Synchroextracting chirplet transform-based epileptic seizures detection using EEG

As a typical nonstationary signal, rolling bearing fault signals exhibit dynamic characteristics and low signal-to-noise ratio, which lead to fuzzy spectrograms from traditional time–frequency analysis (TFA) methods. It is a challenging task to accurately represent its instantaneous frequency (IF) trajectory. To solve this problem, this article proposes a TFA method which is called match-extracting chirplet transform for analyzing multicomponent dynamic signals. It generates a time–frequency (TF) representation of high energy concentration by constructing a basis function that matches the chirp rate with the original signal at any TF point. A matching extraction operator is built to extract the best matching ridges on the IF trajectory to further improve the quality of the spectrum. The proposed method can effectively characterize the dynamic characteristics of multicomponent signals and reduce the energy divergence. Meanwhile the algorithm retains signal reconstruction and can be used to recover significant components by adaptively searching modal ridges. Numerical verification shows that this method has a better performance in TF location and noise robustness. Finally, the validity of this method in mechanical fault diagnosis is verified by applying it to actual bearing signals.

Multi-scale chirplet synchroextracting transform for accurate characterization of adjacent fault features in rotating machinery

An Instantaneous Frequency Estimation Approach in a High Noise Environment

Slope synchronous chirplet transform and its application to tacho-less order tracking of rotating machineries

Accurate extraction of time-varying instantaneous frequency (IF) is crucial for fault diagnosis in rotating machinery operating under time-varying speed conditions, as real-world signals often exhibit nonlinearity and complexity. Variational nonlinear chirp mode decomposition (VNCMD) demonstrates significant capability and adaptability in extracting time-varying IFs by converting broadband signals into narrowband signals through a demodulation technique. However, its accuracy is limited by the fact that it only enforces smoothness on the demodulated signals, and it does not consider the inherent proportional relationships among IFs in rotating machine vibration signals. These limitations hinder VNCMD from accurately extracting IFs and result in poor noise robustness, a strong dependence on the initial IFs, and difficulties in handling nonlinear chirp signals (NCSs) with closely spaced IFs. To overcome these limitations, this article proposes hybrid constraints embedding VNCMD (HCVNCMD), which places further constraints on demodulated signals and IFs. Specifically, a sparse constraint is first applied to the demodulated signals. This improves their estimation accuracy and reduces errors in the subsequent IF estimates. Second, a low-rank constraint is applied to the IFs, effectively capturing their proportional relationships and optimizing inaccurate initial IFs to achieve the true IFs. The hybrid constraints embedded in HCVNCMD significantly enhance noise robustness and improve IF estimation accuracy, enabling effective processing of NCSs with closely spaced IFs. Both simulation and experimental cases demonstrate that the HCVNCMD outperforms existing time–frequency analysis (TFAs) methods in accurately estimating the IFs of NCSs. Furthermore, it successfully identifies fault features in gear and bearing under time-varying speed conditions, confirming its effectiveness and practicability.

A boosted SVM classifier trained by incremental learning and decremental unlearning approach

Time-frequency (TF) analysis (TFA) to nonstationary signals can reveal the nonlinearly changing instantaneous frequencies (IFs) of signals; it is, therefore, widely used for rotating machinery fault diagnosis under time-varying speed conditions. However, the traditional TFA methods may only reveal the outline of IFs due to the extra TF diffusion caused by limited TF resolution, hindering the fault diagnosis of rotating machinery. To enhance the readability of the time-frequency representation (TFR) of the signals with IF trajectories linearly time-varying, linear chirplet transform has been proved effective. To effectively tackle the signal with nonlinearly changing IFs, a string of chirp-rates is preferred, where the final TFR is obtained by superposition of each corresponding sub-TFR at each TF point. However, the extra cross-term interferences resulted from a string of chirp-rates cannot be neglected on TFRs. Aiming at alleviating the cross-terms from the TFR, matching and reassignment based TF enhancement strategy is proposed, where only the appropriate chirp-rate and its corresponding TFR slice is retained at each time instant. The appropriate chirp-rate is adaptively selected by the index—spectral kurtosis. To further increase the readability of the resulting TFR, a reassignment technique synchrosqueezing transform is integrated with the proposed matching strategy. By iteratively employing reassignments, TFR with the enhanced energy and sharp IF ridges can be generated. The effectiveness of the proposed method is validated by both simulated and experimental analyses. It is shown that the proposed method is effective in processing time-varying signals and can provide more accurate IF estimation, which paves the way for rotating machinery fault diagnosis under nonstationary speed conditions.

Multi-lifting synchrosqueezing transform for nonstationary signal analysis of rotating machinery

The problem with development of the support vector machine (SVM) classifiers using modified particle swarm optimization (PSO) algorithm and their ensembles has been considered. Solving this problem would allow fulfilling the high-precision data classification, especially Big Data classification, with the acceptable time expenditures. The modified PSO algorithm conducts a simultaneous search of the type of kernel functions, the parameters of the kernel function and the value of the regularization parameter for the SVM classifier. The idea of particles' «regeneration» served as the basis for the modified PSO algorithm. In the implementation of this algorithm, some particles change the type of their kernel function to the one which corresponds to the particle with the best value of the classification accuracy. The offered PSO algorithm allows reducing the time expenditures for the developed SVM classifiers, which is very important for Big Data classification problem. In most cases such SVM classifier provides the high quality of data classification. In exceptional cases the SVM ensembles based on the decorrelation maximization algorithm for the different strategies of the decision-making on the data classification and the majority vote rule can be used. Also, the two-level SVM classifier has been offered. This classifier works as the group of the SVM classifiers at the first level and as the SVM classifier on the base of the modified PSO algorithm at the second level. The results of experimental studies confirm the efficiency of the offered approaches for Big Data classification.

A time-varying instantaneous frequency fault features extraction method of rolling bearing under variable speed

Electroencephalogram (EEG) is often used in clinical epilepsy treatment to monitor electrical signal changes in the brain of patients with epilepsy. With the development of signal processing and artificial intelligence technology, artificial intelligence classification method plays an important role in the automatic recognition of epilepsy EEG signals. However, traditional classifiers are easily affected by impurities and noise in epileptic EEG signals. To solve this problem, this paper develops a noise robustness low-rank learning (NRLRL) algorithm for EEG signal classification. NRLRL establishes a low-rank subspace to connect the original data space and label space. Making full use of supervision information, it considers the local information preservation of samples to ensure the low-rank representation of within-class compactness and between-classes dispersion. The asymmetric least squares support vector machine (aLS-SVM) is embedded into the objective function of NRLRL. The aLS-SVM finds the maximum quantile distance between the two classes of samples based on the pinball loss function, which further improves the noise robustness of the model. Several classification experiments with different noise intensity are designed on the Bonn data set, and the experiment results verify the effectiveness of the NRLRL algorithm.

Self-paced learning for instantaneous frequencies estimation in heavy noise environments

The use of linear time-frequency (TF) representa-tions as instantaneous frequency (IF) estimators arises in various fundamental disciplines, mainly thanks to their simplicity and immunity against interfering cross-terms. In this paper, we derive the optimal window width for IF estimation of noisy multicomponent signals based on a family of linear TF transforms that use Gaussian windowing functions and the Fourier oscillatory kernel. Closed-form formulas concerning the estimation bias and the variance are presented, which, thanks to their generality, describe the statistical performance of IF estimators based on transforms with fixed, time-adaptive, frequency-adaptive, or time-frequency adaptive windows. The optimal window is dependent on the unknown first derivative of the IF; therefore, we employ a low-complexity procedure to infer the derivative and optimize the width accordingly. Two adaptive and fully automated TF representations (TFRs) are developed; the first employs a time-adaptive window that minimizes the sum of the mean-squared errors (MSEs) of the IF estimates at each time instant, while in the second TFR, the window is adaptive over time and frequency, minimizing the estimation MSE at each location in the TF domain. Examples using synthetic and real-world signals demonstrate that the proposed algorithms may outperform many popular state-of-the-art techniques, including those that are signal-adaptive, in terms of IF estimation.

A two-layer method based on support vector machines (SVMs) has been developed to distinguish epoxide hydrolases (EHs) from other enzymes and to classify its subfamilies using its primary protein sequences. SVM classifiers were built using three different feature vectors extracted from the primary sequence of EHs: the amino acid composition (AAC), the dipeptide composition (DPC), and the pseudo-amino acid composition (PAAC). Validated by 5-fold cross tests, the first layer SVM classifier can differentiate EHs and non-EHs with an accuracy of 94.2% and has a Matthew's correlation coefficient (MCC) of 0.84. Using 2-fold cross validation, PAAC-based second layer SVM can further classify EH subfamilies with an overall accuracy of 90.7% and MCC of 0.87 as compared to AAC (80.0%) and DPC (84.9%). A program called EHPred has also been developed to assist readers to recognize EHs and to classify their subfamilies using primary protein sequences with greater accuracy.

In order to improve the performance of Support Vector Machine (SVM) classifier for imbalanced data, this paper proposes dynamic cost-sensitive SVM classifier based on chaos particle swarm optimization (CPDC_SVM). Firstly, this paper introduces dynamic cost-sensitive thought to SVM classifier, and gives the method for structuring dynamic cost and cost-sensitive SVM model. Secondly, we propose the evaluation methodology performance for classifier, and adopts decimal base to code the particles. At last, chaos thought is introduced in particle swarm optimization algorithm, and the Algorithm of the dynamic cost-sensitive SVM classifier is given, which improves convergent speed and accuracy of particle swarm optimization, and can optimize dynamic cost-sensitive SVM well, so CPDC_SVM adds effectively the convergence speed and accuracy for the particle swarm optimization algorithm. Experimental results show CPDC_SVM has higher precision than traditional SVM classifier, and dynamic cost and chaos particle swarm optimization can improve the performance for classifier.