修回日期: 2023-08-16
- 网络出版日期: 2023-09-04

Research on high sampling frequency mine electric spark image recognition and anti-interference methods

School of Artificial Intelligence, China University of Mining and Technology-Beijing, Beijing 100083, China

摘要

摘要: 隔爆外壳外的电缆和电气设备漏电、大功率无线电发射在金属支护和机电设备金属上感生电动势放电产生的矿井电火花，会引起瓦斯和煤尘爆炸及矿井火灾事故，因此有必要尽早感知矿井电火花。影响矿井电火花识别的主要是矿井光源，为减少矿井光源对矿井电火花图像识别的干扰，提出了一种高采样频率的矿井电火花图像识别及抗干扰方法：依据电火花的最长持续发光时间和闪光光源的最短持续发光时间，计算摄像机的采样频率，保证每次电火花出现时，电火花图像只出现在1帧图像上，且矿井光源存在时，干扰光源图像至少出现在连续2帧图像上；计算每帧图像的像素灰度和，若当前帧图像的像素灰度和与前后相邻帧图像的像素灰度和的差值均大于设定的阈值，则发出矿井电火花报警信号。试验结果表明：在无干扰光源条件下，该方法可准确识别矿井电火花图像，准确率达100%；在有日光灯、白炽灯等常亮光源干扰条件下，电火花与日光灯混合图像中电火花识别准确率达99.40%，电火花与白炽灯混合图像中电火花识别准确率达99.67%；在有闪光光源干扰条件下，电火花与闪光灯混合图像中电火花识别准确率达100%。
- 矿井电火花 /
- 电火花识别 /
- 图像识别 /
- 矿井光源 /
- 高采样频率
Abstract: Leakage of electricity from cables and electrical equipment outside the explosion-proof enclosure, and mine sparks generated by high-power radio transmissions on metal supports and metal of electromechanical equipment due to induced electromotive discharges, can cause gas and coal dust explosions and mine fires. Therefore, it is necessary to detect mine electrical sparks as soon as possible. The main factor affecting the recognition of mine electric sparks is the mine light source. In order to reduce the interference of mine light sources on mine electric spark image recognition, a high sampling frequency mine electric spark image recognition and anti-interference method has been proposed. Based on the longest continuous emission time of the electric spark and the shortest continuous emission time of the flash light source, the sampling frequency of the camera is calculated to ensure that the electric spark image only appears in one frame of the image each time the electric spark appears. When the mine light source exists, the interference light source image appears on at least 2 consecutive frames of image. The method calculates the pixel grayscale sum of each image frame. If the difference between the pixel grayscale of the current frame image and the pixel grayscale sum of adjacent frames is greater than the set threshold, a mine electric spark alarm signal will be issued. The experimental results show that under the condition of no interference light source, this method can accurately recognize mine electric spark images with an accuracy rate of 100%. Under the interference of constant light sources such as fluorescent lamps and incandescent lamps, the recognition accuracy of electric sparks in mixed images of electric sparks and fluorescent lamps reaches 99.40%. The recognition accuracy of electric sparks in mixed images of electric sparks and incandescent lamps reaches 99.67%. Under the interference of a flashing light source, the accuracy of electric spark recognition in the mixed image of electric spark and flash lamp reaches 100%.
- mine electric spark /
- spark recognition /
- image recognition /
- mine light source /
- high sampling frequency

HTML全文

图 1 高采样频率的矿井电火花图像识别及抗干扰方法流程

Figure 1. Flow of mine electric spark image recognition and anti-interference method with high sampling frequency

下载: 全尺寸图片幻灯片

图 2 电火花发生装置及其产生的电火花

Figure 2. Electric spark generator device and electric spark generated

下载: 全尺寸图片幻灯片

图 3 紫外摄像机及紫外滤光片

Figure 3. Ultraviolet camera and ultraviolet filter

下载: 全尺寸图片幻灯片

图 4 无光源干扰条件下电火花图像像素灰度和分布

Figure 4. Distribution of the sum of pixel grayscale of electric spark image without light source interference

下载: 全尺寸图片幻灯片

图 5 无光源干扰条件下电火花图像识别帧数

Figure 5. Number of frames for electric spark image recognition without light source interference

下载: 全尺寸图片幻灯片

图 6 日光灯干扰条件下电火花图像像素灰度和分布

Figure 6. Distribution of the sum of pixel grayscale of electric spark image under fluorescent lamp interference

下载: 全尺寸图片幻灯片

图 7 日光灯干扰条件下电火花图像识别帧数

Figure 7. Number of frames for electric spark image recognition under fluorescent lamp interference

下载: 全尺寸图片幻灯片

图 8 白炽灯干扰条件下电火花图像像素灰度和分布

Figure 8. Distribution of the sum of pixel grayscale of electric spark image under incandescent lamp interference

下载: 全尺寸图片幻灯片

图 9 白炽灯干扰条件下电火花图像识别帧数

Figure 9. Number of frames for electric spark image recognition under incandescent lamp interference

下载: 全尺寸图片幻灯片

图 10 闪光灯干扰条件下电火花图像像素灰度和分布

Figure 10. Distribution of the sum of pixel grayscale of electric spark image under flash interference

下载: 全尺寸图片幻灯片

图 11 闪光灯干扰条件下电火花图像识别帧数

Figure 11. Number of frames for electric spark image recognition under flash interference

下载: 全尺寸图片幻灯片

表 1 电火花图像识别结果

Table 1. Electric spark image recognition results

干扰光源	样本帧数	电火花帧数	识别帧数	正确帧数	误检帧数	漏检帧数	召回率/%	精确率/%	准确率/%
无光源	600	28	28	28	0	0	100	100	100
日光灯	500	28	29	27	2	1	96.43	93.10	99.40
白炽灯	898	56	59	56	3	0	100	94.91	99.67
闪光灯	800	48	48	48	0	0	100	100	100

下载: 导出CSV

参考文献(21)

[1]	孙继平. 屯兰煤矿“2·22”特别重大瓦斯爆炸事故原因及教训[J]. 煤炭学报,2010,35(1):72-75. doi: 10.13225/j.cnki.jccs.2010.01.020 SUN Jiping. The causes and lessons of "2.22" gas explosion disaster at Tunlan Coal Mine[J]. Journal of China Coal Society,2010,35(1):72-75. doi: 10.13225/j.cnki.jccs.2010.01.020
[2]	孙继平,李小伟,徐旭,等. 矿井电火花及热动力灾害紫外图像感知方法研究[J]. 工矿自动化,2022,48(4):1-4,95. doi: 10.13272/j.issn.1671-251x.17917 SUN Jiping,LI Xiaowei,XU Xu,et al. Research on ultraviolet image perception method of mine electric spark and thermal power disaster[J]. Journal of Mine Automation,2022,48(4):1-4,95. doi: 10.13272/j.issn.1671-251x.17917
[3]	孙继平,李小伟,王建业. 基于图像邻帧像素灰度和的矿井电火花识别及报警方法研究[J]. 工矿自动化,2023,49(7):1-5. doi: 10.13272/j.issn.1671-251x.18141 SUN Jiping,LI Xiaowei,WANG Jianye. Research on mine electric spark recognition and alarm method based on the sum of adjacent frame pixel grayscale of images[J]. Journal of Mine Automation,2023,49(7):1-5. doi: 10.13272/j.issn.1671-251x.18141
[4]	孙继平. 煤矿瓦斯和煤尘爆炸感知报警与爆源判定方法研究[J]. 工矿自动化,2020,46(6):1-5,11. doi: 10.13272/j.issn.1671-251x.17617 SUN Jiping. Research on method of coal mine gas and coal dust explosion perception alarm and explosion source judgment[J]. Industry and Mine Automation,2020,46(6):1-5,11. doi: 10.13272/j.issn.1671-251x.17617
[5]	孙继平,钱晓红. 2004—2015年全国煤矿事故分析[J]. 工矿自动化,2016,42(11):1-5. doi: 10.13272/j.issn.1671-251x.2016.11.001 SUN Jiping,QIAN Xiaohong. Analysis of coal mine accidents in China during 2004-2015[J]. Industry and Mine Automation,2016,42(11):1-5. doi: 10.13272/j.issn.1671-251x.2016.11.001
[6]	孙继平. 互联网+煤矿监控与通信[M]. 北京: 煤炭工业出版社, 2016. SUN Jiping. Internet+coal mine monitoring and communication[M]. Beijing: China Coal Industry Press, 2016.
[7]	孙继平. 煤矿事故分析与煤矿大数据和物联网[J]. 工矿自动化,2015,41(3):1-5. doi: 10.13272/j.issn.1671-251x.2015.03.001 SUN Jiping. Accident analysis and big data and Internet of things in coal mine[J]. Industry and Mine Automation,2015,41(3):1-5. doi: 10.13272/j.issn.1671-251x.2015.03.001
[8]	余星辰,李小伟.基于特征融合的煤矿瓦斯和煤尘爆炸声音识别方法[J/OL].煤炭学报:1-10 [2023-07-28]. https://doi.org/10.13225/j.cnki.jccs.2022.1421. YU Xingchen, LI Xiaowei. Sound recognition method of coal mine gas and coal dust explosion based on feature fusion[J/OL]. Journal of China Coal Society: 1-10 [2023-07-28]. https://doi.org/10.13225/j.cnki.jccs.2022.1421.
[9]	孙继平,范伟强. 基于视频图像的瓦斯和煤尘爆炸感知报警及爆源判定方法[J]. 工矿自动化,2020,46(7):1-4,48. doi: 10.13272/j.issn.1671-251x.17629 SUN Jiping,FAN Weiqiang. Gas and coal dust explosion perception alarm and explosion source judgment method based on video image[J]. Industry and Mine Automation,2020,46(7):1-4,48. doi: 10.13272/j.issn.1671-251x.17629
[10]	徐晓冰,许可义,穆道明,等. 矿井LED灯的发热分析及光源设计[J]. 煤矿机械,2017,38(4):12-15. doi: 10.13436/j.mkjx.201704005 XU Xiaobing,XU Keyi,MU Daoming,et al. Heat analysis and light source design of mine LED lamp[J]. Coal Mine Machinery,2017,38(4):12-15. doi: 10.13436/j.mkjx.201704005
[11]	国家安全生产监督管理总局. 煤矿安全规程[M]. 北京: 煤炭工业出版社, 2022: 2-115. State Administration of Work Safety. Coal mine safety regulations[M]. Beijing: China Coal Industry Publishing House, 2022: 2-115.
[12]	陈坤,张小良,陶光远,等. 影响静电火花放电的因素[J]. 中国粉体技术,2021,27(5):1-10. doi: 10.13732/j.issn.1008-5548.2021.05.001 CHEN Kun,ZHANG Xiaoliang,TAO Guangyuan,et al. Influence factors of electrostatic spark discharge[J]. China Powder Science and Technology,2021,27(5):1-10. doi: 10.13732/j.issn.1008-5548.2021.05.001
[13]	刘佳. 静电火花放电特性探究[D]. 大连: 大连理工大学, 2020. LIU Jia. Exploring the characteristics of electrostatic spark discharge[D]. Dalian: Dalian University of Technology, 2020.
[14]	梁天宇. 浅谈电火花加工的要素[J]. 中国高新技术企业,2015(4):91-92. doi: 10.13535/j.cnki.11-4406/n.2015.0327 LIANG Tianyu. Discussion on the elements of electrical discharge machining[J]. China High-Tech Enterprises,2015(4):91-92. doi: 10.13535/j.cnki.11-4406/n.2015.0327
[15]	GB 17509—2008 汽车及挂车转向信号灯配光性能[S]. GB 17509-2008 Photometric characteristics of direction indicators for motor vehicles and their trailers[S].
[16]	GB 14886—2016 道路交通信号灯设置与安装规范[S]. GB 14886-2016 Specifications for road traffic signal setting and installation[S].
[17]	GA/T 743—2016 闪光警告信号灯[S]. GA/T 743-2016 Flash alarm signals[S].
[18]	JB/T 12707—2016 道路监控电子闪光装置[S]. JB/T 12707-2016 Electronic flash apparatus for road monitoring[S].
[19]	曹玉超,范伟强. 基于不同深度识别算法的矿井水位标尺刻度识别性能分析与研究[J]. 煤炭学报,2019,44(11):3529-3538. doi: 10.13225/j.cnki.jccs.2019.1047 CAO Yuchao,FAN Weiqiang. Performance analysis and research of mine water level scale recognition based on different depth recognition algorithms[J]. Journal of China Coal Society,2019,44(11):3529-3538. doi: 10.13225/j.cnki.jccs.2019.1047
[20]	余星辰,王云泉. 基于小波包能量的煤矿瓦斯和煤尘爆炸声音识别方法[J]. 工矿自动化,2023,49(1):131-139. doi: 10.13272/j.issn.1671-251x.18070 YU Xingchen,WANG Yunquan. Coal mine gas and coal dust explosion sound recognition method based on wavelet packet energy[J]. Journal of Mine Automation,2023,49(1):131-139. doi: 10.13272/j.issn.1671-251x.18070
[21]	王建业. 矿井电火花图像感知方法研究[D]. 北京: 中国矿业大学（北京）, 2023: 11-15. WANG Jianye. Research on mine electric spark image perception method[D]. Beijing: China University of Mining and Technology-Beijing, 2023: 11-15.