Maximum Correlated Kurtosis Deconvolution Research Articles

Maximum Gpq–mean deconvolution for the impulsive fault feature enhancement of rolling bearing

Abstract The bearing fault signal is easily obscured by background noise and random shocks in the initial stage. The maximum Gpq–mean deconvolution (MGD) method is proposed to address the challenge of extracting fault feature signals in the presence of impact interference. The use of a nonlinear activation function in MGD enhances the distribution characteristics of the filtered signal. The proposed method adopts a new sparse measurement method, which enhances the sparse measurement capability and solves the problem of the difficulty in extracting periodic fault signals under impact. The superiority of the method in rolling bearing diagnosis is demonstrated through simulation and experimental analyses. In comparison with traditional methods, such as minimum entropy deconvolution (MED), optimal minimum entropy deconvolution adjustment (OMEDA), and maximum correlated kurtosis deconvolution (MCKD), the proposed method in this paper significantly improves the ability of extracting bearing fault signals.
Keywords: Minimum Entropy Deconvolution; Kurtosis; Blind Deconvolution; Sparse Metric

Fault diagnosis of tooth surface spalling based on variational mode decomposition and maximum correlation kurtosis method

As the early fault features of tooth surface spalling are very weak and difficult to extract because of random noise and other types of signal interference, a method that combines maximum correlation kurtosis uncoiling and variational mode decomposition is proposed herein. First, a series of modes are obtained by variational mode decomposition, and the kurtosis criterion is applied to select the modes containing rich fault information for reconstruction and noise reduction. Second, the maximum correlation kurtosis deconvolution method is used to enhance the selected signals. Finally, the fault features are extracted by envelope demodulation of the reconstructed signal. The effectiveness of the proposed method is verified by analysis, and the different frequency components of the vibration signals of tooth surface spalling faults are shown to be separated accurately.

A novel time-frequency slice extraction method for target recognition and local enhancement of non-stationary signal features

Blind deconvolution can remove the effects of complex paths and extraneous disturbances, thus recovering simple features of the original fault source, and is used extensively in the field of fault diagnosis. However, it can only identify and extract the statistical mean of the fault impact features in a single domain and is unable to simultaneously highlight the local features of the signal in the time-frequency domain. Therefore, the extraction effect of weak fault signals is generally not ideal. In this paper, a new time-frequency slice extraction method is proposed. The method first computes a high temporal resolution spectrum of the signal by short-time Fourier transform to obtain multiple frequency slices with distinct temporal waveforms. Subsequently, the constructed harmonic spectral feature index is used to quantify and target the intensity of feature information in each frequency slice and enhance their fault characteristics using maximum correlation kurtosis deconvolution. Enhancing the local features of selected frequency slice clusters can reduce noise interference and obtain signal components with more obvious fault signatures. Finally, the validity of the method was confirmed by a simulated signal and fault diagnosis of the rolling bearing outer and inner rings was accomplished sequentially. Compared with other common deconvolution methods, the proposed method obtains more accurate and effective results in identifying fault messages.

Complementary Ensemble Empirical Mode Decomposition and Maximum Correlated Kurtosis Deconvolution for Wind Turbine Bearing Fault Feature Extraction

Wind turbine bearing fault signals exhibit characteristics such as nonlinearity, non-stationarity, and susceptibility to external noise interference, making it challenging to extract fault features and identify them accurately. In light of these issues, this paper proposes a fault signal feature extraction method that combines complementary ensemble empirical mode decomposition (CEEMD) and maximum correlated kurtosis deconvolution (MCKD). CEEMD is utilized to decompose the signals, reducing mode mixing and eliminating residual auxiliary noise in the decomposition process, thereby obtaining linear and stationary signals that enhance the significance of the features. MCKD is employed to increase the kurtosis value of the fault signals, facilitating the extraction of continuous transient impacts from weak fault signals. Finally, a Convolutional Neural Network (CNN) is employed to validate that the method enhances fault characteristics and improves the accuracy of fault signal recognition.

Fault diagnosis method of weak vibration signal based on improved VMD and MCKD

During the manufacturing process of electronic equipment, objects such as tin beads and glue blocks may be left in the electronic equipment, causing failure of the electronic equipment. This paper uses experimental equipment to collect weak vibration signals on the surface of electronic equipment. In view of the nonlinear and non-stationary characteristics of the vibration signal and its easy to be masked by strong background noise, a fault diagnosis method of weak vibration signal based on improved variational mode decomposition (VMD) and maximum correlation kurtosis deconvolution (MCKD) is proposed. Cosine factors and adaptive weights are introduced to improve the convergence accuracy of the Whale Optimization Algorithm (WOA). The envelope spectrum peak factor is used as the adaptability function of the improved whale algorithm (IWOA) to optimize the parameters of VMD and MCKD. Firstly, based on the decomposition results of weak fault signals by IWOA-VMD, the optimal modal components are selected. Secondly, the fault impact component in the optimal modal component is enhanced based on the IWOA-MCKD algorithm. Finally, the fault characteristic frequency is extracted through the envelope spectrum. The feasibility and superiority of the proposed optimization method are verified through simulation signal analysis and actual case study.

Remaining Useful Life Prediction of Rolling Bearings Based on Multi-scale Permutation Entropy and ISSA-LSTM.

The performance of bearings plays a pivotal role in determining the dependability and security of rotating machinery. In intricate systems demanding exceptional reliability and safety, the ability to accurately forecast fault occurrences during operation holds profound significance. Such predictions serve as invaluable guides for crafting well-considered reliability strategies and executing maintenance practices aimed at enhancing reliability. In the real operational life of bearings, fault information often gets submerged within the noise. Furthermore, employing Long Short-Term Memory (LSTM) neural networks for time series prediction necessitates the configuration of appropriate parameters. Manual parameter selection is often a time-consuming process and demands substantial prior knowledge. In order to ensure the reliability of bearing operation, this article investigates the application of three advanced techniques-Maximum Correlation Kurtosis Deconvolution (MCKD), Multi-Scale Permutation Entropy (MPE), and Long Short-Term Memory (LSTM) recurrent neural networks-for the prediction of the remaining useful life (RUL) of rolling bearings. The improved sparrow search algorithm (ISSA) is employed for configuring parameters in the Long Short-Term Memory (LSTM) network. Each technique's principles, methodologies, and applications are comprehensively reviewed, offering insights into their respective strengths and limitations. Case studies and experimental evaluations are presented to assess their performance in RUL prediction. Findings reveal that MCKD enhances fault signatures, MPE captures complexity, and LSTM excels in modeling temporal patterns. The root mean square error of the prediction results is 0.007. The fusion of these techniques offers a comprehensive approach to RUL prediction, leveraging their unique attributes for more accurate and reliable predictions.

Research on fault diagnosis model for drilling pump fluid end based on enhanced vibration-strain signals under multiple operating conditions

Fault diagnosis of the fluid end faces two challenges. One is that the vibration signal used for diagnosis contains a lot of noise, and the other is that the vibration signal cannot fully reflect the fault state. In this paper, a model based on enhanced vibration-strain signals is proposed to improve the fault diagnosis accuracy of the drilling pump fluid end. First, the sparrow search algorithm (SSA) is employed to optimize maximum correlated kurtosis deconvolution (MCKD) to enhance the impact component of the vibration signal. Second, the enhanced vibration-strain signals are proposed to accurately describe the working state of the fluid end. Third, a one-dimensional convolutional neural network (CNN) with dual-signal feature fusion is established to diagnose faults of the fluid end. The results demonstrate that when utilizing the SSA-MCKD enhanced vibration-strain signal as input, the CNN model achieved an outstanding average diagnosis accuracy of 99.26% across various operating conditions.

Blind extraction of acoustic signals from rolling bearing composite faults based on ISCA-IMCKD

In production practice, the signal gathered by a sensor often includes strong ambient noise, and its composition is complex. Focusing on the problem that traditional methods are difficult to separate and extract fault frequencies from strong background noise, a novel compound fault blind extraction method based on improved sparse component analysis (ISCA) and improved maximum correlation kurtosis deconvolution (IMCKD)-named ISCA‐IMCKD- is suggested. Initially, the signal that the sensor has collected is shifted into time-frequency area signal by short-time Fourier transform (STFT). In addition, the single source domain characteristic data is screened by improved single source point detection to determine the number of sources. Second, the ISCA method is optimized by using cosine distance improved fuzzy C-means clustering, which is utilized to further process the characteristic data to calculate the mixing matrix. Moreover, the estimated source signal is initially extracted according to the membership degree of clustering results. Finally, the estimated source signal is shifted into the time area by inverse STFT transform, and the IMCKD is employed to enhance the characteristics of the projected source signals. Meanwhile, the initially estimated source signal is completely separated, and the defect frequencies of the composite faults are finally extracted by envelope analysis. Simulation experiments and measured data are employed to certify the viability of the proposed means. The defect detection of rolling bearings is finished while the time cost is significantly saved.

SO-IMCKD processed signal improving MSCNN model’s fault diagnosis accuracy for drilling pump fluid end

Drilling pump is the ‘heart’ of drilling construction. The key to accurate fault diagnosis is to extract useful fault features from noisy raw signals. In order to improve the accuracy of fault diagnosis of drilling pump fluid end, this paper proposes a fault diagnosis method based on multi-scale convolutional neural network (MSCNN) combined with the snake optimization optimized maximum correlation kurtosis deconvolution (SO-IMCKD). First, the SO algorithm is employed to optimize the filter length and the shift number of IMCKD to process the raw signal, enhancing the fault features from the raw signal. Second, the continuous wavelet transform is used to convert the enhanced signals into time-frequency images which are input into an established MSCNN to extract the fault feature more effectively. Finally, by changing the training batchsize of the MSCNN model, the identification effect of the model to the normal state, minor damage, and serious damage of the fluid end is analyzed. The identification of nine states of the fluid end is successfully carried out, with an average diagnostic accuracy of 99.93%. Moreover, the adaptability of the proposed method is verified with the Mechanical Failure Prevention Technology Association dataset. The method has high accuracy and good adaptability, which has desired prospect for drilling pump fault diagnosis and bearing fault diagnosis.

Application of Demodulation Frequency Band Optimization in Compound Fault Detection of Rolling Element Bearing Based on Fast Spectrum Correlation

The key to demodulation analysis is determining the appropriate demodulation frequency band. However, the coupling of compound faults significantly increases the difficulty. How to determine the fault-related demodulation frequency band is a challenge for the application of demodulation analysis in compound fault detection. To address this issue, a demodulation frequency band optimization method based on fast spectral correlation (Fast-SC) is proposed to detect compound faults of rolling element bearing in this paper. Firstly, the bi-variable map of vibration signal is obtained by Fast-SC. Secondly, the bi-variable map is sliced according to the theoretical fault-related frequency along the carrier frequency axis, obtaining a curve of correlation value versus carrier frequency, which is regarded as the target spectrum correlation curves (T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scc</sub> ). Thirdly, the carrier frequency corresponding to the maximum value of the T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scc</sub> obtained from each component is used to determine the initial demodulation frequency band. Fourthly, the crest of envelope spectrum (EC) is used to optimize the demodulation frequency band. Finally, the characteristic frequencies are exposed by utilizing the envelope demodulation on the frequency bands of each component. Simulation and experiment show that the proposed method is effective for the detection of rolling element bearing compound faults. Compared with maximum correlated kurtosis deconvolution(MCKD) and variational mode decomposition(VMD), the calculation cost of the proposed method is significantly reduced to about 6.6% of the above two methods.

Fault Traveling Wave Detection Method based on ICEEMDAN-MCKD

To address the challenge of calibrating the traveling wave-front for fault location in high noise environments, we propose an improved method that combines the ICEEMDAN and maximum correlation kurtosis deconvolution (MCKD). Our approach first decomposes the fault traveling wave signal into modal components using the ICEEMDAN algorithm. Next, the MCKD algorithm enhances the energy amplitude of the decomposed signal, suppresses strong background noise interference, and accurately calibrates the fault traveling wave-front. Simulation results demonstrate that ICEEMDAN-MCKD achieves precise calibration of the wave-front, exhibits strong denoising ability, and performs better than existing methods in terms of detecting traveling waves and minimizing wave-front determination time errors in noisy environments.

Incipient Fault Feature Enhancement of Rolling Bearings Based on CEEMDAN and MCKD

A rolling bearing vibration signal fault feature enhancement method based on adaptive complete ensemble empirical mode decomposition with adaptive noise algorithm (CEEMDAN) and maximum correlated kurtosis deconvolution (MCKD) is proposed to address the issue that rolling bearings are prone to noise in the early stage and difficult to extract feature information accurately. The method uses the CEEMDAN algorithm to reduce the noise of the rolling bearing vibration signal in the first step; then, the MCKD algorithm is used to deconvolve the signal to enhance the weak shock components in the signal and improve the SNR. Finally, the envelope spectrum analysis is performed to extract the feature frequencies. Simulation and experimental results show that the CEEMDAN-MCKD method can highlight the fault characteristic frequency and multiplier frequency better than other methods and realize the characteristic enhancement of incipient fault vibration signals of rolling bearings under constant and variable operating conditions.

A novel method for early fault diagnosis of planetary gearbox with distributed tooth surface wear

Planetary gearbox (PGB) usually work in harsh working conditions with low speed and heavy load, and they are prone to wear. Different from the local faults, the distributed faults such as tooth surface wear are often weak and difficult to detect in the early stage, and it is difficult to extract fault characteristic. This paper presents an early fault diagnosis method for the distributed tooth surface wear of PGB to solve this problem. The proposed multi-channel optimal maximum correlation kurtosis deconvolution (MCO_MCKD) algorithm is used to extract fault characteristic. In order to enhance the effect of fault characteristic extraction (FCE), the algorithm first uses the sliding window principle to segment the input signal to establishes multiple channels for maximum correlation kurtosis (max_CK) optimization based on all the short signals obtained. The finite impulse response (FIR) filter with the max_CK is selected to filter the input signal, in order to realize FCE. The influence of tooth wear is mainly reflected in the frequency-domain signal amplitude. In order to realize early fault diagnosis, the frequency-domain statistical indicator fault characteristic energy ratio (FCER) is proposed based on this characteristic. The health status of the equipment is monitored by calculating the FCER of the signal after FCE. Early fault diagnosis is realized based on the mutation of the FCER. The simulation results show that MCO_MCKD algorithm has strong robustness. The experimental results show this proposed method is effective and superior.

Bearing fault-induced feature enhancement via adaptive multi-band denoising model

To accurately extract the bearing fault-induced impulse features from the vibration signals corrupted by heavy noise and large-amplitude random impulses, an adaptive multi-band denoising model based on the Morlet wavelet filter and sparse representation is put forward. First, to locate the desired frequency band associated with fault components, the Morlet wavelet filter is employed to band-pass the signal from the perspective of the frequency-domain. Herein, an improved Protrugram-based index, termed as windowed envelope spectral kurtosis, is designed as the objective function to choose the optimal center frequency and the bandwidth of the Morlet wavelet filter. Furthermore, benefitting from the time-domain characteristics of the vibration signal, the in-band noise is eliminated by sparse representation. One of the critical parameters (resonance frequency) of the wavelet atom used in the sparse representation dictionary is directly taken as the center frequency of the Morlet wavelet filter, which makes full use of the information derived from the filter, and thus significantly improves the calculation efficiency. Finally, the recovery signal is demodulated by the Hilbert transform to extract the fault characteristic frequency. The effectiveness and superiority of the proposed method are demonstrated through a complete analysis of the simulated, experimental, and engineering signals, as well as a comparison with such prevalent methods as Kurtogram, individual sparse representation, and Morlet wavelet filter combined with the maximum correlation kurtosis deconvolution.

Blind Deconvolution Based on Correlation Spectral Negentropy for Bearing Fault.

Blind deconvolution is a method that can effectively improve the fault characteristics of rolling bearings. However, the existing blind deconvolution methods have shortcomings in practical applications. The minimum entropy deconvolution (MED) and the optimal minimum entropy deconvolution adjusted (OMEDA) are susceptible to extreme values. Furthermore, maximum correlated kurtosis deconvolution (MCKD) and multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) are required prior knowledge of faults. On the basis of the periodicity and impact of bearing fault signals, a new deconvolution algorithm, namely one based on maximum correlation spectral negentropy (CSNE), which adopts the particle swarm optimization (PSO) algorithm to solve the filter coefficients, is proposed in this paper. Verified by the simulated vibration model signal and the experimental simulation signal, the PSO-CSNE algorithm proposed in this paper overcomes the influence of harmonic signals and random pulse signals more effectively than other blind deconvolution algorithms when prior knowledge of the fault is unknown.

A Portable Microwave Intracranial Hemorrhage Imaging System Based on PSO-MCKD-CEEMDAN Method

A novel signal processing method to directly extract the hemorrhage response signals using the maximum correlation kurtosis deconvolution (MCKD) technique and complete ensemble empirical mode decomposition (CEEMDAN) algorithm is proposed in this article. This method only needs to acquire the raw data measured one time, which saves a lot of time in data acquisition. In emergency cases, a shorter time in detection means a better prognosis and better life for the patients. A portable microwave brain hemorrhage imaging system comprising a portable vector network analyzer (VNA), a small-sized antenna array (30 mm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 30.5 mm of each antenna), a flexible substrate, simple structure, and wideband (0.5–6 GHz) is established by applying this proposed signal processing method. The preliminary results from the experiments on the head phantom demonstrate the capability and effectiveness of this proposed method. Final results show that the proposed portable microwave imaging system can successfully detect brain hemorrhage with a size of 17 mm in diameter. The robustness of the proposed method is verified by successfully detecting the brain hemorrhage with a size of 20 mm in diameter.

Research on the detection of axle abnormal noise based on maximum autocorrelation kurtosis deconvolution

The axle off-line detection is an important link to ensure the sound quality of the axle. The traditional methods mainly rely on condition indicators, psychoacoustic parameters and artificial intelligence, in which the generation mechanism of the abnormal signal is ignored, thus leading to low accuracy and poor interpretability. To solve these problems, a vehicle axle abnormal sound detection method based on abnormal sound mechanism is proposed in this paper. Firstly, the sound quality of 30 newly produced axles is determined by subjective evaluation, and it is clear that the tooth frequency impulse is the main reason for the abnormal sound of axles. Then, a new objective function, autocorrelation kurtosis, is used to deconvolute the axle vibration signal for the periodic impulse feature. Simulation and experimental results show that the proposed maximum autocorrelation kurtosis deconvolution (MACKD) is more effective than maximum correlation kurtosis deconvolution (MCKD) and minimum entropy deconvolution (MED). On this basis, the impulse autocorrelation kurtosis index (IACK) is constructed and used to quantify the abnormal sound of the axle. The results show that the correlation between the proposed index and the subjective evaluation results is more than 0.9, which can better identify the sound quality of the axle.

Deep network-based maximum correlated kurtosis deconvolution: A novel deep deconvolution for bearing fault diagnosis

Deconvolution methods (DMs) which can adaptively design the filter for the feature extraction is the most effective tool to counteract the effect of the transmission path. Convolutional sparse filter (CSF) as a new deconvolution mode, which transfers the complicated numeric calculation to the simple feature learning for the optimization and solution of the deconvolution filter coefficient using neural network, has a remarkable superiority especially under the heavy noise condition compared with the traditional DMs. Yet, the problems of the filter length selection and the sensibility to random interference largely confine its application. Motived by this, a novel deep network-based maximum correlated kurtosis deconvolution (MCKD-DeNet) is proposed in this paper. Firstly, according to the multiple-inputs way of the neural network, a filter initialization is designed using the Hanning window. With different filters guided by the initialization, a serial of filtered signals is input to learn the fault feature. Secondly, correlated kurtosis, which can simultaneously evaluate the periodicity and impulsiveness of the signal, is chosen as the new cost function to train the neural network. And the input period is estimated between the layers by calculating the autocorrelation of the most informative filtered signal. Subsequently, the component with most fault information is locked as the output of MCKD-DeNet using the proposed dimension reduction method based on the correlation coefficient. Finally, compared with previous CSF and improved maximum correlated kurtosis deconvolution, the proposed MCKD-DeNet is verified to have the performance superiority by simulated signal with different noise levels and interference as well as experimental data collected from wind turbine experiment bench with bearing fault.

PSO-MCKD-MFFResnet based fault diagnosis algorithm for hydropower units.

Due to the coupling effect of external environmental noise and vibration noise, the feature rate of the original hydroelectric unit fault signal is not prominent, which will affect the performance of fault diagnosis algorithms. To solve the above problems, this paper proposes a PSO-MCKD-MFFResnet algorithm for fault diagnosis of hydropower units (Particle swarm optimization, PSO; Maximum correlation kurtosis deconvolution, MCKD; Multi-scale feature fusion residual network, MFFResnet). In practical applications, the selection of key parameters in the traditional MCKD method is heavily dependent on prior knowledge. First, this paper proposes a PSO-MCKD enhancement algorithm for fault features, which uses the PSO algorithm to search for the influencing parameters of MCKD to enhance the features from the original fault signal. Second, a fault feature diagnosis algorithm based on MFFResnet is proposed to improve the utilization of local features. The multi-scale residual module is used to extract features at different scales and then put the enhanced signal into MFFResnet for training and classification. The experimental results show that our approach can accurately and effectively classify the fault types of hydropower units, with an accuracy rate of 98.85. It is superior to other representative algorithms in different indicators and has a good stability.

Fault feature extraction method of pump data sample under strong impact and strong noise environment

The condition monitoring and fault diagnosis of pump stations are essential to ensure the normal operation of pump stations. This work monitors the vibration, swing, pressure pulsation, noise, speed of the pump unit in the steady and transient operation process and diagnoses the equipment state to judge the safety and health of the unit. The fault feature extraction method suitable for the environment of strong impact and strong noise is studied. The frequency band segmentation, accuracy chart to determine the resonance frequency band and the maximum correlation kurtosis deconvolution method are used to enhance the fault feature. Finally, the data measured are sampled and selected, and the kurtosis of the system software is measured the skewness and other indicators are compared with the indicators of handheld analysis and measurement data. The total accuracy rate of data collected by the system software reaches 98.22%.