矿用千米定向钻机动作识别方法

向学艺; 雷志鹏; 栗林波; 任瑞斌; 李杰; 王飞宇

doi:10.13272/j.issn.1671-251x.2022030103

矿用千米定向钻机动作识别方法

向学艺^{1, 2,},
雷志鹏^{1, 3, ,},
栗林波⁴,
任瑞斌⁴,
李杰^{1, 2},
王飞宇^{1, 2}

1.
太原理工大学矿用智能电器技术国家地方联合工程实验室，山西太原　030024
2.
太原理工大学煤矿电气设备与智能控制山西省重点实验室，山西太原　030024
3.
晋能控股山西科学技术研究院有限公司（晋城）技术中心，山西晋城　048000
4.
山西金鼎高宝钻探有限责任公司，山西晋城　048000

基金项目: 山西省重点研发计划项目（202003D111008）；山西省“1331”工程项目（晋教科〔2017〕 10号）。

详细信息

作者简介:
向学艺(1994—)，男，湖北武汉人，硕士研究生，主要研究方向为矿用智能电器，E-mail：xiangxueyi1@163.com

通讯作者:
雷志鹏(1983—)，男，山西太原人，副教授，博士，主要研究方向为矿用智能电器和电气绝缘性能评估，E-mail：leizhipeng@163.com

中图分类号: TD67
计量
- 文章访问数: 285
- HTML全文浏览量: 41
- PDF下载量: 26
出版历程
- 收稿日期: 2022-03-30
- 修回日期: 2022-09-11
- 网络出版日期: 2022-07-06
- 刊出日期: 2022-09-25

Action recognition method for mine kilometer directional drilling rig

XIANG Xueyi^{1, 2,},
LEI Zhipeng^{1, 3, ,},
LI Linbo⁴,
REN Ruibin⁴,
LI Jie^{1, 2},
WANG Feiyu^{1, 2}

1.
National & Provincial Joint Engineering Laboratory of Mining Intelligent Electrical Apparatus Technology, Taiyuan University of Technology, Taiyuan 030024, China
2.
Shanxi Key Laboratory of Mining Electrical Equipment and Intelligent Control, Taiyuan University of Technology, Taiyuan 030024, China
3.
Jinneng Holding Shanxi Science and Technology Research Institute Co., Ltd.(Jincheng) Technology Centre, Jincheng 048000, China
4.
Shanxi Jinding Gaobao Drilling Co., Ltd., Jincheng 048000, China

摘要

摘要: 目前矿用千米定向钻机的行走、钻进等各项操作均由司钻工人手动操作实现，智能化水平低，且缺少对千米定向钻机动作类型与液压泵站振动状态二者关联性的研究，远程识别千米定向钻机动作类型困难。针对上述问题，提出了一种基于经验小波变换（EWT）和模糊C均值（FCM）聚类算法的矿用千米定向钻机动作识别方法。首先利用EWT方法分析千米定向钻机执行5种不同动作（千米定向钻机启动和动力头不带钻杆旋转、带钻杆旋转、带钻杆向前慢速钻进和带钻杆向前快速钻进）时液压泵站3个关键部位（电动机、液压泵和联轴器）的频率特征信息，分别选取每处振动特征最明显方向上的振动信号构成动作识别原信号组。然后结合EWT分解和相关系数选取规则提取动作识别原信号组中包含钻机动作信息的特征量，并确认不同特征量的权重，构建标准识别特征量。最后利用FCM聚类算法得到待识别动作特征量与5种动作识别标准特征量之间的隶属度，实现对千米定向钻机动作类型的智能识别。以ZYL−17000D型矿用千米定向钻机为研究对象，对基于EWT和FCM聚类算法的矿用千米定向钻机动作识别方法的可靠性进行实验验证，实验采集了电动机、液压泵、联轴器的轴向、水平径向、垂直径向等方向在5种动作下的振动数据，结果表明：钻机执行不同动作时，其电动机、液压泵和联轴器振动信号的经验小波函数表现出了不同的特征，其中液压泵轴向振动信号特征量的聚类性能最好，根据提取的特征量在不同动作下的差异性可实现对动作类型的识别。基于测试数据的动作识别结果表明，该方法能够有效识别千米定向钻机的动作类型，且在隶属度大于0.9的条件下，识别准确率达96.8%。
- 矿用千米定向钻机 /
- 动作识别 /
- 带钻杆旋转 /
- 带钻杆钻进 /
- 振动信号 /
- 标准识别特征量 /
- 经验小波变换 /
- 模糊C均值聚类算法
Abstract: At present, the walking and drilling operations of the mine kilometer directional drilling rig are all realized by the manual operation of drillers. The intelligence level is low. At present, there is no research on the correlation between the action type of kilometer directional drilling rig and the vibration state of the hydraulic pump station. Therefore, it is difficult to remotely identify the action type of the kilometer directional drilling rig. In order to solve the above problems, an action recognition method for mine kilometer directional drilling rig based on empirical wavelet transform (EWT) and fuzzy C-means (FCM) clustering algorithm is proposed. Firstly, the EWT method is used to analyze the frequency characteristic information of the three key parts (motor, hydraulic pump and coupling) of the hydraulic pump station when the kilometer directional drilling rig performs five different actions (the start of the kilometer directional drilling rig, the rotation of the power head without drill pipe, the rotation with drill pipe, the forward slow drilling with drill pipe and the forward fast drilling with drill pipe). The vibration signals in the most obvious direction of each vibration characteristic are selected to form the original signal group for action recognition. Secondly, the combination of EWT decomposition and correlation coefficient selection rules is used to extract eigenvectors containing drill action information in the original signal group for action recognition. The weight of different eigenvectors is confirmed. The standard recognition eigenvector is constructed. Finally, the membership degree between the action eigenvector to be identified and the five action recognition standard eigenvectors is obtained by using the FCM clustering algorithm. The intelligent recognition of the action types of the kilometer directional drilling rig is realized. Taking the ZYL-17000D type mine kilometer directional drilling rig as the research object, the reliability of the action recognition method based on EWT and FCM clustering algorithm for mine kilometer directional drilling rig is verified by experiments. The vibration data of the motor, hydraulic pump and coupling in the axial, horizontal and vertical radial directions under five actions are collected in the experiment. The results show that the empirical wavelet functions of the vibration signals of the motor, hydraulic pump and coupling of the drilling rig show different characteristics when it performs different actions. The clustering performance of the eigenvectors of the axial vibration signals of hydraulic pumps is the best. According to the difference of extracted eigenvectors under different actions, action types can be identified. The results of action recognition based on test data show that this method can effectively identify the action type of kilometer directional drilling rig, and the recognition accuracy is 96.8% when the membership degree is greater than 0.9.
- mine kilometer directional drilling rig /
- action recognition /
- rotation with drill pipe /
- drilling with drill pipe /
- vibration signal /
- standard recognition eigenvector /
- empirical wavelet transform /
- fuzzy C-means clustering algorithm

HTML全文

图 1 基于EWT和FCM聚类算法的矿用千米定向钻机动作识别流程

Figure 1. Action recognition process of mine directional kilometer drilling rig based on EWT and FCM clustering algorithm

下载: 全尺寸图片幻灯片

图 2 ZYL−17000D型矿用千米定向钻机

Figure 2. ZYL-17000D mine kilometer directional drilling rig

下载: 全尺寸图片幻灯片

图 3 5种动作下8路振动原信号

Figure 3. Eight channels original vibration signals under five actions

下载: 全尺寸图片幻灯片

图 4 5种动作下电动机轴向振动信号的EWF各分量频谱

Figure 4. Spectrum of EWF components of motor axial vibration signal under five actions

下载: 全尺寸图片幻灯片

图 5 电动机轴向振动信号EWT时频谱

Figure 5. The EWT time-frequency spectrum of the motor axial vibration signal

下载: 全尺寸图片幻灯片

图 6 不同权重下动作识别特征量聚类结果

Figure 6. Clustering results of action recognition characteristic quantities under different weights

下载: 全尺寸图片幻灯片

表 1 振动方向编号

Table 1 Label of vibration direction

编号	振动方向	编号	振动方向
1	电动机水平径向	5	液压泵轴向
2	电动机轴向	6	液压泵垂直径向
3	电动机垂直径向	7	联轴器轴向
4	液压泵水平径向	8	联轴器垂直径向

下载: 导出CSV

表 2 5种动作识别原信号组的特征量

Table 2 Eigenvectors of the original signal group for action recognition under five working conditions

动作	V₁	V₂	V₃
R₁	[1.789 1.244 0.908 1.307]	[5.618 7.259 11.32 0]	[8.243 6.932 12.67 7.165]
	[1.604 1.414 1.115 1.377]	[5.649 7.391 11.32 0]	[8.239 6.929 12.67 7.163]
	[1.705 1.452 1.148 1.374]	[5.630 7.367 11.33 0]	[8.240 6.929 12.67 7.164]
R₂	[3.694 2.032 1.581 0]	[7.304 13.68 8.482 11.37]	[10.30 11.08 6.856 6.829]
	[3.718 2.123 1.568 0]	[7.288 13.64 8.485 11.40]	[10.30 11.07 6.855 6.830]
	[3.718 2.122 1.567 0]	[7.272 13.66 8.460 11.41]	[10.47 11.15 6.816 6.773]
R₃	[3.355 2.251 3.171 0]	[7.382 9.222 5.399 3.358]	[13.04 15.63 9.577 0]
	[3.354 2.251 3.171 0]	[7.356 9.222 5.398 3.379]	[13.05 15.63 9.572 0]
	[3.353 2.252 3.171 0]	[7.356 9.222 5.396 3.382]	[13.06 15.63 9.577 0]
R₄	[1.664 2.434 1.805 0]	[5.867 5.485 5.259 3.975]	[5.521 7.742 5.007 5.391]
	[2.223 2.396 2.014 0]	[5.890 5.490 5.255 3.969]	[5.521 7.742 5.006 5.391]
	[1.664 2.434 1.804 0]	[5.811 5.478 5.275 3.981]	[5.521 7.741 5.008 5.390]
R₅	[6.984 1.997 0 0]	[12.48 11.71 0 0]	[10.59 23.16 12.41 0]
	[6.985 1.997 0 0]	[12.60 11.74 0 0]	[10.58 23.15 12.41 0]
	[6.589 2.927 0 0]	[12.56 11.70 0 0]	[11.46 23.64 13.42 0]

下载: 导出CSV

表 3 10组测试样本的隶属度

Table 3 Membership degree of test samples (group 1-10)

动作	隶属度										判别结果
动作	R₁样本1	R₁样本2	R₂样本1	R₂样本2	R₃样本1	R₃样本2	R₄样本1	R₄样本2	R₅样本1	R₅样本2	判别结果
R₁	9.99×10⁻¹	9.99×10⁻¹	4.03×10⁻⁴	3.43×10⁻⁴	2.43×10⁻⁴	4.12×10⁻⁵	3.47×10⁻⁷	1.21×10⁻⁴	3.14×10⁻⁵	2.21×10⁻⁵	正确
R₂	8.41×10⁻⁵	2.34×10⁻⁴	9.89×10⁻¹	9.91×10⁻¹	1.10×10⁻³	2.44×10⁻⁴	2.15×10⁻⁵	2.04×10⁻⁴	7.04×10⁻⁴	4.32×10⁻⁴	正确
R₃	4.25×10⁻⁵	1.21×10⁻⁴	9.11×10⁻⁴	7.50×10⁻⁴	9.97×10⁻¹	9.99×10⁻¹	7.39×10⁻⁴	3.17×10⁻⁴	6.35×10⁻⁵	3.43×10⁻⁵	正确
R₄	3.38×10⁻⁵	9.34×10⁻⁵	8.02×10⁻³	7.47×10⁻⁴	4.44×10⁻⁴	7.48×10⁻⁵	9.99×10⁻¹	9.98×10⁻¹	5.46×10⁻⁵	2.29×10⁻⁴	正确
R₅	8.25×10⁻⁵	2.66×10⁻⁴	9.21×10⁻⁴	7.32×10⁻³	1.05×10⁻³	2.46×10⁻⁴	1.35×10⁻⁶	5.45×10⁻⁴	9.99×10⁻¹	9.99×10⁻¹	正确

下载: 导出CSV

参考文献(16)

[1]	王天龙,马斌,董洪波. 煤矿用自动化钻机远程监测系统研制[J]. 煤田地质与勘探,2022,50(1):80-85. DOI: 10.12363/issn.1001-1986.21.12.0723 WANG Tianlong,MA Bin,DONG Hongbo. Development of a remote monitoring system for coal mine automatic drilling rigs[J]. Coal Geology & Exploration,2022,50(1):80-85. DOI: 10.12363/issn.1001-1986.21.12.0723
[2]	经哲,郭利. 基于广义相关系数自适应随机共振的液压泵振动信号预处理方法[J]. 振动与冲击,2016,35(16):72-78,85. DOI: 10.13465/j.cnki.jvs.2016.16.013 JING Zhe,GUO Li. Hydraulic pump vibration signal pretreatment based on adaptive stochastic resonance with a general correlation function[J]. Journal of Vibration and Shock,2016,35(16):72-78,85. DOI: 10.13465/j.cnki.jvs.2016.16.013
[3]	李洪儒,王余奎,马济乔,等. 基于MMSE和ABCSVM的液压泵故障模式识别[J]. 振动与冲击,2016,35(9):152-158. DOI: 10.13465/j.cnki.jvs.2016.09.024 LI Hongru,WANG Yukui,MA Jiqiao,et al. Fault pattern recognition of hydraulic pumps based on MMSE and ABCSVM[J]. Journal of Vibration and Shock,2016,35(9):152-158. DOI: 10.13465/j.cnki.jvs.2016.09.024
[4]	姜万录,李振宝,张生,等. 基于递归定量分析的液压泵故障识别方法[J]. 液压与气动,2019(2):18-23. DOI: 10.11832/j.issn.1000-4858.2019.02.004 JIANG Wanlu,LI Zhenbao,ZHANG Sheng,et al. Fault recognition method based on recurrent quantitation analysis for hydraulic pump[J]. Chinese Hydraulics & Pneumatics,2019(2):18-23. DOI: 10.11832/j.issn.1000-4858.2019.02.004
[5]	郑直,李世峰,郭洋,等. 基于液压泵复数信号的log−SAM故障诊断方法研究[J]. 振动与冲击,2021,40(6):79-85. DOI: 10.13465/j.cnki.jvs.2021.06.010 ZHENG Zhi,LI Shifeng,GUO Yang,et al. Hydraulic pump fault diagnosis method using log-SAM on complex signals[J]. Journal of Vibration and Shock,2021,40(6):79-85. DOI: 10.13465/j.cnki.jvs.2021.06.010
[6]	张幼振,刘焱杰,钟自成,等. 煤矿全液压动力头式钻机振动测试与分析[J]. 煤炭科学技术,2022,50(2):271-279. DOI: 10.13199/j.cnki.cst.2021-1303 ZHANG Youzhen,LIU Yanjie,ZHONG Zicheng,et al. Vibration measurement and analysis of full hydraulic power head drilling rig in coal mine[J]. Coal Science and Technology,2022,50(2):271-279. DOI: 10.13199/j.cnki.cst.2021-1303
[7]	杜名喆,王宝中. 基于经验小波分解和卷积神经网络的液压泵故障诊断[J]. 液压与气动,2020(1):163-170. DOI: 10.11832/j.issn.1000-4858.2020.01.027 DU Mingzhe,WANG Baozhong. Fault diagnosis of hydraulic pump based on empirical wavelet transform and convolutional neural network[J]. Chinese Hydraulics & Pneumatics,2020(1):163-170. DOI: 10.11832/j.issn.1000-4858.2020.01.027
[8]	HU Mantang, WANG Guofeng, MA Kaile, et al. Bearing performance degradation assessment based on optimized EWT and CNN[J]. Measurement, 2020, 172（1）. DOI: 10.1016/j.measurement.2020.108868.
[9]	LI Yuxing,JIAO Shangbin,GAO Xiang. A novel signal feature extraction technology based on empirical wavelet transform and reverse dispersion entropy[J]. Defence Technology,2020,17(5):1-11.
[10]	赵妙颖,许刚. 基于经验小波变换的变压器振动信号特征提取[J]. 电力系统自动化,2017,41(20):63-69,91. DOI: 10.7500/AEPS20170327001 ZHAO Miaoying,XU Gang. Feature extraction for vibration signals of power transformer based on empirical wavelet transform[J]. Automation of Electric Power Systems,2017,41(20):63-69,91. DOI: 10.7500/AEPS20170327001
[11]	LU Chuanqi,WANG Shaoping,ZHANG Chao. Fault diagnosis of hydraulic piston pumps based on a two-step EWFD method and fuzzy C-means clustering[J]. Proceedings of the Institution of Mechanical Engineers,Part C:Journal of Mechanical Engineering Science,2016,230(16):203-210.
[12]	倪卫宁,张晓彬,万勇,等. 随钻方位电磁波电阻率测井仪分段组合线圈系设计[J]. 石油钻探技术,2017,45(2):115-120. NI Weining,ZHANG Xiaobin,WAN Yong,et al. The design of the coil system in LWD tools based on azimuthal electromagnetic-wave resistivity combined with sections[J]. Petroleum Drilling Techniques,2017,45(2):115-120.
[13]	PAN Yuna,CHEN Jin,LI Xinglin. Bearing performance degradation assessment based on lifting wavelet packet decomposition and fuzzy C-means[J]. Mechanical Systems and Signal Processing,2010,24:559-566. DOI: 10.1016/j.ymssp.2009.07.012
[14]	尚海昆,苑津莎,王瑜,等. 基于交叉小波变换和相关系数矩阵的局部放电特征提取[J]. 电工技术学报,2014,29(4):274-281. DOI: 10.3969/j.issn.1000-6753.2014.04.035 SHANG Haikun,YUAN Jinsha,WANG Yu,et al. Feature extraction for partial discharge based on cross-wavelet transform and correlation coefficient matrix[J]. Transactions of China Electrotechnical Society,2014,29(4):274-281. DOI: 10.3969/j.issn.1000-6753.2014.04.035
[15]	郑直,王宝中,刘佳鑫,等. 辛几何模态分解和广义形态分形维数的液压泵故障诊断[J]. 哈尔滨工程大学学报,2020,41(5):724-730. ZHENG Zhi,WANG Baozhong,LIU Jiaxin,et al. Hydraulic pump fault diagnosis method of symplectic geometry mode decomposition and generalized morphological fractal dimensions[J]. Journal of Harbin Engineering University,2020,41(5):724-730.
[16]	郭文琪,田慕琴,宋建成,等. 基于多源信号融合的离心泵叶轮磨损故障分析[J]. 工矿自动化,2018,44(6):74-79. DOI: 10.13272/j.issn.1671-251x.2018020029 GUO Wenqi,TIAN Muqin,SONG Jiancheng,et al. Wear fault analysis of centrifugal pump impeller based on multi-source signal fusion[J]. Industry and Mine Automation,2018,44(6):74-79. DOI: 10.13272/j.issn.1671-251x.2018020029

施引文献(25)

期刊类型引用(10)

1.	柳圆，司垒，王忠宾，魏东，顾进恒. 基于电磁波的煤岩识别技术研究进展. 工矿自动化. 2024(01): 42-48+65 . 本站查看
2.	姜子超. 太赫兹技术在识别煤和煤矸石中的应用. 无线互联科技. 2023(16): 96-98 . 百度学术
3.	王文海，蒋力帅，王庆伟，冯昊，唐鹏. 煤矿综采工作面智能开采技术现状与展望. 中国煤炭. 2021(11): 51-55 . 百度学术
4.	汪春宏，梅杰. 微型近红外物联网节点状态的实时检测与分析研究. 激光杂志. 2020(06): 63-66 . 百度学术
5.	葛世荣，郝尚清，张世洪，张幸福，张林，王世博，王忠宾，鲍久圣，杨小林，杨健健. 我国智能化采煤技术现状及待突破关键技术. 煤炭科学技术. 2020(07): 28-46 . 百度学术
6.	庞义辉. 综采工作面智能化发展现状与展望. 智能矿山. 2020(01): 21-29 . 百度学术
7.	杨恩，王世博，葛世荣. 典型煤系岩石的可见-近红外光谱特征研究. 工矿自动化. 2019(03): 45-51+89 . 本站查看
8.	杨恩，王世博，葛世荣，向阳. 基于反射光谱的煤岩感知实验研究. 煤炭学报. 2019(12): 3912-3920 . 百度学术
9.	王昕，赵端，丁恩杰. 基于太赫兹光谱技术的煤岩识别方法. 煤矿开采. 2018(01): 13-17+91 . 百度学术
10.	刘忠超，刘勇军. 煤岩识别现状分析与发展方向. 南阳理工学院学报. 2018(04): 26-30 . 百度学术