智能制造

基于全矢增强深度森林的旋转设备智能故障诊断方法

展开
  • 1.燕山大学河北省重型机械流体动力传输与控制重点实验室,秦皇岛,066004
    2.燕山大学先进锻压成形技术与科学教育部重点实验室,秦皇岛,066004
    3.燕山大学电气工程学院,秦皇岛,066004
姜万录,男,1964年生,教授、博士研究生导师。研究方向为现代检测技术与信号处理、控制理论与控制工程、故障诊断与智能信息处理、冷轧工艺及厚度控制。E-mail:wljiang@ysu.edu.cn。

收稿日期: 2021-06-09

  网络出版日期: 2022-06-30

基金资助

国家自然科学基金(51875498);河北省自然科学基金(E2018203339,F2020203058)

Intelligent Fault Diagnosis Method for Rotating Equipment Based on Full Vector Enhanced Deep Forest

Expand
  • 1.Hebei Provincial Key Laboratory of Heavy Machinery Fluid Power Transmission and Control,Yanshan University,Qinhuangdao,Hebei,066004
    2.Key Laboratory of Advanced Forging & Stamping Technology and Science(Yanshan University),Ministry of Education of China,Qinhuangdao,Hebei,066004
    3.School of Electrical Engineering,Yanshan University,Qinhuangdao,Hebei,066004

Received date: 2021-06-09

  Online published: 2022-06-30

摘要

针对传统智能诊断方法需要专家知识和复杂特征提取,而深度神经网络模型复杂度高、构建难度大,以及单源信号信息不完备等问题,提出了一种新颖的全矢数据融合增强深度森林的旋转设备故障诊断方法。该方法根据旋转设备振动信号的特点,选择全矢谱技术与深度森林多粒度扫描相结合,用于接收同源双通道信号输入,增强了数据的完备性,并通过改善深度森林级联层来减少深层特征消失和特征冗余。为了验证所提出方法的有效性,分别进行了滚动轴承与轴向柱塞泵两例故障诊断实验研究,结果表明,该方法在不同旋转设备上都有很好的诊断效果,并可以实现端到端故障诊断。此外,该方法在小训练数据集上的故障识别准确率也非常高。

本文引用格式

姜万录, 李满, 张培尧, 赵亚鹏, 张淑清 . 基于全矢增强深度森林的旋转设备智能故障诊断方法[J]. 中国机械工程, 2022 , 33(11) : 1324 -1335 . DOI: 10.3969/j.issn.1004-132X.2022.11.009

Abstract

A new fault diagnosis method for rotating equipment was proposed based on deep forest improved by full vector data fusion to solve the problems that traditional intelligent diagnostic methods required expert knowledge and complex feature extraction, deep neural network model had complex structure and was difficult to construct, and the single-channel signals were incompleteness. According to the characteristics of vibration signals of rotating equipment, the full vector data fusion technology was combined with multi-grained scanning of deep forest to receive the homologous double-channel signals, so as to enhance the completeness of data. At the same time, the cascade layer of deep forest was improved to reduce the deep feature disappearance and feature redundancy. In order to verify the effectiveness of the proposed method, two fault diagnosis experiments of rolling bearing and axial plunger pump were carried out respectively. The results show that this method achieves a good diagnostic effectiveness on different rotating equipment and end-to-end fault diagnosis may be realized. In addition, it is also very excellent in fault recognition accuracy on small training data sets.

参考文献

[1]郑直,李世峰,郭洋,等. 基于液压泵复数信号的log-SAM故障诊断方法研究[J]. 振动与冲击, 2021, 40(6):79-85.
ZHENG Zhi,LI Shifeng,GUO Yang,et al. Hydraulic Pump Fault Diagnosis Method Using Log-SAM on Complex Signals[J]. Journal of Vibration and Shock, 2021, 40(6):79-85.
[2]YU He, LI Hongru, LI Yaolong, et al. A Novel Improved Full Vector Spectrum Algorithm and Its Application in Multi-sensor Data Fusion for Hydraulic Pumps[J]. Measurement, 2019, 133:145-161.
[3]GAI Jingbo, SHEN Junxian, HU Yifan, et al. An Integrated Method Based on Hybrid Grey Wolf Optimizer Improved Variational Mode Decomposition and Deep Neural Network for Fault Diagnosis of Rolling Bearing[J]. Measurement, 2020, 162:107901.
[4]王振亚, 姚立纲. 广义精细复合多尺度样本熵与流形学习相结合的滚动轴承故障诊断方法[J]. 中国机械工程, 2020, 31(20):2463-2471.
WANG Zhenya, YAO Ligang. Rolling Bearing Fault Diagnosis Method Based on Generalized Refined Composite Multiscale Sample Entropy and Manifold Learning[J]. China Mechanical Engineering, 2020, 31(20):2463-2471.
[5]林辉翼,郝伟,郝旺身,等. 全矢谱和稀疏分解结合的轴承故障特征提取[J]. 机械设计与制造, 2019(6):146-149.
LIN Huiyi, HAO Wei, HAO Wangshen, et al. Bearing Early Fault Feature Extraction Based on Full Vector Spectrum and Sparse Decomposition[J]. Machinery Design & Manufacture, 2019(6):146-149.
[6]胡泽,张智博,王晓杰,等. 基于希尔伯特-黄变换和神经网络的滚动轴承故障诊断[J]. 电动工具, 2020(1):11-18.
HU Ze, ZHANG Zhibo, WANG Xiaojie, et al. Fault Diagnosis of Rolling Bearing Based on Hilbert Huang Transform and Neural Network[J]. Electrokinetic Tool, 2020(1):11-18.
[7]杜振东, 赵建民, 李海平, 等. 基于SA-EMD-PNN的柱塞泵故障诊断方法研究[J]. 振动与冲击, 2019, 38(8):145-152.
DU Zhendong,ZHAO Jianmin,LI Haiping,et al. A Fault Diagnosis Method of a Plunger Pump Based on SA-EMD-PNN[J]. Journal of Vibration and Shock, 2019, 38(8):145-152.
[8]周建民,王发令,张臣臣,等. 基于特征优选和GA-SVM的滚动轴承智能评估方法[J]. 振动与冲击, 2021, 40(4):227-234.
ZHOU Jianmin, WANG Faling, ZHANG Chenchen, et al. An Intelligent Method for Rolling Bearing Evaluation Using Feature Optimization and GA-SVM[J]. Journal of Vibration and Shock 2021, 40(4):227-234.
[9]ZHONG Ting, QU Jianfeng, FANG Xiaoyu, et al. The Intermittent Fault Diagnosis of Analog Circuits Based on EEMD-DBN[J]. Neurocomputing, 2021, 436:74-91.
[10]姜万录, 李金虎, 李振宝, 等. 基于改进的堆叠降噪自动编码器深度模型的转子转轴系统故障诊断方法[J]. 机床与液压, 2020, 48(23):218-223.
JIANG Wanlu, LI Jinhu, LI Zhenbao, et al. Fault Diagnosis Method of Rotor-shaft System Based on the Improved Stacked Denoising Auto Encoder Depth Model[J]. Machine Tool & Hydraulics, 2020, 48(23):218-223.
[11]KANG Jialin. Visualization Analysis for Fault Diagnosis in Chemical Processes Using Recurrent Neural Networks[J]. Journal of the Taiwan Institute of Chemical Engineers, 2020, 112:137-151.
[12]LIANG Pengfei, DENG Chao, WU Jun, et al. Compound Fault Diagnosis of Gearboxes via Multi-label Convolutional Neural Network and Wavelet Transform[J]. Computers in Industry, 2019, 113:103132.
[13]HU Guangzheng, LI Huifang, XIA Yuanqiang, et al. A Deep Boltzmann Machine and Multi-grained Scanning Forest Ensemble Collaborative Method and Its Application to Industrial Fault Diagnosis[J]. Computers in Industry, 2018, 100:287-296.
[14]高山,周玉平,陈宏,等.全矢EEMD在轴承故障诊断中的应用[J]. 机械设计与制造, 2021(3):118-121.
GAO Shan, ZHOU Yuping, CHEN Hong, et al. Application of Full Vector-spectrum EEMD in Bearing Fault Diagnosis[J]. Machinery Design & Manufacture, 2021(3):118-121.
[15]HIANG Hongcheng, WANG Xiongdong, HUANG Guoyong. Approach to Fault Feature Extractions of Rolling Bearing via EEMD and Full-vector Envelope Spectrum[C]∥29th Chinese Control and Decision Conference (CCDC). Chongqing, 2017:6492-6497.
[16]ZHOU Zhihua. Deep Forest:towards an Alternative to Deep Neural Networks [C]∥26th International Joint Conference on Artificial Intelligence (IJCAI). Melbourne,2017:3553-3559.
[17]卞凌志, 王直杰. 基于增强多维多粒度级联森林的信用评分模型[J]. 计算机应用, 2021, 41(9):2539-2544. 
BIAN Lingzhi,WANG Zhijie. Credit Scoring Model Based on Enhanced Multi-dimensional and Multi-grained Cascade Forest Algorithm[J]. Journal of Computer Applications, 2021, 41(9):2539-2544.
[18]PANG Ming, TING Kaiming, ZHAO Peng, et al. Improving Deep Forest by Screening[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 1:1-14.
[19]巩晓赟. 基于全矢谱的非平稳故障诊断关键技术研究[D]. 郑州:郑州大学, 2013.
GONG Xiaoyun. Research on Key Technology of Nonstationary Fault Diagnosis Based on Full Vector Spectrum[D]. Zhengzhou:Zhengzhou University, 2013.
[20]WU F Q, MENG G. Compound Rub Malfunctions Feature Extraction Based on Full-spectrum Cascade Analysis and SVM[J]. Mechanical Systems and Signal Processing, 2006, 20(8):2007-2021.
[21]蔡长征. 数据驱动算法在旋转机械故障诊断中的应用研究[J]. 机床与液压, 2020, 48(23):218-223.
CAI Changzheng. Application of Data-driven Algorithms in Fault Diagnosis of Rotating Machinery[J]. Machine Tool & Hydraulics, 2020, 48(23):218-223.
[22]ZHANG Meiyang, ZHANG Zili. Small-scale Data Classification Based on Deep Forest[C]∥International Conference on Knowledge Science, Engineering and Management. Athens, 2019:428-439.
[23]郭庭炜. 基于信息熵与深度森林的蛋白质亚细胞位置预测[D].重庆:西南大学, 2019.
GUO Tingwei. Protein Subcellular Location Prediction Based on Information Entropy and Deep Forest[D]. Chongqing:Southwest University, 2019.
[24]YANG Liang, WU Xizhu, JIANG Yuan. Multi-Label Learning with Deep Forest[C]∥24th European Conference on Artificial Intelligence(ECAI). Santiago de Compostela, 2020:1634-1641.
[25]WANG Biao, LEI Yaguo, LI Naipeng, et al. A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings[J]. IEEE Transactions on Reliability, 2020, 69(1):401-412.
[26]苏乃权,熊建斌,张清华,等. 旋转机械故障诊断研究方法综述[J]. 机床与液压, 2018, 46(7):133-139.
SU Naiquan, XIONG Jianbin, ZHANG Qinghua, et al. Research Methods of the Rotating Machinery Fault Diagnosis[J]. Machine Tool & Hydraulics, 2018, 46(7):133-139.
[27]邵怡韦,陈嘉宇,林翠颖,等.小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法[J].航空学报, 2021, 42(增刊):25-29.
SHAO Yiwei, CHEN Jiayu, LIN Cuiying, et al. Gearbox Fault Diagnosis under Small Training Samples:an Improved Deep Forest Based Method[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(S):25-29.
[28]丁家满,吴晔辉,罗青波,等. 基于深度森林的轴承故障诊断方法[J]. 振动与冲击, 2021, 40(12):107-113.
DING Jiaman,WU Yehui,LUO Qingbo,et al. A Fault Diagnosis Method of Mechanical Bearing Based on the Deep Forest[J]. Journal of Vibration and Shock, 2021, 40(12):107-113.
[29]ANOWAR F, SADAOUI S, SELIM B. Conceptual and Empirical Comparison of Dimensionality Reduction Algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE)[J]. Computer Science Review, 2021, 40:100378.
[30]赵春华,胡恒星,陈保家,等. 基于深度学习特征提取和WOA-SVM状态识别的轴承故障诊断[J]. 振动与冲击, 2019, 38(10):31-37.
ZHAO Chunhua, HU Hengxing, CHEN Baojia, et al. Bearing Fault Diagnosis Based on the Deep Learning Feature Extraction and WOA SVM State Recognition[J]. Journal of Vibration and Shock, 2019, 38(10):31-37.
文章导航

/

〈 〉