Please wait a minute...
工程设计学报  2024, Vol. 31 Issue (6): 793-800    DOI: 10.3785/j.issn.1006-754X.2024.14.02
【特约专栏】“2024’工程机械行业科技节”成果展示——创新技术及其应用     
基于数据驱动的液压马达预测性维护研究
刘强1,4(),朱建新2,3,崔瑜源2
1.长沙职业技术学院 智能制造工程学院,湖南 长沙 410100
2.中南大学 高性能复杂制造国家重点实验室,湖南 长沙 410100
3.长沙市特种工程装备工业技术研究院有限公司,湖南 长沙 410100
4.山河智能装备股份有限公司 国家级企业技术中心,湖南 长沙 410100
Data-driven predictive maintenance research on hydraulic motor
Qiang LIU1,4(),Jianxin ZHU2,3,Yuyuan CUI2
1.School of Intelligent Manufacturing Engineering, Changsha Vocational and Technical College, Changsha 410100, China
2.State Key Laboratory of High Performance Complex Manufacturing, Central South University, Changsha 410100, China
3.Changsha Special Engineering Equipment Industrial Technology Research Institute Co. , Ltd. , Changsha 410100, China
4.National Enterprise Technology Center, Sunward Intelligent Equipment Co. , Ltd. , Changsha 410100, China
 全文: PDF(2934 KB)   HTML
摘要:

预测性维护是数字孪生典型应用之一,数据驱动是实现预测性维护的主要方式。针对预测性维护中故障特征提取困难、预测结果偏差较大的问题,提出了一种基于变分模态分解(variational mode decomposition,VMD)算法与希尔伯特-黄变换(Hilbert-Huang transform,HHT)算法相结合的预测性维护模型的构建方法。用VMD+HHT算法提取振动信号时域特征,结合深度稀疏自编码器(deep sparse auto-encoder,DSAE)进行数据降维,采用支持向量数据描述(support vector data description,SVDD)算法来形成健康度曲线,并基于长短时记忆网络(long short-term memory,LSTM)算法建立预测性维护模型。将该方法应用于一款旋挖钻机液压马达的预测性维护。提取马达外壳的振动信号,构建液压马达预测性维护模型,并通过试验来验证该方法的有效性与准确性。试验结果表明,采用基于DSAE+SVDD+LSTM算法构建的预测性维护模型可避免模态混叠及端点效应等问题,预测精度达90%以上,模型具有实用价值。研究结果可为液压元件数字孪生预测性维护应用场景的建设提供重要参考。

关键词: 数据驱动液压马达预测性维护    
Abstract:

Predictive maintenance is one of the typical applications of digital twin, and data-driven is the main way to realize predictive maintenance. Aiming at the problems of difficult fault feature extraction and large deviation of prediction results in predictive maintenance, a predictive maintenance model building method based on the combination of VMD (variational mode decomposition) algorithm and HHT (Hilbert-Huang transform) algorithm was proposed. The time-domain features of the vibration signal were extracted by VMD+HHT algorithm, the data dimension was reduced by combining deep sparse auto-encoder (DSAE), support vector data description (SVDD) algorithm was used to form a health index curve, and a predictive maintenance model was established based on long short-term memory (LSTM) algorithm. The method was applied to the predictive maintenance of a hydraulic motor of a rotary drilling rig. The vibration signal of the motor housing was extracted, the predictive maintenance model of the hydraulic motor was constructed, and the validity and accuracy of the method were verified by test. The test results showed that adopting the predictive maintenance model based on DSAE+SVDD+LSTM algorithm could avoid the problems of mode aliasing and endpoint effect, the prediction accuracy could reach more than 90%, and the model had practical value. The research results can provide important reference for the construction of hydraulic component digital twin predictive maintenance application scenarios.

Key words: data-driven    hydraulic motor    predictive maintenance
收稿日期: 2024-04-15 出版日期: 2024-12-31
CLC:  TH 17  
基金资助: 湖南省十大科技攻关项目(2021GK1150);湖南省自然科学基金资助项目(2024JJ8044)
作者简介: 刘 强(1984—),男,高级工程师,博士,从事工程机械数字孪生研究,E-mail: liuqiang4109@163.com, https://orcid.org/0000-0002-4394-7101
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
刘强
朱建新
崔瑜源

引用本文:

刘强,朱建新,崔瑜源. 基于数据驱动的液压马达预测性维护研究[J]. 工程设计学报, 2024, 31(6): 793-800.

Qiang LIU,Jianxin ZHU,Yuyuan CUI. Data-driven predictive maintenance research on hydraulic motor[J]. Chinese Journal of Engineering Design, 2024, 31(6): 793-800.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2024.14.02        https://www.zjujournals.com/gcsjxb/CN/Y2024/V31/I6/793

图1  轴承加速退化试验台
图2  原始振动信号
图3  振动信号时频分析结果
图4  基于HHT算法的边际谱变化
图5  部分振动信号降维数据
图6  轴承HI曲线
图7  轴承剩余寿命预测结果
轴承编号预测起始时间/s预测截止时间/s真实截止时间/s

相对误差/

%

1-318 02022 40022 730-1.45
1-411 39011 69011 5001.65
1-524 55024 86024 6300.93
1-624 10024 47024 480-0.04
1-722 50022 85022 5901.15
表1  轴承剩余寿命预测误差
图8  旋挖钻机动力头液压马达
图9  液压马达试验平台
设备数量
马达试验台架1套
液压马达4台
马达柱塞4组
PCB356A26三轴加速度传感器3个
西门子LMS振动噪声测试系统1套
表2  液压马达测试用设备
图10  中度磨损马达壳体切向振动信号
图11  液压马达振动信号IMF分量
图12  液压马达振动信号HHT时频谱
图13  液压马达HI曲线
图14  液压马达退化趋势预测结果
1 李向前. 复杂装备故障预测与健康管理关键技术研究[D]. 北京: 北京理工大学, 2014: 2-3.
LI X Q. Research on key technologies of fault prediction and health management of complex equipment[D]. Beijing: Beijing Institute of Technology, 2014: 2-3.
2 郭宇. 基于故障预测的设备预防性维护策略研究及应用[D]. 重庆: 重庆大学, 2017.
GUO Y. Research and application of equipment preventive maintenance policies based on fault prediction[D]. Chongqing: Chongqing University, 2017.
3 RAY A, TANGIRALA S. Stochastic modeling of fatigue crack dynamics for on-line failure prognostics[J]. IEEE Transactions on Control Systems Technology, 1996, 4(4): 443-451.
4 LI Y, BILLINGTON S, ZHANG C, et al. Adaptive prognostics for rolling element bearing condition[J]. Mechanical Systems and Signal Processing, 1999, 13(1): 103-113.
5 GLODEŽ S, ŠRAML M, KRAMBERGER J. A computational model for determination of service life of gears[J]. International Journal of Fatigue, 2002, 24(10): 1013-1020.
6 SIDAR M, DOOLIN B. On the feasibility of real-time prediction of aircraft carrier motion at sea[J]. IEEE Transactions on Automatic Control, 1983, 28(3): 350-356.
7 HUANG R Q, XI L F, LI X L, et al. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods[J]. Mechanical Systems and Signal Processing, 2007, 21(1): 193-207.
8 COPPE A, PAIS M J, HAFTKA R T, et al. Using a simple crack growth model in predicting remaining useful life[J]. Journal of Aircraft, 2012, 49(6): 1965-1973.
9 STANDER C J, HEYNS P S, SCHOOMBIE W. Using vibration monitoring for local fault detection on gears operating under fluctuating load conditions[J]. Mechanical Systems and Signal Processing, 2002, 16(6): 1005-1024.
10 DONG M, HE D. A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology[J]. Mechanical Systems and Signal Processing, 2007, 21(5): 2248-2266.
11 GEBRAEEL N Z, LAWLEY M A. A neural network degradation model for computing and updating residual life distributions[J]. IEEE Transactions on Automation Science and Engineering, 2008, 5(1): 154-163.
12 MIRIKITANI D T, NIKOLAEV N. Recursive Bayesian recurrent neural networks for time-series modeling[J]. IEEE Transactions on Neural Networks, 2010, 21(2): 262-274.
13 ZHOU F N, HU P, YANG X H. RUL prognostics method based on real time updating of LSTM parameters[C]//2018 Chinese Control and Decision Conference, Shenyang, China, Jun. 09-11, 2018: 3966-3971.
14 ZHANG W T, YANG D, WANG H C. Data-driven methods for predictive maintenance of industrial equipment: A survey[J]. IEEE Systems Journal, 2019, 13(3): 2213-2227.
15 陈远航. 滚动轴承剩余寿命预测算法研究及监测软件开发[D]. 哈尔滨: 哈尔滨工业大学, 2020: 50-52.
CHEN Y H. Study on algorithm for rolling bearing remaining useful life prediction and development of monitor software[D]. Harbin: Harbin Institute of Technology, 2020: 50-52.
16 张国辉. 基于深度置信网络的时间序列预测方法及其应用研究[D]. 哈尔滨: 哈尔滨工业大学, 2017: 46-51. doi:10.18178/ijiee.2017.7.4.674
ZHANG G H. Research on time series prediction and its application based on deep belief network[D]. Harbin: Harbin Institute of Technology, 2017: 46-51.
doi: 10.18178/ijiee.2017.7.4.674
17 PATRICK N, RAFAEL G, KAMAL M. Pronostia: An experimental platform for bearings accelerated life test[C]//IEEE International Conference on Prognostics and Health Management, Denver, Colorado, United States, Jun. 18-21, 2012.
18 魏晓良, 潮群, 陶建峰, 等. 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报, 2021, 42(3): 423876. doi:10.7527/S1000-6893.2020.23876
WEI X L, CHAO Q, TAO J F, et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(3): 423876.
doi: 10.7527/S1000-6893.2020.23876
19 侍晓冬. 基于深度学习DSAE与LSTM的液压泵剩余使用寿命预测[D]. 秦皇岛: 燕山大学, 2021: 60-62.
SHI X D. Remaining useful life prediction of hydraulic pump based on deep learning DSAE and LSTM[D]. Qinhuangdao: Yanshan University, 2021: 60-62.
[1] 张旭辉,鞠佳杉,杨文娟,吕欣媛. 基于数字孪生的复杂矿用设备预测性维护系统[J]. 工程设计学报, 2022, 29(5): 643-650.