Feature Extraction Technology for Rolling Bearings Based on Local Tangent Space Alignment

2015 ◽  
Vol 764-765 ◽  
pp. 274-279
Author(s):  
Zhi Wen ◽  
Chen Lu ◽  
Hong Mei Liu
Keyword(s):  
Tangent Space ◽  
Feature Vector ◽  
Wavelet Packet ◽  
Linear Structure ◽  
Extraction Technology ◽  
Rolling Bearings ◽  
Time Frequency ◽  
Non Linear ◽  
Non Stationary Signal ◽  
Local Tangent

Health assessment and fault diagnosis for rolling bearings mostly adopt traditional methods, such as time-frequency, spectral, and wavelet packet analyses, to extract the feature vector. These methods are suitable for processing data with a linear structure. However, for the non-linear and non-stationary signal, the result of these methods is not ideal. Thus, this study proposes a suitable method to extract the feature vector in nonlinear signals. Local tangent space alignment of a manifold algorithm is employed to extract the feature vector from the rolling bearings. Results verify the advantage of the manifold algorithm for non-linear and non-stationary signals.

COMPREHENSIVE ANALYSIS OF NORMAL AND DIABETIC HEART RATE SIGNALS: A REVIEW

2012 ◽  
Vol 12 (05) ◽  
pp. 1240033 ◽  
Author(s):  
OLIVER FAUST ◽  
V. RAMANAN PRASAD ◽  
G. SWAPNA ◽  
SUBHAGATA CHATTOPADHYAY ◽  
TEIK-CHENG LIM
Keyword(s):  
Heart Rate ◽  
Organ Damage ◽  
Extraction Methods ◽  
Time Frequency ◽  
Ecg Signals ◽  
Cardiac Health ◽  
Non Linear ◽  
Non Stationary Signal ◽  
Early Diagnosis Of Diabetes ◽  
Typical Range

A large section of the world's population is affected by diabetes mellitus (DM), commonly referred to as "diabetes." Every year, the number of cases of DM is increasing. Diabetes has a strong genetic basis, hence it is very difficult to cure, but can be controlled with medications to prevent subsequent organ damage. Therefore, early diagnosis of diabetes is very important. In this paper, we examine how diabetes affects cardiac health, which is reflected through heart rate variability (HRV), as observed in electrocardiography (ECG) signals. Such signals provide clues for both the presence and severity of diabetes as well as diabetes-induced cardiac impairments. Heart rate (HR) is a non-linear and non-stationary signal. Thus, extracting useful information from HRV signals is a difficult task. We review several sophisticated signal processing and information extraction methods in order to establish measurable relationships between the presence and the extent of diabetes as well as the changes in the HRV signals. Furthermore, we discuss a typical range of values for several statistical, geometric, time domain, frequency domain, time–frequency, and non-linear features for HR signals from 15 normal and 15 diabetic subjects. We found that non-linear analysis is the most suitable approach to capture and analyze the subtle changes in HRV signals caused by diabetes.

scholarly journals Multi-fault Diagnosis of Rolling Bearing using Two-dimensional Feature Vector of WP-VMD and PSO-KELM Algorithm

2021 ◽  
Author(s):  
tingyu jiang ◽  
Sheng Hong ◽  
Hao Liu
Keyword(s):  
Fault Diagnosis ◽  
Feature Vector ◽  
Wavelet Packet ◽  
Random Noise ◽  
Rolling Bearing ◽  
Two Dimensional ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Stable Performance ◽  
Learning Machine

Abstract In order to achieve accurate fault diagnosis of rolling bearing under random noise, a new fault diagnosis method based on wavelet packet-variational mode decomposition (WP-VMD) and kernel extreme learning machine (KELM) optimized by particle swarm optimization (PSO) is proposed in this paper. Firstly, the time-frequency domain feature vectors of the original rolling bearing fault signals are effectively obtained by preprocessing of WMD and decomposition and reconstruction of VMD. Then, the extracted two-dimensional feature vector is input into the KELM neural network for fault identification, and combined with PSO, KELM parameters were optimized. The experimental results show that the proposed method can effectively diagnose the rolling bearing under random noise, with the features of fast speed, stable performance and high accuracy. By comparison, this paper obtains better accuracy and real-time performance with fewer features, which provides a simple and efficient solution for fault diagnosis of rolling bearings.

scholarly journals An Integrated Fault Identification Approach for Rolling Bearings Based on Dual-Tree Complex Wavelet Packet Transform and Generalized Composite Multiscale Amplitude-Aware Permutation Entropy

2020 ◽  
Vol 2020 ◽  
pp. 1-18
Author(s):  
Wuqiang Liu ◽  
Xiaoqiang Yang ◽  
Shen Jinxing
Keyword(s):  
Wavelet Packet ◽  
Wavelet Packet Transform ◽  
Good Time ◽  
Permutation Entropy ◽  
Fault Identification ◽  
Nonlinear Dimensionality Reduction ◽  
Rolling Bearings ◽  
Time Frequency ◽  
Fault Type ◽  
Complex Wavelet

The health condition of rolling bearings, as a widely used part in rotating machineries, directly influences the working efficiency of the equipment. Consequently, timely detection and judgment of the current working status of the bearing is the key to improving productivity. This paper proposes an integrated fault identification technology for rolling bearings, which contains two parts: the fault predetection and the fault recognition. In the part of fault predetection, the threshold based on amplitude-aware permutation entropy (AAPE) is defined to judge whether the bearing currently has a fault. If there is a fault in the bearing, the fault feature is adequately extracted using the feature extraction method combined with dual-tree complex wavelet packet transform (DTCWPT) and generalized composite multiscale amplitude-aware permutation entropy (GCMAAPE). Firstly, the method decomposes the fault vibration signal into a set of subband components through the DTCWPT with good time-frequency decomposing capability. Secondly, the GCMAAPE values of each subband component are computed to generate the initial candidate feature. Next, a low-dimensional feature sample is established using the t-distributed stochastic neighbor embedding (t-SNE) with good nonlinear dimensionality reduction performance to choose sensitive features from the initial high-dimensional features. Afterwards, the featured specimen representing fault information is fed into the deep belief network (DBN) model to judge the fault type. In the end, the superiority of the proposed solution is verified by analyzing the collected experimental data. Detection and classification experiments indicate that the proposed solution can not only accurately detect whether there is a fault but also effectively determine the fault type of the bearing. Besides, this solution can judge the different faults more accurately compared with other ordinary methods.

scholarly journals A Novel End-To-End Fault Diagnosis Approach for Rolling Bearings by Integrating Wavelet Packet Transform into Convolutional Neural Network Structures

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4965 ◽  
Author(s):  
Shoucong Xiong ◽  
Hongdi Zhou ◽  
Shuai He ◽  
Leilei Zhang ◽  
Qi Xia ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Frequency Analysis ◽  
Wavelet Packet ◽  
Wavelet Packet Transform ◽  
Rolling Bearings ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
End To End

Accidental failures of rotating machinery components such as rolling bearings may trigger the sudden breakdown of the whole manufacturing system, thus, fault diagnosis is vital in industry to avoid these massive economical costs and casualties. Since convolutional neural networks (CNN) are poor in extracting reliable features from original signal data, the time-frequency analysis method is usually called for to transform 1D signal into a 2D time-frequency coefficient matrix in which richer information could be exposed more easily. However, realistic fault diagnosis applications face a dilemma in that signal time-frequency analysis and fault classification cannot be implemented together, which means manual signal conversion work is also needed, which reduces the integrity and robustness of the fault diagnosis method. In this paper, a novel network named WPT-CNN is proposed for end-to-end intelligent fault diagnosis of rolling bearings. WPT-CNN creatively uses the standard deep neural network structure to realize the wavelet packet transform (WPT) time-frequency analysis function, which seamlessly integrates fault diagnosis domain knowledge into deep learning algorithms. The overall network architecture can be trained with gradient descent backpropagation algorithms, indicating that the time-frequency analysis module of WPT-CNN is also able to learn the dataset characteristics, adaptively representing signal information in the most suitable way. Two experimental rolling bearing fault datasets were used to validate the proposed method. Testing results showed that WPT-CNN obtained the testing accuracies of 99.73% and 99.89%, respectively, in two datasets, which exhibited a better and more reliable diagnosis performance than any other existing deep learning and machine learning methods.

Research of Pipeline Leak Eigenvector Extracting Based on Wavelet Packet

2014 ◽  
Vol 986-987 ◽  
pp. 1426-1430
Author(s):  
Xiao Yun Liu ◽  
Xiang Fen Zhang ◽  
Yan Ma ◽  
Yan Qin Yang
Keyword(s):  
Frequency Domain ◽  
Feature Vector ◽  
Wavelet Packet ◽  
Leak Detection ◽  
Time Frequency ◽  
Feature Vectors ◽  
Mixing Effects ◽  
Traditional Algorithm ◽  
Pipeline Safety ◽  
Improved Algorithm

As an important part of pipeline safety, pipeline leak detection is usually done by extracting feature vectors of leakage signal. Many researchers used wavelet packet algorithm to extract feature vector, but because of mixing effects of wavelet packet, the acquired feature vector may be not accurate. To solve this problem, the authors propose an improved wavelet packet algorithm to extract the feature vector. The improved algorithm is different from the traditional algorithm in decomposition and reconstruction and the feature vector is constituted by three time-frequency domain parameters. A lot of experiments have been performed to extract feature vector based on the proposed algorithm, with the results showing that the proposed algorithm can overcome the mixing effects and accurately extract the feature vector.

Entropy-based feature extraction technique in conjunction with wavelet packet transform for multi-mental task classification

2019 ◽  
Vol 64 (5) ◽  
pp. 529-542
Author(s):  
Caglar Uyulan ◽  
Türker Tekin Ergüzel ◽  
Nevzat Tarhan
Keyword(s):  
Feature Extraction ◽  
Wavelet Packet ◽  
Series Representation ◽  
Feature Selection Method ◽  
Wavelet Packet Transform ◽  
Control Group ◽  
Mental Task ◽  
Time Frequency ◽  
Non Stationary Signal ◽  
Mental Tasks

Abstract Event-related mental task information collected from electroencephalography (EEG) signals, which are functionally related to different brain areas, possesses complex and non-stationary signal features. It is essential to be able to classify mental task information through the use in brain-computer interface (BCI) applications. This paper proposes a wavelet packet transform (WPT) technique merged with a specific entropy biomarker as a feature extraction tool to classify six mental tasks. First, the data were collected from a healthy control group and the multi-signal information comprised six mental tasks which were decomposed into a number of subspaces spread over a wide frequency spectrum by projecting six different wavelet basis functions. Later, the decomposed subspaces were subjected to three entropy-type statistical measure functions to extract the feature vectors for each mental task to be fed into a backpropagation time-recurrent neural network (BPTT-RNN) model. Cross-validated classification results demonstrated that the model could classify with 85% accuracy through a discrete Meyer basis function coupled with a Renyi entropy biomarker. The classifier model was finally tested in the Simulink platform to demonstrate the Fourier series representation of periodic signals by tracking the harmonic pattern. In order to boost the model performance, ant colony optimization (ACO)-based feature selection method was employed. The overall accuracy increased to 88.98%. The results underlined that the WPT combined with an entropy uncertainty measure methodology is both effective and versatile to discriminate the features of the signal localized in a time-frequency domain.

Fast Algorithm for Adaptive Gaussian Chirplet Signal Decomposition

2014 ◽  
Vol 556-562 ◽  
pp. 4755-4758
Author(s):  
Jian Feng Guo ◽  
Wei Dong Wang ◽  
Jin Zhao Liu
Keyword(s):  
Fast Algorithm ◽  
Signal Decomposition ◽  
Frequency Resolution ◽  
Decomposition Algorithms ◽  
Short Time Fourier Transform ◽  
Time Frequency ◽  
Non Linear ◽  
Linear Signal ◽  
Non Stationary Signal ◽  
Short Time

It is well known that adaptive Gaussian chirplet signal decomposition algorithm has the best time frequency resolution in all signal decomposition algorithms. It is widely used in non linear and non stationary signal decomposition, especially for the signal which is superposition of chirplet functions decomposition. But it has a large amount of computation. In this paper, we propose a fast algorithm based on short time Fourier transform (STFT) method and we change parameters’ domain. Using this fast algorithm to decompose a four atoms non-linear signal computes very fast and it can also avoid the cross term’s interferer of the Wigner-Ville distribution.

scholarly journals Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression

2021 ◽  
Vol 11 (11) ◽  
pp. 4773
Author(s):  
Qiaoping Tian ◽  
Honglei Wang
Keyword(s):  
Quantile Regression ◽  
Probability Density ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Health State ◽  
Rolling Bearings ◽  
Data Set ◽  
Time Frequency ◽  
Useful Life ◽  
Degradation Indicator

High precision and multi information prediction results of bearing remaining useful life (RUL) can effectively describe the uncertainty of bearing health state and operation state. Aiming at the problem of feature efficient extraction and RUL prediction during rolling bearings operation degradation process, through data reduction and key features mining analysis, a new feature vector based on time-frequency domain joint feature is found to describe the bearings degradation process more comprehensively. In order to keep the effective information without increasing the scale of neural network, a joint feature compression calculation method based on redefined degradation indicator (DI) was proposed to determine the input data set. By combining the temporal convolution network with the quantile regression (TCNQR) algorithm, the probability density forecasting at any time is achieved based on kernel density estimation (KDE) for the conditional distribution of predicted values. The experimental results show that the proposed method can obtain the point prediction results with smaller errors. Compared with the existing quantile regression of long short-term memory network(LSTMQR), the proposed method can construct more accurate prediction interval and probability density curve, which can effectively quantify the uncertainty of bearing running state.

Sign in / Sign up

Export Citation Format

Share Document