Selection Of Intrinsic Mode Functions Research Articles

Rotating machinery fault diagnosis based on parameter-optimized variational mode decomposition

Variational Mode Decomposition (VMD) has been widely applied in rotating machinery fault diagnosis. However, VMD needs to solve two key problems in its application: parameter optimization and the selection of high-quality Intrinsic Mode Functions (IMFs). To address these issues, firstly, the Sparrow Search Algorithm (SSA) is employed to optimize VMD parameters, incorporating fitness functions based on the Hoyer measure and the square envelope spectrum negative entropy. Subsequently, by minimizing the fitness function, optimal parameters for VMD are obtained. Secondly, a novel IMF selection method is proposed, evaluating IMF quality through sample entropy, energy ratio, and Spearman rank correlation coefficient to identify IMFs sensitive to fault features. Finally, the proposed method is validated using gear and bearing datasets containing noise of varying intensities, demonstrating its outstanding capability for extracting sensitive information in different noise environments.

A hybrid ICEEMDAN and OMEDA-based vibrodiagnosis method for the bearing of rolling stock

Purpose. To develop a hybrid method based on ICEEMDAN and OMEDA for high-fidelity detection of the diagnostic features of the technical condition of roller bearing. Methodology. Due to digital signal processing the search was made of the informative components on the broadband spectra, envelope spectra, squared envelope spectra. The usage of the methods of mathematical statistics for the selection of informative IMFs as a result of iterative calculate procedures. The introduction of blind deconvolution method with a proper objective function for the enhancement of impulse fault features. Findings. The use of traditional spectral methods provided an incomplete list of diagnostic features of bearing roller damage. The empirical mode decomposition (EMD) method and its minor versions provide the series of intrinsic mode functions (IMFs). On the broadband vibration spectra of the selected low-frequency IMFs, diagnostic features were not detected in a sufficient number. Further research focused on the development of a hybrid method that takes into account the demodulation procedure of the high-frequency components of those IMFs that were selected according to the complex evaluation index. The Fast Kurtogram technique determined an informative frequency band of 7.2–7.5 kHz for demodulation and construction of the squared envelope spectra, where harmonics of the roller spin frequency and some side bands with a width equal to the separator rotation frequency appeared. The use of OMEDA caused the reduction of residual noise on the squared envelope spectra and bilateral sidebands to appear around all harmonics of the roller spin frequency. Originality. For the first time, the whole list of the diagnostic features of roller faults of the axle-box bearing was identified using the developed hybrid method, which involves steps of noise reduction for enhancing a physical meaning of a proper frequency components, associated with faults. The usage of the optimal minimum entropy deconvolution adjusted method helped to eliminate noise and provide all diagnostic features of the technical condition on the squared envelope spectrum. Practical value. The results of the study help to control the quality of repair of the axle-box rolling bearings on the test rig at the workshop of the freight railway car depot.

Time-Domain Electromagnetic Noise Suppression Using Multivariate Variational Mode Decomposition

Noise suppression is essential in time-domain electromagnetic (TDEM) data processing and interpretation. TDEM data are typically in broadband signal, which makes it difficult to separate the signal in the whole frequency band. The conventional methods tend to process data trace by trace, ignoring the lateral continuity between channels. This paper proposes a workflow based on multivariate variational mode decomposition (MVMD) and multivariate detrended fluctuation analysis (MDFA) to deal with the noise in 2-D TDEM data. The proposed method initially employs MVMD to decompose TDEM signals into a series of intrinsic mode functions (IMFs). Subsequently, MDFA is used to calculate the scaling exponent of each IMF, facilitating the selection of signal-dominant IMFs. Finally, the signal IMFs are summed up to reconstruct the TDEM signal. Both simulation and field results demonstrate that, by considering the lateral continuity of data across channels, the proposed method is more effective at noise removal than other single-channel data processing techniques.

An adaptive enhanced envelope spectrum technique for bearing fault detection in conditions characterized by strong noise

Rolling bearings are widely used in rotating machinery and have a high failure rate. Regrettably, the task of ensuring dependable bearing fault detection presents a formidable challenge, especially when the bearing fault-related characteristics are non-stationary or even affected by strong noise. In response to this challenge, a novel adaptive enhanced envelope spectrum (AEES) technique is proposed in this study. Firstly, it generates representative intrinsic mode functions (IMFs) using the variational mode decomposition algorithm. Then, based on the analysis of the envelope spectrum normalized mutual information and time-domain fuzzy entropy, a new IMF selection and integration strategy combining time- and frequency-domain metrics is suggested to reconstruct the most informative analytical signal. An adaptive filter is employed to post-process the reconfigured signal to reinforce fault-related impulsive characteristics, the optimal length of which is ascertained through the proposed variable step-size search technique based on unbiased autocorrelation analysis. The efficacy of the AEES technique has been validated through a sequence of experiments conducted under diverse bearing conditions. Its robustness and distinct advantages under strong noise conditions are tested using a publicly available dataset. The validation results show that the AEES technique can effectively identify the health conditions of bearings under high noise conditions (signal-to-noise ratios between 1 dB and 3 dB). Compared with two relevant techniques in the existing literature and a classical method, the proposed AEES technique can achieve signal processing results with fewer interference components and more prominent characteristic frequency information and has a unique ability to identify fault features in some challenging situations.

New health indicators for the monitoring of bearing failures under variable loads

Bearings are one of the most critical components in rotating machines. Unexpected failure of this components may cause serious damages and unplanned breakdowns. In this paper, a new method is proposed for bearing fault diagnosis under various loads based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and the sequential backward selection (SBS). The CEEMDAN is used for the automatic selection of intrinsic mode functions from vibration signals to build a bank of health indicators. Then, the SBS algorithm is used to select the most relevant indicators of the bearing different failure modes. To test the proposed method accuracy, it was first applied to the Case Western Reserve University dataset. Then, data collected from a dedicated test bench of the Laboratory of Signal and Industrial Process Analysis were introduced to this method to classify different bearing health states. The obtained results show that the proposed method is effective in identifying and classifying bearing faults under various loads with high accuracy. This method can be used for condition monitoring of bearings and prognostics in real industrial applications.

An Improved Denoising Method for Fault Vibration Signals of Wind Turbine Gearbox Bearings

Vibration monitoring (VM) is an important tool for fault diagnosis in key components of wind turbine gearboxes (WTGs). However, due to the influence of white noise and random interference, it is difficult to realize high-quality denoising of WTG-VM signals. To overcome this limitation, a novel joint denoising method for fault WTG-VM signals is proposed in this article, which we have named EWTKC-SVD. First, the empirical wavelet transform (EWT) boundary exploration method is used to optimize frequency band allocation and obtain the multiple intrinsic mode functions (IMFs). Second, the sensitive IMFs are selected according to the calculated correlation coefficient and kurtosis index, avoiding IMF redundancy. Finally, the fault WTG-VM signals are obtained using SVD denoising. Using this approach, the proposed method realizes high-quality denoising of WTG-VM signals. Furthermore, it also effectively solves the existing problems of conventional methods, namely, inefficient IMF selection, high noise, false frequencies, mode mixing, and end effect. Finally, the effectiveness, superiority, and reliability of the proposed method are proved using simulation and practical case results.

Automatic selection of IMFs to denoise the sEMG signals using EMD

Surface Electromyography (sEMG) signals are muscle activation signals, which has applications in muscle diagnosis, rehabilitation, prosthetics, and speech etc. However, they are known to be affected by noises such as Power Line Interference (PLI), motion artifacts etc. Currently, Empirical Mode Decomposition (EMD) and its modifications such as Ensemble EMD (EEMD), and Complementary EEMD (CEEMD) are used to decompose EMG into a series of Intrinsic Mode Functions (IMFs). The denoised EMG can be obtained from the selected IMFs. Statistical methods are used to select the signal dominant IMFs to reconstruct the denoised signal. In this work, a novel procedure is proposed to automatically separate noisy IMFs from the original sEMG signal. For this purpose, Permutation Entropy (PE) is employed in EEMD sifting process called Partly EEMD (PEEMD), to separate the noisy IMFs from the original sEMG signal according to the preset PE threshold. PEEMD decomposes the original signal into various modes according to a preset PE threshold and the denoised signal is reconstructed from resultant IMFs. The PEEMD denoising procedure is applied on the experimental sEMG data collected from eight subjects, that include six various upper limb movement classes. The proposed denoising procedure achieved an improved denoising performance in comparison with EMD, EEMD, and CEEMD. An alternate measure called Sample Entropy (SE) is also used in place of PE, for the automated sifting process as a comparison. Signal to Noise Ratio (SNR), Root Mean Square Error (RMSE), and Reconstruction Error (RE) parameters are used to evaluate the denoising performance. The results, averaged across eight subjects, demonstrate that the proposed denoising procedure outperforms the state-of-the-art EMD techniques in terms of these performance measures on the experimentally collected sEMG data samples.

A Multi-Scale Anti-Multipath Algorithm for GNSS-RTK Monitoring Application.

During short baseline measurements in the Real-Time Kinematic Global Navigation Satellite System (GNSS-RTK), multipath error has a significant impact on the quality of observed data. Aiming at the characteristics of multipath error in GNSS-RTK measurements, a novel method that combines improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and adaptive wavelet packet threshold denoising (AWPTD) is proposed to reduce the effects of multipath error in GNSS-RTK measurements through modal function decomposition, effective coefficient sieving, and adaptive thresholding denoising. It first utilizes the ICEEMDAN algorithm to decompose the observed data into a series of intrinsic mode functions (IMFs). Then, a novel IMF selection method is designed based on information entropy to accurately locate the IMFs containing multipath error information. Finally, an optimized adaptive denoising method is applied to the selected IMFs to preserve the original signal characteristics to the maximum possible extent and improve the accuracy of the multipath error correction model. This study shows that the ICEEMDAN-AWPTD algorithm provides a multipath error correction model with higher accuracy compared to singular filtering algorithms based on the results of simulation data and GNSS-RTK data. After the multipath correction, the accuracy of the E, N, and U coordinates increased by 49.2%, 65.1%, and 56.6%, respectively.

Hob vibration signal denoising and effective features enhancing using improved complete ensemble empirical mode decomposition with adaptive noise and fuzzy rough sets

The acquired hob vibration signals are inevitably contaminated by noise in the industrial environment, which changes the vibration signal frequency distribution and reduces the accuracy of feature extraction and hob wear identification. To solve this problem, a novel hob vibration signal denoising and effective feature enhancement method, CEEMDAN-FRS, is proposed based on the improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and fuzzy rough sets (FRS). First, the effective frequency distributions of gear hobbing, particularly the modulation sidebands, were obtained as prior knowledge by analyzing the hob vibration response mechanism. Then, the two key parameters of CEEMDAN (i.e., noise standard deviation and ensemble size) were adaptively determined based on signal characteristics to achieve improved decomposition compared with the use of fixed values. The evaluation and selection of intrinsic mode functions (IMFs) based on a single feature such as kurtosis or root mean square, only focus on the partial characteristics, leading to an identification bias. Thus, 11 features with different sensitivities of IMFs are weighted based on FRS, and fused as a unified feature to conduct a comprehensive IMF evaluation. Finally, a reweighted IMF reconstruction strategy is proposed. The comparisons of the proposed method and related approaches to hob vibration signals show that the proposed method achieves better performance in terms of effective feature enhancement, noise removal, and signal-to-noise ratio improvement

Fault diagnosis method of rolling bearings based on adaptive modified CEEMD and 1DCNN model

The working environment of rolling bearings is highly complex and often the vibration signal of the bearing is mixed with noise, which makes fault diagnosis challenging. As such, it is imperative to denoise the vibration signal of rolling bearings, extract effective vibration features, and improve classification accuracy. In this research, we propose a rolling bearing fault diagnosis model based on adaptive modified complementary ensemble empirical mode decomposition (AMCEEMD) and a one-dimensional convolutional neural network (1DCNN). Firstly, the AMCEEMD method is proposed. This algorithm is an improved signal processing technique based on CEEMD, which introduces fuzzy entropy and kurtosis values to remove noise and identify impulse signals. The purpose of AMCEEMD is to obtain standard Intrinsic Mode Functions (IMFs) while removing noise. Secondly, we introduce the energy ratio, fuzzy entropy, and kurtosis as selection indices for IMFs. The selection of IMFs is adapted, and the selected IMF features are inputted into 1DCNN for fault classification. Finally, it was validated by two bearing experiments and compared with other classification methods. The classification accuracy of AMCEEMD-1DCNN method in this study is higher than other methods. The effectiveness of the AMCEEMD-1DCNN fault diagnosis model was verified.

A hybrid data-driven framework for satellite telemetry data anomaly detection

Anomaly detection based on telemetry data is a prominent health condition monitoring task that plays an increasingly crucial role in identifying unexpected events and improving overall satellite reliability. In this paper, a new hybrid data-driven framework for satellite telemetry data anomaly detection is constructed by an integration of ensemble empirical mode decomposition with complexity deviation index and grey wolf optimizer-optimized support vector machine. Initially, the ensemble empirical mode decomposition algorithm is employed to decompose the raw telemetry data into a collection of intrinsic mode functions that represent different inherent oscillatory modes or characteristics. A critical intrinsic mode function selection method, i.e., the complexity deviation index method, is proposed based on the sample entropy theory to select the most appropriate intrinsic mode functions with the goal of improving the sufficiency of the ensemble empirical mode decomposition algorithm and enhancing the anomalous characteristics of the telemetry data. Subsequently, a grey wolf optimizer-optimized support vector machine model is developed to forecast the variation tendency of the synthesized series of the selected intrinsic mode functions. The prediction residual between the ground truth and model estimator is calculated and the optimal threshold for anomaly detection is set according to the principle of maximum Youden index. Finally, the proposed method is applied to analyze and detect anomalies in telemetry data collected from a real-world satellite. The experimental results verify the capability of the proposed method in anomaly detection for satellite telemetry data.

A FCEEMD Energy Kurtosis Mean Filtering-Based Fault Feature Extraction Method

Aiming at the problem that fault feature extraction is susceptible to background noises and burrs, we proposed a new feature extraction method based on a new decomposition method and an effective intrinsic mode function (IMF) selection method. Firstly, pairs of white noises with opposite signs were introduced to neutralize the residual noises in ensemble empirical mode decomposition (EEMD) and suppress mode mixing. Both the reconstruction error (1.8445 × 10−17) and decomposition time (0.01 s) were greatly reduced through fast, complementary ensemble empirical mode decomposition (FCEEMD). Secondly, we integrated the energy and kurtosis of the IMF and proposed an effective IMF selection method based on energy kurtosis mean filtering, and the background noise of the signal was greatly suppressed. Finally, the periodic impacts were extracted from the IMF reconstruction signal by multipoint optimal minimum entropy deconvolution adjusted (MOMEDA). The fault frequencies were extracted from the periodic impacts through Hilbert demodulation, and the relative errors between the measured values and the theoretical values were all less than 0.05. The experimental results show that the proposed method can extract fault features more efficiently and provide a novel method for the fault diagnosis of rotating machinery.

Error Compensation for Optical Encoder via Local-Sinusoidal-Assisted Empirical Mode Decomposition With an Optimization Scheme

The measurement precision of the optical encoder is influenced by coupling interferences from the system and the environment. To further improve the measurement precision of the optical encoder, in this article, a nonlinear error compensation method is proposed to extract the optimal underlying trend of the measurement error, which is based on the empirical mode decomposition (EMD) with a local-sinusoidal-assisted (LSA) scheme and an adaptive intrinsic mode function (IMF) selection scheme. To solve the inherent problem of mode-mixing phenomena existing in the decomposed IMFs from the measurement error, an LSA scheme is proposed to adaptively change the extreme distribution of the measurement error, which is based on an abnormal segment discrimination rule. An adaptive IMF selection scheme is proposed to construct the optimal underlying trend of the measurement error, which is first formulated as an optimization problem. Next, a significant factor is defined to select the eligible IMFs with more contributions to the underlying trend. Comparison experiments indicate that the eligible IMFs can be adaptively selected, and the proposed compensation method achieves an excellent compensation performance with the root-mean-square error of 0.380 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mu$</tex-math></inline-formula> m in the 95% confidence interval of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$-$</tex-math></inline-formula> 0.017–0.016 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mu$</tex-math></inline-formula> m, which is superior to the previous EMD-based compensation methods.

Empirical mode decomposition based techniques for imaging of shallow delamination in concrete using impact echo

An impact echo (IE) signal comprises different frequency components as a result of interaction between stress waves and targets. Empirical mode decomposition (and its improved techniques), an adaptive and fully data-driven technique have been used to separate different components of an IE signal into what is known as intrinsic mode functions (IMF). The applications of improved versions of EMD and their advantages over other new adaptive decomposition techniques have also been demonstrated. This separation of modes differentiates constituent signals such as surface wave, echo wave, and flexural wave into corresponding IMFs and thus allows reconstruction of a new signal using only desirable components. An image reconstruction strategy for the selection of appropriate IMFs based on correlation coefficient is found to produce an improved image of the delamination or flaws compared to the raw signal images. The IE signal processed with noise-assisted EMD based techniques profoundly increased the accuracy of flaw features over the raw data. This improvement is validated with a quantification approach using amplitude histogram and binary mapping of flaws in B-scan and C-scan respectively. The study demonstrated that the flexural mode of vibration produced due to shallow delamination can be used for accurate imaging of flaws provided a suitable signal processing technique is used. The technique employed in this study can also be extended for imaging of deep delamination which is exhibited by echo waves in IE signals.

Fault Diagnosis of Rolling Bearing Based on an Improved Denoising Technique Using Complete Ensemble Empirical Mode Decomposition and Adaptive Thresholding Method

PurposeThe vibration signals captured for rolling bearing are generally polluted by excessive noise and can lose the fault information at the early development phase. Therefore, denoising is required to enhance the signal quality by improving kurtosis parameter sensitivity and envelope spectrum performance for early fault detection.MethodsIn this paper, an improved denoising technique is proposed for early faults diagnosis of rolling bearing based on the complete ensemble empirical mode decomposition (CEEMD) and adaptive thresholding (ATD) method. Firstly, the bearing vibration signals are decomposed into a set of various intrinsic mode functions (IMFs) using the CEEMD algorithm. The IMFs grouping and selection are formed based upon the approximate entropy and correlation coefficient value. After IMFs selection, the noise-predominant IMFs are subjected to adaptive thresholding for denoising and then added to the low-frequency IMFs for signal reconstruction.ResultsThe effectiveness of the proposed method denoised signals are tested on two experimental datasets based on kurtosis value and the envelope spectrum analysis. The results on the first dataset shows significant improvement in the kurtosis parameter values such as 92.99, 90.92, 97.39, and 78.35 for inner race fault in the bearing and 113.1, 170, 195.1, and 197.4 for outer race fault in the bearing rotating at four different speeds of 1797, 1772, 1750, and 1730 rpm, respectively, and enhances the amplitude of envelope spectrum to easily detect the bearing fault characteristics frequencies. The developed methods are further tested on the second dataset yielding similar improvement in kurtosis value and envelope spectrum analysis.ConclusionThe presented method results on experimental datasets illustrate that the proposed approach is an effective denoising technique for early fault detection in the rolling bearing compared to the original and other two conventional approaches.

Health condition monitoring of bearings based on multifractal spectrum feature with modified empirical mode decomposition-multifractal detrended fluctuation analysis

Multifractal detrended fluctuation analysis (MFDFA) is proved to be a powerful tool for fault diagnosis of rotating machinery due to its ability to reveal multifractal structures hidden in nonstationary and nonlinear vibration signals. To overcome the discontinuity of the fitting scale-dependent trend and the poor adaptability of this algorithm, Empirical Mode Decomposition-Multifractal Detrended Fluctuation Analysis (EMD-MFDFA) is introduced. However, EMD-MFDFA runs into difficulties in reverse segmentation and the selection of the expected Intrinsic Mode Functions (IMFs). Aiming at solving these deficiencies, a Modified EMD-MFDFA (MEMD-MFDFA) approach with IMF selection strategy and Step-Moving Window (SMW) segmentation method is proposed in this paper. In MEMD-MFDFA, a metric for distinguishing deterministic and random components is established to select expected IMF components by scaling exponent. Meanwhile, SMW segmentation method is exploited to reduce the estimated errors caused by reverse segmentation. The robustness of the proposed method is investigated through comparing MEMD-MFDFA, MFDFA, and EMD-MFDFA by multifractality of simulated signals with different Signal-to-Noise Ratio (SNR). Furthermore, the proposed approach is applied to three bearing run-to-failure datasets containing three types of faults, and the results show that the multifeatures of the multifractal spectrum obtained by MEMD-MFDFA have the ability to simultaneously identify early fault and assess performance degradation of bearings.

Anomaly Detection Collaborating Adaptive CEEMDAN Feature Exploitation with Intelligent Optimizing Classification for IIoT Sparse Data

IIoT (Industrial Internet of Things) has gained considerable attention and has been increasingly applied due to its ubiquitous sensing and communication. However, the sparse characteristic of sensing data in distributed IIoT networks may bring out tremendous challenges to implement the security protection measures. Based on the design of centralized data gathering and forwarding, this paper proposes a novel anomaly detection approach for IIoT sparse data, which can successfully collaborate the adaptive CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) feature exploitation with one intelligent optimizing classification. Furthermore, in the adaptive CEEMDAN feature exploitation, the CEEMDAN energy entropy based on adaptive IMF (Intrinsic Mode Function) selection is designed to extract the sensing features from IIoT sparse data; in the intelligent optimizing classification, one effective OCSVM (One-Class Support Vector Machine) classifier optimized by the IABC (Improved Artificial Bee Colony) swarm intelligence algorithm is introduced to detect various abnormal sensing features. The experimental results show that, not only does the CEEMDAN energy entropy based on adaptive IMF selection accurately describe the change of industrial production by analyzing the probability distribution and energy distribution of sparse sensing data, but also the proposed IABC-OCSVM classifier has higher detection efficiency compared with the OCSVM classifiers optimized by other swarm intelligence algorithms.

Laser gyro signal filtering by combining CEEMDAN and principal component analysis

In order to suppress the random shift error of laser gyro and improve the practical precision of inertial navigation system, an improved gyro filtering method is proposed by combining the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and principal component analysis (PCA). Firstly, the gyro signal is decomposed by CEEMDAN, and the noise energy of each intrinsic mode function (IMF) is estimated according to the distribution model of noise energy. Then, on basis of noise energy, the principal component analysis is used to remove the noise IMF to achieve the final denoising of gyro signal. In the proposed method, CEEMD can improve the mode mixing and denoising effect of gyro signal. Moreover, PCA is used to decompose each IMF. According to the noise energy, the noise of each IMF is removed adaptively to avoid the selection of noise IMF and better retain the useful information of the signal. The proposed method is completely dependent on the characteristics of gyro signal and has good adaptability and strong denoising ability. Furthermore, the filtered effect of different methods is analyzed by overlapping Allan variance. The experimental results show that the proposed method can suppress the gyro random drift more efficiently, and the effect of removing noise is better than EMD threshold method and EMD correlation coefficient method.

Remaining Useful Life Prediction for Rolling Bearings Using EMD-RISI-LSTM

Bearings are applied in rotating machinery commonly, and the effective prediction of remaining useful life (RUL) plays an increasingly crucial role in establishing reasonable maintenance decision-making with the goal of avoiding sudden downtime and ensuring machinery safety. The selection of representative degradation features and the prediction algorithm are the key factors of RUL prediction. In this work, based on empirical mode decomposition (EMD) and long short-term memory (LSTM) network, a novel prediction architecture is proposed to improve accuracy and robustness under different working conditions. The architecture integrates three parts. Initially, a failure vibration signal is decomposed into several intrinsic mode functions (IMFs) and a residual through EMD decomposition, meanwhile, a novel similarity measurement method based on Euclidean distance and cosine similarity, namely the representative IMF selection index method (RISI), is presented to select the IMFs with more degradation features. Then, the LSTM model is trained for each of the selected IMFs and residuals. Ultimately, the prediction results of selected IMFs are utilized to determine the output for RUL prediction. Typical examples and comparative experimental analysis illustrate that the proposed prediction architecture can provide an efficient reference to predict the RUL of rolling bearings.

Fault diagnosis based on the quantification of the fault features in a rotary machine

Fault diagnosis of rotary machinery is essential to fixing defective rotary machines and preventing rotary systems from breaking. Recently, fault diagnosis techniques have moved from traditional methods to artificial intelligence techniques. Many research groups have reported on the development of various artificial intelligence-based classifiers to improve diagnostic performance. In classifier design, selecting the datasets that include standard or fault features is essential to obtaining a high-performance classifier. However, there are few studies on the techniques to evaluate the quality of datasets numerically. In this study, we have developed a fault severity criterion to quantify the faultless and fault features of measured data. Using the proposed criterion, we have determined the dominant direction of representative faults in a rotary machine. The standard and fault data have been obtained, considering the dominant direction of each fault. The intrinsic mode function (IMF) that presents the fault features has been obtained by an empirical mode decomposition and a sensitive IMF selection criterion. Finally, we have designed an accurate and memory-efficient classifier using the extracted data and verified its performance by diagnosing a 7.5 kW servo motor. A conventional support vector machine has been used to verify the effects of the proposed algorithm on the classifier’s performance improvement. The developed classifier demonstrated an increase of performance up to an average of 51.9%, compared with the classifiers using training datasets measured in an arbitrary direction, with the detection rate of 99.9%. The study results suggest that the proposed classifier design technique based on the quantification of the fault features is useful for creating high-quality training datasets, machine learning, and deep learning-based classifiers.