scholarly journals A Novel Method for Identifying Crack and Shaft Misalignment Faults in Rotor Systems under Noisy Environments Based on CNN

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5158 ◽  
Author(s):  
Wang Zhao ◽  
Chunrong Hua ◽  
Dawei Dong ◽  
Huajiang Ouyang
Keyword(s):  
Signal To Noise Ratio ◽  
Principal Component ◽  
Rotor System ◽  
Fault Classification ◽  
Vibration Signals ◽  
Rotor Systems ◽  
Response Characteristics ◽  
Mode Decomposition ◽  
Shaft Misalignment ◽  
Band Limited

Crack and shaft misalignment are two common types of fault in a rotor system, both of which have very similar dynamic response characteristics, and the vibration signals are vulnerable to noise contamination because of the interaction among different components of rotating machinery in the actual industrial environment, resulting in great difficulties in fault identification of a rotor system based on vibration signals. A method for identification of faults in the form of crack and shaft misalignments is proposed in this paper, which combines variational mode decomposition (VMD) and probabilistic principal component analysis (PPCA) to denoise the collected vibration signals from a test rig and then achieve signal feature extraction and fault classification with convolutional artificial neural network (CNN). The key parameters of the CNN are optimized and determined by genetic algorithm (GA) firstly, and the domain adaptability of the trained network is verified by the signals with different signal-to-noise ratio (SNR) values; then, the noisy vibration signals are decomposed into multiple band-limited intrinsic modal functions by VMD, and further data dimension reduction is performed by PPCA to realize the separation of the useful signals from noise; finally, the crack and shaft misalignment of the rotor system are identified by the optimized CNN. The results show that the proposed method can effectively remove the interference noise and extract the intrinsic features of the vibration signals, and the recognition rates of crack and shaft misalignment faults for the rotor system with different SNR values are more than 99%, which is considered to be very effective and useful.

Vibration Analysis of Coupled Faults Diagnosis in a Rotor System Using Wavelet De-Noising and KPCA Data Fusion

2012 ◽  
Vol 192 ◽  
pp. 233-236
Author(s):  
Xiu Mei Zhu
Keyword(s):  
Fault Diagnosis ◽  
Principal Component ◽  
Rotor System ◽  
Kernel Principal Component Analysis ◽  
Vibration Signals ◽  
Rotor Systems ◽  
Fault Features ◽  
Simultaneous Existence ◽  
Faults Diagnosis

In a rotor system, simultaneous existence of coupled faults, i.e. a crack couples with a misalignment, is very common. However, the single fault diagnosis has been investigated extensively in previous work while the issue of coupled faults diagnosis (i.e. considering two or more than two faults at a time) has been addressed insufficiently. In order to detect the existence of coupled faults and to prevent a fatigue crack in the rotor shaft, a new method is proposed to analyze the vibration signals using the Wavelet de-nosing and kernel principal component analysis (KPCA) in this work. The Wavelet was firstly used to de-noise the original vibration signals, and then the KPCA was adopted to extract useful fault features for the coupled faults detection. A case study on the coupled fault diagnosis of the rotor system has been implemented. The diagnosis results demonstrate that the proposed method is feasible for the coupled fault diagnosis of rotor systems. The fault detection rate is 91.0%.

scholarly journals A Fault Diagnosis Method for Out-of-Round Faults of Metro Vehicle Wheels with Strong Noise

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Haifeng Huang ◽  
Heli Wang ◽  
Weijiu Zhang ◽  
Weijie Gu
Keyword(s):  
Signal To Noise Ratio ◽  
Principal Component ◽  
Kernel Principal Component Analysis ◽  
Node Number ◽  
Vibration Signals ◽  
Mode Decomposition ◽  
Diagnosis Method ◽  
Testing Accuracy ◽  
Different Dimensions ◽  
Diagnosis Model

Detection of out-of round (OOR) faults of metro vehicle wheels is very important to improve stationarity and stability in metro vehicles and avoid accidents caused by OOR faults. Diagnosis of OOR faults demands extracting useful information accurately from mass of vibration signals with poor signal-to-noise ratio (SNR) of metro vehicle wheels for complex running condition. In this paper, we proposed a diagnosis method on OOR faults of metro vehicle wheels combined with variational mode decomposition (VMD), kernel principal component analysis (KPCA), and deep belief network (DBN) to diagnose the OOR faults of metro wheels. Vibration signals of China metro vehicle wheels collected while the metro vehicle is running are used to train the diagnosis model and adjust parameters of DBN and KPCA based on testing accuracy. The different dimensions of KPCA, epoch number, and node number of DBN are compared, and the better parameters of diagnosis model based on vibration signals are concluded in this paper. The generalization of the diagnosis model is checked nine times by testing the calculation of each group of parameters and using an error declining process. The mean accuracy of diagnosis model proposed in this paper is 0.9136, and the diagnosis model presented in this paper is very significant to detect OOR faults online.

scholarly journals Phase Synchrony Analysis of Rolling Bearing Vibrations and Its Application to Failure Identification

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2964 ◽  
Author(s):  
Qing Zhang ◽  
Tingting Jiang ◽  
Joseph D. Yan
Keyword(s):  
Phase Synchronization ◽  
Chaotic Behavior ◽  
Rolling Bearing ◽  
Bearing Failure ◽  
Phase Synchrony ◽  
Vibration Signals ◽  
Mode Decomposition ◽  
Initial Stage ◽  
Failure Evolution ◽  
Band Limited

As the failure-induced component (FIC) in the vibration signals of bearings transmits through housings and shafts, potential phase synchronization is excited among multichannel signals. As phase synchrony analysis (PSA) does not involve the chaotic behavior of signals, it is suitable for characterizing the operating state of bearings considering complicated vibration signals. Therefore, a novel PSA method was developed to identify and track the failure evolution of bearings. First, resonance demodulation and variational mode decomposition (VMD) were combined to extract the mono-component or band-limited FIC from signals. Then, the instantaneous phase of the FIC was analytically solved using Hilbert transformation. The generalized phase difference (GPD) was used to quantify the relationship between FICs extracted from different vibration signals. The entropy of the GPD was regarded as the indicator for quantifying failure evolution. The proposed method was applied to the vibration signals obtained from an accelerated failure experiment and a natural failure experiment. Results showed that phase synchronization in bearing failure evolution was detected and evaluated effectively. Despite the chaotic behavior of the signals, the phase synchronization indicator could identify bearing failure during the initial stage in a robust manner.

scholarly journals Combining DBN and FCM for Fault Diagnosis of Roller Element Bearings without Using Data Labels

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Fan Xu ◽  
Yan jun Fang ◽  
Dong Wang ◽  
Jia qi Liang ◽  
Kwok Leung Tsui
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Clustering Algorithm ◽  
Principal Component ◽  
Belief Networks ◽  
Deep Belief Networks ◽  
Vibration Signals ◽  
Fuzzy C Means ◽  
Roller Bearings ◽  
Mode Decomposition

Because deep belief networks (DBNs) in deep learning have a powerful ability to extract useful information from the raw data without prior knowledge, DBNs are used to extract the useful feature from the roller bearings vibration signals. Unlike classification methods, the clustering method can classify the different fault types without data label. Therefore, a method based on deep belief networks (DBNs) in deep learning (DL) and fuzzy C-means (FCM) clustering algorithm for roller bearings fault diagnosis without a data label is presented in this paper. Firstly, the roller bearings vibration signals are extracted by using DBN, and then principal component analysis (PCA) is used to reduce the dimension of the vibration signal features. Secondly, the first two principal components (PCs) are selected as the input of fuzzy C-means (FCM) for roller bearings fault identification. Finally, the experimental results show that the fault diagnosis of the method presented is better than that of other combination models, such as variation mode decomposition- (VMD-) singular value decomposition- (SVD-) FCM, and ensemble empirical mode decomposition- (EEMD-) fuzzy entropy- (FE-) PCA-FCM.

Misalignment Characteristic Analysis Based on Advanced Empirical Mode Decomposition

2013 ◽  
Vol 325-326 ◽  
pp. 1559-1563
Author(s):  
Hui Min Li ◽  
Wei Zhao ◽  
Yun Zhang
Keyword(s):  
Empirical Mode Decomposition ◽  
Rotor System ◽  
Experimental Results ◽  
Intrinsic Mode Functions ◽  
Characteristic Analysis ◽  
Wavelet Method ◽  
Vibration Signals ◽  
Multicomponent Signal ◽  
Mode Decomposition ◽  
Misalignment Fault

A new method of misalignment characteristic analysis, which is based on advanced empirical mode decomposition (AEMD), is presented in this paper. At first the vibration signals of a rotor system with different misalignments is collected separately. Then the multicomponent signal x (t) is decomposed into a number of the so-called intrinsic mode functions (IMFs) by use of AEMD respectively. For these IMFs the wavelet method is used to extract the interesting features. It is found that the IMF2 contains the interesting misalignment character. Additionally the experimental results substantiate that the proposed method for misalignment analysis can identify the varying trend of misalignment fault clearly.

scholarly journals Enhanced Partial Discharge Signal Denoising Using Dispersion Entropy Optimized Variational Mode Decomposition

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1567
Author(s):  
Ragavesh Dhandapani ◽  
Imene Mitiche ◽  
Scott McMeekin ◽  
Venkateswara Sarma Mallela ◽  
Gordon Morison
Keyword(s):  
Performance Metrics ◽  
Regularization Parameter ◽  
Signal To Noise Ratio ◽  
Partial Discharge ◽  
Sensor Data ◽  
Variational Mode Decomposition ◽  
Intrinsic Mode Functions ◽  
Denoising Method ◽  
Mode Decomposition ◽  
Band Limited

This paper presents a new approach for denoising Partial Discharge (PD) signals using a hybrid algorithm combining the adaptive decomposition technique with Entropy measures and Group-Sparse Total Variation (GSTV). Initially, the Empirical Mode Decomposition (EMD) technique is applied to decompose a noisy sensor data into the Intrinsic Mode Functions (IMFs), Mutual Information (MI) analysis between IMFs is carried out to set the mode length K. Then, the Variational Mode Decomposition (VMD) technique decomposes a noisy sensor data into K number of Band Limited IMFs (BLIMFs). The BLIMFs are separated as noise, noise-dominant, and signal-dominant BLIMFs by calculating the MI between BLIMFs. Eventually, the noise BLIMFs are discarded from further processing, noise-dominant BLIMFs are denoised using GSTV, and the signal BLIMFs are added to reconstruct the output signal. The regularization parameter λ for GSTV is automatically selected based on the values of Dispersion Entropy of the noise-dominant BLIMFs. The effectiveness of the proposed denoising method is evaluated in terms of performance metrics such as Signal-to-Noise Ratio, Root Mean Square Error, and Correlation Coefficient, which are are compared to EMD variants, and the results demonstrated that the proposed approach is able to effectively denoise the synthetic Blocks, Bumps, Doppler, Heavy Sine, PD pulses and real PD signals.

scholarly journals Identification of Bearing Dynamic Parameters and Unbalanced Forces in a Flexible Rotor System Supported by Oil-Film Bearings and Active Magnetic Devices

Actuators ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 216
Author(s):  
Yinsi Chen ◽  
Ren Yang ◽  
Naohiro Sugita ◽  
Junhong Mao ◽  
Tadahiko Shinshi
Keyword(s):  
Variable Stiffness ◽  
Rotor System ◽  
Unknown Parameters ◽  
Oil Film ◽  
Rotor Systems ◽  
Response Characteristics ◽  
Unbalanced Force ◽  
Displacement Force ◽  
The Stability ◽  
And Control

As the rotational speed of conventional rotor systems supported by oil-film bearings has increased, vibration problems such as oil whip and oil whirl have become apparent. Our group proposed the use of active magnetic bearings (AMBs)/bearingless motors (BELMs) to stabilize these systems. In such a system, measuring the variable stiffness and damping of the oil-film bearings, the current-force and displacement-force parameters of the AMBs/BELMs, and the residual unbalanced force is necessary to satisfy the stability of the rotor system. These parameters are the foundation for the rotor dynamics analysis and optimization of the control strategy. In this paper, we propose a method to simultaneously identify the parameters of the oil-film bearings and AMBs/BELMs along with the residual unbalanced forces during the unbalanced vibration of the rotor. The proposed method requires independent rotor responses and control currents to form a regression equation to estimate all the unknown parameters. Independent rotor responses are realized by changing the PID control parameters of the AMBs/BELMs. Numerical simulation results show that the proposed method is highly accurate and has good robustness to measurement noise. The experimental results show that the unknown parameters identified by the responses generated by different controller parameters are similar. To confirm that the identification results are correct, verification experiments were carried out. The vibration amplitude of the rotor was successfully suppressed by applying a force to the rotor in the opposite direction to the residual unbalanced force. The frequency response characteristics and unbalanced responses of the rotor estimated by the values of the parameters identified show good consistency with the measured results.

Gear Fault Classification Using Kernel Discriminant Analysis

2006 ◽  
Vol 321-323 ◽  
pp. 1556-1559
Author(s):  
Wei Hua Li ◽  
Kang Ding ◽  
Tie Lin Shi ◽  
Guang Lan Liao
Keyword(s):  
Feature Extraction ◽  
Discriminant Analysis ◽  
Principal Component ◽  
Operating Conditions ◽  
Fault Classification ◽  
Kernel Principal Component Analysis ◽  
Kernel Discriminant Analysis ◽  
Vibration Signals ◽  
Gearbox Vibration ◽  
Gear Fault

This paper presents a study of KDA(kernel discriminant analysis) in gearbox failure feature extraction and classification. Experimental gearbox vibration signals measured from normal, gear small spall, gear severe spall and gear wear operating conditions are analyzed using either KPCA(kernel principal component analysis) or KDA as the feature extraction and fault classification methods. Experiment results indicate the effectiveness and thesuperiority of KDA for gear fault classification over KPCA.

Investigation on the Excitation Characteristics and Dynamic Response of the Multi-Support Flexible Rotor With Misalignment

2017 ◽  
Author(s):  
Sen Xiao ◽  
FaYong Wu ◽  
YanHong Ma ◽  
Jie Hong
Keyword(s):  
Dynamic Response ◽  
High Speed ◽  
Structural Characteristics ◽  
Rotation Frequency ◽  
Frequency Component ◽  
Typical Feature ◽  
Rotor System ◽  
Flexible Rotor ◽  
Rotor Systems ◽  
Response Characteristics

Aiming at the misaligned problems of high-speed flexible multi-supported rotor system, considering the structural characteristics and load characteristics of the rotor, the unbalanced excitation of the rotor with misalignment is presented and quantitatively described. The mechanical model of the high-speed flexible rotor system with multi-support under misaligned excitation is established. Based on the finite element method, the dynamic equation of the rotor system is given and the dynamic response characteristics of rotor systems are studied. The results show that the misalignment for the highspeed multi-support flexible rotor system can not only lead to 2X excitation and support stiffness nonlinearity, but also bring additional unbalanced excitation to the rotor system. The 2X frequency component is one typical feature for the rotor system with bearing misalignment. The vibration response of the rotor showed a trend of “increased slowly first, then reduced quickly as the rotation frequency increased”, and it turns to be more obvious with the increasing of the nonlinear stiffness and unbalance.

Sign in / Sign up

Export Citation Format

Share Document