Baoping Tang

Method for eliminating mode mixing of empirical mode decomposition based on the revised blind source separation

Since mode mixing of empirical mode decomposition (EMD) is mainly caused by the intermittence and noise, we propose a novel method to eliminate mode mixing of EMD based on the revised blind source separation. To this aim, an optimal morphological filter is employed to eliminate the noise. As a result, the component of mode mixing caused by noise is suppressed. Furthermore, the de-noised signal is decomposed into different intrinsic mode function (IMF) components through the EMD algorithm. Since it is impossible to apply blind source separation to a single channel signal directly, the IMF component, which has mode mixing is chosen and reconstructed in the phase space. Following that, the equivalent hypothetical signals are obtained. Finally, an improved fixed-point algorithm based on independent component analysis (ICA) is introduced to separate the overlapping components. The analysis of simulation and practical application demonstrates that our proposed method can effectively tackle the mode mixing problem of EMD.

Weak fault diagnosis of rotating machinery based on feature reduction with Supervised Orthogonal Local Fisher Discriminant Analysis

A new weak fault diagnosis method based on feature reduction with Supervised Orthogonal Local Fisher Discriminant Analysis (SOLFDA) is proposed. In this method, the Shannon mutual information (SMI) between all samples and training samples is combined into SMI feature sets to represent the mutual dependence of samples as incipient fault features. Then, SOLFDA is proposed to compress the high-dimensional SMI fault feature sets of testing and training samples into low-dimensional eigenvectors with clearer clustering. Finally, Optimized Evidence-Theoretic k-Nearest Neighbor Classifier (OET-KNNC) is introduced to implement weak failure recognition for low-dimensional eigenvectors. Under the supervision of class labels, SOLFDA achieves good discrimination property by maximizing the between-manifold divergence and minimizing the within-manifold divergence. Meanwhile, an orthogonality constraint on SOLFDA can make the output sparse features statistically uncorrelated. Therefore, SMI feature set combining SOLFDA is able to extract the essential but weak fault features of rotating machinery effectively, compared with popular signal processing techniques and unsupervised dimension reduction methods. The weak fault diagnosis example on deep groove ball bearings demonstrates the advantage of the weak fault diagnosis method proposed in this paper. A high-precision weak fault diagnosis method is proposed.Feature set of weak fault based on Shannon mutual information is constructed.Supervised Orthogonal Local Fisher Discriminant Analysis is proposed.Optimized Evidence-Theoretic k-Nearest Neighbor Classifier is introduced.

Life grade recognition method based on supervised uncorrelated orthogonal locality preserving projection and K-nearest neighbor classifier

Abstract A novel life grade recognition method based on Supervised Uncorrelated Orthogonal Locality Preserving Projection (SUOLPP) and K-nearest neighbor classifier (KNNC) is proposed in this paper. A time–frequency domain feature set is first constructed to completely extract the feature of different life grades, then SUOLPP is proposed to automatically compress the high-dimensional time–frequency domain feature sets of training and test samples into the low-dimensional eigenvectors with better discrimination, and finally the low-dimensional eigenvectors of training and test samples are input into KNNC to conduct life grade recognition. SUOLPP algorithm considers both local information and label information in designing the similarity matrix, and requires the output basis vectors to be statistically uncorrelated and orthogonal in order to improve the life grade feature extraction power of OLPP. KNNC ranks the test samples׳ neighbors among the training samples and uses the class labels of similarity neighbors to classify the unknown input test samples, so that it has such advantages as less calculation amount, finer timeliness and higher pattern recognition accuracy compared with support vector machine (SVM) and Fuzzy C-Means Clustering (FCM). The life grade recognition example on deep groove ball bearings demonstrated the effectivity of the proposed life grade recognition method.

Adaptive signal decomposition based on wavelet ridge and its application

Signal decomposition is a widely-used approach for multicomponent signal processing. To improve the accuracy and anti-noise performance of multicomponent decomposition, this paper proposes a novel multicomponent signal decomposition method based on wavelet ridge extraction, called the Wavelet ridge signal decomposition (WRSD). A wavelet ridge extraction algorithm is introduced. We find that this algorithm can obtain the wavelet ridge of one component in a multicomponent signal and the initial scale will determine the wavelet ridge of which component is extracted. Since the instantaneous frequency obtained by wavelet ridge has small frequency fluctuation, low-pass filtering is used to increase the accuracy of instantaneous frequency estimation. With the improved instantaneous frequency, the synchronous demodulation method is used to separate the corresponding component from the signal composition. By repeating this process, all components can be adaptively and automatically obtained. This method is employed to analyze three typical simulated vibration signals and compared with Hilbet vibration decomposition and empirical mode decomposition. The comparison results demonstrate its superiority in decomposition accuracy and noise insensitivity. Finally, the proposed WRSD method is successfully applied to the diagnosis of a shaft misalignment fault and a gearbox wear fault. An adaptive and automatic multicomponent signal decomposition method is proposed.The initial scale determines the wavelet ridge of which component is extracted.This method has higher accuracy and is less sensitive to noise than HVD and EMD.The method can be effectively applied to the weak fault feature extraction.

Higher density wavelet frames with symmetric low-pass and band-pass filters

This paper presents a new set of higher density wavelet frames with symmetric low-pass and band-pass wavelet filters. Based on the maximally flat low-pass linear-phase FIR filter and spectral factorization, two types of design approaches are proposed, which can respectively obtain odd-length FIR filters and even-length FIR filters. The two compact support wavelets respectively have a specified order of vanishing moments and a high degree of regularity. Several design examples are given. The denoising experiments show that the proposed wavelet frames have better shift invariance and denoising performance than the wavelet frames constructed by I.W. Selesnick. In engineering application, the proposed wavelet frame is applied to extract the fault feature of a roller bearing with out-race fault.

Fault diagnosis of rolling element bearing based on S transform and gray level co-occurrence matrix

Time-frequency analysis is an effective tool to extract machinery health information contained in non-stationary vibration signals. Various time-frequency analysis methods have been proposed and successfully applied to machinery fault diagnosis. However, little research has been done on bearing fault diagnosis using texture features extracted from time-frequency representations (TFRs), although they may contain plenty of sensitive information highly related to fault pattern. Therefore, to make full use of the textural information contained in the TFRs, this paper proposes a novel fault diagnosis method based on S transform, gray level co-occurrence matrix (GLCM) and multi-class support vector machine (Multi-SVM). Firstly, S transform is chosen to generate the TFRs due to its advantages of providing frequency-dependent resolution while keeping a direct relationship with the Fourier spectrum. Secondly, the famous GLCM-based texture features are extracted for capturing fault pattern information. Finally, as a classifier which has good discrimination and generalization abilities, Multi-SVM is used for the classification. Experimental results indicate that the GLCM-based texture features extracted from TFRs can identify bearing fault patterns accurately, and provide higher accuracies than the traditional time-domain and frequency-domain features, wavelet packet node energy or two-direction 2D linear discriminant analysis based features of the same TFRs in most cases.

Quantitative rotor damage detection based on piezoelectric impedance

To realize the quantitative damage detection of a rotor, firstly an impedance analytic model is built. Then the change of bending stiffness is introduced as the damage index. Given the circular boundary condition of a rotor, annular elements are used as the analyzed objects and spectral element method is used. The electro-mechanical (E/M) coupled impedance expression of an undamaged rotor is derived with the application of a low-cost impedance test circuit. A Taylor expansion method is used to obtain the approximate E/M coupled impedance expression for the damaged rotor. After obtaining the difference between the undamaged and damaged rotor impedance, a rotor damage detection algorithm is proposed. In this paper, a preset damage configuration is used for the numerical simulation and experiment validation. The detection results have shown that the quantitative damage detection algorithm based on spectral element method and piezoelectric impedance proposed in this paper can identify the location and the severity of the damaged rotor accurately.

Quantum weighted gated recurrent unit neural network and its application in performance degradation trend prediction of rotating machinery

Abstract Traditional gated recurrent unit neural network (GRUNN) generally faces the challenges of poor generalization ability and low training efficiency in performance degradation trend prediction of rotating machinery. In this paper, a novel quantum neural network called quantum weighted gated recurrent unit neural network (QWGRUNN) is proposed. Firstly, quantum bits are introduced into gated recurrent unit (GRU) to express network weights and activity values. Then, a new learning algorithm based on quantum phase-shift gate and quantum gradient descent is presented to quickly update the quantum parameters of weight-qubits and activity-qubits, thus endowing QWGRUNN with faster convergence speed, superior nonlinear approximation capability and higher computational efficiency than GRUNN. Performance degradation trend prediction for rolling bearings demonstrates that higher prediction accuracy and shorter computation time can be obtained due to the advantages of QWGRUNN in terms of convergence speed, nonlinear approximation capability and computational efficiency. It is believed that the proposed method using QWGRUNN is effective for performance degradation trend prediction of rotating machinery.

Quantum weighted long short-term memory neural network and its application in state degradation trend prediction of rotating machinery

Classical long short-term memory neural network (LSTMNN) generally faces the challenges of poor generalization property and low training efficiency in state degradation trend prediction of rotating machinery. In this paper, a novel quantum neural network called quantum weighted long short-term memory neural network (QWLSTMNN) is proposed. First, quantum bits are introduced into the long short-term memory unit to express network weights and activity values. Then, a new learning algorithm based on quantum phase-shift gate and quantum gradient descent is presented to quickly update the quantum parameters of weight qubits and activity qubits. The above characteristics endow QWLSTMNN with better nonlinear approximation capability, higher generalization property and faster convergence speed than LSTMNN. State degradation trend prediction for rolling bearings demonstrates that higher prediction accuracy and higher computational efficiency can be obtained due to the advantages of QWLSTMNN in terms of nonlinear approximation capability, generalization property and convergence speed. It is believed that the proposed method based on QWLSTMNN is effective for state degradation trend prediction of rotating machinery.

A Fault Feature Extraction Method for Rolling Bearing Based on Pulse Adaptive Time-Frequency Transform

Shock pulse method is a widely used technique for condition monitoring of rolling bearing. However, it may cause erroneous diagnosis in the presence of strong background noise or other shock sources. Aiming at overcoming the shortcoming, a pulse adaptive time-frequency transform method is proposed to extract the fault features of the damaged rolling bearing. The method arranges the rolling bearing shock pulses extracted by shock pulse method in the order of time and takes the reciprocal of the time interval between the pulse at any moment and the other pulse as all instantaneous frequency components in the moment. And then it visually displays the changing rule of each instantaneous frequency after plane transformation of the instantaneous frequency components, realizes the time-frequency transform of shock pulse sequence through time-frequency domain amplitude relevancy processing, and highlights the fault feature frequencies by effective instantaneous frequency extraction, so as to extract the fault features of the damaged rolling bearing. The results of simulation and application show that the proposed method can suppress the noises well, highlight the fault feature frequencies, and avoid erroneous diagnosis, so it is an effective fault feature extraction method for the rolling bearing with high time-frequency resolution.