Vibration Signals Of Rotating Machinery Research Articles

A Time–Frequency Image Quality Evaluation Method Based on Improved LIME

Deep learning has the characteristics of high efficiency, high accuracy and low knowledge dependence, and has become a hot method in the research field of rotating machinery fault diagnosis. The time–frequency transform can show both the time and frequency characteristics of the vibration signal, so the time–frequency image is often used as the input of deep learning networks. At present, there are many time–frequency transform methods, and how to choose one is a problem worth discussing. This paper proposed a time–frequency image quality evaluation method based on improved local interpretable model-agnostic explanations (LIME). With the input of deep learning networks as the application background, this method evaluates the time–frequency image quality of rotating machinery vibration signals from two aspects: the accuracy of the diagnosis results and the consistency of the interpretation results with prior knowledge. The feasibility of the proposed evaluation method is verified by experiments on the measured data set, and engineers’ trust in the deep learning model is improved.

Conditional Variational Encoder Classifier for Open Set Fault Classification of Rotating Machinery Vibration Signals

Conditional Variational Encoder Classifier for Open Set Fault Classification of Rotating Machinery Vibration Signals

Synchroextracting frequency synchronous chirplet transform for fault diagnosis of rotating machinery under varying speed conditions

The fault diagnosis of rotating machine is essential to maintain its operational safety and avoid catastrophic accidents. The vibration signals collected from the varying speed rotating machinery are non-stationary, and time–frequency analysis (TFA) is a feasible method for varying speed fault diagnosis by revealing time-varying instantaneous frequency (IF) information in signals. However, most conventional TFA methods are not specifically designed for rotating machinery vibration signals and may not be able to handle these signals, especially in the presence of noise. Therefore, this paper develops a unique TFA method designated as synchroextracting frequency synchronous chirplet transform (SEFSCT) for vibration signal analysis and fault diagnosis of rotating machinery. In the proposed method, the frequency synchronous chirplet transform (FSCT) that utilizes the frequency synchronous chirp rate is first introduced, which takes fully into account the intrinsic proportional relationship of time-varying IFs of the signal. Then, to further concentrate the time–frequency representation (TFR) of FSCT, the synchroextracting operator is constructed based on the Gaussian modulated linear chirp model and the SEFSCT is naturally developed by integrating the FSCT and synchroextracting operator. With the proposed SEFSCT, a high-quality TFR can be generated, thus the time-varying IFs and mechanical failure can be accurately identified. The SEFSCT is employed to deal with synthetic and actual signals, and the results illustrate its efficacy in handling non-stationary signals and diagnosing the mechanical failure.

Health Status Recognition Method for Rotating Machinery Based on Multi-Scale Hybrid Features and Improved Convolutional Neural Networks

Rotating machinery is susceptible to harsh environmental interference, and fault signal features are challenging to extract, leading to difficulties in health status recognition. This paper proposes multi-scale hybrid features and improved convolutional neural networks (MSCCNN) health status identification methods for rotating machinery. Firstly, the rotating machinery vibration signal is decomposed into intrinsic modal components (IMF) using empirical wavelet decomposition, and multi-scale hybrid feature sets are constructed by simultaneously extracting time-domain, frequency-domain and time-frequency-domain features based on the original vibration signal and the intrinsic modal components it decomposes. Secondly, using correlation coefficients to select features sensitive to degradation, construct rotating machinery health indicators based on kernel principal component analysis and complete health state classification. Finally, a convolutional neural network model (MSCCNN) incorporating multi-scale convolution and hybrid attention mechanism modules is developed for health state identification of rotating machinery, and an improved custom loss function is applied to improve the superiority and generalization ability of the model. The bearing degradation data set of Xi’an Jiaotong University is used to verify the effectiveness of the model. The recognition accuracy of the model is 98.22%, which is 5.83%, 3.30%, 2.29%, 1.52%, and 4.31% higher than that of SVM, CNN, CNN + CBAM, MSCNN, and MSCCNN + conventional features, respectively. The PHM2012 challenge dataset is used to increase the number of samples to validate the model effectiveness, and the model recognition accuracy is 97.67%, which is 5.63%, 1.88%, 1.36%, 1.49%, and 3.69% higher compared to SVM, CNN, CNN + CBAM, MSCNN, and MSCCNN + conventional features methods, respectively. The MSCCNN model recognition accuracy is 98.67% when validated on the degraded dataset of the reducer platform.

Slope synchronous chirplet transform and its application to tacho-less order tracking of rotating machineries

Chirplet transform (CT) has been widely used in time–frequency analysis (TFA) of rotating machinery vibration signals. However, due to the smear effect and time–frequency resolution limitation, CT and most of its improved algorithms cannot achieve sufficient refined time–frequency representation (TFR) for the instantaneous frequency (IF) close-spaced and IF trajectory slope mutation signals. Aiming at the aforementioned shortcomings, a novel TFA method named slope synchronous chirplet transform (SSCT) is proposed to address this problem. The proposed SSCT algorithm can adaptively adjust the window lengths according to the slope variation of the IF trajectory, thereby higher time–frequency resolution can be obtained for the IF close-spaced components. Besides, the proposed method utilizes a high-order phase operator to accurately capture the trend of IF trajectory slope, so that the time–frequency (TF) energy of the IF trajectory can be better concentrated, thereby the weak TF energy of the IF trajectory can be uncovered. The effectiveness of the proposed method is verified by simulated signals and an aero-engine vibration signal measured under a transient operating mode, the validation results indicate the proposed method outperforms some latest reported TFA algorithms and is available for accurate estimation of instantaneous angular speed for tacho-less order tracking of rotating machineries.

Time-varying filtering for nonstationary signal analysis of rotating machinery: Principle and applications

Rotating machinery vibration signals are composed of multiple time-varying frequency components under nonstationary conditions, and they usually overlap in the frequency domain. Effective extraction of these time-varying components is vital for rotating machinery fault diagnosis. This paper proposes a time-varying filtering (TVF) method for extraction of time-varying components. Its upper and lower cutoff frequencies are time-varying and independent. The TVF uses locally designed bandpass filters to achieve local filtering in the time domain, and exploits filtering with phase correction (FPC) and local filter lengths to ensure the phase and amplitude consistency of filtered signals. It cannot only extract time-varying mono-components but also separate time-varying frequency bands from highly nonstationary signals, for further time–frequency analysis: (1) fine time–frequency representations based on mono-components extraction, and (2) time-varying demodulation of time-varying frequency band of interests. The proposed method is illustrated and validated through numerical simulation, and signal analyses of typical rotating machines including a hydraulic turbine rotor, an aircraft engine rolling bearing, a multistage planetary gearbox, and a fixed shaft gearbox.

Rotating Machinery Fault Diagnosis Based on Adaptive Vibration Signal Processing under Safety Environment Conditions

At present, the degree of industrialization in China is deepening, and various types of production equipment appear. However, during the startup and operation of mechanical equipment, fracture and wear will occur due to various factors. Therefore, once the mechanical equipment fails, it must be diagnosed as soon as possible to avoid serious economic losses and casualties. Rotating machinery is an important power device, so it is necessary to regularly detect and monitor equipment signals to avoid the consequences of wrong control methods. In this study, the fault diagnosis of rotating machine based on adaptive vibration signal processing is studied under the safe environmental conditions. The fault diagnosis process of rotating machinery is to first collect vibration signals, then process signal noise reduction, and then extract fault characteristic signals to further identify and classify fault status and diagnose fault degree. This study briefly introduces several rotating machinery vibration signal processing methods and identifies the fault state of the rotating machine based on the high-order cumulant. By building a DDS fault diagnosis test bench, the chaotic particle swarm parameter optimization algorithm is used to calculate the accurate stochastic resonance parameters. After noise processing, the high-frequency part is significantly reduced. The results show that, after stochastic resonance wavelet decomposition and denoising processing, the number of intrinsic functions can be significantly reduced, the fault frequency can be increased, the high-frequency noise can be reduced, and the fault analysis accuracy can be improved. We identify the fault state of rotating machinery based on the high-order cumulant, train the four states of the bearing, and compare the four types of faults, no fault, inner ring fault, rolling element fault, and outer ring fault through the comparison of the actual test set and the predicted test set. It is concluded that the rotating machinery fault belongs to the rolling element fault and the identification accuracy rate is 95%. Finally, based on the LMD morphological filtering, the rotating machinery fault diagnosis is carried out, and the feature extraction is carried out based on the LMD algorithm to decompose the bearing fault signal. Finally, the result after the morphological filtering and LMD decomposition and extraction can avoid noise interference.

Adaptive high-resolution order spectrum for complex signal analysis of rotating machinery: Principle and applications

Order spectrum analysis is commonly used in rotating machinery vibration signal analysis under nonstationary conditions, because of its capability in detecting the rotating frequency and harmonics. Nevertheless, the conventional order spectrum suffers from some inherent drawbacks. For example, its application is limited by the inconvenience of rotary encoder or tachometer installation on running machines. Meanwhile, it is subjected to disturbances by speed-irrelative components, such as resonances and background noise, and angular resampling errors as well. More importantly, it is obtained by Fourier transforming the angular resampled signal, but the amplitude envelope after angular resampling is still nonstationary under time-varying conditions, leading to spectral blur of frequency orders and low resolution. To address the above issues, we propose an adaptive high-resolution order spectrum method, by exploiting the capability of multiple order probabilities approach (MOPA) in estimating rotating speed and that of adaptive iterative generalized demodulation (AIGD) in identifying true signal components of interest respectively. Firstly, the MOPA is utilized to extract the rotating speed from vibration signals, instead of using rotary encoders or tachometers. Then, the AIGD is adopted to identify true speed-related mono-components adaptively, thus eliminating interferences by speed-irrelative components. Finally, the order spectrum is constructed based on the average amplitude envelope and frequency order of each true component, instead of through angular resampling and Fourier transform. By doing so, the proposed order spectrum can adaptively identify rotating frequency orders in high resolution. The adaptability lies in that it does not need rotary encoders or tachometers, but adaptively estimates speed and identify rotating frequency harmonics, and therefore is more convenient in applications. The high resolution lies in that the energy highly concentrates at true frequency order, because it does not involve Fourier transform and angular resampling, thus being free of spectral blur, interferences by speed-irrelative components and resampling errors. The proposed method is illustrated and validated by analyses of numerical simulation and typical rotating machinery signals, including lab experiment and in-situ measurement of planetary gearboxes, and on-site measurement of a hydraulic turbine.

Multisource Fault Signal Separation of Rotating Machinery Based on Wavelet Packet and Fast Independent Component Analysis

The vibration signal of rotating machinery compound faults acquired in actual fields has the characteristics of complex noise sources, the strong background noise, and the nonlinearity, causing the traditional blind source separation algorithm not be suitable for the blind separation of rotating machinery coupling fault. According to these problems, an extraction method of multisource fault signals based on wavelet packet analysis (WPA) and fast independent component analysis (FastICA) was proposed. Firstly, according to the characteristic of the vibration signal of rotating machinery, an effective denoising method of wavelet packet based on average threshold is presented and described to reduce the vibration signal noise. In the method, the thresholds of every node of the best wavelet packet basis are acquired and averaged, and then the average value is used as a global threshold to quantize the decomposition coefficient of every node. Secondly, the mixed signals were separated by using the improved FastICA algorithm. Finally, the results of simulations and real rotating machinery vibration signals analysis show that the method can extract the rotating machinery fault characteristics, verifying the effectiveness of the proposed algorithm.

Adaptive correlated Kurtogram and its applications in wheelset-bearing system fault diagnosis

As one of the crucial subsystems, the performance of the wheelset-bearing system will significantly affect the running safety, stability and comfort of a high-speed train. Compared with the traditional rotating machinery vibration signals, those of wheelset-bearing systems have a distinct difference, for instance, the wheelset tread damage induced vibrations and bearing fault-related vibrations coexist and have similar wave-forms. Therefore, it is necessary to advance a reasonable method to identify the two kinds of cyclo-stationary components. To achieve this purpose, the adaptive correlated Kurtogram (ACK) is proposed. The proposed ACK method has two advantages: the first one is it can adaptively generate the paving of the plane for Kurtogram by using scale-space representation (SSR) to guarantee the detected boundaries cover the resonant frequency band well; the second one is it can highlight the special periodic impulses by correlated kurtosis. The scale-scale plane (SSP), which is obtained by SSR, is used to represent the frequency distribution characteristic of the acquired signal, firstly. After that, the paving of the plane is arbitrarily divided based on the SSP. Then the empirical wavelet transform (EWT) is employed to construct the sub-band signals according to the paving of the plane. The correlated kurtosis values with interesting periodic are calculated to distinguish the special repetitive transients. The nodes with the largest correlated kurtosis values are used to conduct a further envelope spectrum analysis. ACK method improves the effectiveness of the identification of the frequency bands containing impact information, and is capable of detecting multiple frequency bands simultaneously. The proposed ACK method is demonstrated by the simulated signal and two experimental signals acquired from a wheelset-bearing system test bench. The results indicate that the ACK can simultaneously extract the wheelset tread damage and bearing fault-related vibration component, and it is superior to the other traditional methods.

Sparse Representation Classification With Structured Dictionary Design Strategy for Rotating Machinery Fault Diagnosis

Fault diagnosis technique is the core of Prognostics and Health Management (PHM) system, which plays a crucial role in the intelligent operation and maintenance of various rotating machineries. In this paper, we present a novel sparse representation classification framework with structured dictionary design strategy (SRC-SDD) for intelligent fault diagnosis of rotating machineries. The proposed SRC-SDD method consists of two stages, i.e., the structured dictionary design stage and the sparsity-based intelligent diagnosis stage. In the first stage, the novelty of SRC-SDD lies in the overlapping segmentation strategy for structured dictionary design, which leverages the structured prior knowledge of rotating machinery vibration signals, namely, the periodic self-similarity and shift-invariance properties. In the second stage, SRC-SDD achieves fault recognitions of testing samples using a sparsity-based diagnosis strategy based on the minimum sparse reconstruction error. The proposed structured dictionary design strategy can enhance the representation power of dictionaries and thus promote the recognition performance of the sparsity-based diagnosis strategy. Finally, the effectiveness of SRC-SDD has been validated on the gearbox fault dataset from IEEE PHM society. The diagnosis results show that SRC-SDD achieves the excellent recognition accuracy of 100% for predicting six different gearbox health states. Further, the comparative studies with three conventional SRC methods prove the superiority of SRC-SDD in terms of both the recognition performance and computation efficiency.

General Parameterized Synchrosqueezing Transform and Its Application in Rotating Machinery Vibration Signal

General Parameterized Synchrosqueezing Transform and Its Application in Rotating Machinery Vibration Signal

An Enhancement Deep Feature Extraction Method for Bearing Fault Diagnosis Based on Kernel Function and Autoencoder

Rotating machinery vibration signals are nonstationary and nonlinear under complicated operating conditions. It is meaningful to extract optimal features from raw signal and provide accurate fault diagnosis results. In order to resolve the nonlinear problem, an enhancement deep feature extraction method based on Gaussian radial basis kernel function and autoencoder (AE) is proposed. Firstly, kernel function is employed to enhance the feature learning capability, and a new AE is designed termed kernel AE (KAE). Subsequently, a deep neural network is constructed with one KAE and multiple AEs to extract inherent features layer by layer. Finally, softmax is adopted as the classifier to accurately identify different bearing faults, and error backpropagation algorithm is used to fine-tune the model parameters. Aircraft engine intershaft bearing vibration data are used to verify the method. The results confirm that the proposed method has a better feature extraction capability, requires fewer iterations, and has a higher accuracy than standard methods using a stacked AE.

Pedestal looseness fault diagnosis in a rotating machine based on variational mode decomposition

According to the non-stationary characteristic of rotating machinery vibration signals of a rotor system with a loose pedestal fault, variational mode decomposition was applied in the pedestal looseness fault diagnosis for such a rotor system. Variational mode decomposition is used to decompose the rotor vibration signal into several stable components. This can achieve the separation of the pedestal looseness fault signal from the background signals, and extract the fault characteristic of a vibration signal from a rotor system with pedestal looseness. Experimental data from a rotor system with pedestal looseness were used to verify the proposed method. The results showed that the stable components of the rotor vibration signal obtained by variational mode decomposition have obvious amplitude modulation characteristics. The components which contain fault information were analyzed by envelope demodulation, which can extract the pedestal looseness fault features of a rotor vibration signal. Therefore, the variational mode decomposition method can be effectively applied to the pedestal looseness fault diagnosis of such a rotor system.

A hybrid fault diagnosis method based on second generation wavelet de-noising and local mean decomposition for rotating machinery

In order to extract fault features of large-scale power equipment from strong background noise, a hybrid fault diagnosis method based on the second generation wavelet de-noising (SGWD) and the local mean decomposition (LMD) is proposed in this paper. In this method, a de-noising algorithm of second generation wavelet transform (SGWT) using neighboring coefficients was employed as the pretreatment to remove noise in rotating machinery vibration signals by virtue of its good effect in enhancing the signal–noise ratio (SNR). Then, the LMD method is used to decompose the de-noised signals into several product functions (PFs). The PF corresponding to the faulty feature signal is selected according to the correlation coefficients criterion. Finally, the frequency spectrum is analyzed by applying the FFT to the selected PF. The proposed method is applied to analyze the vibration signals collected from an experimental gearbox and a real locomotive rolling bearing. The results demonstrate that the proposed method has better performances such as high SNR and fast convergence speed than the normal LMD method.

Rotating Machinery Vibration Signal Processing And Fault Diagnosis Based on LMD

There are abundant of fault information in rotating machinery vibration signal. On account of the nonlinearity and non-stationarity, the paper first does pre-process to the vibration signal using wavelet threshold denoising method and this method can bring a smooth signal. Then it decomposes the vibration signal using local mean decomposition(LMD), which is effective to the vibration signal. The LMD decomposes the signal into many PFs as the frequency from high to low. These PFs are composed of the production of envelop signal and pure frequency modulated signal. Finally, it takes most use of the kurtosis which is sensitive to the fault impact. By calculating the kurtosis of PF, it can assess the distribution of fault impact signal in every frequency band, consequently distinguishing the operating state of bearing and recognizing the fault mode according to the growth of turtosis. The experiment of actual bearing vibration signal demonstrates that the methods this paper proposed can effectively diagnose the vibration fault and has good performance.

A Vibration Signal Analysis Method based on Enforced De-Noising and Modified EMD

To deal with the noise from rotating machinery vibration signal and analysis the fault signal, a rotating machinery fault diagnosis method based on enforced de-noising and modified EMD is proposed. Firstly, fault signals were de-noised by the wavelet with enforced threshold in order to filter the noises in the high frequency, and then the EMD method used to decompose the fault signals into a finite number of stationary intrinsic mode function (IMFs), then the linear correlation coefficient between two sets of data is proposed to select the useful IMF. In order to restrain the endpoint effect of EMD, in this paper, the cosine window function is employ to the fault signals, and then the envelope error of the fault signals is controlled at the both endpoints of the vibration signals. Experimental results shows: this proposed method can extract the fault information effectively, with overcoming the drawbacks of EMD well.

Application of Virtual Instrument on Condition Monitoring and Fault Diagnosis System of the Rotating Machinery

In the paper it can be easier to realize the acquisition of the rotating machinery vibration signal and condition monitoring through the configuration the platform of virtual instrumentation. For the data acquisition it is enough to be plus with two acceleration sensors and a counter. The system is divided into parameter setting module, data acquisition, storage and display module, amplitude domain analysis module, time-domain analysis module, frequency domain analysis module, time-frequency domain analysis module and fault diagnosis module. The signal acquisition is got by using the PCI-6024E data acquisition card. And it is can be saved as binary data stream files and waveform data file according to the requirements of the sequence data processing. Signal analysis is conducted by using LabVIEW software and draw out the vibration spectrum diagram in order to achieve fault diagnosis of rotating machinery.

Fault Diagnosis System of Rotating Machinery Vibration Signal

A high demand has been presented in the measuring and diagnosis of vibration signal of rotating machinery, which can reflect the running state information of rotating machinery equipment. This paper designs a new type of fault diagnosis system of rotating machinery vibration signal, which can measure the vibration acceleration and velocity signals accurately, and analyze the vibration severity and frequency division amplitude spectrum of vibration signal. Experiment showed that our system can diagnose typical mechanical fault.

Application of SVM and SVD Technique Based on EMD to the Fault Diagnosis of the Rotating Machinery

Targeting the characteristics that periodic impulses usually occur whilst the rotating machinery exhibits local faults and the limitations of singular value decomposition (SVD) techniques, the SVD technique based on empirical mode decomposition (EMD) is applied to the fault feature extraction of the rotating machinery vibration signals. The EMD method is used to decompose the vibration signal into a number of intrinsic mode functions (IMFs) by which the initial feature vector matrices could be formed automatically. By applying the SVD technique to the initial feature vector matrices, the singular values of matrices could be obtained, which could be used as the fault feature vectors of support vector machines (SVMs) classifier. The analysis results from the gear and roller bearing vibration signals show that the fault diagnosis method based on EMD, SVD and SVM can extract fault features effectively and classify working conditions and fault patterns of gears and roller bearings accurately even when the number of samples is small.