基于振动信号的采矿机截割负载分类

许志鹏; 刘振坚; 庄德玉; 尹玉玺

doi:10.13272/j.issn.1671-251x.2022070078

基于振动信号的采矿机截割负载分类

doi: 10.13272/j.issn.1671-251x.2022070078

1.
煤炭科学研究总院, 北京　100013
2.
中煤科工集团上海有限公司, 上海　200030

基金项目: 中国煤炭科工集团有限公司科技创新创业资金项目（21-TD-MS005）。

详细信息

作者简介:
许志鹏（1997—），男，湖南益阳人，硕士研究生，主要研究方向为矿山设备状态监测与故障诊断，E-mail:602411924@qq.com

中图分类号: TD421
计量
- 文章访问数: 154
- HTML全文浏览量: 49
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-28
- 修回日期: 2022-12-06
- 网络出版日期: 2022-11-28

Mining machine cutting load classification based on vibration signal

1.
China Coal Research Institute, Beijing 100013, China
2.
CCTEG Shanghai Research Institute, Shanghai 200030, China

摘要

摘要: 针对人为判断采矿机截割负载类型的方式具有一定误差和滞后性的问题，提出了一种基于小波包分解和麻雀搜索算法优化BP神经网络（SSA−BPNN）的采矿机截割负载分类方法。该方法包括信号特征提取和模式分类2个部分：在信号特征提取部分，对采集的采矿机摇臂振动信号进行小波包分解，得到各子频带能量及信号总能量，经归一化处理后得到表征不同负载类型的特征向量，并利用主成分分析法对特征向量进行降维处理；在模式分类部分，通过SSA优化BPNN的初始权值和阈值，将特征向量作为SSA−BPNN的输入，从而实现负载分类识别。以MG500/1170−AWD1采矿机为对象，将磁吸式加速度传感器吸附于采矿机摇臂一轴靠近支架侧的壳体处，采集采矿机滚筒空载、截割铝土和岩石3种工况下的振动信号进行试验。试验结果表明：不同截割负载下振动信号在各子频带能量上表现出一定的差异性，表明经小波包分解后得到的能量特征可以作为区分不同负载类型的特征向量；与BPNN相比，SSA−BPNN收敛速度更快、识别准确率更高，负载分类识别准确率达95.3%。
- 采矿机 /
- 截割负载分类 /
- 摇臂振动信号 /
- 小波包分解 /
- 麻雀搜索算法 /
- BP神经网络
Abstract: There are some errors and lags in the way of judging the cutting load type of the mining machine manually. In order to solve the above problem, a classification method of mining machine cutting load based on wavelet packet decomposition and sparrow search algorithm optimized BP neural network (SSA-BPNN) is proposed. The method comprises two parts of signal feature extraction and mode classification. In the part of signal feature extraction, the collected vibration signal of the mining machine rocker arm is decomposed by wavelet packet to obtain the energy of each subband and the total energy of the signal. After normalization, feature vectors representing different load types are obtained. The principal component analysis is used to reduce the dimensions of the feature vector. In the mode classification part, SSA is used to optimize the initial weight and threshold of BPNN. The feature vector is used as the input of SSA-BPNN to realize the load classification and recognition. Taking the MG500/1170-AWD1 mining machine as an object, the magnetic acceleration sensor is attached to the shell of the rocker arm of the mining machine near the bracket side. The vibration signals of the mining machine drum under three working conditions of no-load, cutting bauxite and rock are collected and tested. The experimental results show that the vibration signals under different cutting loads have some differences in the energy of each sub-band. This result indicates that the energy features obtained by wavelet packet decomposition can be used as feature vectors to distinguish different load types. Compared with BPNN, SSA-BPNN has faster convergence speed and higher recognition accuracy, and the recognition accuracy of load classification is 95.3%.
- mining machine /
- cutting load classification /
- rocker arm vibration signal /
- wavelet packet decomposition /
- sparrow search algorithm /
- BP neural network

HTML全文

图 1 基于小波包分解和SSA−BPNN的截割负载类型识别流程

Figure 1. Cutting load type identification process based on wavelet packet decomposition and sparrow search algorithm optimized back propagation neural network

下载: 全尺寸图片幻灯片

图 2 测点布置

Figure 2. Arrangement of measuring points

下载: 全尺寸图片幻灯片

图 3 加载试验平台

Figure 3. Loading test platform

下载: 全尺寸图片幻灯片

图 4 不同工况下各轴振动信号的均方根

Figure 4. Root mean square of vibration signal of each shaft under different working conditions

下载: 全尺寸图片幻灯片

图 5 不同工况下各轴振动信号的峭度

Figure 5. Kurtosis of vibration signal of each shaft under different working conditions

下载: 全尺寸图片幻灯片

图 6 传感器安装位置

Figure 6. Sensor installation position

下载: 全尺寸图片幻灯片

图 7 各子频带能量

Figure 7. Energy of each sub-band

下载: 全尺寸图片幻灯片

图 8 主成分贡献率

Figure 8. Contribution rate of principal component

下载: 全尺寸图片幻灯片

图 9 均方误差曲线

Figure 9. Mean square error curve

下载: 全尺寸图片幻灯片

图 10 负载分类结果

Figure 10. Load classification results

下载: 全尺寸图片幻灯片

表 1 工作面地质赋存

Table 1. Geological occurrence of working face

层位	岩性	岩性描述
基本顶	灰岩	灰色薄−中厚层状细晶灰岩，夹灰−深灰色薄−中厚层状含泥质灰岩和灰黑色薄层含生物碎屑泥灰岩，含线状、脉状灰白色方解石
直接顶	泥岩、泥质灰岩、白云质灰岩	灰−深灰色薄中厚层状含泥质灰岩，夹杂生物碎屑灰岩，含线状灰白色方解石
伪顶	炭质泥岩、铝土岩	深灰色、黑色炭质泥岩，灰绿色致密铝土岩
矿体	铝土矿	灰白色、浅黄灰色碎屑状、豆状、半土状铝土矿，含少量星点状细粒黄铁矿
直接底	铝土岩、铝土质泥岩	深灰绿色致密铝土岩、深灰−灰黑色薄−中厚层状含炭质泥，含团块状细−中粒黄铁矿
基本底	泥（页）岩	灰白色中厚层灰岩夹灰绿色薄层绿泥石岩、紫红色夹灰绿色薄层泥岩、浅紫红色片状薄层页岩

下载: 导出CSV

表 2 传感器参数

Table 2. 2 Sensor parameters

指标	值
轴向灵敏度/（mV·g⁻¹）	100
工作温度/℃	−40～+120
冲击极限/g	2 000
频率范围/Hz	0.5～7 000

下载: 导出CSV

表 3 小波包能量特征向量

Table 3. 3 Wavelet packet energy feature vectors

序号	特征向量
1	[0.275 2　0.340 7　0.101 8　0.440 6　0.119 3　0.081 8　 0.018 4　0.018 3　0.890 3]
2	[0.316 7　0.339 3　0.107 6　0.049 4　0.095 0　0.061 8　 0.012 7　0.017 5　0.886 2]
3	[0.282 6　0.332 4　0.092 2　0.045 7　0.109 6　0.094 4　 0.021 5　0.021 6　0.877 9]
	
3 000	[0.444 5　0.252 0　0.084 2　0.707 0　0.072 6　0.043 7　 0.016 2　0.016 1　0.440 1]

下载: 导出CSV

参考文献(15)

[1]	张海坤,胡鹏,姜军胜,等. 铝土矿分布特点、主要类型与勘查开发现状[J]. 中国地质,2021,48(1):68-81. doi: 10.12029/gc20210105 ZHANG Haikun,HU Peng,JIANG Junsheng,et al. Distribution,genetic types and current situation of exploration and development of bauxite resources[J]. Geology in China,2021,48(1):68-81. doi: 10.12029/gc20210105
[2]	展明鹏,马军强,姚强岭. 铝土矿综合机械化开采及应用研究[J]. 矿业研究与开发,2022,42(1):1-5. doi: 10.13827/j.cnki.kyyk.2022.01.001 ZHAN Mingpeng,MA Junqiang,YAO Qiangling. Comprehensive mechanized mining of bauxite and its application research[J]. Mining Research and Development,2022,42(1):1-5. doi: 10.13827/j.cnki.kyyk.2022.01.001
[3]	张强,张润鑫,刘峻铭,等. 煤矿智能化开采煤岩识别技术综述[J]. 煤炭科学技术,2022,50(2):1-26. doi: 10.13199/j.cnki.cst.2021-1333 ZHANG Qiang,ZHANG Runxin,LIU Junming,et al. Review on coal and rock identification technology for intelligent mining in coal mines[J]. Coal Science and Technology,2022,50(2):1-26. doi: 10.13199/j.cnki.cst.2021-1333
[4]	郭伟超,赵怀山,李成,等. 基于小波包能量谱与主成分分析的轴承故障特征增强诊断方法[J]. 兵工学报,2019,40(11):2370-2377. doi: 10.3969/j.issn.1000-1093.2019.11.022 GUO Weichao,ZHAO Huaishan,LI Cheng,et al. Fault feature enhancement method for rolling bearing fault diagnosis based on wavelet packet energy spectrum and principal component analysis[J]. Acta Armamentarii,2019,40(11):2370-2377. doi: 10.3969/j.issn.1000-1093.2019.11.022
[5]	孙全,孙渊. 基于麻雀搜索算法的BP神经网络优化技术[J]. 上海电机学院学报,2022,25(1):12-16. doi: 10.3969/j.issn.2095-0020.2022.01.003 SUN Quan,SUN Yuan. Optimization technology of BP neural network based on sparrow search algorithm[J]. Journal of Shanghai Dianji University,2022,25(1):12-16. doi: 10.3969/j.issn.2095-0020.2022.01.003
[6]	王冬云,张文志. 基于小波包变换的滚动轴承故障诊断[J]. 中国机械工程,2012,23(3):295-298. WANG Dongyun,ZHANG Wenzhi. Fault diagnosis study of ball bearing based on wavelet packet transform[J]. China Mechanical Engineering,2012,23(3):295-298.
[7]	鞠晨,张超,樊红卫,等. 基于小波包分解和PSO−BPNN的滚动轴承故障诊断[J]. 工矿自动化,2020,46(8):70-74. doi: 10.13272/j.issn.1671-251x.2019120022 JU Chen,ZHANG Chao,FAN Hongwei,et al. Rolling bearing fault diagnosis based on wavelet packet decomposition and PSO-BPNN[J]. Industry and Mine Automation,2020,46(8):70-74. doi: 10.13272/j.issn.1671-251x.2019120022
[8]	葛渊博, 卢文喜, 白玉堃, 等. 基于SSA−BP与SSA的地下水污染源反演识别[J/OL]. 中国环境科学: 1-11[2022-07-21]. DOI: 10.19674/j.cnki.issn1000-6923.20220711.006. GE Yuanbo, LU Wenxi, BAI Yukun, et al. Inversion and identification of groundwater pollution sources based on SSA-BP and SSA[J/OL]. China Environmental Science: 1-11[2022-07-21]. DOI: 10.19674/j.cnki.issn1000-6923.20220711.006.
[9]	郭名诚,侯珂,李鑫浩. 基于SSA−BPNN模型的Web服务质量评价[J]. 信息技术与信息化,2021(10):13-15. doi: 10.3969/j.issn.1672-9528.2021.10.003 GUO Mingcheng,HOU Ke,LI Xinhao. Web service quality evaluation based on SSA-BPNN model[J]. Information Technology and Informatization,2021(10):13-15. doi: 10.3969/j.issn.1672-9528.2021.10.003
[10]	陈晓玉,杜雅欣,刘亚茹,等. 三维荧光光谱结合2DPCA−SSA−GRNN对柴油占比的检测[J]. 中国激光,2022,49(18):175-182. CHEN Xiaoyu,DU Yaxin,LIU Yaru,et al. Detection of diesel proportion using three-dimensional fluorescence spectrum and 2DPCA-SSA-GRNN[J]. Chinese Journal of Lasers,2022,49(18):175-182.
[11]	刘湲,王芳. 麻雀搜索算法优化BP神经网络的短期风功率预测[J]. 上海电机学院学报,2022,25(3):132-136. doi: 10.3969/j.issn.2095-0020.2022.03.002 LIU Yuan,WANG Fang. BP neural networks optimized by sparrow search algorithm for short-term wind power prediction[J]. Journal of Shanghai Dianji University,2022,25(3):132-136. doi: 10.3969/j.issn.2095-0020.2022.03.002
[12]	黄龙杨,夏正洪,贾鑫磊. 基于SSA−BP的离港航班滑出时间预测[J]. 科学技术与工程,2022,22(16):6607-6612. HUANG Longyang,XIA Zhenghong,JIA Xinlei. Departure flights' taxi-out time prediction based on SSA-BP algorithm[J]. Science Technology and Engineering,2022,22(16):6607-6612.
[13]	王耀国, 李勇永, 郭涛. 基于改进的SSA优化BP神经网络的导水断裂带高度预测[J/OL]. 煤矿安全: 1-8[2022-07-22]. DOI: 10.13347/j.cnki.mkaq.2023.02.001. WANG Yaoguo, LI Yongyong, GUO Tao. Prediction of height of water flowing fractured zone based on improved SSA to optimize BP neural network[J/OL]. Safety in Coal Mines: 1-8[2022-07-22]. DOI: 10.13347/j.cnki.mkaq.2023.02.001.
[14]	李福涛,王忠宾,司垒,等. 基于振动信号的采煤机煤岩截割状态识别[J]. 煤炭工程,2022,54(1):123-127. LI Futao,WANG Zhongbin,SI Lei,et al. Coal cutting state recognition of shearer based on vibration signal[J]. Coal Engineering,2022,54(1):123-127.
[15]	蒋干. 基于多传感信息融合的采煤机煤岩截割状态识别技术研究[D]. 徐州: 中国矿业大学, 2019. JIANG Gan. Research on recognition technology of shearer coal-rock cutting status based on multi-sensor information fusion[D]. Xuzhou: China University of Mining and Technology, 2019.