Partial discharge (PD) fault analysis is an important tool for insulation condition diagnosis of electrical equipment. In order to conquer the limitations of traditional PD fault diagnosis, a novel feature extraction approach based on variational mode decomposition (VMD) and multi-scale dispersion entropy (MDE) is proposed. Besides, a hypersphere multiclass support vector machine (HMSVM) is used for PD pattern recognition with extracted PD features. Firstly, the original PD signal is decomposed with VMD to obtain intrinsic mode functions (IMFs). Secondly proper IMFs are selected according to central frequency observation and MDE values in each IMF are calculated. And then principal component analysis (PCA) is introduced to extract effective principle components in MDE. Finally, the extracted principle factors are used as PD features and sent to HMSVM classifier. Experiment results demonstrate that, PD feature extraction method based on VMD-MDE can extract effective characteristic parameters that representing dominant PD features. Recognition results verify the effectiveness and superiority of the proposed PD fault diagnosis method.

Order tracking is an effective fault diagnosis method for rotating machinery under variable speed conditions. Accurate instantaneous frequency is the premise of this method. In recent years, the tacholess method has been widely used to estimate instantaneous frequency. However, the method’s accuracy requires further improvement. Thus, this paper proposes an instantaneous frequency estimation method based on short-time fractional Fourier transform for tacholess order tracking. First, the principle and main error sources of the order tracking are analyzed. On this basis, we present three quantitative evaluation indicators of instantaneous frequency accuracy that are applicable to different scenarios. Second, an efficient and accurate instantaneous frequency estimation method based on short-time fractional Fourier transform that benefits from the first-order approximation of the linear frequency modulation kernel function to the instantaneous frequency and a series of improvement measures to avoid redundant rotation angle calculation is proposed. Finally, order spectrum is employed after tacholess order tracking to achieve fault diagnosis. The effectiveness of the proposed method is proven by the wind turbine gearbox data collected in the field. Verification results show that the proposed method is superior to the comparison methods in terms of instantaneous frequency accuracy and efficiency.

Enhancing the reliability of wind turbines is essential for reducing operational and maintenance costs in wind farms. However, the challenges of effectively extracting spatiotemporal features of fault signals in harsh environments, along with the limitations imposed by traditional diagnostics that rely solely on single signal, inhibit improvements in diagnostic accuracy. To address these issues, we propose an end-to-end fault diagnosis method based on a multi-source signal fusion, implemented through a Convolutional Neural Network-Bidirectional Gated Recurrent Unit (CNN-BiGRU). Initially, the model embeds a lightweight Convolutional Block Attention Module (CBAM), which leverages CNN to capture spatial data features and BiGRU to process temporal features. This CBAM attention mechanism enhances the network’s feature representation capabilities, enabling comprehensive end-to-end fault diagnosis. Furthermore, the Dezert-Smarandache Theory (DSmT) is employed to integrate preliminary diagnostic results from acoustic, vibration, and Supervisory Control And Data Acquisition (SCADA) data, culminating in a robust gearbox fault diagnosis. Comparative case studies demonstrate that the proposed model effectively reduces the diagnostic uncertainty compared to single-signal analysis approaches. Additionally, the model achieves stable diagnostic accuracy in both steady and variable operating conditions, as well as in various noisy environments. The comparative case validates the effectiveness and feasibility of the proposed method for practical applications.

Aiming at the problems of poor time–frequency (TF) aggregation and severe noise interference when traditional TF analysis (TFA) methods deal with complex multi-component signals, this paper proposes a new TFA method—local maximum synchrosqueezing reassigning chirplet transform (LMSRCT). The core idea of the method is to introduce the principle of general linear chirplet transform (CT) into synchro-reassigning transform, followed by reassigning the results of local maximum synchrosqueezing CT, and then introducing the innovative synchro-reassigning operator. This results to a novel three-step method for extracting instantaneous frequency (IF), which ultimately yields the final TF representation. This method ensures the integrity of each IF, solves the problem of energy divergence problems, and improves aggregation. Simulation and experimental results show that the LMSRCT can provide better characterisation results compared to other methods and can effectively solve the different situations that occur between the IFs of complex signals. The proposed method can effectively estimate transmission speed, which achieves fault diagnosis under tacholess conditions, and the order analysis results are more accurate and reliable.

Instantaneous angular speed (IAS) as a key variable represents the running state of rolling bearings. The combination of IAS and various technologies can improve the accuracy of rolling bearing fault diagnosis. However, the accuracy and efficiency of the existing tachometer-free IAS estimation methods need to be further improved to meet the requirements of practical applications. To address the aforementioned issue, an IAS estimation method based on Short-Time Fractional Fourier Transform (STFrFT) has been proposed. The main idea is to leverage the linear frequency modulation basis function of the STFrFT to accurately represent non-stationary vibration signals with nonlinear frequency modulation functions, fundamentally improving the accuracy of IAS estimation. Secondly, by comprehensively analyzing the redundant computations in the parameter optimization process of the algorithm, three refining strategies to improve computation efficiency are proposed. Finally, the detailed algorithm implementation, as well as qualitative and quantitative evaluations of the algorithm, are presented. After validation on two motor-bearing vibration datasets, compared to lots of typical methods, the proposed method has advantages in both the accuracy and efficiency of IAS estimation.

Fault characteristic frequency is the main basis for rolling element bearing diagnostics, but finding a suitable frequency band for demodulation and searching for the fault characteristic frequencies consume a lot of time and manpower in practice. A data-driven method based on recursive variational mode decomposition (RVMD) and envelope order capture is proposed to realize the automatic fault diagnosis of bearing under different operating conditions. The process starts with a new proposed RVMD of vibration signal, where the mode with maximum kurtosis of the unbiased autocorrelation of envelope is selected to get envelope order spectrum. Thereafter, an order capture algorithm is designed to automatically search for the fault characteristic orders in theory which are used for constructing feature vectors for diagnosis. The proposed method is tested on two test-beds which both contain the same type of bearing(SKF6205), but operate in different conditions, and gets a good performance in bearing diagnosis. In addition, fault diagnosis of test-bed two using training samples which are from test-bed one is investigated. This method reveals well generalization capability in fault diagnosis of the same type of rolling element bearing under different operating conditions.