Search Results (11)

Fault diagnosis in electrical machines is a cornerstone of operational reliability and cost-effective maintenance strategies. This review provides a comprehensive exploration of the integration of higher-order spectral analysis (HOSA) techniques—such as a bispectrum, spectral kurtosis, and multifractal wavelet analysis—with advanced artificial intelligence (AI) methodologies, including deep learning, clustering algorithms, Transformer models, and transfer learning. The synergy between HOSA’s robustness in noisy and transient environments and AI’s automation of complex classifications has significantly advanced fault diagnosis in synchronous and DC motors. The novelty of this work lies in its detailed examination of the latest AI advancements, and the hybrid framework combining HOSA-derived features with AI techniques. The proposed approaches address challenges such as computational efficiency and scalability for industrial-scale applications, while offering innovative solutions for predictive maintenance. By leveraging these hybrid methodologies, the work charts a transformative path for improving the reliability and adaptability of industrial-grade electrical machine systems. Full article

This article proposes a new method for determining the pathological state of a plant, based on a combination of the method for measuring the dynamics of photosystem II pigment fluorescence in the leaves of L. sativa plants and analyzing the resulting time series using bispectral analysis based on the wavelet transform. The article theoretically shows a possible mechanism for the appearance of a peak on the map of bispectrum indexes during nonlinear analog conversion of a physiological signal in a biological object. The phenomenon of increasing the degree of nonlinearity in the transmission of an external periodic signal in plant signaling systems has been experimentally demonstrated. Full article

In future aviation surveillance, the demand for higher real-time updates for global flights can be met by deploying automatic dependent surveillance–broadcast (ADS-B) receivers on low Earth orbit satellites, capitalizing on their global coverage and terrain-independent capabilities for seamless monitoring. Specific emitter identification (SEI) leverages the distinctive features of ADS-B data. High data collection and annotation costs, along with limited dataset size, can lead to overfitting during training and low model recognition accuracy. Transfer learning, which does not require source and target domain data to share the same distribution, significantly reduces the sensitivity of traditional models to data volume and distribution. It can also address issues related to the incompleteness and inadequacy of communication emitter datasets. This paper proposes a distributed sensor system based on transfer learning to address the specific emitter identification. Firstly, signal fingerprint features are extracted using a bispectrum transform (BST) to train a convolutional neural network (CNN) preliminarily. Decision fusion is employed to tackle the challenges of the distributed system. Subsequently, a transfer learning strategy is employed, incorporating frozen model parameters, maximum mean discrepancy (MMD), and classification error measures to reduce the disparity between the target and source domains. A hyperbolic space module is introduced before the output layer to enhance the expressive capacity and data information extraction. After iterative training, the transfer learning model is obtained. Simulation results confirm that this method enhances model generalization, addresses the issue of slow convergence, and leads to improved training accuracy. Full article

Ensuring operational reliability in machinery requires accurate fault detection. While time-domain vibration pulsation signals are intuitive for pattern recognition and feature extraction, downsampling can reduce analytical complexity, but may result in low-precision data, affecting fault detection performance. To address this, we propose time–frequency feature fusion, combining information from both the time and frequency domains for fault detection. Our approach transforms vibrational pulse data into instantaneous revolutions per minute (RPM) and employs statistical analysis for the time-domain features. For the frequency-domain features, we use the combined method of empirical mode decomposition and independent component analysis (EMD-ICA), along with the Wigner bispectrum method to capture the nonlinear characteristics and phase conjugation. Using a deep neural network (DNN), we classify the anomaly states, demonstrating the effectiveness and versatility of our approach in detecting anomalies and improving diagnostic precision. Compared to using time or frequency features alone, our time–frequency feature fusion model achieves higher accuracy, with 100% accuracy at lower downsampling rates and 96.3% accuracy at a downsampling rate of 100×. Full article

Mechanical unbalance is a phenomenon that concerns rotating elements, including rotors in electrical machines. An unbalanced rotor generates vibration, which is transferred to the machine body. The vibration contributes to reducing drive system reliability and, as a consequence, leads to frequent downtime. Therefore, from an economic point of view, monitoring the unbalance of rotating elements is justified. In this paper, the rotor unbalance of a drive system with a permanent magnet synchronous motor (PMSM) was physically modelled using a specially developed shield, with five test masses fixed at the motor shaft. The analysed diagnostic signal was mechanical vibration. Unbalance was detected using selected signal analysis methods, such as frequency-domain methods (classical spectrum analysis FFT and a higher-order bispectrum method) and two methods applied in technical diagnostics (order analysis and orbit method). The efficiency of unbalance symptom detection using these four methods was compared for the frequency controlled PMSM. The properties of the analysed diagnostic methods were assessed and compared in terms of their usefulness in rotor unbalance diagnosis, and the basic features characterizing the usefulness of these methods were determined depending on the operating conditions of the drive. This work could have a significant impact on the process of designing diagnostic systems for PMSM drives. Full article

This paper aims to develop an efficient pattern recognition method for engine fault end-to-end detection based on the echo state network (ESN) and multi-verse optimizer (MVO). Bispectrum is employed to transform the one-dimensional time-dependent vibration signal into a two-dimensional matrix with more impact features. A sparse input weight-generating algorithm is designed for the ESN. Furthermore, a deep ESN model is built by fusing fixed convolution kernels and an autoencoder (AE). A novel traveling distance rate (TDR) and collapse mechanism are studied to optimize the local search of the MVO and speed it up. The improved MVO is employed to optimize the hyper-parameters of the deep ESN for the two-dimensional matrix recognition. The experiment result shows that the proposed method can obtain a recognition rate of 93.10% in complex engine faults. Compared with traditional deep belief networks (DBNs), convolutional neural networks (CNNs), the long short-term memory (LSTM) network, and the gated recurrent unit (GRU), this novel method displays superior performance and could benefit the fault end-to-end detection of rotating machinery. Full article

This paper deals with the area of structural damage monitoring of steel strands wire ropes embedded into various equipment and mechanical systems. Of the currently available techniques and methods for wire ropes health monitoring, the authors focused on the group of techniques based on operational dynamics investigation of such systems. Beyond the capability and efficiency of both occasionally and continuously monitoring application, the dynamics-based methods are able to provide additional information regarding the structural integrity and functional operability of the entire ensemble embedding the wire ropes. This paper presents the results gained by the authors using a laboratory setup that can simulate the operational condition usually used for regular applications of wire ropes. The investigations were conducted on three directions of acquired signals post-processing. Firstly, the classical fast Fourier transform was used to evaluate the potential changes within the spectral distribution of transitory response. The other two directions involved high-order spectral analyses in terms of bi-spectrum and Wigner–Ville distribution and multi-scale analysis based methods such as complex wavelet cross-correlation and complex wavelet coherency. The results indicate that each direction of analysis can provide suitable information regarding potential wire rope damage, but the ensemble of post-processing methods offers supplementary precision. Full article

Heart diseases are in the front rank among several kinds of life threats, due to its high incidence and mortality. Regarded as a powerful tool in the diagnosis of the cardiac disorder and arrhythmia detection, analysis of electrocardiogram (ECG) signals has become the focus of numerous researches. In this study, a feature extraction method based on the bispectrum and 2D graph Fourier transform (GFT) was developed. High-order matrix founded on bispectrum are extended into structured datasets and transformed into the eigenvalue spectrum domain by GFT, so that features can be extracted from statistical quantities of eigenvalues. Spectral features have been computed to construct the feature vector. Support vector machine based on the radial basis function kernel (SVM-RBF) was used to classify different arrhythmia heartbeats downloaded from the Massachusetts Institute of Technology - Beth Israel Hospital (MIT-BIH) Arrhythmia Database, according to the Association for the Advancement of Medical Instrumentation (AAMI) standard. Based on the cross-validation method, the experimental results depicted that our proposed model, the combination of bispectrum and 2D-GFT, achieved a high classification accuracy of 96.2%. Full article

This article presents the effectiveness of bispectrum analysis for the detection of the rotor unbalance of an induction motor supplied by the mains and a frequency converter. Two diagnostic signals were analyzed, as well as the stator current and mechanical vibrations of the tested motors. The experimental tests were realized for two low-power induction motors, with one and two pole pairs, respectively. The unbalance was modeled using a test mass mounted on a specially prepared disc and directly on the rotor and the influence of this unbalance location was tested and discussed. The results of the bispectrum analysis are compared with results of Fourier transform and the effectiveness of unbalance detection are discussed and compared. The influence of the registration time of the analyzed signal on the quality of fault symptom analyses using both transforms was also tested. It is shown that the bispectrum analysis provides an increased number of fault symptoms in comparison with the classical spectral analysis as well as it is not sensitive to a shorter registration time of the diagnostic signals. Full article

The flame combustion processes involves chemical reactions and therefore flame stability is difficult to accurately assess. Based on flame radiation measuring parameters, a new synthetic evaluation system of flame combustion stability is established. A series of combustion conditions with various fuel/air ratios is investigated. Flame radiation luminance fluctuating information is acquired on a low-cost flame detection device. Power spectrum and bi-spectral information of the phase domain are derived from time domain signals based on Fourier transform and higher order statistics based upon a de-noising algorithm. The time–frequency characteristics and the features of the bi-spectrum under various combustion conditions are qualitatively analyzed, and the simultaneous descriptive parameters from time, frequency, and phase domain are extracted. A theoretical model for comprehensive fuzzy evaluation has been constructed, and also an index system has been established. It is demonstrated that this judgment system is reasonable and effective. The results can be used as an analyzing tool for process engineers for improving combustion conditions. Full article

The aim of this work is to find out, through the analysis of the time and frequency domains, significant differences that lead us to obtain one or several variables that may result in an indicator that allows diagnosing the condition of the rotor in an induction motor from the processing of the stray flux signals. For this, the calculation of two indicators is proposed: the first is based on the frequency domain and it relies on the calculation of the sum of the mean value of the bispectrum of the flux signal. The use of high order spectral analysis is justified in that with the one-dimensional analysis resulting from the Fourier Transform, there may not always be solid differences at the spectral level that enable us to distinguish between healthy and faulty conditions. Also, based on the high-order spectral analysis, differences may arise that, with the classical analysis with the Fourier Transform, are not evident, since the high order spectra from the Bispectrum are immune to Gaussian noise, but not the results that can be obtained using the one-dimensional Fourier transform. On the other hand, a second indicator based on the temporal domain that is based on the calculation of the square value of the median of the autocovariance function of the signal is evaluated. The obtained results are satisfactory and let us conclude the affirmative hypothesis of using flux signals for determining the condition of the rotor of an induction motor. Full article