Original Fault Signal Research Articles

Few-shot bearing fault diagnosis method based on an EEMD parallel neural network and a relation network

Bearing fault diagnosis presents challenges, such as insufficient fault samples and significant fault data distribution variation in different bearing operating conditions. These problems cause traditional deep learning models to show poor generality and accuracy during bearing fault diagnosis. To address these challenges, this paper proposed a few-shot bearing fault diagnosis method based on an Ensemble Empirical Mode Decomposition (EEMD) parallel neural network and a relation network (RN). First, the original bearing fault vibration signal was decomposed by EEMD, while the decomposed signal components were processed via Short Time Fourier Transfor (STFT) to obtain a two-dimensional time-frequency feature map. Then, a parallel neural network was used for initial fault feature extraction, after which the extracted features were fused to construct a more accurate multi-dimensional fault feature map. A more precise fault feature vector was generated via the feature embedding module of the RN, and the fault features of the support and query sets were stitched to create a fault feature vector set. Finally, the relation module of the RN was used for the nonlinear distance determination of the fault feature vector set and to generate the relation score for the few-shot variable condition bearing fault diagnosis. In this paper, EEMD module is introduced into RN to construct multi-dimensional fault characteristics of the original fault signal. Original signal decomposition, STFT transformation and splicing effectively improve the randomness and blindness of convolution operations, improve the accuracy of fault feature extraction in RN, and thus improve the overall diagnostic performance of the model. The experimental results showed that the proposed model obtained higher diagnostic accuracy than the matching network (MN) and RN meta-learning fault diagnosis (MLFD) methods. The accuracy of fault diagnosis of the model in 5Way-Nshot is >80%, and the accuracy of fault diagnosis in 5Way-10shot is the highest at 95.2%.

Fault diagnosis of railway freight car rolling bearings based on ACMD and improved MCKD

To address the issue of accurately extracting fault characteristic information of railway freight car bearings under noisy conditions, this paper proposes a fault diagnosis method based on Adaptive Chirp Mode Decomposition (ACMD) and an optimized Maximum Correlation Kurtosis Deconvolution (MCKD) using a Sparrow Search Algorithm Combining Sine-Cosine and Cauchy Mutation (SCSSA). Firstly, ACMD is used to decompose and reconstruct the original fault signal to obtain several Intrinsic Mode Functions (IMFs). Then, the IMFs are filtered according to the Gini coefficient indicator, with the IMF having the largest Gini coefficient selected as the optimal component. Secondly, the SCSSA is employed to iteratively optimize the filter length L, fault signal period T, and displacement parameter M in the MCKD algorithm, determining the optimal parameter combination for MCKD. This avoids the limitations of manual settings and enhances the accuracy of fault diagnosis. The optimized MCKD is then applied to the optimal component, and deconvolution is performed using maximum correlation kurtosis as the criterion to extract fault characteristic information through its envelope spectrum. To verify the effectiveness and generalizability of the proposed method, simulations, experimental signals from the Case Western Reserve University Bearing Center, and actual measured signals from railway freight car bearing 353130B are used to analyze inner ring faults. The experimental results demonstrate that the method can accurately extract fault characteristic information of railway freight car bearings under noise interference and identify the fault type.

Fault Location of Grid-connected Microgrid Lines Based on AVMD and Double-ended Traveling Wave Ranging

To enhance the accuracy of fault location in microgrid lines, a fault location method based on adaptive variational mode decomposition (AVMD) and double-ended traveling wave ranging is proposed. Firstly, a microgrid radial structure model, incorporating wind, light, and water systems, is established. The parameters of variational mode decomposition are optimized by using the Aquila optimizer (AO) algorithm, allowing the original fault signal to be decomposed into multiple modal components using AVMD. Only a limited number of modal components retain the fault signal information. The effective weighted peak relevance index (EWPR) is employed to select the sensitive modal components, identified as the four modes that best preserve the fault information, for signal reconstruction. Finally, the reconstructed signal is applied for fault localization. Simulation results indicate that the proposed method is scarcely influenced by the fault type, exhibiting superior accuracy compared to the single-ended traveling wave method.

A Rolling Bearing Fault Feature Extraction Algorithm Based on IPOA-VMD and MOMEDA.

Since the rolling bearing fault signal captured by a vibration sensor contains a large amount of background noise, fault features cannot be accurately extracted. To address this problem, a rolling bearing fault feature extraction algorithm based on improved pelican optimization algorithm (IPOA)-variable modal decomposition (VMD) and multipoint optimal minimum entropy deconvolution adjustment (MOMEDA) methods is proposed. Firstly, the pelican optimization algorithm (POA) was improved using a reverse learning strategy for dimensional-by-dimensional lens imaging and circle mapping, and the optimization performance of IPOA was verified. Secondly, the kurtosis-square envelope Gini coefficient criterion was used to select the optimal modal components from the decomposed components of the signal, and MOMEDA was used to process the optimal modal components in order to obtain the optimal deconvolution signal. Finally, the Teager energy operator (TEO) was employed to demodulate and analyze the optimally deconvoluted signal in order to enhance the transient shock component of the original fault signal. The effectiveness of the proposed method was verified using simulated and actual signals. The results showed that the proposed method can accurately extract failure characteristics in the presence of strong background noise interference.

Transient Fault Signal Identification of AT Traction Network Based on Improved HHT and LSTM Neural Network Algorithm

This paper aims to address the difficult to pinpoint fault cause of the full parallel AT traction power supply system with special structure. The fault characteristics are easily covered up, and high transition impedance only affects the singularity of the wavehead, making the traveling waves hard to identify. Moreover, the classification accuracy of the traditional time-frequency analysis method is not sufficiently high to distinguish precisely. In this paper, a fault classification method of traction network based on single-channel improved Hilbert–Huang transform and deep learning is proposed. This method extracts effective fault features directly from the original fault signals and classifies the fault types at the same time. The accuracy of data categorization is increased by directly applying the Hilbert–Huang transform to fault signals to extract transient fault features and produce one-dimensional feature data, which are analyzed by the time-frequency energy spectrum. Using the similarity recognition method of long-short-term memory neural network, the extracted high-frequency one-dimensional feature data are trained and tested to classify fault signals more accurately. In order to verify the effectiveness of this method, several kinds of short-circuit and lightning strike faults are continuously simulated and verified in this paper. Considering various fault conditions and factors, the proposed improved HHT+LSTM method is compared with the LSTM method for direct processing of the original signals. The improved HHT + LSTM classification algorithm achieves an accuracy of 99.99%.

Fault diagnosis model of multi-axis industrial robot based on triplet network

Fault diagnosis is an important link in intelligent development of industrial robots. Aiming at the problem of weak fault diagnosis performance caused by insufficient training samples, a fault diagnosis model based on triplet network is proposed. Firstly, we combine the multiscale convolutional neural network (MSCNN) with channel attention networks (squeeze-and-excitation network, SENet), and use it to construct a triple sub-network structure MS-SECNN, which can adaptively extract features from the original fault signal. Then, the feature similarity is calculated by triplet loss in the low dimensional space to realize the fault classification task. The experiments are based on the real industrial robot operation data set. In this model, we use Few-shot learning strategy to test the diagnostic performance under small samples, and compare it with WDCNN, FDCNN and MSCNN models. Experimental results show that the proposed model has more effective fault classification ability under small samples. In addition, when the training sample size is 1400, the average accuracy of MS-SECNN reaches 99.21%.

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.

Bearing Fault Diagnosis Based on Mel Frequency Cepstrum Coefficient and Deformable Space-Frequency Attention Network

The main bearing is the core component of gas-fired generator, and its reliability directly affects the stability of the whole system. Therefore, it is of great significance to study the fault diagnosis of the main bearing of gas-fired generator. In the bearing fault diagnosis based on vibration signal, how to extract the signature features of fault effectively is the key to achieving accurate fault diagnosis. Based on extracting the signature features of faults, how to classify the fault features efficiently is another key to achieving accurate fault diagnosis. Based on this, we propose a bearing fault diagnosis method based on Mel frequency cepstrum coefficient (MFCC) and deformable space-frequency attention network (DSFAN). In view of the inconsistent feature distribution of different types of faults, the MFCC algorithm is introduced to preprocess the original fault signals and extract their signature features. Then, the network model DSFAN is constructed based on the space-frequency feature attention mechanism (SFFAM). DSFAN can extract the global constraint features and distributed constraint features of fault signals and realize bearing fault diagnosis. To make full use of classification information, the data processed by MFCC is constructed into a three-dimensional data cube as the input of DSFAN. Finally, the validity of the proposed method MFCC-DSFAN is verified on CWRU, XJTU, and gas-fired generator data sets. The experimental results show the excellent performance of MFCC-DSFAN for fault diagnosis and prove the effectiveness of the attention module in feature extraction.

A Fast Sparse Decomposition Based on the Teager Energy Operator in Extraction of Weak Fault Signals.

In order to diagnose an incipient fault in rotating machinery under complicated conditions, a fast sparse decomposition based on the Teager energy operator (TEO) is proposed in this paper. In this proposed method, firstly, the TEO is employed to enhance the envelope of the impulses, which is more sensitive to frequency and can eliminate the low-frequency harmonic component and noise; secondly, a smoothing filtering algorithm was adopted to suppress the noise in the TEO envelope; thirdly, the fault signal was reconstructed by multiplication of the filtered TEO envelope and the original fault signal; finally, sparse decomposition was used based on a generalized S-transform (GST) to obtain the sparse representation of the signal. The proposed preprocessing method using the filtered TEO can overcome the interference of high-frequency noise while maintaining the structure of fault impulses, which helps the processed signal perform better on sparse decomposition; sparse decomposition based on GST was used to represent the fault signal more quickly and more accurately. Simulation and application prove that the proposed method has good accuracy and efficiency, especially in conditions of very low SNR, such as impulses with anSNR of −8.75 dB that are submerged by noise of the same amplitude.

Composite Multiscale Transition Permutation Entropy-Based Fault Diagnosis of Bearings.

When considering the transition probability matrix of ordinal patterns, transition permutation entropy (TPE) can effectively extract fault features by quantifying the irregularity and complexity of signals. However, TPE can only characterize the complexity of the vibration signals at a single scale. Therefore, a multiscale transition permutation entropy (MTPE) technique has been proposed. However, the original multiscale method still has some inherent defects in the coarse-grained process, such as considerably shortening the length of time series at large scale, which leads to a low entropy evaluation accuracy. In order to solve these problems, a composite multiscale transition permutation entropy (CMTPE) method was proposed in order to improve the incomplete coarse-grained analysis of MTPE by avoiding the loss of some key information in the original fault signals, and to improve the performance of feature extraction, robustness to noise, and accuracy of entropy estimation. A fault diagnosis strategy based on CMTPE and an extreme learning machine (ELM) was proposed. Both simulation and experimental signals verified the advantages of the proposed CMTPE method. The results show that, compared with other comparison strategies, this strategy has better robustness, and can carry out feature recognition and bearing fault diagnosis more accurately and with improved stability.

MobileNetV2 Combined with Fast Spectral Kurtosis Analysis for Bearing Fault Diagnosis

Bearings are an important component in mechanical equipment, and their health detection and fault diagnosis are of great significance. In order to meet the speed and recognition accuracy requirements of bearing fault diagnosis, this paper uses the lightweight MobileNetV2 network combined with fast spectral kurtosis to diagnose bearing faults. On the basis of the original MobileNetV2 network, a progressive classifier is used to compress the feature information layer by layer with the network structure to achieve high-precision and rapid identification and classification. A cross-local connection structure is added to the network to increase the extracted feature information to improve accuracy. At the same time, the original fault signal of the bearing is a one-dimensional vibration signal, and the signal contains a large number of non-Gaussian noise and accidental shock defects. In order to extract fault features more efficiently, this paper uses the fast spectral kurtosis algorithm to process the signal, extract the center frequency of the original signal, and calculate the spectral kurtosis value. The kurtosis map generated by signal preprocessing is used as the input of the MobileNetV2 network for fault classification. In order to verify the effectiveness and generality of the proposed method, this paper uses the XJTU-SY bearing fault dataset and the CWRU bearing dataset to conduct experiments. Through data preprocessing methods, such as data expansion for different fault types in the original dataset, input data that meet the experimental requirements are generated and fault diagnosis experiments are carried out. At the same time, through the comparison with other typical classification networks, the paper proves that the proposed method has significant advantages in terms of accuracy, model size, training speed, etc., and, finally, proves the effectiveness and generality of the proposed network model in the field of fault diagnosis.

Fault diagnosis for rolling bearing based on parameter transfer Bayesian network

AbstractAt the beginning of the change in bearing condition, the bearing fault features are weak, often drowning in the background noise. It makes difficult to extract weak fault features from the vibration signal. If the fault features cannot be effectively extracted, the diagnostic accuracy will be greatly affected. Under this background, a fault diagnosis framework including two stages of signal enhancement and intelligent fault recognition is proposed in this work. Firstly, use a genetic algorithm to obtain the optimal combination of parameters, upon which the original fault signals are decomposed into intrinsic modal function components. Then, they are transformed into the spectrum signals and inputted into the proposed Bayesian network using dynamic weighted transfer learning (DWTL). This paper uses the DWTL method to set the source domain weight factor and the balance coefficient based on data quantity in different source and target domains. The DWTL method proposed in this paper can improve the fault diagnosis accuracy and effectively avoid the negative transfer phenomenon. An example of rolling bearing fault diagnosis is conducted. The results show that the accuracy of fault diagnosis based on the proposed framework is about 10% higher than that of other fault diagnosis methods. Therefore, the validity and feasibility of the proposed fault diagnosis framework are proved.

Motor Fault Diagnosis Using Image Visual Information and Bag of Words Model

In order to solve the tough issue that is difficult to extract the representative fault features of the hybrid vibration signals from the various industrial applications, a motor fault diagnosis method based on image visual information and bag of words model (BoW) are proposed in this paper. Based on the redundancy information of raw signals, the mapping which is between the original fault signal and the visual information is obtained by the methods of SDP (Symmetrized Dot Pattern) image and dense SIFT (Scale Invariant Feature Transform) features. The bag of visual word (BoVW) and pyramid histogram intersection kernel support vector machine (PHIK-SVM) are applying to complete the fault diagnosis and state recognition of related motors. The test results reveal that the diagnostic accuracy of four fault states could reach 99.50%, moreover, the diagnostic accuracy of different operating conditions under each fault could reach 91.83% as well. Compared with the traditional methods, the proposed method is able to obtain the detailed characteristics of various motors from the perspective of visual knowledge, furthermore, it is more robust and without complex data processing.

Automatic quantitative diagnosis for rolling bearing compound faults via adapted dictionary free orthogonal matching pursuit

Vibration signals of rolling bearings can reflect not only the concrete faulty component, but also the faulty status, e.g., the severity. Motivated by the fault status assessment, a sparse step-impact characteristic-oriented quantitative diagnosis method is developed for the automatic size estimations of compound faults. First, based on the excitation mechanism of bearing step-impact signals, a right-angle quadrilateral model is established for size estimation. Then the linear time-invariant (LTI) filter and autoregressive model (AR model) are used to pre-process the original fault signal. Technically supported by the adapted dictionary free orthogonal matching pursuit (ADOMP), through correlating the Asymmetric Gaussian Chirplet Model (AGCM) atoms and bearing signals, the location of step-impact points are parameterized and the selection strategy for the most suitable AGCM atoms are also investigated, guaranteeing the successful separation of severe and slight fault step-impact components. Finally, the estimations for compound fault sizes are automatically realized via combining the time shift factors of AGCM atoms and proposed right-angle quadrilateral model. The simulated result shows that the proposed right-angle quadrilateral model and quantitative diagnosis method can be reliably applied to the automatic estimations of compound fault sizes. The experimental results show that, the estimation deviations for compound sizes (2.5 mm and 1.0 mm) come only to 1.61% and 6.49% at 300r/min, respectively, superior to Symlet5 wavelet decomposition. Furthermore, the proposed method is applied to the quantitative analysis at different speeds and compound fault sizes, and the satisfactory diagnosis results are obtained.

Weak fault diagnosis of rolling bearing based on FRFT and DBN

ABSTRACT When diagnosing the weak fault of rolling bearing, the fault characteristic is difficult to be extracted because the fault signal has a small amplitude and is susceptible to noise. Aiming at this problem, a fault diagnosis method is proposed based on fractional Fourier transform (FRFT) and deep belief networks (DBN). The original fault signal is first transformed into the fractional domain, and the signal is filtered in this domain to extract the fault features. The characteristic signal is then input to the DBN, and the whole network is optimized to finally realized fault diagnosis by using the pre-training and the reverse propagation algorithm. The simulation results show that the method can effectively detect the weak fault of rolling bearing.

Application of optimized variational mode decomposition based on kurtosis and resonance frequency in bearing fault feature extraction

Variational mode decomposition (VMD) is an adaptive signal processing method proposed recently. It has gradually been widely used due to its good performance. According to the problem that the parameters of VMD need to be determined in advance, a simple and feasible method of determining the influence parameters based on the principle of kurtosis maximum is put forward. A novel intrinsic mode function (IMF) selection method based on resonance frequency is proposed in order to select the IMF that contains the abundant fault feature information. Firstly, the parameters of VMD are optimized by the principle of kurtosis maximum, the optimal penalty parameter and mode number of VMD are set, and the original fault signal is processed by the optimized VMD to obtain the established IMF components. Then, the sensitive IMF(s) with the fault information is selected by resonance frequency. Finally, the selected IMF(s) is analyzed by the envelope demodulation analysis to extract the fault characteristic frequency to judge the fault type of the rolling bearing. It is shown that the method can extract the weak characteristics of the early fault signal of the rolling bearing, and it can realize the judgment of the bearing fault accurately through the analysis of simulated signal and the actual data of bearing.

Real‐time digital filtering algorithm for elimination of the decaying DC component using mathematical morphology

Fundamental phasor estimation is one of the most important jobs to be done by the digital protective relay (DPR). However, fault signals given to DPR consist of decaying DC (DDC) components, harmonics, and noise which can lead to inaccuracy in phasor estimation. Hence, for accurate results, digital filtering algorithms (DFAs) are mandatory to wipe out all these unwanted components. In modern DPR, discrete Fourier transform (DFT) is extensively used DFA for fundamental phasor estimation. However, the accuracy of DFT is affected by the presence of DDC. Hence, to tackle this problem, a new real-time fast DFA based on the mathematical morphology (MM) technique is put forward. First, the DDC components are filtered out using the morphological median filter (MMF) and are subtracted from the original fault signal. Afterwards, the fundamental phasor is extracted from the residual DDC-free signal using the DFT. Several computer-simulated, EMTP-generated, and real-field fault signals are used to examine the efficacy of the proposed DFA. In addition, the proposed DFA is compared with other existing techniques. The obtained results prove that the suggested DFA has vigorous performance in the presence of multiple DDC components, noise, and severe harmonic conditions with a low computational burden and high accuracy.

Hydraulic Pump Fault Diagnosis Based on Empirical Wavelet Transform and Extreme Learning Machine

In order to recognize the conditions of a hydraulic pump quickly and effectively, a fault diagnosis method based on empirical wavelet transform (EWT) and extreme learning machine (ELM) is proposed in this paper. EWT, a new self-adaptive signal decomposition method, is used to adaptively decompose the original fault signal from low frequency to high frequency according to frequency characteristics. After extracting the characteristics of the decomposed signal, ELM is applied to achieve the fault classification of hydraulic pump with its advantages of high learning speed and generalization performance. Experiments show that above method captures fault information of hydraulic pump well and performs feasible and effective.

Fault classification and faulted phase selection for transmission line using morphological edge detection filter

In this study, a novel algorithm for detecting and classifying faults in transmission lines is proposed. The algorithm is based on mathematical morphology and initial current travelling waves. A new morphological edge detection (MED) filter to extract the transient features from the original fault signal is designed. This MED filter can fast and accurately detect the arrival time and polarity of travelling waves in all conditions. The appropriate criteria of fault classification and faulted-phase selection are introduced based on polarity of initial current travelling waves. The simulations based on the electromagnetic transients program and MATLAB have been done to evaluate the validity of the proposed algorithm.

The Method of Quantitative Trend Diagnosis of Rolling Bearing Fault Based on Protrugram and Lempel–Ziv

This paper proposes a new method to realize the quantitative trend diagnosis of bearings based on Protrugram and Lempel–Ziv. Firstly, the fault features of original fault signals of bearing inner and outer race with different severity are extracted using Protrugram algorithm, and the optimal analysis frequency band is selected which reflects the fault characteristic. Then, the Lempel–Ziv complexity of the frequency band is calculated. Finally, the relationship between Lempel–Ziv complexity and fault size is obtained. Analysis results show that the severity of fault is proportional to the Lempel–Ziv complexity index value under different fault types. The Lempel–Ziv complexity showed different trend rules, respectively, in the inner and outer race, which realized the quantitative trend diagnosis of bearing faults.