Vibration signal component separation by iteratively using basis pursuit and its application in mechanical fault detection

2013 ◽  
Vol 332 (20) ◽  
pp. 5217-5235 ◽  
Author(s):  
Yi Qin ◽  
Yongfang Mao ◽  
Baoping Tang
Keyword(s):  
Fault Detection ◽  
Vibration Signal ◽  
Component Separation ◽  
Basis Pursuit ◽  
Signal Component

Development of a machine learning algorithm for fault detection in a cantilever beam

2021 ◽  
pp. 095745652110004
Author(s):  
Amit Kumar Gorai ◽  
Tarapada Roy ◽  
Sumeet Mishra
Keyword(s):  
Mechanical Properties ◽  
Fault Detection ◽  
Cantilever Beam ◽  
Learning Algorithm ◽  
Model Development ◽  
Vibration Signal ◽  
Beam Specimen ◽  
Discrete Wavelet ◽  
Feed Forward Network ◽  
Model Training

The mechanical properties of a component change with any type of damage such as crack development, generation of holes, bend, excessive wear, and tear. The change in mechanical properties causes the material to behave differently in terms of noise and vibration under different loading conditions. Thus, the present study aims to develop an artificial neural network model using vibration signal data for early fault detection in a cantilever beam. The discrete wavelet transform coefficients of de-noised vibration signals were used for model development. The vibration signal was recorded using the OROS OR35 module for different fault conditions (no fault, notch fault, and hole fault) of a cantilever beam. A feed-forward network was trained using backpropagation to map the input features to output. A total of 603 training datasets (201 datasets for three types of cantilever beam—no fault, notch fault, and hole fault) were used for training, and 201 datasets were used for testing of the model. The testing dataset was recorded for a hole fault cantilever beam specimen. The results indicated that the proposed model predicted the test samples with 78.6% accuracy. To increase the accuracy of prediction, more data need to be used in the model training.

scholarly journals Engine Fault Detection Approach Based on Angle Domain Signal Model

2021 ◽  
Vol 2068 (1) ◽  
pp. 012034
Author(s):  
Hai Zeng ◽  
Ning Zeng ◽  
Jin Han ◽  
Yan Ding
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Failure Detection ◽  
Vibration Signal ◽  
Bench Test ◽  
Signal Model ◽  
Vibration Signals ◽  
Engine Vibration ◽  
Detection Approach ◽  
Diagnosis Approach

Abstract Engine vibration signals include strong noise and non-stationary signals. By the time domain signal processing approach, it is hard to extract the failure features of engine vibration signals, so it is hard to identify engine failures. For improving the success rate of engine failure detection, an engine angle domain vibration signal model is established and an engine fault detection approach based on the signal model is proposed. The angle domain signal model reveals the modulation feature of the engine angular signal. The engine fault diagnosis approach based on the angle domain signal model involves equal angle sampling and envelope analysis of engine vibration signals. The engine bench test verifies the effectiveness of the engine fault diagnosis approach based on the angle domain signal model. In addition, this approach indicates a new path of engine fault diagnosis and detection.

Pattern Changes of Time-Shifted Vibration Signals on Wavelet Time-Scale Maps

1995 ◽  
Author(s):  
Da Jun Chen ◽  
Wei Ji Wang
Keyword(s):  
Wavelet Transform ◽  
Time Scale ◽  
Wavelet Transforms ◽  
Vibration Signal ◽  
Continuous Wavelet ◽  
Time Axis ◽  
Orthogonal Wavelet ◽  
Signal Component ◽  
Analysis Technique ◽  
Map Analysis

Abstract As a multi-resolution signal decomposition and analysis technique, the wavelet transforms have been already introduced to vibration signal processing. In this paper, a comparison on the time-scale map analysis is made between the discrete and the continuous wavelet transform. The orthogonal wavelet transform decomposes the vibration signal onto a series of orthogonal wavelet functions and the number of wavelets on one wavelet level is different from those on the other levels. Since the grids are unevenly distributed on the time-scale map, it is shown that a representation pattern of a vibration component on the map may be significantly altered or even be broken down into pieces when the signal has a shift along the time axis. On contrary, there is no such uneven distribution of grids on the continuous wavelet time-scale map, so that the representation pattern of a vibration signal component will not change its shape when the signal component shifts along the time axis. Therefore, the patterns in the continuous wavelet time-scale map are more easily recognised by human visual inspection or computerised automatic diagnosis systems. Using a Gaussian enveloped oscillation wavelet, the wavelet transform is capable of retaining the frequency meaning used in the spectral analysis, while making the interpretation of patterns on the time-scale maps easier.

Adaptive fault detection of the bearing in wind turbine generators using parameterless empirical wavelet transform and margin factor

2019 ◽  
Vol 25 (6) ◽  
pp. 1263-1278 ◽  
Author(s):  
Wei Teng ◽  
Wei Wang ◽  
Haixing Ma ◽  
Yibing Liu ◽  
Zhiyong Ma ◽  
...  
Keyword(s):  
Wavelet Transform ◽  
Fault Detection ◽  
Wind Turbines ◽  
Vibration Signal ◽  
Scale Space ◽  
Operating Conditions ◽  
Turbine Generators ◽  
Detection Approach ◽  
Empirical Wavelet Transform ◽  
Fault Information

Wind turbines revolve in difficult operating conditions due to stochastic loads and produce massive vibration signals, which cause obstacles in detecting potential fault information. To overcome this, an adaptive fault detection approach is presented in this paper on the basis of parameterless empirical wavelet transform (PEWT) and the margin factor. PEWT can decompose the vibration signal into a series of empirical modes (EMs) through splitting its Fourier spectrum, using the scale space method and adaptively constructing an orthogonal wavelet filter bank. The margin factor is utilized as a key metric for automatically selecting the EM which is sensitive to the potential faults. The method presented in this paper will improve the efficiency and accuracy of fault information for the condition monitoring of wind turbines.

scholarly journals Laplace Prior-Based Bayesian Compressive Sensing Using K-SVD for Vibration Signal Transmission and Fault Detection

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 517 ◽  
Author(s):  
Yunfei Ma ◽  
Xisheng Jia ◽  
Qiwei Hu ◽  
Daoming Xu ◽  
Chiming Guo ◽  
...  
Keyword(s):  
Fault Detection ◽  
Compressive Sensing ◽  
Health Management ◽  
Signal Transmission ◽  
Vibration Signal ◽  
Experimental Tests ◽  
Reconstructed Signal ◽  
Signal Simulation ◽  
Value Decomposition ◽  
Laplace Priors

Vibration signal transmission plays a fundamental role in equipment prognostics and health management. However, long-term condition monitoring requires signal compression before transmission because of the high sampling frequency. In this paper, an efficient Bayesian compressive sensing algorithm is proposed. The contribution is explicitly decomposed into two components: a multitask scenario and a Laplace prior-based hierarchical model. This combination makes full use of the sparse promotion under Laplace priors and the correlation between sparse blocks to improve the efficiency. Moreover, a K-singular value decomposition (K-SVD) dictionary learning method is used to find the best sparse representation of the signal. Simulation results show that the Laplace prior-based reconstruction performs better than typical algorithms. The comparison between a fixed dictionary and learning dictionary also illustrates the advantage of the K-SVD method. Finally, a fault detection case of a reconstructed signal is analyzed. The effectiveness of the proposed method is validated by simulation and experimental tests.

Fault Detection of Broken Rotor Bar Using an Improved form of Hilbert–Huang Transform

2018 ◽  
Vol 17 (02) ◽  
pp. 1850012 ◽  
Author(s):  
F. Sabbaghian-Bidgoli ◽  
J. Poshtan
Keyword(s):  
Signal Processing ◽  
Fault Detection ◽  
Hilbert Transform ◽  
Wavelet Packet ◽  
Amplitude Spectrum ◽  
Vibration Signal ◽  
External Noise ◽  
Vibration Signals ◽  
Broken Rotor Bar ◽  
Hilbert Huang Transform

Signal processing is an integral part in signal-based fault diagnosis of rotary machinery. Signal processing converts the raw data into useful features to make the diagnostic operations. These features should be independent from the normal working conditions of the machine and the external noise. The extracted features should be sensitive only to faults in the machine. Therefore, applying more efficient processing techniques in order to achieve more useful features that bring faster and more accurate fault detection procedure has attracted the attention of researchers. This paper attempts to improve Hilbert–Huang transform (HHT) using wavelet packet transform (WPT) as a preprocessor instead of ensemble empirical mode decomposition (EEMD) to decompose the signal into narrow frequency bands and extract instantaneous frequency and compares the efficiency of the proposed method named “wavelet packet-based Hilbert transform (WPHT)” with the HHT in the extraction of broken rotor bar frequency components from vibration signals. These methods are tested on vibration signals of an electro-pump experimental setup. Moreover, this project applies wavelet packet de-noising to remove the noise of vibration signal before applying both methods mentioned and thereby achieves more useful features from vibration signals for the next stages of diagnosis procedure. The comparison of Hilbert transform amplitude spectrum and the values and numbers of detected instantaneous frequencies using HHT and WPHT techniques indicates the superiority of the WPHT technique to detect fault-related frequencies as an improved form of HHT.

Sign in / Sign up

Export Citation Format

Share Document