Diagnosis method for planetary gear faults in shearer under strong noise interference
-
摘要: 采煤机摇臂截割部行星齿轮的健康状态直接影响截割效率。针对采煤机截割煤岩过程中受多重冲击引起的强噪声干扰、齿轮结构复杂且传递路径多变导致故障特征难以提取等特点，提出了一种基于频谱平均降噪和相关谱的采煤机行星齿轮故障诊断方法。根据信号频谱分布特征及噪声随机特性，采用频谱平均降噪方法抑制噪声对信号频谱的干扰，获得信号降噪频谱。构建相关谱以建立少样本降噪频谱和多样本降噪频谱的内在联系，减少频谱平均降噪对样本数量的需求。采用一维卷积神经网络（1D CNN）建立相关谱与故障类别之间的精确映射关系，以相关谱为输入、故障类别为输出，实现行星齿轮故障分类识别。在DDS传动系统故障诊断实验台对基于频谱平均降噪和相关谱的采煤机行星齿轮故障诊断方法进行实验验证，结果表明该方法能够增强表征故障特征的关键频率，对正常、断齿、磨损、缺齿和裂纹5种行星齿轮健康状态信号的整体识别率达96%，在信噪比不低于15 dB时可有效、准确地实现齿轮故障诊断。Abstract: The health status of the planetary gears in the cutting section of shearer's rocker arm directly affects the cutting efficiency. The strong noise interference caused by multiple impacts during the cutting of coal and rock by the shearer, the complex gear structure, and the variable transmission path make it difficult to extract fault features. In order to solve the above problems, a fault diagnosis method for planetary gears in shearer based on spectral average denoising and correlation spectrum is proposed. Based on the distribution features of signal spectrum and the random features of noise, the spectrum average denoising method is adopted to suppress the interference of noise on the signal spectrum and obtain the signal denoising spectrum. The method constructs relevant spectra to establish the intrinsic relationship between few sample denoising spectra and multi sample denoising spectra, and reduce the demand for sample size for average spectrum denoising. The method uses a one-dimensional convolutional neural network (1D CNN) to establish an accurate mapping relationship between correlation spectra and fault categories, with correlation spectra as input and fault categories as output, to achieve planetary gear fault classification and recognition. The experimental verification of the fault diagnosis method for planetary gears in shearer based on spectral average denoising and correlation spectrum is carried out on the drivetrain diagnostics simulator transmission system fault diagnosis experimental platform. The results show that the method can enhance the key frequency that characterizes the fault features. The overall recognition rate for five types of health status signals of planetary gears, including normal, broken teeth, wear, missing teeth, and cracks, reaches 96%. Gear fault diagnosis can be effectively and accurately achieved when the signal-to-noise ratio is not less than 15 dB.
-
-
![]()
图 1 1D CNN结构
Figure 1. Structure of one-dimensional convolutional neural network (1D CNN)
![]()
图 2 采煤机截割部行星齿轮故障诊断流程
Figure 2. Fault diagnosis flow of planetary gear in cutting section of shearer
![]()
图 3 DDS传动系统故障诊断实验台
Figure 3. Experimental platform for fault diagnosis of drivetrain diagnostics simulator (DDS) transmission system
![]()
图 4 太阳轮5种健康状态信号样本实例
Figure 4. Signal samples examples of five types of sun gear health states
![]()
图 5 不同信噪比下的断齿故障信号
Figure 5. Fault signals of broken tooth under different signal-to-noise ratio
![]()
图 6 断齿信号频谱平均降噪结果
Figure 6. Average denoising results of frequency spectrum of broken tooth signals
![]()
图 7 不同叠加样本数量下齿轮健康状态信号降噪效果
Figure 7. Denosing effect of gear health state signals under different superposed samples number
![]()
图 8 测试信号与频谱参照样本集的相关谱及其可视化显示
Figure 8. Correlation spectrum of test signals and frequency spectrum reference sample sets and its visual display
![]()
图 9 信噪比为15 dB时1D CNN训练过程和识别结果
Figure 9. 1D CNN training process and fault recognition results when signal-to-noise ratio is 15 dB
![]()
图 10 不同信噪比和叠加样本数量下齿轮故障诊断结果
Figure 10. Fault diagnosis results of gear under different signal-to-noise ratio and superposed sample number
表 1 降噪信号的频谱峰均差
Table 1 Difference of frequency spectrum peak value and its average value of the denosing signal
叠加样本数量/个 频谱峰值/g 频谱平均值/g 频谱峰均差/g 1 0.006 48 0.002 13 0.004 35 2 0.006 94 0.002 30 0.004 64 3 0.009 25 0.003 04 0.006 21 4 0.013 34 0.004 41 0.008 93 5 0.015 60 0.005 64 0.009 96 6 0.019 15 0.006 68 0.012 47 7 0.021 87 0.007 33 0.014 54 8 0.026 13 0.008 44 0.017 69 
下载: 导出CSV
-
[1] 焦玉冰,李杰,马喜宏,等. 一种采煤机截割部滚动轴承故障诊断方法[J]. 计算机测量与控制,2023,31(5):73-79. JIAO Yubing,LI Jie,MA Xihong,et al. A fault diagnosis method for rolling bearing of shearer cutting section[J]. Computer Measurement & Control,2023,31(5):73-79.
[2] 毛清华,张勇强,赵晓勇,等. 变速工况下采煤机行星齿轮传动系统故障诊断[J]. 工矿自动化,2021,47(7):8-13. MAO Qinghua,ZHANG Yongqiang,ZHAO Xiaoyong,et al. Fault diagnosis method of shearer planetary gear transmission system under variable speed conditions[J]. Industry and Mine Automation,2021,47(7):8-13.
[3] 史志远,滕虎,马驰. 基于多信息融合和卷积神经网络的行星齿轮箱故障诊断[J]. 工矿自动化,2022,48(9):56-62. SHI Zhiyuan,TENG Hu,MA Chi. Fault diagnosis of planetary gearbox based on multi-information fusion and convolutional neural network[J]. Journal of Mine Automation,2022,48(9):56-62.
[4] PAN Yubin,WANG Hua,CHEN Jie,et al. Fault recognition of large-size low-speed slewing bearing based on improved deep belief network[J]. Journal Vibration and Control,2023,29(11/12):2829-2841.
[5] 李华,刘韬,伍星,等. 相关奇异值比的SVD在轴承故障诊断中的应用[J]. 机械工程学报,2021,57(21):138-149. DOI: 10.3901/JME.2021.21.138 LI Hua,LIU Tao,WU Xing,et al. Application of SVD based on correlated singular value ratio in bearing fault diagnosis[J]. Journal of Mechanical Engineering,2021,57(21):138-149. DOI: 10.3901/JME.2021.21.138
[6] 刘湘楠,赵学智,上官文斌. 强背景噪声振动信号中滚动轴承故障冲击特征提取[J]. 振动工程学报,2021,34(1):202-210. LIU Xiangnan,ZHAO Xuezhi,SHANGGUAN Wenbin. The impact features extraction of rolling bearing under strong background noise[J]. Journal of Vibration Engineering,2021,34(1):202-210.
[7] CHENG Jian,YANG Yu,LI Xin,et al. An early fault diagnosis method of gear based on improved symplectic geometry mode decomposition[J]. Measurement,2020,151. DOI: 10.1016/j.measurement.2019.107140.
[8] NIAKI S T,ALAVI H,OHADI A. Incipient fault detection of helical gearbox based on variational mode decomposition and time synchronous averaging[J]. Structural Health Monitoring,2023,22(2):1494-1512.
[9] 崔玲丽,刘银行,王鑫. 基于改进奇异值分解的滚动轴承微弱故障特征提取方法[J]. 机械工程学报,2022,58(17):156-169. DOI: 10.3901/JME.2022.17.156 CUI Lingli,LIU Yinhang,WANG Xin. Feature extraction of weak fault for rolling bearing based on improved singular value decomposition[J]. Journal of Mechanical Engineering,2022,58(17):156-169. DOI: 10.3901/JME.2022.17.156
[10] 刘宝华,张穆勇,臧延旭,等. 基于AIF和TT的滚动轴承复合故障诊断[J]. 振动. 测试与诊断,2022,42(6):1206-1211,1249. LIU Baohua,ZHANG Muyong,ZANG Yanxu,et al. Compound fault diagnosis of rolling bearings based on AIF and improved time-time transform[J]. Journal of Vibration,Measurement & Diagnosis,2022,42(6):1206-1211,1249.
[11] 吕琛,宋希庚,邹积斌. 基于DSP的振动信号阶比与时域同步平均分析[J]. 振动与冲击,2002,21(2):53-57. DOI: 10.3969/j.issn.1000-3835.2002.02.015 LYU Chen,SONG Xigeng,ZOU Jibin. DSP-based order domain and time domain synchronous averaging analysis of vibration signal[J]. Journal of Vibration and Shock,2002,21(2):53-57. DOI: 10.3969/j.issn.1000-3835.2002.02.015
[12] 郭远晶,金晓航,魏燕定,等. 改进TSA降噪与平方包络谱分析的故障特征提取[J]. 振动工程学报,2021,34(2):402-410. GUO Yuanjing,JIN Xiaohang,WEI Yanding,et al. Fault feature extraction based on improved TSA denoising and squared envelope spectrum[J]. Journal of Vibration Engineering,2021,34(2):402-410.
[13] 杜文辽,高军杰,杨凌凯,等. 多尺度加权CEEMD−1DCNN旋转机械故障诊断[J]. 机床与液压,2023,51(17):202-208. DOI: 10.3969/j.issn.1001-3881.2023.17.033 DU Wenliao,GAO Junjie,YANG Lingkai,et al. Multi-scale weighted CEEMD-1DCNN rotating machinery fault diagnosis[J]. Machine Tool & Hydraulics,2023,51(17):202-208. DOI: 10.3969/j.issn.1001-3881.2023.17.033
[14] 候双珊,郑近德,潘海洋,等. 基于复合多尺度交叉模糊熵的行星齿轮箱故障诊断[J]. 振动与冲击,2023,42(20):130-135,171. HOU Shuangshan,ZHENG Jinde,PAN Haiyang,et al. Planetary gearbox fault diagnosis based on composite multi-scale cross fuzzy entropy[J]. Journal of Vibration and Shock,2023,42(20):130-135,171.
[15] ZHAN Shanning,SHAO Ruipeng,MEN Chengjie,et al. Fault diagnosis method for planetary gearbox based on intrinsic feature extraction and attention mechanism[J]. Measurement Science and Technology,2024,35(3). DOI: 10.1088/1361-6501/AD147B.
[16] 崔石玉,朱志宇. 基于参数迁移和一维卷积神经网络的海水泵故障诊断[J]. 振动与冲击,2021,40(24):180-189. CUI Shiyu,ZHU Zhiyu. Seawater pump fault diagnosis based on parameter transfer and one-dimensional convolutional neural network[J]. Journal of Vibration and Shock,2021,40(24):180-189.
[17] GUO Runxia,LI Haonan,HUANG Chao. Operation stage division and RUL prediction of bearings based on 1DCNN-ON-LSTM[J]. Measurement Science and Technology,2024,35(2). DOI: 10.1088/1361-6501/AD0E3A.
[18] 张搏文,庞新宇,关重阳. 基于DPD−1DCNN的行星齿轮箱故障诊断方法研究[J]. 机械传动,2023,47(3):113-119. ZHANG Bowen,PANG Xinyu,GUAN Chongyang. Research on fault diagnosis method of planetary gearboxes based on DPD-1DCNN[J]. Journal of Mechanical Transmission,2023,47(3):113-119.
[19] GAO Shuzhi,LI Tianchi,ZHANG Yimin,et al. Fault diagnosis method of rolling bearings based on adaptive modified CEEMD and 1DCNN model[J]. ISA Transactions,2023,140:309-330. DOI: 10.1016/j.isatra.2023.05.014
[20] JIANG Jun,LI Wei,WEN Zhe,et al. Series arc fault detection based on random forest and deep neural network[J]. IEEE Sensors Journal,2021,21(15):17171-17179. DOI: 10.1109/JSEN.2021.3082294
[21] 陈曦晖. 强噪声干扰下行星轮系振动信号分析及其故障诊断技术研究[D]. 徐州:中国矿业大学,2017. CHEN Xihui. Research of vibration signal analysis and fault diagnosis technology of planetary gear in strong noise interference[D]. Xuzhou:China University of Mining and Technology,2017.
-
期刊类型引用(14)
1. 赵磊. 切顶卸压沿空留巷无煤柱开采技术实践. 陕西煤炭. 2024(08): 57-61 . 
百度学术
2. 刘浡. 金辛达煤矿沿空留巷切顶卸压技术. 山西焦煤科技. 2023(04): 42-44+48 . 百度学术
3. 刘毅. 浅部复杂地质条件下切顶卸压无煤柱自成巷技术及应用. 当代化工研究. 2023(16): 120-122 . 百度学术
4. 王艳龙，牛冠宇，高成章，薛勤. 高瓦斯矿井沿空留巷瓦斯治理技术研究与应用. 煤炭与化工. 2023(07): 107-109+114 . 百度学术
5. 冀星忠. 无煤柱110工法切缝孔深度及角度对留巷压力的影响. 能源与节能. 2022(09): 185-188 . 百度学术
6. 于创，王飞，贺志宏，刘振明，焦治平，申龙. 增韧剂改性矿用酚尿醛泡沫的实验研究. 中国矿业. 2021(02): 133-138 . 百度学术
7. 葛晓伟. 厚煤层无煤柱自成巷110工法技术的应用实践. 能源与节能. 2021(03): 178-179 . 百度学术
8. 刘诗杰. 煤矿无煤柱高效精准锯式切顶技术研究. 西部探矿工程. 2021(06): 171-172 . 百度学术
9. 吕人杰，张科学，亢磊，杨海江，王晓玲，朱俊傲. 黄家沟煤矿切顶卸压沿空留巷技术研究与应用. 中国煤炭. 2021(08): 41-47 . 百度学术
10. 杜艳奎. 慈林山煤矿15102沿空留巷工作面综合防灭火技术研究. 煤矿现代化. 2021(06): 64-66 . 百度学术
11. 申斌学，周宏范，朱磊，吴玉意，秋丰岐，王国普，郭林，黄剑斌. 深井复合顶板切顶卸压柔模墙支护沿空留巷技术. 工矿自动化. 2021(11): 101-106 . 本站查看
12. 王正达. 工作面沿空留巷切顶卸压关键参数及主要设备选型. 机械管理开发. 2021(12): 85-86+89 . 百度学术
13. 袁存发. 无煤柱综采工作面沿空留巷支护技术应用. 现代矿业. 2020(05): 33-36 . 百度学术
14. 董志勇. 煤矿井下水力压裂切顶卸压护巷技术应用研究. 工矿自动化. 2019(10): 99-103 . 本站查看
其他类型引用(3)
计量
- 文章访问数: 473
- HTML全文浏览量: 33
- PDF下载量: 30
- 被引次数: 17
