强噪声条件下基于EMD-AE优选特征的离心泵多故障诊断方法

PDF(3561 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (23) : 66-74.

论文

强噪声条件下基于EMD-AE优选特征的离心泵多故障诊断方法

向明胜1,2，冯坤1,2，贾韶辉3，赵衍2,4

作者信息 +

Multi-fault diagnosis method for centrifugal pumps based on EMD-AE optimal selected features under strong noise conditions

XIANG Mingsheng1,2, FENG Kun1,2, JIA Shaohui3, ZHAO Yan2,4

Author information +

文章历史 +

摘要

工业离心泵故障诊断中常常受到噪声的干扰，针对这一问题，本文提出一种强噪声条件下基于经验模态分解和自编码器的优选特征方法。首先利用补偿距离评估技术确定出有效的时频特征，然后通过经验模态分解处理，得到包含不同尺度和频率特性的模态分量。通过能量比变异系数确定出有效的分析分量，通过提取出所选分量的有效特征，拼接构造高维的深度特征。最后通过自编码器对深度特征做降维处理，进一步优选特征，得到最终的故障敏感特征，完成特征提取。本文选用支持向量机作为故障诊断模型，通过工业离心泵多故障数据进行对比实验。结果表明所提方法在信噪比为-5dB、-7dB和-10dB强噪声干扰条件下，准确率较传统时频特征分别提高了6.13%、7.46%、12%。该方法有较强的抗噪声的能力，在噪声干扰下能有效提取表征设备状态的敏感特征。

Abstract

Noise frequently interferes with the fault diagnosis of industrial centrifugal pumps. To address this issue, this paper introduces a feature selection method that combines empirical mode decomposition and an autoencoder. Initially, effective time-frequency features are identified using compensation distance evaluation technology. Subsequently, modal components, which contain various scale and frequency features, are derived through empirical mode decomposition. The component with significant energy ratio variation is selected as the effective analysis component, from which effective features are extracted. These features are then concatenated to construct high-dimensional deep features. An autoencoder is subsequently utilized to reduce the dimensionality of these deep features, further refining the selection process to isolate the final fault-sensitive features for comprehensive feature extraction. In this study, a support vector machine is employed as the fault diagnosis model. Comparative analysis of multiple fault data from industrial centrifugal pumps demonstrates that the accuracy of the proposed method surpasses traditional time-frequency feature-based approaches by 6.13%、7.46% and 12% under -5dB, -7dB, and -10dB strong noise conditions, respectively. This method exhibits robust noise resistance and effectively extracts sensitive equipment state features under noise interference.

导出引用

向明胜1, 2, 冯坤1, 2, 贾韶辉3, 赵衍2, 4. 强噪声条件下基于EMD-AE优选特征的离心泵多故障诊断方法[J]. 振动与冲击, 2024, 43(23): 66-74

XIANG Mingsheng1, 2, FENG Kun1, 2, JIA Shaohui3, ZHAO Yan2, 4. Multi-fault diagnosis method for centrifugal pumps based on EMD-AE optimal selected features under strong noise conditions[J]. Journal of Vibration and Shock, 2024, 43(23): 66-74

参考文献

[1] 王青华, 杨天海, 沈润杰，等. 抽水蓄能机组振动故障诊断专家系统[J]. 振动与冲击, 2012, 31(07): 158-161+170.
WANG Qing-hua, Yang Tian-hai, Shen Run-jie et al. Expert System for Vibration Fault Diagnosis of pumped storage Unit [J]. Journal of Vibration and Shock, 2012, 31(07): 158-161+170.
[2] Yan C, Wang H, Zhou L, et al. Fault diagnosis expert system of turbine generator sets based on rule reasoning and case reasoning[J]. Applied Mechanics and Materials, 2014, 513: 4443-4448.
[3] 李进. 基于规则和相似度的海洋石油设备智能诊断技术研究[J]. 北京石油化工学院学报, 2019, 27(03): 17-21.
LI Jin. Research on intelligent diagnosis technology of offshore oil equipment based on rules and similarity [J]. Journal of Beijing Institute of Petrochemical Technology, 2019, 27(03): 17-21.
[4] Tamilselvan P, Wang P. A tri-fold hybrid classification approach for diagnostics with unexampled faulty states[J]. Mechanical Systems and Signal Processing, 2015, 50: 437-455.
[5] Muralidharan V, Sugumaran V, Indira V. Fault diagnosis of monoblock centrifugal pump using SVM[J]. Engineering Science and Technology, an International Journal, 2014, 17(3): 152-157.
[6] 王新, 闫文源. 基于变分模态分解和SVM的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(18):252-256.
Wang Xin, Yan Wenyuan. Fault Diagnosis of Rolling Bearing Based on Variational Mode Decomposition and SVM [J]. Journal of Vibration and Shock, 2017, 36(18):252-256.
[7] 何大伟,彭靖波,胡金海等. 基于改进FOA优化的CS-SVM轴承故障诊断研究[J]. 振动与冲击, 2018, 37(18):108-114.
He Dawei, Peng Jingbo, Hu Jinhai et al. Research on CS-SVM Bearing Fault Diagnosis Based on Improved FOA Optimization [J]. Journal of Vibration and Shock, 2018, 37(18):108-114.
[8] Zhao W, Wang Z, Lu C, et al. Fault diagnosis for centrifugal pumps using deep learning and softmax regression[C] 2016 12th world congress on intelligent control and automation (WCICA). IEEE, 2016: 165-169.
[9] 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.
[10] Li X, Li X, Ma H. Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery[J]. Mechanical Systems and Signal Processing, 2020, 143: 106825.
[11] 杜先君, 贾亮亮. 基于优化堆叠降噪自编码器的滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(12):2827-2838.
Du Xianjun, Jia Liangliang. Fault Diagnosis of Rolling Bearing Based on Optimized Stack noise reduction autoencoder [J]. Journal of Jilin University (Engineering and Technology Edition),2022,52(12):2827-2838.
[12] 齐咏生, 巩育瑞, 高胜利等. 基于中心损失-改进卷积自编码器的滚动轴承半监督故障诊断[J]. 振动与冲击, 2023, 42(07):301-311.
Qi Yongsheng, Gong Yurui, Gao Shengli, etc. Semi-supervised Fault diagnosis of rolling bearings based on Center loss-Improved Convolutional autoencoder [J]. Journal of Vibration and Shock, 2019, 42(07):301-311.
[13] Pan H, He X, Tang S, et al. An improved bearing fault diagnosis method using one-dimensional CNN and LSTM[J]. Strojniski Vestnik/Journal of Mechanical Engineering, 2018, 64.
[14] Hasan M J, Rai A, Ahmad Z, et al. A fault diagnosis framework for centrifugal pumps by scalogram-based imaging and deep learning[J]. IEEE Access, 2021, 9: 58052-58066.
[15] 焦瀚晖, 胡明辉, 江志农等. 基于补偿距离评估和一维卷积神经网络的离心泵故障快速智能识别方法[J]. 振动与冲击, 2021, 40(10):41-49.
Jiao Hanhui, HU Minghui, JIANG Zhinong et al. Fast and intelligent fault identification method of centrifugal pump based on compensation distance evaluation and one-dimensional convolutional neural network [J]. Journal of Vibration and Shock, 21,40(10):41-49.
[16] 宫文峰, 陈辉, 张泽辉等. 基于改进卷积神经网络的滚动轴承智能故障诊断研究[J].振动工程学报, 2020, 33(02):400-413.
Gong Wenfeng, Chen Hui, ZHANG Zehui et al. Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Convolutional Neural Network [J]. Journal of Vibration Engineering, 2019, 33(02):400-413.
[17] 李俊, 刘永葆, 余又红. 卷积神经网络和峭度在轴承故障诊断中的应用[J]. 航空动力学报, 2019, 34(11):2423-2431.
Li Jun, LIU Yongbao, YU Youhong. Application of Convolutional neural networks and Kurtosis in Bearing Fault Diagnosis [J]. Journal of Aerodynamics, 2019, 34(11):2423-2431.
[18] 吴佳, 李明宸, 唐文妍. 基于DTCNN-SVM的工业循环水系统供水泵故障诊断[J]. 振动与冲击, 2023, 42(13): 226-234.
Wu Jia, LI Ming-chen, TANG Wen-yan. Fault diagnosis of supply pump in industrial circulating water system based on DTCNN-SVM [J]. Vibration and shock, 2023, 42(13): 226-234.
[19] 蒋爱华, 张志谊, 章艺等. 离心泵噪声研究的综述和展望[J].振动与冲击, 2011, 30(02):77-84.
Jiang Aihua, Zhang Zhiyi, Zhang Yi, et al. Review and prospect of centrifugal pump noise research [J]. Journal of Vibration and Shock, 2011, 30(02):77-84.
[20] Han T, Jiang D. Fault diagnosis of multistage centrifugal pump unit using non-local means-based vibration signal denoising[J]. Eksploatacja i Niezawodność, 2019, 21(4).
[21] 卢军民, 刘照, 荀杰. 离心泵常见故障的诊断[J]. 煤矿机械, 2007(06): 180-182.
Lu Junmin, Liu Zhao, Xun Jie. Diagnosis of Common Faults of centrifugal Pump [J]. Coal Mine Machinery, 2007(06): 180-182.
[22] Lei Y, He Z, Zi Y, et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems and Signal Processing, 2008, 22(2): 419-435.
[23] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 1998, 454(1971): 903-995.
[24] 王宏超, 陈进, 董广明. 基于补偿距离评估-小波核PCA的滚动轴承故障诊断[J]. 振动与冲击, 2013, 32(18):87-90+94.
Wang Hongchao, Chen Jin, Dong Guangming. Fault diagnosis of Rolling Bearing based on compensated distance evaluation and wavelet kernel PCA [J]. Journal of Vibration and Shock, 2013, 32(18):87-90+94.
[25] Carroll J D, Arabie P. Multidimensional scaling[J]. Measurement, judgment and decision making, 1998: 179-250.
[26] Abdi H, Willians L J. Principal component analysis[J]. Wiley Interdisciplinary Reviews: Computational Statistics, 2010, 2(4): 433-459.