HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings

2004 ◽  
Vol 127 (4) ◽  
pp. 299-306 ◽  
Author(s):  
Hasan Ocak ◽  
Kenneth A. Loparo
Keyword(s):  
Fault Detection ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Fault Detection And Diagnosis ◽  
Markov Modeling ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Hidden Markov Modeling ◽  
Rolling Element ◽  
Detection And Diagnosis

In this paper, we introduce a new bearing fault detection and diagnosis scheme based on hidden Markov modeling (HMM) of vibration signals. Features extracted from amplitude demodulated vibration signals from both normal and faulty bearings were used to train HMMs to represent various bearing conditions. The features were based on the reflection coefficients of the polynomial transfer function of an autoregressive model of the vibration signals. Faults can be detected online by monitoring the probabilities of the pretrained HMM for the normal case given the features extracted from the vibration signals. The new technique also allows for diagnosis of the type of bearing fault by selecting the HMM with the highest probability. The new scheme was also adapted to diagnose multiple bearing faults. In this adapted scheme, features were based on the selected node energies of a wavelet packet decomposition of the vibration signal. For each fault, a different set of nodes, which correlates with the fault, is chosen. Both schemes were tested with experimental data collected from an accelerometer measuring the vibration from the drive-end ball bearing of an induction motor (Reliance Electric 2 HP IQPreAlert) driven mechanical system and have proven to be very accurate.

Rolling Element Bearing Fault Detection Using Redundant Second Generation Wavelet Packet Transform

2011 ◽  
Vol 199-200 ◽  
pp. 931-935 ◽  
Author(s):  
Ning Li ◽  
Rui Zhou
Keyword(s):  
Wavelet Transform ◽  
Fault Detection ◽  
Second Generation ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Bearing Fault ◽  
Rolling Element ◽  
Element Bearing ◽  
Second Generation Wavelet

Wavelet transform has been widely used for the vibration signal based rolling element bearing fault detection. However, the problem of aliasing inhering in discrete wavelet transform restricts its further application in this field. To overcome this deficiency, a novel fault detection method for roll element bearing using redundant second generation wavelet packet transform (RSGWPT) is proposed. Because of the absence of the downsampling and upsampling operations in the redundant wavelet transform, the aliasing in each subband signal is alleviated. Consequently, the signal in each subband can be characterized by the extracted features more effectively. The proposed method is applied to analyze the vibration signal measured from a faulty bearing. Testing results confirm that the proposed method is effective in extracting weak fault feature from a complex background.

scholarly journals Vibration-Based Bearing Fault Detection and Diagnosis via Image Recognition Technique Under Constant and Variable Speed Conditions

2018 ◽  
Vol 8 (8) ◽  
pp. 1392 ◽  
Author(s):  
Moussa Hamadache ◽  
Dongik Lee ◽  
Emiliano Mucchi ◽  
Giorgio Dalpiaz
Keyword(s):  
Fault Detection ◽  
Image Recognition ◽  
Fault Detection And Diagnosis ◽  
Variable Speed ◽  
Vibration Signals ◽  
Bearing Faults ◽  
Bearing Fault ◽  
Bearing Fault Detection ◽  
Detection And Diagnosis ◽  
Recognition Technique

This paper addresses the application of an image recognition technique for the detection and diagnosis of ball bearing faults in rotating electrical machines (REMs). The conventional bearing fault detection and diagnosis (BFDD) methods rely on extracting different features from either waveforms or spectra of vibration signals to detect and diagnose bearing faults. In this paper, a novel vibration-based BFDD via a probability plot (ProbPlot) image recognition technique under constant and variable speed conditions is proposed. The proposed technique is based on the absolute value principal component analysis (AVPCA), namely, ProbPlot via image recognition using the AVPCA (ProbPlot via IR-AVPCA) technique. A comparison of the features (images) obtained: (1) directly in the time domain from the original raw data of the vibration signals; (2) by capturing the Fast Fourier Transformation (FFT) of the vibration signals; or (3) by generating the probability plot (ProbPlot) of the vibration signals as proposed in this paper, is considered. A set of realistic bearing faults (i.e., outer-race fault, inner-race fault, and balls fault) are experimentally considered to evaluate the performance and effectiveness of the proposed ProbPlot via the IR-AVPCA method.

scholarly journals Generative Oversampling Method for Imbalanced Data on Bearing Fault Detection and Diagnosis

2019 ◽  
Vol 9 (4) ◽  
pp. 746 ◽  
Author(s):  
Sungho Suh ◽  
Haebom Lee ◽  
Jun Jo ◽  
Paul Lukowicz ◽  
Yong Lee
Keyword(s):  
Fault Detection ◽  
Test Bench ◽  
Imbalanced Data ◽  
Fault Detection And Diagnosis ◽  
Data Driven ◽  
Image Transformation ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Transformation Procedure ◽  
Detection And Diagnosis

In this study, we developed a novel data-driven fault detection and diagnosis (FDD) method for bearing faults in induction motors where the fault condition data are imbalanced. First, we propose a bearing fault detector based on convolutional neural networks (CNN), in which the vibration signals from a test bench are used as inputs after an image transformation procedure. Experimental results demonstrate that the proposed classifier for FDD performs well (accuracy of 88% to 99%) even when the volume of normal and fault condition data is imbalanced (imbalance ratio varies from 20:1 to 200:1). Additionally, our generative model reduces the level of data imbalance by oversampling. The results improve the accuracy of FDD (by up to 99%) when a severe imbalance ratio (200:1) is assumed.

A Method of Fault Detection and Diagnosis for Electromagnetic Direction Valve Based on Artificial Neural Network

2012 ◽  
Vol 476-478 ◽  
pp. 2384-2388
Author(s):  
Min Qiang Dai ◽  
Wei Cai ◽  
Sheng Dun Zhao
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fault Detection ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Fault Detection And Diagnosis ◽  
Line Detection ◽  
On Line ◽  
Artificial Neural ◽  
Detection And Diagnosis

The magnetic field and vibration signal of electromagnetic direction valve can be detected real-timely by a non-intrusive on line detection device, which can use to monitor working state of the valve. A method of fault detection and diagnosis for electromagnetic direction valve from the signal detected by the non-intrusive on line detection device is presented in this paper. The wave frequency bands energy analysis method is adopted to distinguish the electromagnetic direction valve’s state, and the vibration signal are decomposed by three-layer wavelet packet which wavelet basis is db10. The fault identification method is based on BP artificial neural network (ANN), which is the most well-known three-layers BP ANN whose input and output layers have 8 and 3 neurons respectively.

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.

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).

Sign in / Sign up

Export Citation Format

Share Document