scholarly journals Rolling Bearing Fault Diagnosis Method Based on Multisynchrosqueezing S Transform and Faster Dictionary Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Guodong Sun ◽  
Ye Hu ◽  
Bo Wu ◽  
Hongyu Zhou
Keyword(s):  
Dictionary Learning ◽  
Nonnegative Matrix ◽  
Texture Features ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Time Frequency ◽  
Fault Recognition ◽  
S Transform ◽  
Diagnosis Method ◽  
Low Dimensional

Addressing the problem that it is difficult to extract the features of vibration signal and diagnose the fault of rolling bearing, we propose a novel diagnosis method combining multisynchrosqueezing S transform and faster dictionary learning (MSSST-FDL). Firstly, MSSST is adopted to transform vibration signals into high-resolution time-frequency images. Then, the local binary pattern (LBP) operator is introduced to extract the low-dimensional texture features of time-frequency images, which improves the speed of fault recognition. Finally, nonnegative matrix factorization (NMF) with only one hyperparameter and nonnegative linear equation are used to solve the dictionary learning and feature coding, respectively. The feature coding is input into the classifier for training and recognition. Experiments show that our method performs well on the rolling bearing dataset of Case Western Reserve University (CWRU) and the Society for Machinery Failure Prevention Technology (MFPT). Further, the proposed method is applied to the loudspeaker pure-tone detection dataset, and the loudspeaker anomaly diagnosis is achieved. The diagnosis results verify that our method can meet the needs of practical engineering.

scholarly journals Fine-Grained Fault Diagnosis Method of Rolling Bearing Combining Multisynchrosqueezing Transform and Sparse Feature Coding Based on Dictionary Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-13
Author(s):  
Guodong Sun ◽  
Yuan Gao ◽  
Kai Lin ◽  
Ye Hu
Keyword(s):  
Fault Diagnosis ◽  
Dictionary Learning ◽  
Nonnegative Matrix ◽  
Rolling Bearing ◽  
Fault Classification ◽  
Support Vector ◽  
Time Frequency ◽  
Fine Grained ◽  
Diagnosis Method

To accurately diagnose fine-grained fault of rolling bearing, this paper proposed a new fault diagnosis method combining multisynchrosqueezing transform (MSST) and sparse feature coding based on dictionary learning (SFC-DL). Firstly, the high-resolution time-frequency images of raw vibration signals, including different kinds of fine-grained faults of rolling bearing, were constructed by MSST. Then, the basis dictionary was trained through nonnegative matrix factorization with sparseness constraints (NMFSC), and the trained basis dictionary was employed to extract features from time-frequency matrixes by using nonnegative linear equations. Finally, a linear support vector machine (LSVM) was trained with features of training samples, and the trained LSVM was employed to diagnosis the fault classification of test samples. Compared with state-of-the-art fault diagnosis methods, the proposed method, which was tested on the bearing dataset from Case Western Reserve University (CWRU), achieved the fine-grained classification of 10 mixed fault states. Meanwhile, the proposed method was applied on the dataset from the Machinery Failure Prevention Technology (MFPT) Society and realized the classification of 3 fault states under different working conditions. These results indicate that the proposed method has great robustness and could better meet the needs of practical engineering.

Enhanced deep residual network with multilevel correlation information for fault diagnosis of rotating machinery

2020 ◽  
pp. 107754632094971 ◽  
Author(s):  
Shoucong Xiong ◽  
Shuai He ◽  
Jianping Xuan ◽  
Qi Xia ◽  
Tielin Shi
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Learning Algorithms ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Classification Performance ◽  
Residual Network ◽  
Time Frequency ◽  
Correlation Information

Modern machinery becomes more precious with the advance of science, and fault diagnosis is vital for avoiding economical losses or casualties. Among massive diagnosis methods, deep learning algorithms stand out to open an era of intelligent fault diagnosis. Deep residual networks are the state-of-the-art deep learning models which can continuously improve performance by deepening the network structures. However, in vibration-based fault diagnosis, the transient property instability of vibration signal usually calls for time–frequency analysis methods, and the characters of time–frequency matrices are distinct from standard images, which brings some natural limitations for the diagnosis performance of deep learning algorithms. To handle this issue, an enhanced deep residual network named the multilevel correlation stack-deep residual network is proposed in this article. Wavelet packet transform is used to preprocess the sensor signal, and then the proposed multilevel correlation stack-deep residual network uses kernels with different shapes to fully dig various kinds of useful information from any local regions of the processed input. Experiments on two rolling bearing datasets are carried out. Test results show that the multilevel correlation stack-deep residual network exhibits a more satisfactory classification performance than original deep residual networks and other similar methods, revealing significant potentials for realistic fault diagnosis applications.

Vibration-Based Fault Diagnosis of Pump Using WPT

2008 ◽  
Author(s):  
Pan Hong ◽  
Zheng Yuan
Keyword(s):  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Accurate Method ◽  
Singularity Analysis ◽  
Good Time ◽  
Signal Denoising ◽  
Good Tool ◽  
Time Frequency ◽  
Diagnosis Method

A vibration-based fault diagnosis method of pump units based on wavelet packet transform (WPT) is proposed in this paper. Compared with Fourier transform (FT) and wavelet transform (WT), WPT can subdivide the whole time-frequency domain. It can perform signals with good time resolution at high frequency and vice versa. WPT is considered as a good tool to signal denoising, accounting for its perfect ability in decomposing and reconstructing signal and its characteristic of no redundancy and divulges after denoising. In addition, WPT modulus maximal coefficient provides a simple but accurate method in calculating the Lipschitz exponents, which is the measurement of signal singularity. According to the singularity analysis results of vibration signal, we can recognize the fault pattern of pump units. This paper makes a detail research on signal denoising and singularity analysis based on WPT. Taking the main shaft and thrust bearing vibration signal for example, the experimental results show that WPT is effectively in the fault diagnosis system of pump unit.

A NewFault Detection and Diagnosis Method Based on Wigner-Ville Spectrum Entropy for the Rolling Bearing

2012 ◽  
Vol 197 ◽  
pp. 346-350 ◽  
Author(s):  
Ping Xie ◽  
Yu Xin Yang ◽  
Guo Qian Jiang ◽  
Yi Hao Du ◽  
Xiao Li Li
Keyword(s):  
Fault Detection ◽  
Rolling Bearing ◽  
Work Conditions ◽  
Fault Detection And Diagnosis ◽  
Vibration Signals ◽  
Time Frequency ◽  
Diagnosis Method ◽  
Bearing Vibration ◽  
Detection And Diagnosis ◽  
Critical Components

The rolling bearings are one of the most critical components in rotary machinery. To prevent unexpected bearing failure, it is crucial to develop the effective fault detection and diagnosis techniques to realize equipment’s near-zero downtime and maximum productivity. In this paper, a new fault detection and diagnosis method based on Wigner-Ville spectrum entropy (WVSE) is proposed. First, the local mean decomposition (LMD) and the Wigner-Ville distribution (WVD) are combined to develop a new feature extraction approach to extract the fault features in time-frequency domain of the bearing vibration signals. Second, the concept of the Shannon entropy is integrated into the WVD to define the Wigner-Ville spectrum entropy to quantify the energy variation in time-frequency distribution under different work conditions. The research results from the bearing vibration signals demonstrate that the proposed method based on WVSE can identify different fault patterns more accurately and effectively comparing with other methods based on singular spectrum entropy (SSE) or power spectrum entropy (PSE).

scholarly journals Nonnegative Matrix Factorization of time frequency representation of vibration signal for local damage detection – comparison of algorithms

2018 ◽  
Vol 29 ◽  
pp. 00010
Author(s):  
Jacek Wodecki
Keyword(s):  
Damage Detection ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Single Channel ◽  
Classical Method ◽  
Nonnegative Matrix ◽  
Vibration Signal ◽  
Local Damage ◽  
Time Frequency ◽  
Frequency Representation

Local damage detection in rotating machine elements is very important problem widely researched in the literature. One of the most common approaches is the vibration signal analysis. Since time domain processing is often insufficient, other representations are frequently favored. One of the most common one is time-frequency representation hence authors propose to separate internal processes occurring in the vibration signal by spectrogram matrix factorization. In order to achieve this, it is proposed to use the approach of Nonnegative Matrix Factorization (NMF). In this paper three NMF algorithms are tested using real and simulated data describing single-channel vibration signal acquired on damaged rolling bearing operating in drive pulley in belt conveyor driving station. Results are compared with filtration using Spectral Kurtosis, which is currently recognized as classical method for impulsive information extraction, to verify the validity of presented methodology.

A rolling bearing fault diagnosis method based on fastDTW and an AGBDBN

2020 ◽  
Vol 62 (8) ◽  
pp. 457-463 ◽  
Author(s):  
Shang Zhiwu ◽  
Liu Xia ◽  
Li Wanxiang ◽  
Gao Maosheng ◽  
Yu Yan
Keyword(s):  
Fault Diagnosis ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Deep Belief Network ◽  
Residual Vector ◽  
Belief Network ◽  
Network Training ◽  
Diagnosis Method ◽  
Stationary Vibration ◽  
Dynamic Time

In order to improve fault feature extraction and diagnosis for rolling bearings, a fault diagnosis method based on fast dynamic time warping (fastDTW) and an adaptive Gaussian-Bernoulli deep belief network (AGBDBN) is proposed in this paper. Firstly, for the non-stationary vibration signal characteristics of the bearing, the fastDTW algorithm is used to calculate the residual vector of the fault signal, thereby enhancing the fault characteristic information. Then, according to the continuous vibration value of the bearing vibration signal, a standard deep belief network (DBN) is improved to deal with the problem that the optimal setting for the learning rate is difficult to achieve in the deep neural network training process and the AGBDBN model is used for fault diagnosis. Finally, the proposed method is compared with a variety of model diagnosis methods. The experimental results show that the proposed method achieved good diagnostic results.

Blasting Vibration Signals Time-Frequency Analysis Based on S-Transform

2012 ◽  
Vol 588-589 ◽  
pp. 2013-2017
Author(s):  
Dong Tao Li ◽  
Jing Long Yan ◽  
Le Zhang
Keyword(s):  
Frequency Analysis ◽  
Vibration Signal ◽  
Transformation Method ◽  
Blasting Vibration ◽  
Time Duration ◽  
Vibration Signals ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
S Transform ◽  
Vibration Wave

Introduced the theory of S-transform, designed simulation experiment and the frequency components distribution versus time was, verified that the S-transformation method is suitable for blasting vibration signal time-frequency analyzed. Applied it to the time-frequency analysis of measured blasting vibration signals at situ, the results show that S-transform has excellent time-frequency representation ability and higher resolution, reveals the detail information of blasting vibration wave changing with time and frequency, and provides a new way for blasting vibration research. Determined the desired delay intervals through comparing the energy of signal and the time duration of the waveform at characteristic frequency between two-hole blasting vibration signals with different delay intervals.

Gear fault diagnosis based on time–frequency domain de-noising using the generalized S transform

2017 ◽  
Vol 24 (15) ◽  
pp. 3338-3347 ◽  
Author(s):  
Jianhua Cai ◽  
Xiaoqin Li
Keyword(s):  
Fault Diagnosis ◽  
Frequency Domain ◽  
Vibration Signal ◽  
Time Frequency ◽  
Transmission Modes ◽  
S Transform ◽  
Mining Machinery ◽  
Gear Fault ◽  
Generalized S Transform ◽  
Gear Fault Diagnosis

Gears are the most important transmission modes used in mining machinery, and gear faults can cause serious damage and even accidents. In the work process, vibration signals are influenced not only by friction, nonlinear stiffness, and nonstationary loads, but also by strong noise. It is difficult to separate the useful information from the noise, which brings some trouble to the fault diagnosis of mining machinery gears. The generalized S transform has the advantages of the short time Fourier transform and wavelet transform and is reversible. The time–frequency energy distribution of the gear vibration signal can be accurately presented by the generalized S transform, and a time–frequency filter factor can be constructed to filter the vibration signal in the time–frequency domain. These characteristics play an important role when the generalized S transform is used to remove the noise in the time–frequency domain. In this paper, a new gear fault diagnosis based on the time–frequency domain de-noising is proposed that uses the generalized S transform. The application principle, method steps, and evaluation index of the method are presented, and a wavelet soft-threshold filtering method is implemented for comparison with the proposed approach. The effectiveness of the proposed method is demonstrated by numerical simulation and experimental investigation of a gear with a tooth crack. Our analyses also indicate that the proposed method can be used for fault diagnosis of mining machinery gears.

Information Fusion of the Vibration and Acoustic Signals Based Rolling Bearing Incipient Fault Diagnosis Method

2013 ◽  
Vol 774-776 ◽  
pp. 1499-1502
Author(s):  
Ting Feng Ming ◽  
Yong Xiang Zhang ◽  
Jing Li
Keyword(s):  
Fault Diagnosis ◽  
Correlation Analysis ◽  
Information Fusion ◽  
Vibration Signal ◽  
Acoustic Resonance ◽  
Rolling Bearing ◽  
Rolling Bearings ◽  
Diagnosis Method ◽  
Incipient Fault ◽  
Fusion Analysis

The feature of correlation analysis were described and applied to analyzing the vibration signal of the gearbox. Aiming to that the diagnosis effect of the rolling bearings incipient fault was not good through the vibration spectrum and the resonance demodulation spectrum directly, the information fusion technology based on the correlation analysis is proposed to processing the vibration and acoustic resonance demodulation signal. The experimental results show that the presented correlation fusion analysis technology can be as the basis of the effective fault diagnosis method for the rolling bearings incipient defect.

Sign in / Sign up

Export Citation Format

Share Document