Hybrid Signal Processing Research Articles

An adaptable physics-informed fault diagnosis approach via hybrid signal processing and transferable feature learning for structural/machinery health monitoring

An adaptable physics-informed fault diagnosis approach via hybrid signal processing and transferable feature learning for structural/machinery health monitoring

Research on Small Sample Rolling Bearing Fault Diagnosis Method Based on Mixed Signal Processing Technology

The diagnosis of bearing faults is a crucial aspect of ensuring the optimal functioning of mechanical equipment. However, in practice, the use of small samples and variable operating conditions may result in suboptimal generalization performance, reduced accuracy, and overfitting for these methods. To address this challenge, this study proposes a bearing fault diagnosis method based on a symmetric two-stream convolutional neural network (CNN). The method employs hybrid signal processing techniques to address the issue of limited data. The method employs a symmetric parallel convolutional neural network (CNN) for the analysis of bearing data. Initially, the data are transformed into time–frequency maps through the utilization of the short-time Fourier transform (STFT) and the simultaneous compressed wavelet transform (SCWT). Subsequently, two sets of one-dimensional vectors are generated by reconstructing the high-resolution features of the faulty samples using a symmetric parallel convolutional neural network (CNN). Feature splicing and fusion are then performed to generate bearing fault diagnosis information and assist fault classification. The experimental results demonstrate that the proposed mixed-signal processing method is effective on small-sample datasets, and verify the feasibility and generality of the symmetric parallel CNN-support vector machine (SVM) model for bearing fault diagnosis under small-sample conditions.

Hybrid Beamforming Design and Signal Processing with Fully-Connected Architecture for mmWave Integrated Sensing and Communications

Hybrid Beamforming Design and Signal Processing with Fully-Connected Architecture for mmWave Integrated Sensing and Communications

Multidimensional Fiber‐to‐Chip Optical Processing Using Photonic Integrated Circuits

AbstractMultidimensional multiplexing technologies have been proven to be a promising scheme to meet the demands of high‐capacity optical interconnects and optical processing networks. However, challenges remain to realize multidimensional hybrid multiplexing data transmission and signal processing between few‐mode fiber transmission links and on‐chip optical processing networks, since the optical coupling between fiber and chip is almost exclusively in the single‐mode regime. Here, a multidimensional fiber‐to‐chip optical processing system is proposed and demonstrated for hybrid wavelength‐, mode‐, and polarization‐division multiplexing signals, where multidimensional coupling between few‐mode fiber transmission link and on‐chip multi‐mode processing network is realized by using a 3D photonic integrated (de)multiplexers on a glass chip as well as 2D photonic integrated (de)multiplexers on a silicon chip, and the on‐chip multidimensional optical processing network composed by parallel cascaded micro‐ring resonator array performs a function of reconfigurable optical add/drop multiplexer. By operating wavelength‐division multiplexing in conjunction with mode‐division multiplexing and polarization‐division multiplexing, the communication bandwidth of fiber‐to‐chip optical processing systems can be further scaled.

Hybrid Signal Processing for Automatic Detection and Removal of Material Absorption and Noise From Microsphere-Lens-Enhanced Midwave Infrared Type II Strained Layer Superlattice Photodetectors

Hybrid Signal Processing for Automatic Detection and Removal of Material Absorption and Noise From Microsphere-Lens-Enhanced Midwave Infrared Type II Strained Layer Superlattice Photodetectors

Detection of myocardial infarction using Shannon energy envelope, FA-MVEMD and deterministic learning

Myocardial infarction (MI) poses a significant clinical challenge, necessitating expeditious and precise detection to mitigate potentially fatal outcomes. Current MI diagnosis predominantly relies on electrocardiography (ECG); however, it is fraught with limitations, including inter-observer variability and a reliance on expert interpretation. This study introduces an automated MI detection framework that capitalizes on hybrid signal processing methodologies and deterministic learning theory. The initial step involves the extraction of the Shannon energy envelope (SEE) and its derivative from a single-lead ECG. Integration of the SEE into the ECG’s phase portrait provides a means to capture the underlying nonlinear system dynamics. Subsequently, the application of fast and adaptive multivariate empirical mode decomposition (FA-MVEMD) yields discriminative features originating from the most energetically dominant intrinsic mode components (IMFs) within the SEE. Profound dissimilarities are discernible between ECG signals recorded from healthy subjects and those afflicted with MI. In the subsequent phase, deterministic learning theory, implemented through neural networks, is employed to facilitate the classification of ECG signals into two distinct groups. The method’s efficacy is meticulously evaluated using the PTB diagnostic ECG database, resulting in a noteworthy average classification accuracy of 99.21%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} within a tenfold cross-validation framework. In summation, the findings affirm that the proposed features not only complement conventional ECG attributes but also align closely with the underlying dynamics of the ECG system, ultimately fortifying the automatic detection of MI. The imperative requirement for early and accurate MI diagnosis is addressed through our approach, offering a robust and dependable means to fulfill this pivotal clinical need.

A New Paradigm for Adaptive Cyber-Resilience of DC Shipboard Microgrids Using Hybrid Signal Processing with Deep Learning Method

A New Paradigm for Adaptive Cyber-Resilience of DC Shipboard Microgrids Using Hybrid Signal Processing with Deep Learning Method

Fault Diagnosis in a Photovoltaic Grid-Tied CHB Multilevel Inverter Based on a Hybrid Machine Learning and Signal Processing Technique

Fault Diagnosis in a Photovoltaic Grid-Tied CHB Multilevel Inverter Based on a Hybrid Machine Learning and Signal Processing Technique

A Hybrid Signal Processing Method Combining Mathematical Morphology and Walsh Theory for Power Quality Disturbance Detection and Classification

A Hybrid Signal Processing Method Combining Mathematical Morphology and Walsh Theory for Power Quality Disturbance Detection and Classification

A Hybrid Signal Processing Technique for Identification and Categorization of Faults in IEEE-9 Bus System

A hybrid signal processing technique (HSPT) is proposed in this manuscript for identification and categorization of faults in electrical transmission network. A fault indicator (FI) is suggested by decomposition of the currents by application of Alienation coefficient (ACF), Stockwell transform (ST) and Hilbert transform (HT) for identification of faults. An indicator for ground involvement during faulty condition (SGFI) is being suggested to detect the type of fault. The categorization of faults is done by utilizing faulty phase numbers and SGFI. It is found that the proposed technique is effective in identification of faults and to classify them in different scenarios together with fault on A-phase to ground (AGF), double phase fault (ABF), fault on two phases and ground (ABGF), three phase fault (ABCF) and three phase fault including ground (ABCGF). Study is done and validated on IEEE-9 bus system using MATLAB/Simulink environment. The effectiveness and applicability of the proposed technique with respect to different parameters of faults such as Fault Incidence Angle, Fault Impedance, Line loading, Generator Supply and Noise level is also checked. The results shows that proposed scheme is able to detect and classify the faults in different faulty events.

Electro-Acoustic Phase Modulator Based on AlScN Thin Film

Acoustic waveguides and ring resonators based phononic integrated circuits (PnIC) have attracted more and more attention due to potential applications in the quantum system and signal processing. However, there are very few studies on active modulation utilizing electro-acoustic (EA) effect. PnIC requires efficient modulation components as well as a high electromechanical coupling platform. Here we demonstrate an acoustic wave phase modulator based on AlScN thin film. The acoustic wave phase of proposed AlScN thin film devices can be controlled through the driving voltage, modulation length as well as the acoustic wavelength. A π phase shift is obtained at an amplitude of 62.5 V DC bias on an acoustic waveguide of 100 μm long at the acoustic wave of approximately 1.975 GHz, i.e., Vπ∙L = 6.25*10-3 V∙m. Moreover, acoustic frequency combs and serrodyne frequency translators have been demonstrated. Such high performance AlScN thin film EA phase modulator proves a new PnIC platform for future hybrid chip-scale phonon transduction and signal processing.

A review of light‐controlled programmable metasurfaces for remote microwave control and hybrid signal processing

AbstractProgrammable metamaterials and metasurfaces have gained great interest due to real‐time electromagnetic control and digital information processing capabilities. Different from traditional electrically‐controlled programmable metasurfaces, recently, light‐controlled programmable metasurfaces have been presented, on which the microwaves can be manipulated and modulated wirelessly in the space domain or time domain by incident light. More importantly, such the metasurface platform offers an efficient interface to link directly light and microwave signals, showing huge potential to develop wave‐based optoelectronic hybrid devices and relevant applications. Here, we review some of these recent developments, focusing particularly on the mechanisms of light‐controlled programmable metasurfaces and their fascinating functions from remote microwave control to hybrid signal processing. We survey related implementation methods based on the hybrid integrations of microwave digital metasurfaces and different photoresponsive components including photodiodes, photoresistors, infrared modules, and light sensors, as well as discuss their unique advantages. In the summary, the perspective on the challenges and future directions of light‐controlled programmable metasurfaces are presented.

Gait classification for early detection and severity rating of Parkinson's disease based on hybrid signal processing and machine learning methods.

Parkinson's disease (PD) is one of the cognitive degenerative disorders of the central nervous system that affects the motor system. Gait dysfunction represents the pathology of motor symptom while gait analysis provides clinicians with subclinical information reflecting subtle differences between PD patients and healthy controls (HCs). Currently neurologists usually assess several clinical manifestations of the PD patients and rate the severity level according to some established criteria. This is highly dependent on clinician's expertise which is subjective and ineffective. In the present study we address these issues by proposing a hybrid signal processing and machine learning based gait classification system for gait anomaly detection and severity rating of PD patients. Time series of vertical ground reaction force (VGRF) data are utilized to represent discriminant gait information. First, phase space of the VGRF is reconstructed, in which the properties associated with the nonlinear gait system dynamics are preserved. Then Shannon energy is used to extract the characteristic envelope of the phase space signal. Third, Shannon energy envelope is decomposed into high and low resonance components using dual Q-factor signal decomposition derived from tunable Q-factor wavelet transform. Note that the high Q-factor component consists largely of sustained oscillatory behavior, while the low Q-factor component consists largely of transients and oscillations that are not sustained. Fourth, variational mode decomposition is employed to decompose high and low resonance components into different intrinsic modes and provide representative features. Finally features are fed to five different types of machine learning based classifiers for the anomaly detection and severity rating of PD patients based on Hohen and Yahr (HY) scale. The effectiveness of this strategy is verified using a Physionet gait database consisting of 93 idiopathic PD patients and 73 age-matched asymptomatic HCs. When evaluated with 10-fold cross-validation method for early PD detection and severity rating, the highest classification accuracy is reported to be and , respectively, by using the support vector machine classifier. Compared with other state-of-the-art methods, the results demonstrate superior performance and support the validity of the proposed method.

Hybrid Feature Selection Framework for Bearing Fault Diagnosis Based on Wrapper-WPT

A framework aimed to improve the bearing-fault diagnosis accuracy using a hybrid feature-selection method based on Wrapper-WPT is proposed in this paper. In the first step, the envelope vibration signal of the roller bearing is provided to the Wrapper-WPT. There, it is initially decomposed into several sub-bands using Wavelet Packet Transform (WPT), and a set out of nineteen time and frequency domain features are individually extracted from each sub-band of the decomposed vibration signal forming a wide feature pool. In the following step, Wrapper-WPT constructs a final feature vector using the Boruta algorithm, which selects the most discriminant features from the wide feature pool based on the important metric obtained from the Random Forest classifier. Finally, Subspace k-NN is used to identify the health conditions of the bearing, thus forming a hybrid signal processing and machine learning-based model for bearing fault diagnosis. In comparison with other state-of-the-art methods, the proposed method showed higher classification performance on two different bearing-benchmark vibration datasets with variable operating conditions.

A self-adaptive multiple-fault diagnosis system for rolling element bearings

The inevitable simultaneous formation of multiple-faults in bearings generates severe vibrations, causing premature component failure and unnecessary downtime. For accurate diagnosis of multiple-faults, machine learning (ML) models need to be trained with the signature of different multiple-faults, which increases the data acquisition time and expense. This paper proposes a self-adaptive vibration signature-based fault diagnostic method for detecting multiple bearing faults using various single-fault vibration signatures. A time-frequency-based hybrid signal processing technique, which involves discrete wavelet transform and Hilbert transform, was adopted for signal decomposition, followed by the implementation of a sliding window-based feature extraction process. Seven optimized metaheuristic algorithms were used to find the best feature sets, which were further used for the training of three ML models. The results show that the proposed methodology has tremendous potential to detect multiple bearing fault conditions in any possible combination using single-fault data. This will be helpful where accessibility to large amounts of data is limited for multiple-fault diagnosis.

Fault diagnosis of SKF-6205 bearing with modified empirical mode decomposition

Rolling element bearings are broadly used in the rotating machines to support static and dynamic loads. In this research, the advance signal processing techniques are use for processing of bearing fault signals. Experimental validation with genuine vibration signals calculated from bearings with seeded defects on bearing elements. The model-based fault diagnosis method has attempted to diagnose incipient fault detection and classification of bearing with data driven approach. Feature extraction technique has been developed with hybrid signal processing technique based on the band pass filter nature of Empirical mode decomposition (EMD), the resonant frequency bands have owed in specific mono component signals called Intrinsic Mode Functions (IMFs). Synchronized resonant frequency band (SRFB) is obtained on based of orthogonal real wavelet using spectral kurtosis. Biorthogonal 5.5 wavelet, a real wavelet has been selected as a suitable wavelet for WPT based on “Maximum Relative Wavelet Energy” and “Maximum Energy-to-Shannon entropy ratio”. Three, Feature extraction techniques like continuous wavelet transform (CWT), wavelet packet transform (WPT) and modified Hilbert Huang Transforms (HHT) are compared on bases of their classification accuracy with different classification algorithm and filters. Various supervised classifiers have been compared through a common platform of Waikato Environment for Knowledge Analysis (WEKA) and concluded the k- nearest neighbour (KNN) as an effective available classifier for rolling element bearing. Further, asymmetric proximity function based KNN (APF-KNN) has out performs with modified feature selection criteria. Feature extraction through modified HHT and APFKNN has been future as a most effectual fault classification method. For testing any unknown data, simplified method has been demonstrated, which make the proposed data driven approach more realistic, faster and automated.

An intelligent bearing fault diagnosis based on hybrid signal processing and Henry gas solubility optimization

Bearing is regarded as one of the core elements in rotating machines and its fault diagnosis is essential for better reliability and availability of the rotating machines. This paper puts forward an intelligent vibration signal-based fault diagnosis approach for bearing faults identification at an early stage, irrespective of speed conditions. The proposed methodology comprises of a frequency shift-based hybrid signal processing technique that involves a combination of Hilbert Transform (HT) and Discrete Wavelet Transform (DWT) followed by sliding window-based feature extraction. Thereafter, a newly developed Henry Gas Solubility Optimization (HGSO) is implemented to select the relevant features. At last, the optimal attributes are used to train the Artificial Neural Network (ANN) model for the classification of the different bearing faults. To test the effectiveness of the speed independent model, experimental validation was done with constant and varying speed conditions. The results demonstrate that the proposed methodology has a tremendous potential to eliminate unplanned failures caused by bearing in rotating machinery.

Design and Implementation of Hybrid Transmission Line Protection Scheme Using Signal Processing Techniques

A hybrid scheme for transmission line protection (HSTLP) using the Stockwell transform (ST), Wigner distribution function (WDF), and alienation coefficient (ACF) is designed. Current signals are analyzed using the ST, WDF, and ACF to compute the Stockwell fault index (SFI), Wigner fault index (WFI), and alienation coefficient fault index (ACFI), respectively. These fault indexes are used to derive a hybrid signal processing fault index (HSPFI), which is implemented for the detection of transmission line fault events. The peak magnitude of HSPFI is compared with a preset threshold magnitude (TH) to identify the fault. The statistical formulation is proposed for fault location on the power transmission line. Fault classification is achieved using the number of faulty phases. A hybrid ground fault index (HGFI) is used to recognize the involvement of the ground during the fault event. This HGFI is determined by processing zero sequence current using ST and WDF. The performance of algorithm is tested by various case studies for fault impedance variation, variable sampling frequency, fault incidence angle variation, reverse power flow on transmission line, highly loaded line, different fault locations online, and noisy conditions. The algorithm is also validated to detect a fault on a practical transmission line of large area utility grid of Rajasthan Rajya Vidyut Prasaran Nigam Limited (RVPN) in India. The algorithm performs better than the Hilbert–Huang transform (HHT)-based protection scheme and wavelet transform (WT)-based protection scheme available in the literature in terms of mean error of fault location, fault location accuracy, and noise level. The proposed protection scheme efficiently detected, classified, and located the faulty events such as single-phase-to-ground fault (SPGF), two-phase fault (TPF), two-phase-to-ground fault (TPGF), three-line fault (TLF), and three-line-to-ground fault (TLGF). Transmission line fault location accuracy of 99.031% is achieved. The algorithm performs well even with a high noise level of 10 dB SNR.

A Hybrid Signal Processing Technique for Recognition of Complex Power Quality Disturbances

This paper proposes an algorithm based on the Stockwell transform (ST) and Hilbert transform (HT) to classify complex power quality disturbances (CPQDs). Two indices are used for detection and locating the CPQDs. The first index is the hybrid power quality index (HPQI), which is used to classify CPQDs. The Stockwell maximum values factor (SMVF), Stockwell summation values factor (SSVF), and Stockwell variance values factor (SVVF) are computed by utilizing the ST to process a voltage signal having a superimposed PQ disturbance. To compute the Hilbert index (HI), the voltage signal is also processed using the HT. The HPQI index is calculated by element-to-element multiplication of the SMVF, SSVF, SVVF, HI, and a weight factor (WF). The second index is the hybrid power quality disturbance time localization index (HPLI), which is used to locate the complex PQ events in a given time frame. For classification of investigated CPQDs, seven different features extracted from various indices defined using ST and HT are taken as input to the rule-based decision tree (RBDT). RBDT classifies the disturbances using simple decision rules, which has the merit of low computational time. The algorithm is able to correctly detect CPQDs with a 98% accuracy rate. The proposed algorithm outperforms the literature's algorithm, which is based on HT and RBDT. Furthermore, it is demonstrated that the algorithm effectively recognizes CPQDs that occur in real-time on a practical distribution network in Rajasthan State, India.

Rotor fault detection using hybrid signal processing approach for sensorless Backstepping control driven induction motor atlow‐speedoperation

Rotor fault detection using hybrid signal processing approach for sensorless Backstepping control driven induction motor at<scp>low‐speed</scp>operation