基于改进相似模型的采煤机轴承剩余寿命预测方法

李晓昆; 耿毅德; 王宏伟; 付翔; 王然风

doi:10.13272/j.issn.1671-251x.18018

基于改进相似模型的采煤机轴承剩余寿命预测方法

doi: 10.13272/j.issn.1671-251x.18018

李晓昆^{1, 2,},
耿毅德^{2, 3},
王宏伟^{2, 4, 5},
付翔^{1, 2},
王然风^{1, 2, ,}

1.
太原理工大学矿业工程学院, 山西太原　030024
2.
太原理工大学山西省煤矿智能装备工程研究中心, 山西太原　030024
3.
山西焦煤集团有限责任公司博士后工作站, 山西太原　030024
4.
太原理工大学机械与运载工程学院, 山西太原　030024
5.
太原理工大学安全与应急管理工程学院, 山西晋中　030600

基金项目: 国家自然科学基金项目(52274157)；“科技兴蒙”行动重点专项项目(2022EEDSKJXM010)；山西省基础研究计划项目(202103021223123)；山西省重点研发计划项目(202102100401015)；山西省揭榜招标项目(20201101005)。

详细信息

作者简介:
李晓昆（1998—），男，河北承德人，硕士研究生，主要研究方向为煤矿设备故障诊断与预测性维护研究，E-mail：1615098598@qq.com

通讯作者:
王然风（1970—），男，山西长治人，副教授，博士，主要研究方向为智能化开采与分选，E-mail:wrf197010@126.com

中图分类号: TD67
计量
- 文章访问数: 181
- HTML全文浏览量: 30
- PDF下载量: 33
- 被引次数: 0
出版历程
- 收稿日期: 2022-11-22
- 修回日期: 2023-02-20
- 网络出版日期: 2023-05-09

A method for predicting the remaining useful life of shearer bearings based on improved similarity model

LI Xiaokun^{1, 2
,},
GENG Yide^{2, 3},
WANG Hongwei^{2, 4, 5},
FU Xiang^{1, 2},
WANG Ranfeng^{1, 2
, ,}

1.
College of Mining Engineering, Taiyuan University of Technology, Taiyuan 030024, China
2.
Center of Shanxi Engineering Research for Coal Mine Intelligent Equipment, Taiyuan University of Technology, Taiyuan 030024, China
3.
Postdoctoral Workstation, Shanxi Coking Coal Group Co., Ltd., Taiyuan 030024, China
4.
College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan 030024, China
5.
College of Safety and Emergency Management Engineering, Taiyuan University of Technology, Jinzhong 030600, China

摘要

摘要: 采煤机轴承退化过程并非简单的线性或指数关系，应分为不同阶段进行分析。而目前的采煤机轴承剩余使用寿命(RUL)预测方法未充分考虑该因素。针对该问题，提出了一种基于改进相似模型的采煤机轴承剩余寿命预测方法。采用通用的相似模型描述设备退化过程，在此基础上通过对均方根聚类分析，将轴承退化过程划分为平稳运行阶段、初始退化阶段和加速退化阶段，借助传统相似模型思路分段计算采煤机轴承的健康状态并拟合得到退化曲线样本库，通过对离线样本库数据和在线采煤机实时数据进行数据预处理和相似性分析，最终得到采煤机轴承RUL。实验结果表明：基于改进相似模型的采煤机轴承RUL预测方法的误差绝对值均值较卷积门控循环单元（ConvGRU）、空间卷积长短时记忆神经网络（ConvLSTM）、卷积神经网络（CNN）、自组织映射神经网络（SOM）、循环神经网络（RNN）、传统相似模型分别降低了30.49%，7.54%，16.98%，24.74%，17.96%，9.49%，可以较好地预测轴承RUL。现场试验结果表明：对采煤机轴承连续监测87 d，轴承健康状态从0.997逐渐下降到0.972，与现场采煤机轴承实际使用情况基本吻合，验证了该方法的有效性。
- 采煤机轴承 /
- 改进相似模型 /
- 剩余使用寿命 /
- 轴承退化曲线 /
- RUL预测
Abstract: The degradation process of shearer bearings is not a simple linear or exponential relationship. It should be analyzed in different stages. However, the current prediction method for the remaining useful life (RUL) of shearer bearings does not fully consider this factor. In order to solve this problem, a method for predicting the remaining useful life of shearer bearings based on an improved similarity model is proposed. The model uses a universal similarity model to describe the process of equipment degradation. Based on this, through root mean square clustering analysis, the bearing degradation process is divided into the stable operation stage, initial degradation stage, and accelerated degradation stage. With the help of traditional similarity model ideas, the health condition of shearer bearings is calculated by segment. And it is fitted to obtain a degradation curve sample library, Through data preprocessing and similarity analysis on offline sample library data and real-time data of online shearers, the bearing RUL of the shearer is ultimately obtained. The experimental results show that the mean absolute error values of the RUL prediction method for shearer bearings based on improved similarity model are reduced by 30.49%, 7.54%, 16.98%, 24.74%, 17.96% and 9.49% respectively, compared to the convolutional gated recurrent unit (ConvGRU), convolutional long short-term memory neural network (ConvLSTM), convolutional neural networks (CNN), self-organizing map (SOM), recurrent neural networks (RNN), and traditional similarity models. The proposed model can effectively predict bearing RUL. The on-site test results show that after continuous monitoring of the bearing of the shearer for 87 days, the health condition of the bearing is gradually reduced from 0.997 to 0.972. The result is basically consistent with the actual use of the bearing of the shearer on site. It verifies the effectiveness of this method.
- shearer bearing /
- improved similarity model /
- remaining useful life /
- bearing degradation curve /
- RUL prediction

HTML全文

图 1 采煤机轴承RUL预测框架

Figure 1. Remaining useful life prediction framework of shearer bearing

下载: 全尺寸图片幻灯片

图 2 基于改进相似模型的采煤机轴承RUL预测流程

Figure 2. Remaining useful life prediction process of shearer bearing based on improved similarity model

下载: 全尺寸图片幻灯片

图 3 基于改进相似模型的采煤机轴承RUL预测方法

Figure 3. Remaining useful life prediction method of shearer bearing based on improved similarity model

下载: 全尺寸图片幻灯片

图 4 HS划分结果

Figure 4. Health Stage division results

下载: 全尺寸图片幻灯片

图 5 退化曲线族

Figure 5. Degradation curve family

下载: 全尺寸图片幻灯片

图 6 井下传感器布置点位

Figure 6. Arrangement points of underground sensors

下载: 全尺寸图片幻灯片

图 7 采煤机轴承振动信号

Figure 7. Vibration signal of shearer bearing

下载: 全尺寸图片幻灯片

图 8 采煤机轴承振动信号频谱

Figure 8. Spectrum of vibration signal of shearer bearing

下载: 全尺寸图片幻灯片

图 9 采煤机轴承退化曲线

Figure 9. Degradation curve of shearer bearing

下载: 全尺寸图片幻灯片

表 1 IMS Center 的滚动轴承全生命周期数据集

Table 1. Rolling bearing life cycle data set from IMS Center

试验编号	测量方向	样本数量	样本长度	运行时间/d	试验描述
试验A	X/Y	8	2 155	34	3号轴承内圈故障
试验A	X/Y	8	2 155	34	4号轴承滚动体故障
试验B	X	4	984	8	1号轴承外圈故障
试验C	X	4	6 324	51	3号轴承外圈故障

下载: 导出CSV

表 2 可识别性系数归一化结果

Table 2. Normalization results of recognizability coefficient

健康指标	可识别性系数归一化	健康指标	可识别性系数归一化
峭度	0.694 3	峰值	0.450 7
脉冲指标	0.475 3	RMS	1
波形	0.853 2	最大值	0.632 6
裕度	0.417 9	最小值	0.189 8
歪度	0.147 4	平均值	0

下载: 导出CSV

表 3 不同预测方法对比

Table 3. Comparison of different prediction methods %

方法	不同测试集预测误差绝对值						误差绝对值均值
方法	轴承1−3	轴承1−4	轴承1−6	轴承1−7	轴承2−5	轴承2−6	误差绝对值均值
本文方法	22.28	19.57	16.43	13.67	21.23	17.39	18.43
ConvGRU	89.53	44.21	29.17	34.87	60.84	34.88	48.92
ConvLSTM	33.68	47.24	23.28	3.30	39.80	8.52	25.97
CNN−HI	48.52	53.57	19.39	16.27	56.13	18.65	35.41
SOM−HI	31.76	62.76	32.88	11.09	68.61	51.94	43.17
RNN−HI	43.28	67.55	21.33	17.83	54.37	13.95	36.39
相似模型方法	30.52	36.68	21.61	19.65	32.13	26.95	27.92

下载: 导出CSV

表 4 采煤机轴承HC与运行时间关系

Table 4. Relationship between health condition and operation time of shearer bearing

运行时间/d	1	22	44	66	87
采煤机轴承HC	0.997	0.992	0.984	0.979	0.972

下载: 导出CSV

参考文献(22)

[1]	王国法,刘峰,庞义辉,等. 煤矿智能化——煤炭工业高质量发展的核心技术支撑[J]. 煤炭学报,2019,44(2):349-355. WANG Guofa,LIU Feng,PANG Yihui,et al. Coal mine intellectualization:the core technology of high quality development[J]. Journal of China Coal Society,2019,44(2):349-355.
[2]	任怀伟. 我国煤矿综采装备技术的主要进展和发展趋势[J]. 煤矿开采,2014,19(6):11-16. REN Huaiwei. Major process and development tendency of full-mechanized mining equipments in China[J]. Coal Mining Technology,2014,19(6):11-16.
[3]	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.
[4]	丁华,刘恒强,杨琨,等. 基于云化QFD的采煤机服务型制造模型构建[J]. 煤炭学报,2019,44(2):618-627. DING Hua,LIU Hengqiang,YANG Kun,et al. Construction of SOM model of shearer based on QFD-ECM[J]. Journal of China Coal Society,2019,44(2):618-627.
[5]	JARDINE K S A,LIN Daming,BANJEVIC D. A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems & Signal Processing,2006,20(7):1483-1510.
[6]	KAN M S,TAN A C C,MATHEW J. A review on prognostic techniques for non-stationary and non-linear rotating systems[J]. Mechanical Systems and Signal Processing,2015,62/63:1-20. doi: 10.1016/j.ymssp.2015.02.016
[7]	ZHAO Zeqi,LIANG Bin,WANG Xueqian,et al. Remaining useful life prediction of aircraft engine based on degradation pattern learning[J]. Reliability Engineering and System Safety,2017,164:74-83. doi: 10.1016/j.ress.2017.02.007
[8]	DJEZIRI M A,BENMOUSSA S,SANCHEZ R. Hybrid method for remaining useful life prediction in wind turbine systems[J]. Renewable Energy,2017,116:173-187.
[9]	HU Jinqiu,ZHANG Laibin,MA Lin,et al. An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm[J]. Expert Systems with Applications,2011,38(3):1431-1446. doi: 10.1016/j.eswa.2010.07.050
[10]	YANG Lei,LEE J. Bayesian belief network-based approach for diagnostics and prognostics of semiconductor manufacturing system[J]. Robotics and Computer-Integrated Manufacturing,2012,28(1):66-74. doi: 10.1016/j.rcim.2011.06.007
[11]	LEI Yaguo,LI Naipeng,LI Ningbo,et al. Machinery health prognostics:a systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing,2018,104:799-834. doi: 10.1016/j.ymssp.2017.11.016
[12]	王昆, 郭迎清, 赵万里, 等. 基于SSAE和相似性匹配的航空发动机剩余寿命预测[J/OL]. 北京航空航天大学学报: 1-13[2023-03-30]. https://doi.org/10.13700/j.bh.1001-5965.2021.0741. WANG Kun, GUO Yingqing, ZHAO Wanli, et al. Remaining useful life prediction of aeroengine based on SSAE and similarity matching[J/OL]. Journal of Beijing University of Aeronautics and Astronautics: 1-13[2023-03-30]. https://doi.org/10.13700/j.bh.1001-5965.2021.0741.
[13]	于倩影, 李娟, 戴洪德, 等. 基于Lasso变量选择的航空发动机相似性剩余寿命预测[J/OL]. 航空动力学报: 1-8[2023-03-30]. https://doi.org/10.13224/j.cnki.jasp.20210516. YU Qianying, LI Juan, DAI Hongde, et al. Lasso based variable selection for similarity remaining useful life prediction of aero-engine[J/OL]. Journal of Aerospace Power: 1-8[2023-03-30]. https://doi.org/10.13224/j.cnki.jasp.20210516.
[14]	万安平,陈坚红,盛德仁,等. 基于多重环境时间相似理论的燃气轮机热通道部件剩余寿命预测方法[J]. 中国电机工程学报,2013,33(5):95-101,16. WAN Anping,CHEN Jianhong,SHENG Deren,et al. Residual life prediction method for gas turbine HGP component based on multi-environmental time similarity theory[J]. Proceedings of the CSEE,2013,33(5):95-101,16.
[15]	陈云翔,饶益,蔡忠义,等. 基于改进相似性的装备部件剩余寿命预测及经济性储备策略[J]. 系统工程与电子技术,2021,43(9):2688-2696. CHEN Yunxiang,RAO Yi,CAI Zhongyi,et al. Remaining useful lifetime prediction and economic reserve strategy of equipment components based on improved similarity[J]. Systems Engineering and Electronics,2021,43(9):2688-2696.
[16]	任博,董兴辉,郑凯. 基于相似性的风电动机组轴承剩余寿命预测方法[J]. 机械设计与研究,2016,32(4):101-104. REN Bo,DONG Xinghui,ZHENG Kai. Research on similarity-based component remaining life prediction of wind turbine bearing[J]. Machine Design & Research,2016,32(4):101-104.
[17]	丁华,杨亮亮,杨兆建,等. 数字孪生与深度学习融合驱动的采煤机健康状态预测[J]. 中国机械工程,2020,31(7):815-823. DING Hua,YANG Liangliang,YANG Zhaojian,et al. Health prediction of shearers driven by digital twin and deep learning[J]. China Mechanical Engineering,2020,31(7):815-823.
[18]	刘晓波,孔屹刚,李涛,等. 采煤机调高泵隐半马尔可夫模型磨损故障预测[J]. 科学技术与工程,2020,20(29):11980-11986. LIU Xiaobo,KONG Yigang,LI Tao,et al. Wear fault prognostics of hidden semi-markov model of shearer pump[J]. Science Technology and Engineering,2020,20(29):11980-11986.
[19]	孙永新. 煤机设备轴承剩余寿命预测方法研究[J]. 工矿自动化,2021,47(11):126-130. SUN Yongxin. Research on bearing residual life prediction method of coal mine machinery equipment[J]. Industry and Mine Automation,2021,47(11):126-130.
[20]	QIU Hai,LEE J,LIN Jing,et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound and Vibration,2006,289(4/5):1066-1090.
[21]	赵志宏,李晴,李春秀. 基于卷积GRU注意力的设备剩余寿命预测[J]. 振动. 测试与诊断,2022,42(3):572-579,622. ZHAO Zhihong,LI Qing,LI Chunxiu. Remaining useful life prediction based on conv GRU-attention method[J]. Journal of Vibration,Measurement & Diagnosis,2022,42(3):572-579,622.
[22]	王久健,杨绍普,刘永强,等. 一种基于空间卷积长短时记忆神经网络的轴承剩余寿命预测方法[J]. 机械工程学报,2021,57(21):88-95. doi: 10.3901/JME.2021.21.088 WANG Jiujian,YANG Shaopu,LIU Yongqiang,et al. A method of bearing remaining useful life estimation based on convolutional long short-term memory neural network[J]. Journal of Mechanical Engineering,2021,57(21):88-95. doi: 10.3901/JME.2021.21.088