Vibration Signals Of 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

Rotating machinery fault diagnosis using dimension expansion and AntisymNet lightweight convolutional neural network

Deep learning-based methods have made remarkable progress in the field of fault diagnosis for rotating machinery. However, convolutional neural networks are not suitable for industrial applications due to their large model size and high computational complexity. To address this limitation, this paper proposes the Antisym module and constructs AntisymNet, which is combined with dimension expansion algorithms for fault diagnosis of rotating machinery. To begin with, the original vibration signal of the rolling machinery is subjected to time-frequency transformations using the discrete Fourier transform and discrete wavelet transform. Subsequently, each transformed time-frequency signal is expanded in dimensions, resulting in two-dimensional matrix single channel images. These single channel images are then fused into RGB images to enhance the sample features. Finally, the proposed AntisymNet is utilized for recognizing and classifying the expanded signals. To evaluate the performance of AntisymNet, the MiniImageNet image dataset is employed as a benchmark, and a comparison is made with other state-of-the-art lightweight convolutional neural networks. Additionally, the effectiveness of the proposed fault diagnosis model is validated using the CWRU bearing dataset, Ottawa bearing dataset, and the hob dataset. The model achieves an impressive accuracy rate of 99.70% in the CWRU dataset, 99.26% in the Ottawa dataset, and an error rate of only 0.66% in the hob dataset. These results demonstrate the strong performance of the proposed fault diagnosis model.

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.

Parameterized Resampling Time-Frequency Transform

Many signals contain multiple components with time-varying instantaneous frequencies (IFs) which share a common trajectory trend, such as machinery vibration signals, speech signals, and biomedical signals. To analyze this kind of signals and achieve high time-frequency resolution, we propose a method called parameterized resampling time-frequency transform (PRTF transform) in this paper. Adapting the idea of the general parameterized time-frequency transform (GPTF transform), we use a parameterized kernel to represent a resampling function and further construct time-varying and time-invariant resampling operators to eliminate IF variations and relocate IF positions. These operators can improve the energy concentration of multiple components simultaneously in the time-frequency representation (TFR). Typical kernel functions containing the polynomial function and Fourier series are provided for different kinds of signals. A corresponding kernel estimation method is proposed to detect the shared trend of IFs by utilizing multiple components and to recursively approximate kernel parameters. Both numerical simulations and practical experiments show the effectiveness of the proposed method in improving the time-frequency resolution of TFRs for non-stationary multi-component signals.

Feature extraction based on generalized permutation entropy for condition monitoring of rotating machinery

Defective rotating machinery usually exhibits complex dynamic behavior. Therefore, feature representation of machinery vibration signals is always critical for condition monitoring of rotating machinery. Permutation entropy (PeEn), an adaptive symbolic description, can measure complexities of signals. However, PeEn, which compresses all the information into a single parameter, may lack the capability to fully describe the dynamics of complex signals. Afterward, multiscale PeEn (MPeEn) is put forward for coping with nonstationarity, outliers and artifacts emerging in complex signals. In MPeEn, a set of parameters serves to describe the dynamics of complex signals in different time scales. Nonetheless, an average procedure in MPeEn may withhold local information of complex signals and destroy internal structures of complex signals. To overcome deficiencies of PeEn and MPeEn, this paper proposes generalized PeEn (GPeEn) by introducing different orders and time lags into PeEn. In GPeEn, a complex signal is converted into a PeEn matrix rather than a single parameter. Moreover, minimal, maximal and average values of the PeEn matrix serve to briefly describe conditions of rotating machinery. Next, a numerical experiment proves that the proposed method in this paper performs better than skewness, kurtosis, PeEn and MPeEn in characterizing conditions of a Lorenz model. Subsequently, the proposed method in this paper is compared with skewness, kurtosis, PeEn and MPeEn by investigating gear and roll-bearing vibration signals containing different types and severity of faults. The results show that the proposed method in this paper outperforms the other four methods in distinguishing between different types and severity of faults of rotating machinery.

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.

Some aspects regarding planetary precessional transmissions dynamics

A mechanical system theoretically should not generate any vibrations and noise to be considered dynamically an ideal system, because vibrations mean a loss of energy. In planetary precessional reducers vibration can appear at bearings, gears, misaligned shafts, unbalanced rotors, couplings. Changes in dynamic process affects not only normal behaviors of mechanical systems but also the forces that act here. Regarding this aspects, regular vibration measurements during the operating speed provide information about any necessary repairs or maintenance. Here vibration research was made by using GUNT PT500 Machinery Diagnostic System and vibration signals was evaluated by using GUNT PT500.04 software which allow to perform correct Fast Fourier Transformation analysis. Data acquisition was made by using two piezoelectric accelerations sensor type IMI603C01 and one reference photoelectric sensor to record the shaft speed. Research concluded in this paper is made on precessional gearbox 2K-H Type. In first phase the crankshaft was installed with self-alignment on 2 radial bearings with cylindrical roller and second research phase was determination of the resonance domain and performing the spectral analysis by recording several vibrogram.

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.

Application Research of a New Adaptive Noise Reduction Method in Fault Diagnosis

The feature extraction of composite fault of gearbox in mining machinery has always been a difficulty in the field of fault diagnosis. Especially in strong background noise, the frequency of each fault feature is different, so an adaptive time-frequency analysis method is urgently needed to extract different types of faults. Considering that the signal after complementary ensemble empirical mode decomposition (CEEMD) contains a lot of pseudo components, which further leads to misdiagnosis. The article proposes a new method for actively removing noise components. Firstly, the best scale factor of multi-scale sample entropy (MSE) is determined by signals with different signal to noise ratios (SNRs); secondly, the minimum value of a large number of random noise MSE is extracted and used as the threshold of CEEMD; then, the effective Intrinsic mode functions(IMFs) component is reconstructed, and the reconstructed signal is CEEMD decomposed again; finally, after multiple iterations, the MSE values of the component signal that are less than the threshold are obtained, and the iteration is terminated. The proposed method is applied to the composite fault simulation signal and mining machinery vibration signal, and the composite fault feature is accurately extracted.

Compressed sensing reconstruction for axial piston pump bearing vibration signals based on adaptive sparse dictionary model

Aiming at the mechanical equipment in the fault diagnosis process, the traditional Shannon–Nyquist sampling theorem is used for data collection, which faces main problems of storage, transmission, and processing of mechanical vibration signals. This paper presents a novel method of compressed sensing reconstruction for axial piston pump bearing vibration signals based on the adaptive sparse dictionary model. First, vibration signals were divided into blocks, and an energy sequence was produced in accordance with the energy of each signal block. Second, the energy sequence of each signal block was classified by the quantum particle swarm optimization algorithm. Finally, the reconstruction of machinery vibration signals was carried out using the K-SVD dictionary algorithm. The average relative error of the reconstructed signal obtained by the proposed algorithm is 4.25%, and the reconstruction time decreases by 43.6% when the compression ratio is 1.6.

Diagnozowanie uszkodzeń wielostopniowej pompy odśrodkowej z wykorzystaniem metody odszumiania sygnału drgań w oparciu o średnie nielokalne

In real industry environment, the signal characteristics of multistage centrifugal pump vibration signal are easily submerged by strong background noise. To settle this problem, the nonlocal means (NLM) approach is proposed for the denoising of multistage centrifugal pump in this paper. Utilizing the similarity theory, the NLM method has achieved a wide range of applications in the fields of image processing and biomedical signal denoising. Due to the periodic characteristics and redundancy, NLM is successfully applied to the de-noising of 1-D machinery vibration signal. The numerical simulation experiments with different SNRs verify the effectiveness and the superiority of the proposed method. Besides, the selection principles of core parameters in NLM are discussed. The real engineering cases analysis demonstrates that the NLM can effectively filter out the background noise and realize the weak fault feature enhancements. The proposed noise reduction method is superior to traditional wavelet coefficient method.

Velocity Synchronous Linear Chirplet Transform

Linear transform has been widely used in time–frequency analysis of rotational machine vibration. However, the linear transform and its variants in current forms cannot be used to reliably analyze rotational machinery vibration signals under nonstationary conditions because of their smear effect and limited time variability in time–frequency resolution. As such, this paper proposes a new time–frequency method, named velocity synchronous linear chirplet transform (VSLCT). The proposed VSLCT is an extended version of the current linear transform. It can effectively alleviate the smear effect and can dynamically provide desirable time–frequency resolution in response to condition variations. The smearing problem is resolved by using linear chirplet bases with frequencies synchronous with shaft rotational velocity, and the time–frequency resolution is made responsive to signal condition changes using time-varying window lengths. To successfully implement the VSLCT, a kurtosis-guided approach is proposed to dynamically determine the two time-varying parameters, i.e., window length and normalized angle. Therefore, the VSLCT does not require the user to provide such parameters and hence avoids the subjectivity and bias of human judgment that is often time-consuming and knowledge-demanding. This method can also analyze normal monocomponent frequency-modulated signal.

A fault feature extraction method for single-channel signal of rotary machinery based on VMD and KICA

A feature extraction method combined with variational mode decomposition (VMD) and kernel independent component analysis (KICA) is proposed to improve the fault feature extraction of vibration signal of rotary machinery. Firstly, VMD is used to decompose the single-channel vibration signal. Secondly, calculate the correlation coefficient between each component and the original signal. Finally, a new multidimensional observation signal is formed with high correlation components, and the fault signals will be extracted from the new observation signal by KICA. Compared with some typical fault feature extraction methods, the better performance of the proposed method is demonstrated by two experiments which are faulty rolling bearing experiment and a comprehensive experiment with faulty rolling bearing and faulty gear. Furthermore, an experiment of faulty rotary shaft verifies the effectiveness of this method. The results demonstrate that the proposed method is efficient for fault feature extraction of single-channel vibration signal of rotary machinery.