基于多特征融合与RF的球磨机滚动轴承故障诊断

王进花; 周德义; 曹洁; 李亚洁

doi:10.13700/j.bh.1001-5965.2022.0069

基于多特征融合与RF的球磨机滚动轴承故障诊断

doi: 10.13700/j.bh.1001-5965.2022.0069

王进花^1, ,,
周德义¹,
曹洁^{1, 2},
李亚洁¹

1.
兰州理工大学电气工程与信息工程学院，兰州 730050
2.
甘肃省制造信息工程研究中心，兰州 730050

基金项目: 国家重点研发计划(2020YFB1713600)；国家自然科学基金(62063020)；甘肃省自然科学基金(20JR5RA463)

详细信息

通讯作者:
E-mail：wjh0615@lut.edu.cn

中图分类号: TB277；TH133.33
计量
- 文章访问数: 198
- HTML全文浏览量: 79
- PDF下载量: 19
- 被引次数: 0
出版历程
- 收稿日期: 2022-02-14
- 录用日期: 2022-06-25
- 网络出版日期: 2022-09-16
- 整期出版日期: 2023-12-29

Fault diagnosis of ball mill rolling bearing based on multi-feature fusion and RF

WANG Jinhua^{1
, ,},
ZHOU Deyi¹,
CAO Jie^{1, 2},
LI Yajie¹

1.
College of Electrical and Information Engineering，Lanzhou University of Technology，Lanzhou 730050，China
2.
Gansu Manufacturing Information Engineering Research Center，Lanzhou 730050，China

Funds: National Key R & D Program of China (2020YFB1713600); National Natural Science Foundation of China (62063020); Natural Science Foundation of Gansu Province (20JR5RA463)

More Information

Corresponding author: E-mail：wjh0615@lut.edu.cn

摘要

摘要:
由于冶金工业工况复杂，很难从单一信号中获取高质量的故障特征，诊断效果不佳。针对直接使用电流和振动信号进行融合，不能体现2类信号在不同频段上的优势和彼此之间的互补信息，而影响诊断性能的问题，提出一种基于振动和电流信号的多特征互补融合故障诊断方法。将振动信号和电流信号的高频系数特征通过最大绝对值规则融合，形成体现高频段特征的互补特征；将振动信号和电流信号的低频系数特征通过稀疏表示（SR ）融合，形成体现低频段特征的互补特征。通过定义由多特征组成的特征矩阵融合全频段特征，增强全局特征表征能力。采用递归特征消除法消除融合后的冗余特征，提高分类精度，结合随机森林（ RF ）对轴承故障状态进行分类。实验结果表明：所提方法相比基于振动信号和基于电流信号的诊断结果更加准确。
- 特征融合 /
- 故障诊断 /
- 球磨机 /
- 特征提取 /
- 随机森林
Abstract:
The diagnosis effect is unsatisfactory because it is challenging to extract high-quality fault characteristics from a single signal given the complicated working conditions of the metallurgical industry. Aiming at the problem of directly using current and vibration signals for fusion, which cannot reflect the advantages of the two types of signals in different frequency bands and the complementary information between each other, but affects the diagnostic performance, this paper proposes a multi-feature complementary fusion fault diagnosis method based on vibration and current signals. First, the high-frequency coefficient features of the vibration signal and the current signal are fused through the maximum absolute value rule to form complementary features that reflect the high-frequency characteristics. The low-frequency coefficient features of the vibration signal and the current signal are fused through sparse representation (SR) to form complementary features that reflect the low-frequency features. By defining a feature matrix composed of multiple features to fuse full frequency band features, the global feature characterization capability is enhanced. After feature fusion, redundant features are removed to increase classification accuracy and categorize the bearing defect state using a combination of random forest (RF) and recursive feature elimination. Experimental results show that this method is more accurate than the diagnosis results based on vibration signals and current signals.
- feature fusion /
- fault diagnosis /
- ball mill /
- feature extraction /
- random forest

HTML全文

图 1 DWT-SR融合框架

Figure 1. DWT-SR fusion framework

下载: 全尺寸图片幻灯片

图 2 基于RF的球磨机滚动轴承故障诊断流程

Figure 2. Flowchart of fault diagnosis of ball mill rolling bearing based on RF

下载: 全尺寸图片幻灯片

图 3 球磨机实物图

Figure 3. Physical drawing of ball mill

下载: 全尺寸图片幻灯片

图 4 球磨机结构

Figure 4. Ball mill structure

下载: 全尺寸图片幻灯片

图 5 信号的时域图和频域图

Figure 5. Time domain and frequency domain diagrams of signals

下载: 全尺寸图片幻灯片

图 6 实测数据集上的故障分类混淆矩阵

Figure 6. Failure classification confusion matrix on real datasets

下载: 全尺寸图片幻灯片

图 7 轴承状态图

Figure 7. Bearing status diagram

下载: 全尺寸图片幻灯片

图 8 公共数据集上的故障分类混淆矩阵

Figure 8. Failure classification confusion matrix on public datasets

下载: 全尺寸图片幻灯片

表 1 实测数据集上不同方法分类准确率对比

Table 1. Comparison of classification accuracy of various methods on real datasets

方法	信号类型	平均准确率/%	平均F₁分数/%
KNN	振动	66.18	66.18
	电流	56.37	59.37
DT	振动	89.71	89.65
	电流	83.08	83.08
RF	振动	93.38	94.38
	电流	89.46	89.44
本文方法	振动 +电流	99.02	99.02

下载: 导出CSV

表 2 实验数据的轴承代号

Table 2. Bearing code used for experimental data

故障类别	轴承代号	标签
正常（HBD）	K001, K002, K003, K004, K005, K006	0
外圈故障（OR）	KA04, KA15, KA16, KA22, KA30	1
内圈故障（IR）	KI04, KI14, KI16, KI17, KI18,KI21	2

下载: 导出CSV

表 3 公共数据集上不同方法分类准确率对比

Table 3. Comparison of classification accuracy of various methods on public datasets

方法	信号类型	平均准确率/%	平均F₁分数/%
CS1+CNN^[29]	电流	90.93
CS2+CNN^[29]	电流	86.53
CS1+SVM	电流	68.87	68.87
CS1+KNN	电流	49.75	49.75
CS1+DT	电流	88.48	88.48
CS1+RF	电流	93.38	92.98
BT^[30]	振动	83.3
SVM-PSO^[30]	振动	75.8
KNN^[30]	振动	62.5
RF^[30]	振动	98.3
SVM	振动	96.32	95.31
KNN	振动	96.32	96.32
DT	振动	95.34	95.34
RF	振动	98.77	98.77
本文方法	振动 +电流	99.71	99.71

下载: 导出CSV

参考文献(30)

[1]	蔡改贫, 刘鑫, 罗小燕, 等. 基于多尺度模糊熵和改进极限学习机的球磨机负荷状态识别[J]. 吉林大学学报(工学版), 2020, 50(6): 2055-2067. doi: 10.13229/j.cnki.jdxbgxb20190716 CAI G P, LIU X, LUO X Y, et al. Load state recognition of ball mill based on multi-scale fuzzy entropy and improved extreme learning machine[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(6): 2055-2067(in Chinese). doi: 10.13229/j.cnki.jdxbgxb20190716
[2]	JIANG G, ZHAO J, JIA C, et al. Intelligent fault diagnosis of gearbox based on vibration and current signals: A multimodal deep learning approach[C]//Proceedings of the Prognostics and System Health Management Conference. Piscataway: IEEE Press, 2019: 1-6.
[3]	YAN R, GAO R X, CHEN X. Wavelets for fault diagnosis of rotary machines: A review with applications[J]. Signal Processing, 2014, 96: 1-15. doi: 10.1016/j.sigpro.2013.04.015
[4]	LEI Y, LIN J, HE Z, et al. A review on empirical mode decomposition in fault diagnosis of rotating machinery[J]. Mechanical Systems and Signal Processing, 2013, 35(1-2): 108-126. doi: 10.1016/j.ymssp.2012.09.015
[5]	JIANG G Q, PING X, XIAO W, et al. Intelligent fault diagnosis of rotary machinery based on unsupervised multiscale representation learning[J]. Chinese Journal of Mechanical Engineering, 2017, 30(6): 1-11.
[6]	SOUALHI A, MEDJAHER K, ZERHOUNI N. Bearing health monitoring based on Hilbert-Huang transform, support vector machine and regression[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64(1): 52-62. doi: 10.1109/TIM.2014.2330494
[7]	胡显能, 蔡改贫, 罗小燕, 等. 基于 CEEMDAN 和多尺度排列熵的球磨机负荷识别方法[J]. 噪声与振动控制, 2018, 38(3): 146-151. HU X N, CAI G P, LUO X Y, et al. Load identification method of ball mill based on CEEMDAN and multi-scale permutation entropy[J]. Noise and Vibration Control, 2018, 38(3): 146-151(in Chinese).
[8]	CHEN Z, LI W. Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(7): 1693-1702. doi: 10.1109/TIM.2017.2669947
[9]	LU D, GONG X, QIAO W. Current-based diagnosis for gear tooth breaks in wind turbine gearboxes[C]//Proceedings of the IEEE Energy Conversion Congress and Exposition. Piscataway: IEEE Press, 2012: 3780-3786.
[10]	SUN L L, ZHANG K K, LU X D. Stator inter-turn fault diagnosis of induction motor based on wavelet packet decomposition and random forest[C]//Proceedings of the Renewable Power Generation Conference. London: IET, 2019: 1-6.
[11]	WIDODO A, YANG B S, GU D S, et al. Intelligent fault diagnosis system of induction motor based on transient current signal[J]. Mechatronics, 2009, 19(5): 680-689. doi: 10.1016/j.mechatronics.2009.02.002
[12]	WANG J, FU P, ZHANG L, et al. Multilevel information fusion for induction motor fault diagnosis[J]. IEEE/ASME Transactions on Mechatronics, 2019, 24(5): 2139-2150. doi: 10.1109/TMECH.2019.2928967
[13]	XIA M, LI T, XU L, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks[J]. IEEE/ASME Transactions on Mechatronics, 2018, 23(1): 101-110.
[14]	HOU L, BERGMANN N W. Novel industrial wireless sensor networks for machine condition monitoring and fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(10): 2787-2798. doi: 10.1109/TIM.2012.2200817
[15]	LI C, SANCHEZ R V, ZURITA G, et al. Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals[J]. Mechanical Systems and Signal Processing, 2016, 76-77: 283-293.
[16]	MA M, SUN C, CHEN X. Deep coupling autoencoder for fault diagnosis with multimodal sensory data[J]. IEEE Transactions on Industrial Informatics, 2018, 14(3): 1137-1145. doi: 10.1109/TII.2018.2793246
[17]	JING L Y, WANG T Y, ZHAO M, et al. An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox[J]. Sensors (Switzerland), 2017, 17(2): 414.
[18]	WU J D, CHEN J C. Continuous wavelet transform technique for fault signal diagnosis of internal combustion engines[J]. NDT & E International, 2006, 39(4): 304-311.
[19]	LI Z, FENG Z, CHU F. A load identification method based on wavelet multi-resolution analysis[J]. Journal of Sound and Vibration, 2014, 333(2): 381-391. doi: 10.1016/j.jsv.2013.09.026
[20]	ERIŞTI H, UÇAR A, DEMIR Y. Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines[J]. Electric Power Systems Research, 2010, 80(7): 743-752. doi: 10.1016/j.jpgr.2009.09.021
[21]	BLODT M, GRANJON P, RAISON B, et al. Models for bearing damage detection in induction motors using stator current monitoring[J]. IEEE Transactions on Industrial Electronics, 2008, 55(4): 1813-1822. doi: 10.1109/TIE.2008.917108
[22]	MALLAT S G, ZHANG Z. Matching pursuits with time-frequency dictionaries[J]. IEEE Transactions on Signal Processing, 1993, 41(12): 3397-3415. doi: 10.1109/78.258082
[23]	TROPP J A, GILBERT A C. Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53(12): 4655-4666. doi: 10.1109/TIT.2007.909108
[24]	TROPP J A, GILBERT A C, STRAUSS M J. Algorithms for simultaneous sparse approximation. Part I: Greedy pursuit[J]. Signal Processing, 2006, 86(3): 572-588. doi: 10.1016/j.sigpro.2005.05.030
[25]	YANG B, LI S. Pixel-level image fusion with simultaneous orthogonal matching pursuit[J]. Information Fusion, 2012, 13(1): 10-19. doi: 10.1016/j.inffus.2010.04.001
[26]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324
[27]	WAN L, GONG K, ZHANG G, et al. An efficient rolling bearing fault diagnosis method based on spark and improved random forest algorithm[J]. IEEE Access, 2021, 9: 37866-37882. doi: 10.1109/ACCESS.2021.3063929
[28]	TOMA R N, KIM J M. Bearing fault classification of induction motors using discrete wavelet transform and ensemble machine learning algorithms[J]. Applied Sciences, 2020, 10(15): 5251. doi: 10.3390/app10155251
[29]	HOANG D T, KANG H J. A motor current signal-based bearing fault diagnosis using deep learning and information fusion[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(6): 3325-3333.
[30]	LESSMEIER C, KIMOTHO J K, ZIMMER D, et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: A benchmark data set for data-driven classification[C]//Proceedings of the European Conference of the Prognostics and Health Management Society.[S.l.]: PHM Society, 2016: 1-17.