基于稀疏滤波和长短期记忆网络的旋转机械故障诊断方法

李益兵1,2,曹睿1,江丽1,2

振动与冲击 ›› 2022, Vol. 41 ›› Issue (19) : 144-151.

PDF(3249 KB)
PDF(3249 KB)
振动与冲击 ›› 2022, Vol. 41 ›› Issue (19) : 144-151.
论文

基于稀疏滤波和长短期记忆网络的旋转机械故障诊断方法

  • 李益兵1,2,曹睿1,江丽1,2
作者信息 +

Fault diagnosis method of rotating machinery based on sparse filtering and long-short term memory network

  • LI Yibing1,2, CAO Rui1, JIANG Li1,2
Author information +
文章历史 +

摘要

针对原始振动信号不可避免的包含多余噪声问题,提出一种基于稀疏滤波(Sparse Filtering, SF)和长短期记忆网络(Long and Short Term Memory network, LSTM)相结合的旋转机械故障诊断模型,该模型利用快速傅立叶变换将原始时域信号转换成频域信号,再通过SF提取低维故障特征,并将其输入到LSTM堆叠分类器中识别旋转机械故障状态。用轴承和齿轮振动信号为例开展实验研究,并与Softmax、深度神经网络(Deep Neural Networks,DNN)、支持向量机(Support Vector Machine, SVM)、降噪自编码器(Denoising Auto-Encoder,DAE)等方法进行实验对比,结果表明本文所提方法不仅在噪声环境下具有更高的准确率和鲁棒性,而且针对数据不平衡集的诊断也能达到98%以上的准确率。
关键词:旋转机械;特征提取;稀疏滤波;长短期记忆网络;故障诊断

Abstract

Aiming at the problem that the original vibration signal inevitably contains redundant noises, a rotating machinery fault diagnosis model based on Sparse Filtering (SF) and Long and Short-Term Memory network (LSTM) is proposed in this paper. In this model, the original time-domain signals are converted into frequency domain signals by Fast Fourier Transform(FFT), and then the low-dimensional fault features are extracted by SF, which are input into the LSTM stack classifier to identify the fault condition of rotating machinery. The vibration signals of bearings and gears are taken as examples to carry out experimental verification, and compared with Softmax, Deep Neural Networks (DNN), Support Vector Machine (SVM), Denoising Autoencoder (DAE) and other methods. The results show that the proposed method not only has higher accuracy and robustness in noise environment, but also can achieve more than 98% accuracy in the diagnosis of unbalanced data sets.
Key words: rotating machinery; feature extraction; sparse filtering; long and short-term memory network; fault diagnosis

关键词

旋转机械 / 特征提取 / 稀疏滤波 / 长短期记忆网络 / 故障诊断

Key words

rotating machinery / feature extraction / sparse filtering / long and short-term memory network / fault diagnosis

引用本文

导出引用
李益兵1,2,曹睿1,江丽1,2. 基于稀疏滤波和长短期记忆网络的旋转机械故障诊断方法[J]. 振动与冲击, 2022, 41(19): 144-151
LI Yibing1,2, CAO Rui1, JIANG Li1,2. Fault diagnosis method of rotating machinery based on sparse filtering and long-short term memory network[J]. Journal of Vibration and Shock, 2022, 41(19): 144-151

参考文献

[1] Li H, Lian X, Guo C, et al. Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination[J]. Journal of Intelligent Manufacturing, 2015,26(1):189-198.
 [2] Gangsar P, Tiwari R. Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review[J]. Mechanical Systems and Signal Processing, 2020,144(106908).
 [3] 刘湘楠, 赵学智, 上官文斌. 强背景噪声振动信号中滚动轴承故障冲击特征提取[J]. 振动工程学报, 2021,34(01):202-210.
 Liu Xiangnan, Zhao Xuezhi, Shangguan Wenbin. Extraction of impact characteristics of rolling bearing faults in strong background noise vibration signals[J]. Chinese Journal of Vibration Engineering, 2021,34(01):202-210.
 [4] 朱兴统. 旋转机械智能故障诊断方法的研究[D]. 广东工业大学, 2020.
 Zhu Xingtong. Research on Intelligent Fault Diagnosis Method of Rotating Machinery[D]. Guangdong University of Technology, 2020.
 [5] 陈辉, 李伟光, 林鑫, 等. 谱峭度方法在柔性薄壁轴承故障特征频率提取中的应用[J]. 振动与冲击, 2020,39(01):131-139.
 Chen Hui, Li Weiguang, Lin Xin, et al. Application of spectral kurtosis method in the extraction of fault characteristic frequencies of flexible thin-walled bearings[J]. Journal of Vibration and Shock, 2020,39(01):131-139.
 [6] 郑义, 岳建海, 焦静, 等. 基于参数优化变分模态分解的滚动轴承故障特征提取方法[J]. 振动与冲击, 2021,40(01):86-94.
 Zheng Yi, Yue Jianhai, Jiao Jing, et al. Rolling bearing fault feature extraction method based on parameter optimization variational modal decomposition[J]. Journal of Vibration and Shock, 2021,40(01):86-94.
 [7] Cheng Q, Zhao Z, Tang C, et al. Diagnostic of transformer winding deformation fault types using continuous wavelet transform of pulse response[J]. MEASUREMENT, 2019,140:197-206.
 [8] 包文杰, 涂晓彤, 李富才, 等. 参数化的短时傅里叶变换及齿轮箱故障诊断[J]. 振动.测试与诊断, 2020,40(02):272-277.
 Bao Wenjie, Tu Xiaotong, Li Fucai, et al. Parametric short-time Fourier transform and gearbox fault diagnosis[J]. Journal of Vibration. Test & Diagnosis, 2020,40(02):272-277.
 [9] 田晶, 王英杰, 王志, 等. 基于EEMD与空域相关降噪的滚动轴承故障诊断方法[J]. 仪器仪表学报, 2018,39(07):144-151.
 Tian Jing, Wang Yingjie, Wang Zhi, et al. Rolling bearing fault diagnosis method based on EEMD and airspace related noise reduction[J]. Chinese Journal of Scientific Instrument, 2018,39(07):144-151.
[10] 刘义亚, 李可, 陈鹏. 基于同步压缩小波变换的滚动轴承故障诊断[J]. 中国机械工程, 2018,29(05):585-590.
 Liu Yiya, Li Ke, Chen Peng. Fault diagnosis of rolling bearing based on synchronously compressed wavelet transform[J]. China Mechanical Engineering, 2018,29(05):585-590.
[11] 谢佳琪. 深度学习框架下的旋转机械故障诊断研究[D]. 苏州大学, 2020.
 Xie Jiaqi. Research on Fault Diagnosis of Rotating Machinery under the Framework of Deep Learning[D]. Soochow University, 2020.
[12] Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019,115:213-237.
[13] Guo Y, Zhou Y, Zhang Z. Fault diagnosis of multi-channel data by the CNN with the multilinear principal component analysis[J]. Measurement, 2021,171(108513).
[14] Chen X, Zhang B, Gao D. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021, 32: 971-987.
[15] Li Y, Zou L, Jiang L, et al. Fault Diagnosis of Rotating Machinery Based on Combination of Deep Belief Network and One-dimensional Convolutional Neural Network[J]. IEEE Access, 2019,7:165710-165723.
[16] Zhang Z, Chen H, Li S, et al. Sparse filtering based domain adaptation for mechanical fault diagnosis[J]. Neurocomputing, 2020,393:101-111.
[17] Lei Y, Jia F, Lin J, et al. An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data[J]. IEEE Transactions on Industrial Electronics, 2016,63(5):3137-3147.
[18] Cao L, Qian Z, Zareipour H, et al. Fault Diagnosis of Wind Turbine Gearbox Based on Deep Bi-Directional Long Short-Term Memory Under Time-Varying Non-Stationary Operating Conditions[J]. IEEE Access, 2019,7:155219-155228.
[19] Jalayer M, Orsenigo C, Vercellis C. Fault detection and diagnosis for rotating machinery: A model based on convolutional LSTM, Fast Fourier and continuous wavelet transforms[J]. Computers in Industry, 2021, 125: 103378.
[20] Qian Q, Qin Y, Wang Y, et al. A new deep transfer learning network based on convolutional auto-encoder for mechanical fault diagnosis[J]. Measurement, 2021,178(109352).
[21] Jin G, Zhu T, Akram M W, et al. An Adaptive Anti-Noise Neural Network for Bearing Fault Diagnosis Under Noise and Varying Load Conditions[J]. IEEE Access, 2020,8:74793-74807.
[22] Zhang W, Li C, Peng G, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018,100:439-453.
[23] Bubryur K, N. Y, K. R S P, et al. Surface crack detection using deep learning with shallow CNN architecture for enhanced computation[J]. Neural Computing and Applications, 2021(prepublish).
[24] Ngiam J, Koh P W, Chen Z, et al. Sparse Filtering[J]. Adv. Neural Inform, Process. Syst, 2011:1125-1133.
[25] Zhang Z, Li S, Wang J, et al. Enhanced sparse filtering with strong noise adaptability and its application on rotating machinery fault diagnosis[J]. Neurocomputing, 2020,398:31-44.
[26] Jia G, Lu Y, Lu W, et al. Verification method for Chinese aviation radiotelephony readbacks based on LSTM-RNN[J]. Electronics Letters, 2017, 53(6): 401-403.
[27] 李娟. 基于LSTM的齿轮箱故障诊断方法研究[D]. 湖南大学, 2019.
 Li Juan. Research on fault diagnosis method of gearbox based on LSTM[D]. Hunan University, 2019.
[28] Fabio M Z, Ke C. Towards understanding sparse filtering: A theoretical perspective[J]. Neural Networks, 2018,98:154-177.
[29] Yang Z, Chaobo Z, Yiwen Z, et al. A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis[J]. Energy and Built Environment, 2020,1(2):149-164.
[30] Kong W, Dong Z Y, Jia Y, et al. Short-term residential load forecasting based on LSTM recurrent neural network[J]. IEEE Transactions on Smart Grid, 2017, 10(1): 841-851.
[31] Cabrera D, Guamán A, Zhang S, et al. Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor[J]. Neurocomputing, 2020, 380: 51-66.
[32] Loparo K. A. Bearings Vibration Data Set[Db/Ol][J]. Cleveland, Ohio:Case Western Reserve University, 2014:http://Csegroups. Case. Edu/Bearingdatacenter/Home
[33] Liu J, Hu Y, Wang Y, et al. An integrated multi-sensor fusion-based deep feature learning approach for rotating machinery diagnosis[J]. Measurement Science and Technology, 2018, 29(5): 055103.
[34] Karim F, Majumdar S, Darabi H, et al. LSTM Fully Convolutional Networks for Time Series Classification[J]. IEEE Access, 2018,6:1662-1669.

PDF(3249 KB)

Accesses

Citation

Detail

段落导航
相关文章

/