Feature extraction of gear and bearing compound faults based on vibration signal sparse decomposition

2022 ◽  
Vol 189 ◽  
pp. 108604
Author(s):  
Guolin He ◽  
Jianlin Li ◽  
Kang Ding ◽  
Zhigang Zhang
Keyword(s):  
Feature Extraction ◽  
Vibration Signal ◽  
Sparse Decomposition

Feature extraction of latent fault components of rolling bearing based on self-learned sparse atomics and frequency band entropy

2020 ◽  
pp. 107754632092566 ◽  
Author(s):  
HongChao Wang ◽  
WenLiao Du
Keyword(s):  
Feature Extraction ◽  
Frequency Band ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Sparse Decomposition ◽  
Vibration Data ◽  
Fault Features ◽  
Band Pass

As the key rotating parts in machinery, it is crucial to extract the latent fault features of rolling bearing in machinery condition monitoring to avoid the occurrence of sudden accidents. Unfortunately, the latent fault features are hard to extract by using the traditional signal processing method such as envelope demodulation because the effect of envelope demodulation is influenced strongly by the degree of background noise. Sparse decomposition, as a new promising method being able of capturing the latent fault feature components buried in the vibration signal, has attracted a lot of attentions, especially the predefined dictionary-based sparse decomposition methods. However, the feature extraction effect of the predefined dictionary-based sparse decomposition depends on whether the prior knowledge of the analyzed signal is sufficient or not. To overcome the above problems, a feature extraction method of latent fault components of rolling bearing based on self-learned sparse atomics and frequency band entropy is proposed in the article. First, a self-learned sparse atomics method is applied on the early weak vibration signal of rolling bearing and several self-learned atomics are obtained. Then, the self-learned atomics owing bigger kurtosis values are selected and used to reconstruct the vibration signal to remove the other interference signals. Subsequently, the frequency band entropy method is used to analyze the reconstructed vibration signal, and the optimal parameter of band-pass filter could be calculated. At last, the reconstructed vibration signal is filtered using the optimal band-pass filter, envelope demodulation on the filtered signal is applied, and better fault feature is extracted. The feasibility and effectiveness of the proposed method are verified through the vibration data of the accelerated fatigue life test of rolling bearing. Besides, the analysis results of the same vibration data using Autogram and spectral kurtosis methods are also presented to highlight the superiority of the proposed method.

scholarly journals Survey of Marine Organisms Based on Passive Acoustic Technology

2020 ◽  
Vol 15 (5) ◽  
pp. 729-737
Author(s):  
Gong Chen ◽  
Lei Cai ◽  
Lv Zong ◽  
Yan Wang ◽  
Xin Yuan
Keyword(s):  
Feature Extraction ◽  
Acoustic Signal ◽  
Extraction Method ◽  
Acoustic Signals ◽  
Marine Organisms ◽  
Decomposition Algorithm ◽  
Sparse Decomposition ◽  
Feature Extraction Method ◽  
Fish Detection ◽  
Passive Acoustic

Passive acoustic technology (PAT) is an important tool to acquire the passive acoustic signals from marine organisms. In this paper, PAT fish detection is introduced at great length, including the relevant instruments, signal processing methods, and workflow. Focusing on the key tasks of PAT fish detection, the authors proposed a sparse decomposition algorithm that extracts coherent ratio of passive fish acoustic signal, and designed a feature extraction method for that signal based on speech imitation technology. Experimental results demonstrate that the proposed sparse decomposition algorithm can detect fish acoustic signal accurately at low signal-to-noise ratios (SNRs), and the proposed feature extraction method can effectively extract fish acoustic signals from the marine background. The research results shed important new light on the protection and management of fishery resources in the seas and oceans.

scholarly journals Intelligent Fault Diagnosis and Forecast of Time-Varying Bearing Based on Deep Learning VMD-DenseNet

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7467
Author(s):  
Shih-Lin Lin
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Vibration Signal ◽  
Image Feature ◽  
Signal Acquisition ◽  
Time Varying ◽  
Intelligent Fault Diagnosis ◽  
Image Block ◽  
Wide Range

Rolling bearings are important in rotating machinery and equipment. This research proposes variational mode decomposition (VMD)-DenseNet to diagnose faults in bearings. The research feature involves analyzing the Hilbert spectrum through VMD whereby the vibration signal is converted into an image. Healthy and various faults show different characteristics on the image, thus there is no need to select features. Coupled with the lightweight network, DenseNet, for image classification and prediction. DenseNet is used to build a model of motor fault diagnosis; its structure is simple, and the calculation speed is fast. The method of using DenseNet for image feature learning can perform feature extraction on each image block of the image, providing full play to the advantages of deep learning to obtain accurate results. This research method is verified by the data of the time-varying bearing experimental device at the University of Ottawa. Through the four links of signal acquisition, feature extraction, fault identification, and prediction, a mechanical intelligent fault diagnosis system has established the state of bearing. The experimental results show that the method can accurately identify four common motor faults, with a VMD-DenseNet prediction accuracy rate of 92%. It provides a more effective method for bearing fault diagnosis and has a wide range of application prospects in fault diagnosis engineering. In the future, online and timely diagnosis can be achieved for intelligent fault diagnosis.

scholarly journals A Fiber Vibration Signal Identification Method Based on the Combination of EWT-FE and LSTM

2021 ◽  
Vol 2112 (1) ◽  
pp. 012020
Author(s):  
Xin Zhang ◽  
Qingmo Ja ◽  
SaiSai Ruan ◽  
Qin Hu
Keyword(s):  
Feature Extraction ◽  
Recognition Rate ◽  
Real Life ◽  
Vibration Signal ◽  
Machine Learning Algorithms ◽  
Signal Identification ◽  
Feature Vectors ◽  
Identification Method ◽  
Effective Manner ◽  
Empirical Wavelet Transform

Abstract As the optical fiber perimeter security system is widely used in real life, how to identify the types of intrusion events in a timely and effective manner is becoming a major research hotspot. At present, in this field, various signal feature extraction algorithms are usually used to extract intrusion signal features to form feature vectors, and then machine learning algorithms are used to classify the feature vectors to achieve the role of identifying the types of intrusion events. As a common signal feature extraction algorithm, the EMD algorithm has been widely used in the feature extraction of various vibration signals, but it will have the problem of modal aliasing and affect the feature extraction effect of the signal. Therefore, EWT, VMD and other algorithms have been successively used proposed to improve modal aliasing. On the basis of fully comparing the existing algorithms, this paper proposes a fiber vibration signal identification method that decomposes the signal through the empirical wavelet transform (EWT) algorithm and then extracts the fuzzy entropy (FE) of each component, and uses LSTM for classification. The final experiment shows that the method can identify four kinds of fiber intrusion signals in time and effectively, with an average recognition accuracy rate of 97.87%, especially for flap and knock recognition rate of 100%.

A fractal-dimension-based envelope demodulation for rolling element bearing fault feature extraction from vibration signals

2016 ◽  
Vol 230 (18) ◽  
pp. 3194-3211 ◽  
Author(s):  
Juanjuan Shi ◽  
Ming Liang
Keyword(s):  
Feature Extraction ◽  
Fractal Dimension ◽  
Search Algorithm ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Bearing Condition Monitoring ◽  
Interference Frequency ◽  
Fault Feature Extraction

Vibration analysis has been extensively used as an effective tool for bearing condition monitoring. The vibration signal collected from a defective bearing is, however, a mixture of several signal components including the fault feature (i.e. fault-induced impulses), periodic interferences from other mechanical/electrical components, and background noise. The incipient impulses which excite as well as modulate the resonance frequency of the system are easily masked by compounded effects of periodic interferences and noise, making it challenging to do a reliable fault diagnosis. As such, this paper proposes an envelope demodulation method termed short time fractal dimension (STFD) transform for fault feature extraction from such vibration signal mixture. STFD transform calculation related issues are first addressed. Then, by STFD, the original signal can be quickly transformed into a STFD representation, where the envelope of fault-induced impulses becomes more pronounced whereas interferences are partly weakened due to their morphological appearance differences. It has been found that the lower the interference frequency, the less effect the interference has on STFD representations. When interference frequency keeps increasing, more effects on STFD representations will be resulted. Such effects can be reduced by the proposed kurtosis-based peak search algorithm (KPSA). Therefore, bearing fault signature is kept and interferences are further weakened in the STFD-KPSA representation. The proposed method has been favourably compared with two widely used enveloping methods, i.e. multi-morphological analysis and energy operator, in terms of extracting impulse envelopes from vibration signals obscured by multiple interferences. Its performance has also been examined using both simulated and experimental data.

scholarly journals Mechanical Fault Diagnosis of a High Voltage Circuit Breaker Based on High-Efficiency Time-Domain Feature Extraction with Entropy Features

Entropy ◽  
2020 ◽  
Vol 22 (4) ◽  
pp. 478 ◽  
Author(s):  
Jiajin Qi ◽  
Xu Gao ◽  
Nantian Huang
Keyword(s):  
Feature Extraction ◽  
High Voltage ◽  
Time Domain ◽  
High Efficiency ◽  
Circuit Breaker ◽  
Vibration Signal ◽  
Feature Subset ◽  
High Voltage Circuit Breaker ◽  
Optimal Feature Subset ◽  
Optimal Feature

The fault samples of high voltage circuit breakers are few, the vibration signals are complex, the existing research methods cannot extract the effective information in the features, and it is easy to overfit, slow training, and other problems. To improve the efficiency of feature extraction of a circuit breaker vibration signal and the accuracy of circuit breaker state recognition, a Light Gradient Boosting Machine (LightGBM) method based on time-domain feature extraction with multi-type entropy features for mechanical fault diagnosis of the high voltage circuit breaker is proposed. First, the original vibration signal of the high voltage circuit breaker is segmented in the time domain; then, 16 features including 5 kinds of entropy features are extracted directly from each part of the original signal after time-domain segmentation, and the original feature set is constructed. Second, the Split importance value of each feature is calculated, and the optimal feature subset is determined by the forward feature selection, taking the classification accuracy of LightGBM as the decision variable. After that, the LightGBM classifier is constructed based on the feature vector of the optimal feature subset, which can accurately distinguish the mechanical fault state of the high voltage circuit breaker. The experimental results show that the new method has the advantages of high efficiency of feature extraction and high accuracy of fault identification.

Sign in / Sign up

Export Citation Format

Share Document