降噪混合注意力变分自编码器及其在轴向柱塞泵故障诊断中的应用

doi:10.3901/JME.2024.04.167

机械工程学报 ›› 2024, Vol. 60 ›› Issue (4): 167-177.doi: 10.3901/JME.2024.04.167

• 特邀专栏：智能液压元件及系统基础技术 • 上一篇下一篇

扫码分享

降噪混合注意力变分自编码器及其在轴向柱塞泵故障诊断中的应用

王志颖¹, 李天福^1,2, 许文纲¹, 孙闯¹, 张军辉³, 徐兵³, 严如强¹

1. 西安交通大学机械工程学院西安 710049;
2. 洛桑联邦理工大学智能运维与运营系统实验室洛桑 1015 瑞士;
3. 浙江大学流体动力与机电系统国家重点实验室杭州 310027

收稿日期:2023-03-09 修回日期:2023-11-14 出版日期:2024-02-20 发布日期:2024-05-25
通讯作者: 严如强,男,1975年出生,博士,教授,博士研究生导师。主要研究方向为机械系统状态监测与故障诊断、信号处理、无线传感网络。E-mail:yanruqiang@xjtu.edu.cn
作者简介:王志颖,男,1998年出生,博士研究生。主要研究方向为液压泵故障诊断。E-mail:wangzhiying@stu.xjtu.edu.cn
基金资助:
国家自然科学基金重点资助项目(51835009)

Denoising Mixed Attention Variational Auto-encoder for Axial Piston Pump Fault Diagnosis

WANG Zhiying¹, LI Tianfu^1,2, XU Wengang¹, SUN Chuang¹, ZHANG Junhui³, XU Bing³, YAN Ruqiang¹

1. School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049;
2. Laboratory of Intelligent Maintenance and Operations Systems, EPFL, Lausanne 1015, Switzerland;
3. State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang University, Hangzhou 310027

Received:2023-03-09 Revised:2023-11-14 Online:2024-02-20 Published:2024-05-25

摘要/Abstract

摘要： 轴向柱塞泵作为液压系统的供能元件,其故障诊断研究具有重要意义。现有故障诊断方法大多依赖人工经验,提取故障特征需要大量专家知识,且对数据和噪声的鲁棒性较差。针对轴向柱塞泵服役环境复杂、监测信号易受噪声干扰的问题,提出端到端的降噪混合注意力变分自编码器方法,直接提取淹没在噪声中的故障特征,从而实现噪声环境下轴向柱塞泵故障诊断。该方法利用卷积变分自编码器从柱塞泵压力信号和振动信号中提取故障特征,通过引入混合注意力机制,实现编码器隐层特征的加权融合,以增强故障特征并削弱噪声影响;进一步使用自适应软阈值降噪方法,降低噪声干扰,完成强噪声环境下轴向柱塞泵故障诊断。通过轴向柱塞泵故障模拟试验和噪声鲁棒性试验对所提出方法的有效性进行验证,结果表明该方法在5dB噪声下的诊断准确率高达99.32%,在-5d B的强噪声影响下仍能保持69.72%的准确率,优于常用的故障诊断方法。

关键词: 轴向柱塞泵, 故障诊断, 变分自编码器, 注意力机制, 软阈值降噪

Abstract: As an energy supply component of hydraulic system, the fault diagnosis of axial piston pump is of great significance.However, most existing methods rely on expert knowledge for feature extraction, and the robustness to noise is poor. To tackle the problem that complex working conditions bring noise interference to the collected diagnostic signals of axial piston pump, an end-to-end denoising mixed attention variational auto-encoder method is proposed to directly extract the fault characteristics submerged in the noise, to realize the fault diagnosis of axial piston pump under noisy environment. The proposed method employs convolution variational auto-encoder to extract fault features from multivariate signals including pressure and vibration.By introducing the mixed attention mechanism, hidden layer features of the encoder are weighted and fused, enhancing the fault features while weakening the noise. The adaptive soft-threshold denoising method is further applied to reducing the noise interference in extracted features, realizing the fault diagnosis of axial piston pump under strong noise. The effectiveness of the proposed method is verified by the fault implantation experiment and noise robustness experiment of an axial piston pump, and the results show 99.32% diagnosis accuracy under 5 dB noise and 69.72% under-5 dB noise, which outperforms commonly used diagnosis methods.

Key words: axial piston pump, fault diagnosis, variational auto-encoder, attention mechanism, soft-threshold denoising

中图分类号:

TH322

王志颖, 李天福, 许文纲, 孙闯, 张军辉, 徐兵, 严如强. 降噪混合注意力变分自编码器及其在轴向柱塞泵故障诊断中的应用[J]. 机械工程学报, 2024, 60(4): 167-177.

WANG Zhiying, LI Tianfu, XU Wengang, SUN Chuang, ZHANG Junhui, XU Bing, YAN Ruqiang. Denoising Mixed Attention Variational Auto-encoder for Axial Piston Pump Fault Diagnosis[J]. Journal of Mechanical Engineering, 2024, 60(4): 167-177.

参考文献

[1] 杨华勇,张斌,徐兵.轴向柱塞泵/马达技术的发展演变[J].机械工程学报,2008,44(10):1-8.YANG Huayong,ZHANG Bin,XU Bing. Development of axial piston pump/motor technology[J]. Journal of Mechanical Engineering,2008,44(10):1-8.
[2] 高英杰,孔祥东.基于小波包分析的液压泵状态监测方法[J].机械工程学报,2009,45(8):80-88.GAO Yingjie, KONG Xiangdong. Wavelet packets analysis based method for hydraulic pump condition monitoring[J]. Journal of Mechanical Engineering,2009,45(8):80-88.
[3] 杨东亚,李伟涛,李振宇,等.高压柱塞泵摩擦副研究现状与展望[J].液压气动与密封,2022,42(5):1-7.YANG Dongya,LI Weitao,LI Zhenyu,et al. Present situation and forecasting of fraction pairs for high pressure piston pump[J]. Hydraulic Pneumatics & Seals,2022,42(5):1-7.
[4] 周汝胜,焦宗夏,王少萍.液压系统故障诊断技术的研究现状与发展趋势[J].机械工程学报,2006,42(9):6-14.ZHOU Rusheng, JIAO Zongxia, WANG Shaoping.Research status and development trend of hydraulic system fault diagnosis[J]. Journal of Mechanical Engineering,2006,42(9):6-14.
[5] DU J, WANG S, ZHANG H. Layered clustering multi-fault diagnosis for hydraulic piston pump[J].Mechanical Systems & Signal Processing,2013,36(2):487-504.
[6] 陈章位,吕红兵,路甬祥. Wigner谱理论及其在柱塞泵故障诊断中的应用[J].中国机械工程,1992,3(4):4-6,3.CHEN Zhangwei,LÜ Hongbing,LU Yongxiang. Wigner spectrum theory and its application in piston pump fault diagnosis[J]. China Mechanical Engineering,1992,3(4):4-6,3.
[7] 王少萍,苑中魁,杨光琴.液压泵信息融合故障诊断[J].中国机械工程,2005,16(4):327-331.WANG Shaoping,YUAN Zhongkui,YANG Guangqin.Study on fault diagnosis of data fusion in hydraulic pump[J]. China Mechanical Engineering,2005,16(4):327-331.
[8] 赵四军,王少萍,吴柯锐.基于粗糙集和支持向量机的航空液压泵故障诊断[J].中北大学学报,2010,31(3):238-242.ZHAO Sijun, WANG Shaoping, WU Kerui. Fault diagnosis based on rough set and support vector machines for aero hydraulic pump[J]. Journal of North University of China,2010,31(3):238-242.
[9] 姜万录,王益群.混沌振子在液压泵故障诊断中的应用[J].机床与液压,1999(5):52-53,83.JIANG Wanlu,WANG Yiqun. Application of chaotic oscillator in fault diagnosis of hydraulic pump[J].Machine Tool & Hydraulics,1999(5):52-53,83.
[10] 高强,向家伟,汤何胜.基于增强聚类分割与L-峭度的Teager能量算子解调诊断轴向柱塞泵故障[J].机械工程学报,2018,54(18):1-10.GAO Qiang,XIANG Jiawei,TANG Hesheng. Axial piston pump fault diagnosis with Teager energy operator demodulation using improved clustering-based segmentation and L-kurtosis[J]. Journal of Mechanical Engineering,2018,54(18):1-10.
[11] KUMAR A,TANG H,VASHISHTHA G,et al. Noise subtraction and marginal enhanced square envelope spectrum (MESES) for the identification of bearing defects in centrifugal and axial pump[J]. Mechanical Systems and Signal Processing,2022,165:108366.
[12] 雷亚国,贾峰,孔德同,等.大数据下机械智能故障诊断的机遇与挑战[J].机械工程学报,2018,54(5):94-104.LEI Yaguo,JIA Feng,KONG Detong,et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering,2018,54(5):94-104.
[13] ZHAO W,WANG Z,MA J,et al. Fault diagnosis of a hydraulic pump based on the CEEMD-STFT time-frequency entropy method and multiclass SVM classifier[J]. Shock and Vibration,2016,2016:2609856.
[14] LU C,WANG S,ZHANG C. Fault diagnosis of hydraulic piston pumps based on a two-step EMD method and fuzzy C-means clustering[C]//Proceedings of the Institution of Mechanical Engineers,Part C:Journal of Mechanical Engineering Science,2016,230(16):2913-2928.
[15] 姜万录,刘思远.多特征信息融合的贝叶斯网络故障诊断方法研究[J].中国机械工程,2010,21(8):940-945.JIANG Wanlu,LIU Siyuan. Fault diagnosis approach study of Bayesian networks based on multi-characteristic information fusion[J]. China Mechanical Engineering,2010,21(8):940-945.
[16] XIAO C,TANG H,REN Y,et al. Adaptive MOMEDA based on improved advance-retreat algorithm for fault features extraction of axial piston pump[J]. ISA Transactions,2022,128(Part B):503-520.
[17] HE Y,TANG H,REN Y,et al. A deep multi-signal fusion adversarial model based transfer learning and residual network for axial piston pump fault diagnosis[J].Measurement,2022,192:110889.
[18] 王登铭.基于PSO-BP神经网络的柱塞泵故障诊断方法的研究[D].南京:东南大学,2018.WANG Dengming. Research on fault diagnosis method of axial piston pump based on PSO-BP neural network[D].Nanjing:Southeast University,2018.
[19] TANG S,ZHU Y,YUAN S. Intelligent fault diagnosis of hydraulic piston pump based on deep learning and Bayesian optimization[J]. ISA Transactions, 2022,129(Part A):555-563.
[20] LAN Y,HU J,HUANG J,et al. Fault diagnosis on slipper abrasion of axial piston pump based on extreme learning machine[J]. Measurement,2018,124:378-385.
[21] ZHANG J,GAO R X. Deep learning-driven data curation and model interpretation for smart manufacturing[J].Chinese Journal of Mechanical Engineering,2021,34(1):1-21.
[22] ZHAO Z,WU J,LI T,et al. Challenges and opportunities of AI-enabled monitoring,diagnosis & prognosis:A review[J]. Chinese Journal of Mechanical Engineering,2021,34(1):1-29.
[23] 王辉,徐佳文,严如强.基于多尺度注意力深度强化学习网络的行星齿轮箱智能诊断方法[J].机械工程学报,2022,58(11):133-142.WANG Hui,XU Jiawen,YAN Ruqiang. Multi-scale attention based deep reinforcement learning for intelligent fault diagnosis of planetary gearbox[J]. Journal of Mechanical Engineering,2022,58(11):133-142.
[24] 董绍江,裴雪武,吴文亮,等.基于多层降噪技术及改进卷积神经网络的滚动轴承故障诊断方法[J].机械工程学报,2021,57(1):148-156.DONG Shaojiang,PEI Xuewu,WU Wenliang,et al.Rolling bearing fault diagnosis method based on multilayer noise reduction technology and improved convolutional neural network[J]. Journal of Mechanical Engineering,2021,57(1):148-156.
[25] ZHAO Z,LI T,WU J,et al. Deep learning algorithms for rotating machinery intelligent diagnosis:An open source benchmark study[J]. ISA Transactions, 2020, 107:224-255.
[26] WOO S,PARK J,LEE JY,et al. CBAM:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018:3-19.

降噪混合注意力变分自编码器及其在轴向柱塞泵故障诊断中的应用

Denoising Mixed Attention Variational Auto-encoder for Axial Piston Pump Fault Diagnosis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[2]	严如强, 许文纲, 王志颖, 朱启翔, 周峥, 赵志斌, 孙闯, 王诗彬, 陈雪峰, 张军辉, 徐兵. 航空发动机燃油控制系统故障诊断技术研究进展与挑战[J]. 机械工程学报, 2024, 60(4): 3-31.
[3]	张军辉, 刘施镐, 徐兵, 黄伟迪, 吕飞, 黄晓琛. 轴向柱塞泵智能化关键技术研究进展及发展趋势[J]. 机械工程学报, 2024, 60(4): 32-49.
[4]	丁孺琦, 熊文杰, 程敏, 徐兵. 智能化阀口独立电液控制系统安全性能评估[J]. 机械工程学报, 2024, 60(4): 101-112.
[5]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[6]	邵海东, 林健, 闵志闪, 明宇航. 分布外样本干扰下基于改进半监督原型网络的齿轮箱跨域故障诊断[J]. 机械工程学报, 2024, 60(4): 212-221.
[7]	李莹, 张嘉方, 张钊墉, 王鑫丞, 张晋, 孔祥东. 斜盘式轴向柱塞泵柱塞颈部最小直径设计[J]. 机械工程学报, 2024, 60(4): 430-437.
[8]	潘海洋, 徐海锋, 郑近德, 童靳于, 张飞斌. 基于双加权不平衡矩阵分类器的机械故障诊断方法[J]. 机械工程学报, 2024, 60(3): 170-180.
[9]	赵轲, 叶敏, 王瑞欣, 陆海, 刘孟孟, 邵海东. 基于模糊域自适应的源自由域旋转机械故障诊断方法[J]. 机械工程学报, 2024, 60(18): 43-52.
[10]	李志鹏, 马天雨, 刘金平, 向青松, 唐俊杰. 基于非对称性对抗训练的多源域自适应智能故障诊断方法[J]. 机械工程学报, 2024, 60(18): 76-88.
[11]	汪煜坤, 易彩, 汪浩, 周秋阳, 冉乐, 王靖元. PSD引导的自适应频带划分方法及其在轴承故障诊断中的应用[J]. 机械工程学报, 2024, 60(17): 179-193.
[12]	刘一龙, 李心远, 陈银萍, 成玮, 陈雪峰. 基于峭度曲面极大值的电机轴承保持架故障诊断方法[J]. 机械工程学报, 2024, 60(15): 89-99.
[13]	于小洛, 杨阳, 杜明刚, 何清波, 彭志科. 机械传动系统含偏差频率分量协同检测与分解方法[J]. 机械工程学报, 2024, 60(15): 100-112.
[14]	黄包裕, 张永祥. 一种基于三步法的轴承故障诊断方法[J]. 机械工程学报, 2024, 60(14): 51-68.
[15]	付玲, 佘玲娟, 颜镀镭, 张鹏, 龙湘云. 基于内嵌物理信息与注意力机制BiLSTM神经网络的臂架系统疲劳损伤预测模型[J]. 机械工程学报, 2024, 60(13): 205-215.