Using Feature Selection to Determine Optimal Depth for Wavelet Packet Decomposition of Vibration Signals for Ocean System Reliability

2011 ◽  
Author(s):  
Randall Wald ◽  
Taghi M. Khoshgoftaar ◽  
John C. Sloan
Keyword(s):  
Feature Selection ◽  
System Reliability ◽  
Wavelet Packet ◽  
Wavelet Packet Decomposition ◽  
Vibration Signals ◽  
Optimal Depth

Study on a Novel Bearing Fault Diagnosis Method from Frequency and Energy Perspective

2017 ◽  
Vol 18 (6) ◽  
Author(s):  
Xiumei Li ◽  
Yong Liu ◽  
Huiming Zhao ◽  
Wu Deng
Keyword(s):  
Wavelet Packet ◽  
Bottom Layer ◽  
Wavelet Packet Decomposition ◽  
Rolling Element Bearings ◽  
Vibration Signals ◽  
Bearing Faults ◽  
Bearing Fault Diagnosis ◽  
Rolling Element ◽  
Organic Combination ◽  
Component Faults

AbstractEarly identification of faults in rolling element bearings is a challenging task; especially extracting transient characteristics from a noisy signal and identifying bearings fault become critical steps. In this paper, a novel method for real time fault detection in rolling element bearings is proposed to deal with non-stationary fault signals from frequency and energy perspective. Second-order blind identification (SOBI) and wavelet packet decomposition are organically integrated to diagnose the early bearing faults, the fault vibration signals are processed by SOBI algorithm, and feature information is extracted; meanwhile, fault vibration signals are decomposed by the wavelet packet, the energy of terminal nodes(at the bottom layer of wavelet packet decomposition) are analyzed because the energy of terminal nodes has different sensitive to different component faults. Therefore, the bearing faults can be diagnosed by organic combination of fault characteristic frequency analysis and energy of the terminal nodes, and the effectiveness, feasibility and robustness of the proposed method have been verified by experimental data.

FEATURE SELECTION FOR OPTIMIZATION OF WAVELET PACKET DECOMPOSITION IN RELIABILITY ANALYSIS OF SYSTEMS

2013 ◽  
Vol 22 (05) ◽  
pp. 1360011 ◽  
Author(s):  
RANDALL WALD ◽  
TAGHI M. KHOSHGOFTAAR ◽  
JOHN C. SLOAN
Keyword(s):  
Data Mining ◽  
Feature Selection ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Machine Learning Algorithms ◽  
Wavelet Packet Decomposition ◽  
Time Frequency ◽  
Speed Up ◽  
Frequency Domain Techniques ◽  
Feature Selection Techniques

One of the most important types of signal found in the area of machine condition monitoring/prognostic health monitoring (MCM/PHM) is the vibration signal, a type of waveform. Many time-frequency domain techniques have been proposed to interpret such signals, including wavelet packet decomposition (WPD). Previous work has shown how to extend the WPD algorithm to operate on streaming signals, but the number of output variables becomes exponential in the number of levels of decomposition, hindering data mining in limited-memory environments. Feature selection techniques, well understood in other areas of data mining, can be used to greatly reduce the number of output variables and speed up the machine learning algorithms. This paper presents a case study comparing two versions of WPD both with and without feature selection, demonstrating that removing most of the features produced by the WPD does not impair its performance within the context of MCM/PHM.

Time-Frequency Characteristics of Vibration Signals Analysis for Large Instantaneous Impact Mill Rolling Based on Wavelet Packet

2013 ◽  
Vol 834-836 ◽  
pp. 1061-1064
Author(s):  
Qi Jun Xiao ◽  
Zhong Hui Luo
Keyword(s):  
Time Domain ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Signal Wave ◽  
Reconstruction Technique ◽  
Wavelet Packet Decomposition ◽  
Vibration Signals ◽  
Time Frequency ◽  
Impact Vibration ◽  
Signal Time

The wavelet packet decomposition and reconstruction technique is applied to time-frequency analysis of bite steel impact vibration signal by big rolling machine, it is obtained the bite steel impact signal wave packet. According to the size of the wavelet packet energy, it is reconstructed the signal of No.1 and No.2 wavelet packet. According to reconstruction of the signal time domain waveform and FFT spectrum chart, some meaningful conclusions are obtained.

scholarly journals Feature extraction for fault diagnosis based on wavelet packet decomposition: An application on linear rolling guide

2018 ◽  
Vol 10 (8) ◽  
pp. 168781401879636 ◽  
Author(s):  
Hutian Feng ◽  
Rong Chen ◽  
Yiwei Wang
Keyword(s):  
Fault Diagnosis ◽  
Energy Distribution ◽  
Wavelet Packet ◽  
Numerical Control ◽  
Wavelet Packet Decomposition ◽  
Vibration Signals ◽  
Time Frequency ◽  
Good Ability ◽  
Rolling Guide ◽  
Lubrication Conditions

Linear rolling guide is increasingly being used as the transmission system in computer numerical control machine tools due to its high stiffness, low friction, good ability of precision retaining, and so on. The lubrication of rolling linear guide affects significantly its performance and hence monitoring the lubrication condition during its operation is of great importance. In this article, the relation between different lubrication conditions of linear rolling guide and their corresponding vibration signals is studied. Three lubrication conditions labeled as “Poor,”“Medium,” and “Good” are simulated to represent the actual working conditions. A data acquisition system is set up to acquire the vibration signals corresponding to different conditions. The wavelet packet decomposition is employed to perform time–frequency analysis of the raw signal, after which the energy distribution of the decomposed signals is extracted as the feature. Two linear rolling guides manufactured by different companies are used in the experiments. The results demonstrate that the relation between the energy distribution extracted from vibration signals and lubrication conditions follows a certain rule. A typical feedforward backpropagation neural network is used as the classifier to verify the effectiveness of energy distribution. The average classification accuracy of the network with energy distribution as input is more than 95%. The results show that the lubrication conditions can be characterized by “energy” hidden in the vibration signals and the energy distribution is an appropriate feature that can be used for fault diagnosis of linear rolling guide.

scholarly journals Fault Diagnosis Based on BP Neural Network Optimized by Beetle Algorithm

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Maohua Xiao ◽  
Wei Zhang ◽  
Kai Wen ◽  
Yue Zhu ◽  
Yilidaer Yiliyasi
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Wavelet Analysis ◽  
Bp Neural Network ◽  
Wavelet Packet ◽  
Frequency Resolution ◽  
Particle Swarm Algorithm ◽  
Wavelet Packet Decomposition ◽  
Vibration Signals ◽  
Training Time

AbstractIn the process of Wavelet Analysis, only the low-frequency signals are re-decomposed, and the high-frequency signals are no longer decomposed, resulting in a decrease in frequency resolution with increasing frequency. Therefore, in this paper, firstly, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which makes up for the shortcomings of Wavelet Analysis in extracting fault features of nonlinear vibration signals, and different energy values in different frequency bands are obtained by Wavelet Packet Decomposition. The features are visualized by the K-Means clustering method, and the results show that the extracted energy features can accurately distinguish the different states of the bearing. Then a fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify the bearing faults. Compared with the Particle Swarm Algorithm, Beetle Algorithm can quickly find the error extreme value, which greatly reduces the training time of the model. At last, two experiments are conducted, which show that the accuracy of the model can reach more than 95%, and the model has a certain anti-interference ability.

RESONANCE-BASED VIBRATION SIGNAL DENOISING USING WAVELET PACKET DECOMPOSITION

2007 ◽  
Vol 07 (03) ◽  
pp. L257-L262
Author(s):  
M. SHAGHAGHI ◽  
M. H. KAHAEI ◽  
J. POSHTAN
Keyword(s):  
Wavelet Packet ◽  
Computational Cost ◽  
Vibration Signal ◽  
Wavelet Packets ◽  
Signal Denoising ◽  
Wavelet Packet Decomposition ◽  
Noisy Environments ◽  
Vibration Signals ◽  
On Line

This paper presents a new on-line technique for denoising impulsive vibration signals in noisy environments using Wavelet Packets. The proposed algorithm is based on localizing the frequency subbands of the resonances embedded in impulsive vibration signals. The performance of the algorithm is evaluated in denoising real vibration signals measured from faulty bearings. The results compared to the theoretical values and those obtained by the HFD algorithm show the effectiveness of the proposed algorithm while the computational cost reduces to half.

scholarly journals Examining the Applicability of Wavelet Packet Decomposition on Different Forecasting Models in Annual Rainfall Prediction

Water ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 1997
Author(s):  
Hua Wang ◽  
Wenchuan Wang ◽  
Yujin Du ◽  
Dongmei Xu
Keyword(s):  
Wavelet Packet ◽  
Moving Average ◽  
Back Propagation ◽  
Processing Technique ◽  
Annual Rainfall ◽  
Wavelet Packet Decomposition ◽  
Rainfall Forecasting ◽  
Promising Alternative ◽  
Forecasting Models ◽  
Precipitation Prediction

Accurate precipitation prediction can help plan for different water resources management demands and provide an extension of lead-time for the tactical and strategic planning of courses of action. This paper examines the applicability of several forecasting models based on wavelet packet decomposition (WPD) in annual rainfall forecasting, and a novel hybrid precipitation prediction framework (WPD-ELM) is proposed coupling extreme learning machine (ELM) and WPD. The works of this paper can be described as follows: (a) WPD is used to decompose the original precipitation data into several sub-layers; (b) ELM model, autoregressive integrated moving average model (ARIMA), and back-propagation neural network (BPNN) are employed to realize the forecasting computation for the decomposed series; (c) the results are integrated to attain the final prediction. Four evaluation indexes (RMSE, MAE, R, and NSEC) are adopted to assess the performance of the models. The results indicate that the WPD-ELM model outperforms other models used in this paper and WPD can significantly enhance the performance of forecasting models. In conclusion, WPD-ELM can be a promising alternative for annual precipitation forecasting and WPD is an effective data pre-processing technique in producing convincing forecasting models.

Sign in / Sign up

Export Citation Format

Share Document