Yongbin Liu

Remaining Useful Life Prediction of Rolling Bearings Using PSR, JADE, and Extreme Learning Machine

Rolling bearings play a pivotal role in rotating machinery. The degradation assessment and remaining useful life (RUL) prediction of bearings are critical to condition-based maintenance. However, sensitive feature extraction still remains a formidable challenge. In this paper, a novel feature extraction method is introduced to obtain the sensitive features through phase space reconstitution (PSR) and joint with approximate diagonalization of Eigen-matrices (JADE). Firstly, the original features are extracted from bearing vibration signals in time and frequency domain. Secondly, the PSR is applied to embed the original features into high dimensional phase space. The between-class and within-class scatter () are calculated to evaluate the feature sensitivity through the phase point distribution of different degradation stages and then different weights are assigned to the corresponding features based on the calculated . Thirdly, the JADE is employed to fuse the weighted features to obtain the advanced features which can better reflect the bearing degradation process. Finally, the advanced features are input into the extreme learning machine (ELM) to train the RUL prediction model. A set of experimental case studies are carried out to verify the effectiveness of the proposed method. The results show that the extracted advanced features can better reflect the degradation process compared to traditional features and could effectively predict the RUL of bearing.

A Novel Contactless Angular Resampling Method for Motor Bearing Fault Diagnosis Under Variable Speed

This paper proposes a novel contactless angular resampling method for motor bearing fault diagnosis under variable speed. This method involves three steps: (1) the instantaneous rotating angle is measured using the Kanade-Lucas-Tomasi object tracking algorithm from a video that is recorded by a high-speed camera; (2) the bearing signal that is acquired using a microphone is resampled in the angular domain based on the accumulated angle curve; and (3) the resampled signal is demodulated to obtain the bearing fault characteristic frequency for order analysis (OA) and fault recognition. This method has been proven effective in diagnosing a set of defective bearings installed on a brushless direct current motors and a direct current motors test rigs, respectively. As its main contribution, this paper exploits a novel optical measurement method to estimate rotating speed, thereby avoiding the use of a tachometer and overcoming the limitations of conventional tacholess OA methods.

Phase Space Similarity as a Signature for Rolling Bearing Fault Diagnosis and Remaining Useful Life Estimation

Feature extraction from vibration signal is still a challenge in the area of fault diagnosis and remaining useful life (RUL) estimation of rotary machine. In this paper, a novel feature called phase space similarity (PSS) is introduced for health condition monitoring of bearings. Firstly, the acquired signal is transformed to the phase space through the phase space reconstruction (PSR). The similar vibration always exists in the phase space due to the comparable evolution of the dynamics that are characteristic of the system state. Secondly, the normalized cross-correlation (NCC) is employed to calculate the PSS between bearing data with different states. Based on the PSS, a fault pattern recognition algorithm, a bearing fault size prediction algorithm, and a RUL estimation algorithm are introduced to analyze the experimental signal. Results have shown the effectiveness of the PSS as it can better grasp the nature and regularity of the signals.

A Feature Extraction Method Using Improved Multi-Scale Entropy for Rolling Bearing Fault Diagnosis

A feature extraction method named improved multi-scale entropy (IMSE) is proposed for rolling bearing fault diagnosis. This method could overcome information leakage in calculating the similarity of machinery systems, which is based on Pythagorean Theorem and similarity criterion. Features extracted from bearings under different conditions using IMSE are identified by the support vector machine (SVM) classifier. Experimental results show that the proposed method can extract the status information of the bearing. Compared with the multi-scale entropy (MSE) and sample entropy (SE) methods, the identification accuracy of the features extracted by IMSE is improved as well.

Wayside Bearing Fault Diagnosis Based on Envelope Analysis Paved with Time-Domain Interpolation Resampling and Weighted-Correlation-Coefficient-Guided Stochastic Resonance

Envelope spectrum analysis is a simple, effective, and classic method for bearing fault identification. However, in the wayside acoustic health monitoring system, owing to the high relative moving speed between the railway vehicle and the wayside mounted microphone, the recorded signal is embedded with Doppler effect, which brings in shift and expansion of the bearing fault characteristic frequency (FCF). What is more, the background noise is relatively heavy, which makes it difficult to identify the FCF. To solve the two problems, this study introduces solutions for the wayside acoustic fault diagnosis of train bearing based on Doppler effect reduction using the improved time-domain interpolation resampling (TIR) method and diagnosis-relevant information enhancement using Weighted-Correlation-Coefficient-Guided Stochastic Resonance (WCCSR) method. First, the traditional TIR method is improved by incorporating the original method with kinematic parameter estimation based on time-frequency analysis and curve fitting. Based on the estimated parameters, the Doppler effect is removed using the TIR easily. Second, WCCSR is employed to enhance the diagnosis-relevant period signal component in the obtained Doppler-free signal. Finally, paved with the above two procedures, the local fault is identified using envelope spectrum analysis. Simulated and experimental cases have verified the effectiveness of the proposed method.

Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine

Data-driven approaches have been proved effective for remaining useful life estimation of key components (bearings for example) in rotating machinery. In such approaches, it is important to determine an appropriate degradation indicator from the collected run-to-failure life cycle data. In this paper, a new degradation indicator is introduced based on the joint approximate diagonalization of eigen matrices algorithm. First, a matrix consisting of time domain, frequency domain, and time–frequency domain features extracted from the collected data instances is created. Then a two-layer joint approximate diagonalization of eigen matrices is introduced to transform the matrix to the advanced features (a vector) that represents the behavior of the bearing’s degradation. As an independent component analysis method, the designed two-layer joint approximate diagonalization of eigen matrices is able to eliminate the redundancy of the directly extracted features. Further, the obtained vector is input into an extreme learning machine to train a remaining useful life prediction model. Finally, a set of experimental cases are utilized to verify the presented method. Results show that the two-layer joint approximate diagonalization of eigen matrices is capable of exploring features that reflects the trend of bearing’s degradation state much better. And due to the easy parameter configuration and fast learning speed, the extreme learning machine is capable of training a model that can effectively predict the remaining useful life of the bearings.

Enhanced Bearing Fault Detection Using Step-Varying Vibrational Resonance Based on Duffing Oscillator Nonlinear System

Bearing is a key part of rotary machines, and its working condition is critical in normal operation of rotary machines. Vibrational signals are usually analyzed to monitor the status of bearing. However, information on the status of bearing is always buried in heavy background noise; that is, status information of bearing is weaker than the background noise. Extracting the status features of bearing from signals buried in noise is difficult. Given this, a step-varying vibrational resonance (SVVR) method based on Duffing oscillator nonlinear system is proposed to enhance the weak status feature of bearing by tuning different parameters. Extraction ability of SVVR was verified by analyzing simulation signal and practical bearing signal. Experimental results show that SVVR is more effective in extracting weak characteristic information than other methods, including multiscale noise tuning stochastic resonance (SR), Woods–Saxon potential-based SR, and joint Woods–Saxon and Gaussian potential-based SR. Two evaluation indices are investigated to qualitatively and quantitatively assess the fault detection capability of the SVVR method. The results show that the SVVR can effectively identify the weak status information of bearing.

Wayside acoustic fault diagnosis of train wheel bearing based on Doppler effect correction and fault-relevant information enhancement:

Health monitoring of train bearing is crucial to railway transport safety. More and more attention has elicited by the wayside acoustic monitoring technique in recent years than other defect detection techniques. However, wayside acoustic signal contains serious Doppler distortion and heavy background noise because of the high speed of trains. Thus, extracting fault-relevant information is difficult. A novel method for Doppler effect correction is proposed in this study by incorporating the traditional time-domain interpolation resampling with a novel kinematic parameters estimation method. In this kinematic parameters estimation method, an iterative algorithm based on least squares theory is proposed to improve the parameters estimation accuracy. After the Doppler effect correction, the ensemble empirical mode decomposition is employed to further enhance the fault-relevant information. The proposed iteration algorithm can improve the accuracy of kinematic parameters estimation significantly; thus the Doppler distortion can be corrected more accurately. The proposed ensemble empirical mode decomposition can further enhance the fault-relevant information and so that the accuracy and reliability of the diagnosis decision can be improved. The performance of this method has been verified in experimental and simulated cases.

Enhanced bearing fault diagnosis using adaptive stochastic resonance

Signal filtering approaches are always used to attenuate noise and enhance useful signal in bearing fault diagnosis. Stochastic resonance (SR) is a nonlinear filter that can utilize noise to enhance weak periodic signal. This study proposes an adaptive SR method which can automatically enhance the bearing fault characteristic frequency (FCF). First, a second-order SR filter is utilized to purify the demodulated vibration signal. Second, a new criterion that measures both the power spectrum kurtosis and the correlation coefficient is proposed to tune the filter parameters in the SR procedure. Finally, the FCF is enhanced, which facilitates bearing fault identification. Experimental verification is conducted to evaluate the effectiveness of the proposed method.