矿用带式输送机托辊音频故障诊断方法

吴文臻; 程继明; 李标

doi:10.13272/j.issn.1671-251x.2022070071

矿用带式输送机托辊音频故障诊断方法

doi: 10.13272/j.issn.1671-251x.2022070071

吴文臻^{1, 2, 3,},
程继明^{1, 2, 3},
李标^{1, 2, 3}

1.
煤炭科学技术研究院有限公司, 北京　100013
2.
煤矿应急避险技术装备工程研究中心, 北京　100013
3.
北京市煤矿安全工程技术研究中心, 北京　100013

基金项目: 煤炭科学技术研究院有限公司科技发展基金项目（2021CX-I-10）。

详细信息

作者简介:
吴文臻（1983—），男，福建平潭人，副研究员，硕士，主要从事矿山智能化及自动化方面的研究工作，E-mail：wuwenzhen@ccrise.cn

中图分类号: TD634
计量
- 文章访问数: 350
- HTML全文浏览量: 58
- PDF下载量: 45
- 被引次数: 0
出版历程
- 收稿日期: 2022-07-26
- 修回日期: 2022-09-08
- 网络出版日期: 2022-09-01

Audio fault diagnosis method of mine belt conveyor roller

WU Wenzhen^{1, 2, 3
,},
CHENG Jiming^{1, 2, 3},
LI Biao^{1, 2, 3}

1.
China Coal Research Institute Co., Ltd., Beijing 100013, China
2.
Engineering Research Center for Technology Equipment of Emergency Refuge in Coal Mine, Beijing 100013, China
3.
Beijing Coal Mine Safety Engineering Technology Research Center, Beijing 100013, China

摘要

摘要: 现有矿用带式输送机托辊故障诊断方法一般是对托辊信号进行分解并转换至频域，从频域提取特征进行故障诊断，而常用的信号小波分解和经验模态分解方法存在小波基选择困难、易出现频谱混叠和端点效应的问题，导致故障诊断准确率较低。针对上述问题，提出了一种基于变分模态分解（VMD）−BP神经网络的矿用带式输送机托辊音频故障诊断方法。首先通过音频传感器采集矿用带式输送机沿线托辊的音频信号，并对音频信号进行预处理，以抑制音频信息中的噪声信号；然后采用VMD将音频信号按照中心频率分解成不同的IMF（本征模态函数）分量，提取各个IMF分量的峭度、重心频率、频率标准差等特征值；最后将特征值输入到已经训练好的BP神经网络，根据IMF分量特征值的差异，可以实现通过音频对矿用带式输送机托辊故障进行诊断，并可根据音频信号对应的传感器编号确定出故障托辊位置。以某煤矿实际采集的带式输送机托辊音频信息对基于VMD−BP神经网络的矿用带式输送机托辊音频故障诊断方法进行分析验证，结果表明：该方法在分解、提取音频信号特征时，可以避免分解过程中的频谱混叠与端点效应，总体故障诊断准确率达到96.15%，与采用BP神经网络的故障诊断方法和基于小波分解与BP神经网络的故障诊断方法相比分别提高了26.92%，15.38%，同时误检率也明显降低。
- 矿用带式输送机 /
- 托辊 /
- 故障诊断 /
- 故障定位 /
- 音频传感器 /
- 峭度 /
- 重心频率 /
- 频率标准差
Abstract: In the existing fault diagnosis method of mine belt conveyor roller, the roller signal is decomposed and converted to the frequency domain. The fault diagnosis is carried out by extracting characteristics from the frequency domain. The common signal decomposition methods include wavelet decomposition and empirical mode decomposition. The methods have the problems of difficult selection of wavelet basis, frequency spectrum aliasing and endpoint effect, resulting in low fault diagnosis accuracy rate. In view of the above problems, an audio fault diagnosis method of mine belt conveyor roller mine based on variational modal decomposition (VMD)-BP neural network is proposed. Firstly, the audio signal of the roller along the mine belt conveyor is collected by the audio sensor. The audio signal is preprocessed to suppress the noise signal in the audio information. Secondly, VMD is used to decompose the audio signal into different IMF (intrinsic mode function) components according to the center frequency. The method extracts characteristic values of the kurtosis, gravity frequency, frequency standard deviation of each IMF component. Finally, the characteristic values are input into the trained BP neural network. According to the difference in IMF component characteristic values, it is possible to diagnose the mine belt conveyor roller fault through audio, and determine the position of the faulty roller according to the sensor number corresponding to the audio signal. The audio information of the roller of the belt conveyor collected in a coal mine is used to analyze and verify the audio fault diagnosis method of mine belt conveyor roller based on VMD-BP neural network. The results show that the method can avoid spectrum aliasing and endpoint effect in the decomposition process when decomposing and extracting audio signal characteristics. The overall fault diagnosis accuracy rate reaches 96.15%. Compared with the fault diagnosis method based on BP neural network and the fault diagnosis method based on wavelet decomposition and BP neural network, the proposed method has improved the fault diagnosis accuracy rate by 26.92% and 15.38% respectively. The false detection rate has also been significantly reduced.
- mine belt conveyor /
- roller /
- fault diagnosis /
- fault position /
- audio sensor /
- kurtosis /
- gravity frequency /
- frequency standard deviation

HTML全文

图 1 基于VMD−BP神经网络的矿用带式输送机托辊音频故障诊断流程

Figure 1. Flow of audio fault diagnosis of mine belt conveyor roller based on VMD-BP neural network

下载: 全尺寸图片幻灯片

图 2 音频传感器布置

Figure 2. Audio sensor layout

下载: 全尺寸图片幻灯片

图 3 托辊正常状态下音频信号分解结果

Figure 3. Decomposition results of audio signal of roller in normal state

下载: 全尺寸图片幻灯片

图 4 托辊故障状态下音频信号分解结果

Figure 4. Decomposition results of audio signal of roller in fault state

下载: 全尺寸图片幻灯片

图 5 托辊正常状态功率谱

Figure 5. Power spectrum of roller in normal state

下载: 全尺寸图片幻灯片

图 6 托辊故障状态功率谱

Figure 6. Power spectrum of roller in fault state

下载: 全尺寸图片幻灯片

表 1 IMF特征项数据

Table 1. IMF characteristic item data

故障类型	IMF1			IMF2			IMF3			IMF4
故障类型	S₁	C₁/Hz	F₁/Hz	S₂	C₂/Hz	F₂/Hz	S₃	C₃/Hz	F₃/Hz	S₄	C₄/Hz	F₄/Hz
正常托辊	3.08	229.77	225.36	2.53	664.73	158.31	2.62	1357.87	376.96	2.92	1663.87	373.40
轴承故障	2.66	246.51	318.78	2.82	877.43	436.2	2.50	1636.03	411.08	3.501	3588.75	807.46
托辊断裂	5.84	189.45	286.54	3.34	597.36	389.52	3.12	1565.25	447.52	4.53	2687.86	678.69
润滑不良	3.51	354.16	427.24	3.05	975.49	648.25	2.88	1863.82	543.92	4.25	3836.29	924.25
托辊堵转	2.89	316.28	256.24	2.64	680.59	281.42	2.78	1728.46	483.71	4.28	4095.62	728.58

下载: 导出CSV

表 2 基于VMD−BP神经网络的故障诊断方法的故障诊断结果

Table 2. Fault diagnosis results of fault diagnosis method based on VMD-BP neural network

故障	故障出现次数	故障检出次数	误检次数	准确率/%
托辊断裂	0	0	0	0
托辊堵转	3	2	0	66.67
润滑不良	35	34	1	97.14
轴承故障	14	14	1	100.00
合计	52	50	2	96.15

下载: 导出CSV

表 3 基于BP神经网络的故障诊断方法的故障诊断结果

Table 3. Fault diagnosis results of fault diagnosis method based on BP neural network

故障	故障出现次数	故障检出次数	误检次数	准确率/%
托辊断裂	0	0	0	0
托辊堵转	3	0	1	0
润滑不良	35	26	3	74.29
轴承故障	14	10	1	71.43
合计	52	36	5	69.23

下载: 导出CSV

表 4 基于小波分解与BP神经网络的故障诊断方法的故障诊断结果

Table 4. Fault diagnosis results of fault diagnosis method based on wavelet decomposition and BP neural network

故障	故障出现次数	故障检出次数	误检次数	准确率/%
托辊断裂	0	0	0	0
托辊堵转	3	2	1	66.67
润滑不良	35	28	2	80.00
轴承故障	14	12	2	85.71
合计	52	42	5	80.77

下载: 导出CSV

参考文献(15)

[1]	王建勋. 煤矿输送带传输故障实时监测技术[J]. 工矿自动化,2015,41(1):45-48. doi: 10.13272/j.issn.1671-251x.2015.01.012 WANG Jianxun. Real-time fault monitoring technology for coal mine conveying belt[J]. Industry and Mine Automation,2015,41(1):45-48. doi: 10.13272/j.issn.1671-251x.2015.01.012
[2]	张丽. 带式输送机滚筒温度检测装置设计[J]. 工矿自动化,2017,43(7):86-89. doi: 10.13272/j.issn.1671-251x.2017.07.018 ZHANG Li. Design of temperature detection device for drum of belt conveyor[J]. Industry and Mine Automation,2017,43(7):86-89. doi: 10.13272/j.issn.1671-251x.2017.07.018
[3]	杨祥,田慕琴,李璐,等. 矿用带式输送机驱动滚筒轴承振动信号降噪方法[J]. 工矿自动化,2019,45(3):66-70. doi: 10.13272/j.issn.1671-251x.2018080013 YANG Xiang,TIAN Muqin,LI Lu,et al. Vibration signal denoising method for drive roller bearing of mine-used belt conveyor[J]. Industry and Mine Automation,2019,45(3):66-70. doi: 10.13272/j.issn.1671-251x.2018080013
[4]	孙国栋,王俊豪,徐昀,等. CEEMD−WVD 多尺度时频图像的滚动轴承故障诊断[J]. 机械科学与技术,2020,39(5):688-694. SUN Guodong,WANG Junhao,XU Yun,et al. Rolling bearing fault diagnosis based on CEEMD-WVD multi-scale time-frequency image[J]. Mechanical Science and Technology for Aerospace Engineering,2020,39(5):688-694.
[5]	彭程程. 基于二阶瞬态提取变换的滚动轴承故障特征提取方法研究[J]. 机电工程,2021,38(10):1246-1252. doi: 10.3969/j.issn.1001-4551.2021.10.004 PENG Chengcheng. Fault feature extraction method for rolling bearing based on STET[J]. Journal of Mechanical & Electrical Engineering,2021,38(10):1246-1252. doi: 10.3969/j.issn.1001-4551.2021.10.004
[6]	韩涛,胡英贝,张蕾,等. 信息融合技术在托辊轴承故障诊断中的应用[J]. 轴承,2012(6):57-59. doi: 10.19533/j.issn1000-3762.2012.06.019 HAN Tao,HU Yingbei,ZHANG Lei,et al. Application of information fusion technology in fault diagnosis of roller bearings[J]. Bearing,2012(6):57-59. doi: 10.19533/j.issn1000-3762.2012.06.019
[7]	SONG Liuyang,WANG Huaqing,CHEN Peng. Vibration-based intelligent fault diagnosis for roller bearings in low-speed rotating machinery[J]. IEEE Transactions on Instrumentation and Measurement,2018,67(8):1887-1899. doi: 10.1109/TIM.2018.2806984
[8]	JIANG Xiaopeng, CAO Guangqing. Belt conveyor roller fault audio detection based on the wavelet neural network[EB/OL]. [2022-05-16]. https://ieeexplore. ieee.org/document/73781202015.
[9]	曹贯强. 带式输送机托辊故障检测方法[J]. 工矿自动化,2020,46(6):81-86. doi: 10.13272/j.issn.1671-251x.2018100035 CAO Guanqiang. Fault detection method for belt conveyor roller[J]. Industry and Mine Automation,2020,46(6):81-86. doi: 10.13272/j.issn.1671-251x.2018100035
[10]	陈维望,李军霞,张伟. 基于分支卷积神经网络的托辊轴承故障分级诊断研究[J]. 机电工程,2022,39(5):596-603. doi: 10.3969/j.issn.1001-4551.2022.05.004 CHEN Weiwang,LI Junxia,ZHANG Wei. Hierarchical fault diagnosis of idler bearing based on branch convolutional neural network[J]. Journal of Mechanical & Electrical Engineering,2022,39(5):596-603. doi: 10.3969/j.issn.1001-4551.2022.05.004
[11]	YU Dejie,CHENG Junsheng,YANG Yu. Application of EMD method and Hilbert spectrum to the fault diagnosis of roller bearings[J]. Mechanical Systems and Signal Processing,2005,19(2):259-270. doi: 10.1016/S0888-3270(03)00099-2
[12]	蒋留兵,韦洪浪,管四海,等. 基于EEMD和HOC 的超宽带雷达生命探测算法研究[J]. 现代雷达,2015,37(5):25-30. JIANG Liubing,WEI Honglang,GUAN Sihai,et al. A study on UWB vital signal detection method based on EEMD and HOC[J]. Modern Radar,2015,37(5):25-30.
[13]	LEI Yaguo,HE Zhengjia,ZI Yanyang. EEMD method and WNN for fault diagnosis of locomotive roller bearings[J]. Expert Systems with Applications,2011,38(6):7334-7341. doi: 10.1016/j.eswa.2010.12.095
[14]	DRAGOMIRETSKIY K,ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing,2013,62(3):531-544.
[15]	凌标灿,杨佳滨. 电机滚动轴承故障诊断中BP与RBF神经网络的比较[J]. 华北科技学院学报,2018,15(6):53-57. doi: 10.3969/j.issn.1672-7169.2018.06.010 LING Biaocan,YANG Jiabin. Comparison of BP and RBF neural networks in fault diagnosis of motor rolling bearings[J]. Journal of North China Institute of Science and Technology,2018,15(6):53-57. doi: 10.3969/j.issn.1672-7169.2018.06.010