Time-domain Signal Research Articles

A visual faulty feeder detection method for power distribution network based on spatial image generation and deep learning

AbstractIn the case of a single‐phase grounding fault in the distribution network, the transient zero‐sequence current (TZSC) tends to be non‐linear and non‐stationary. The faulty line selection is relatively difficult. The distributed power access further brings many difficulties to faulty line selection. This work proposes a novel method of faulty line selection using spatial image generation and deep learning. At first, the optimal smooth denoising model can be used to smooth the zero‐sequence current for each line, reducing the external environment electromagnetic interference. Then, the treated zero‐sequence current is mapped into the colorful floral hoop image by using symmetrized Hilbert transform pattern (SHTP). The SHTP transforms the one‐dimensional time domain signal into the two‐dimensional space domain image, enhancing invisible information and obtaining more abundant feature information. Finally, the deep features of the SHTP floral hoop image are extracted by means of deep learning method. In order to improve the faulty line selection universality, a mixed sample library containing three different topologies is established, including the 10 kV radial distribution network, IEEE‐13 node model, IEEE‐34 node model and StarSim platform. The comparisons show that the proposed method has a more noticeable visualization effect on fault features, higher classification precision rate, and better anti‐noise performance.

A modified grid search-based optimization for possibly repetitive global extremum with an application to edge intelligence in IIoT towards time-domain signals

A modified grid search-based optimization for possibly repetitive global extremum with an application to edge intelligence in IIoT towards time-domain signals

A machine-learning approach to setting optimal thresholds and its application in rolling bearing fault diagnosis

Bearings are one of the critical components of any mechanical equipment. They induce most equipment faults, and their health status directly impacts the overall performance of equipment. Therefore, effective bearing fault diagnosis is essential, as it helps maintain the equipment stability, increasing economic benefits through timely maintenance. Currently, most studies focus on extracting fault features, with limited attention to establishing fault thresholds. As a result, these thresholds are challenging to utilize in the automatic monitoring diagnosis of intelligent devices. This study employed the generalized fractal dimensions to effectively extract the feature of time-domain vibration signals of bearings. The optimal fault threshold model was developed using the receiver operating characteristic curve, which served as the baseline of exception judgment. The extracted fault threshold model was verified using two bearing operation experiments. The experimental results revealed different damaged positions and components observed in the two experiments. The same fault threshold model was obtained using the method proposed in this study, and it effectively diagnosed the abnormal states within the signals. This finding confirms the effectiveness of the diagnostic method proposed in this study.

Cumulative spectrum distribution entropy for rotating machinery fault diagnosis

Entropy-based methods have shown promise in detecting dynamic changes in non-linear signals and have been widely applied in fault diagnosis for rotating machinery. However, these methods have limitations when it comes to capturing frequency-domain information of fault features, as they are primarily based on time-domain signals. To address this issue, this paper proposes a new entropy measure called cumulative spectrum distribution entropy (CSDEn), which is based on the cumulative distribution of the spectrum and considers both frequency probability and frequency values in the spectrum domain. The proposed method is evaluated using synthetic signals and experimental data from different bearing and gear working states. The results show that CSDEn outperforms other widely used entropy measures in detecting dynamic changes and measuring signal complexity with low noise sensitivity and high computing efficiency. Nonparametric Mann–Whitney U tests reveal significant differences between different working states for proposed CSDEn method, and compared with other entropy methods, CSDEn achieves the highest recognition rates in diagnosing different bearing and gear working states. Moreover, proposed CSDEn method demonstrates its effectiveness in addressing the challenges of small sample datasets and strong noise interference, making it highly competitive in real industrial applications.

A Fault Diagnosis Strategy for Analog Circuits with Limited Samples Based on the Combination of the Transformer and Generative Models.

As a pivotal integral component within electronic systems, analog circuits are of paramount importance for the timely detection and precise diagnosis of their faults. However, the objective reality of limited fault samples in operational devices with analog circuitry poses challenges to the direct applicability of existing diagnostic methods. This study proposes an innovative approach for fault diagnosis in analog circuits by integrating deep convolutional generative adversarial networks (DCGANs) with the Transformer architecture, addressing the problem of insufficient fault samples affecting diagnostic performance. Firstly, the employment of the continuous wavelet transform in combination with Morlet wavelet basis functions serves as a means to derive time-frequency images, enhancing fault feature recognition while converting time-domain signals into time-frequency representations. Furthermore, the augmentation of datasets utilizing deep convolutional GANs is employed to generate synthetic time-frequency signals from existing fault data. The Transformer-based fault diagnosis model was trained using a mixture of original signals and generated signals, and the model was subsequently tested. Through experiments involving single and multiple fault scenarios in three simulated circuits, a comparative analysis of the proposed approach was conducted with a number of established benchmark methods, and its effectiveness in various scenarios was evaluated. In addition, the ability of the proposed fault diagnosis technique was investigated in the presence of limited fault data samples. The outcome reveals that the proposed diagnostic method exhibits a consistently high overall accuracy of over 96% in diverse test scenarios. Moreover, it delivers satisfactory performance even when real sample sizes are as small as 150 instances in various fault categories.

Human behavior in free search online shopping scenarios can be predicted from EEG activation using Hjorth parameters.

The present work investigates whether and how decisions in real-world online shopping scenarios can be predicted based on brain activation. Potential customers were asked to search through product pages on e-commerce platforms and decide, which products to buy, while their EEG signal was recorded. Machine learning algorithms were then trained to distinguish between EEG activation when viewing products that are later bought or put into the shopping card as opposed to products that are later discarded. We find that Hjorth parameters extracted from the raw EEG can be used to predict purchase choices to a high level of accuracy. Above-chance predictions based on Hjorth parameters are achieved via different standard machine learning methods with random forest models showing the best performance of above 80% prediction accuracy in both 2-class (bought or put into card vs. not bought) and 3-class (bought vs. put into card vs. not bought) classification. While conventional EEG signal analysis commonly employs frequency domain features such as alpha or theta power and phase, Hjorth parameters use time domain signals, which can be calculated rapidly with little computational cost. Given the presented evidence that Hjorth parameters are suitable for the prediction of complex behaviors, their potential and remaining challenges for implementation in real-time applications are discussed.

Physics-guided diagnosis framework for bridge health monitoring using raw vehicle accelerations

Damage detection of bridges using vibrations from a passing vehicle has received a lot of interest recently. Though non-modal parameter-based methods (e.g., data-driven approaches) have shown promising results in this context, their advancement towards a comprehensive and rigorous monitoring system is hampered by their overreliance on machine learning techniques. On this background, this paper proposes a novel automatic physics-guided diagnosis framework for bridge health monitoring utilizing only raw vehicle accelerations. First, numerical studies are conducted to investigate the relationship between vehicle time-domain signals and bridge damage, based on which a new damage index is proposed. At the same time, it also explores the identification of damage locations and proposes a location index. Second, a damage diagnosis framework, which consists of a data processing method and a physics-guided model, is designed to overcome deficiencies from a drive-by measurement and to automate the damage detection process. The proposed framework was validated using datasets acquired from laboratory experiments employing a scale vehicle model and a steel beam. The results affirmed the method's efficacy in damage indication, quantification, and localization. Moreover, the superiority of the proposed damage index and the rationale for the proposed physics-guided approach were also demonstrated through comparisons with machine learning-based methods.

Discretized tensor-based model of total focusing method: A sparse regularization approach for enhanced ultrasonic phased array imaging

The total focusing method (TFM) is considered as the standard in ultrasonic phased array imaging and plays a vital role in industrial non-destructive testing (NDT). By utilizing the full matrix capture (FMC) dataset, the TFM can focus on every point within the specified imaging region, and is more accurate than the traditional ultrasonic phased array imaging methods. However, the TFM is essentially a delay and sum technique that often operates linearly on the time-domain signals and takes no prior information into account, so its image quality remains inadequate when dealing with defects in close proximity or scattering materials. To address this problem, this paper formulates the imaging principle of the TFM as a Boolean matrix and establishes the discretized tensor-based model. Subsequently, the model is addressed by employing the sparse regularization strategy, taking into some characteristics of industrial NDT. Regarding the solution algorithm, due to the generation of negative values by the fast iterative shrinkage threshold algorithm (FISTA), this paper introduces the rectified linear unit (ReLU) function as a non-negative constraint and presents a dedicated solution algorithm (ReLU-FISTA) for acquiring detection results. Through verification of simulation and experiment, the proposed approach exhibits superior capabilities of defect characterization and noise suppression when compared to the TFM, leading to substantial enhancements in image quality.

Adaptive Fuzzy Power Management Strategy for Extended-Range Electric Logistics Vehicles Based on Driving Pattern Recognition

The primary objective of an energy management strategy is to achieve optimal fuel economy through proper energy distribution. The adoption of a fuzzy energy management strategy is hindered due to different reasons, such as uncertainties surrounding its adaptability and sustainability compared to conventional energy control methods. To address this issue, a fuzzy energy management strategy based on long short-term memory neural network driving pattern recognition is proposed. The time-frequency characteristics of vehicle speed are obtained using the Hilbert–Huang transform method. The multi-dimensional features are composed of the time-frequency features of vehicle speed and the time-domain signals of the accelerator pedal and brake pedal. A novel driving pattern recognition approach is designed using a long short-term memory neural network. A dual-input and single-output fuzzy controller is proposed, which takes the required power of the vehicle and the state of charge of the battery as the input, and the comprehensive power of the range extender as the output. The parameters of the fuzzy controller are selected according to the category of driving pattern. The results show that the fuel consumption of the method proposed in this paper is 5.8% lower than that of the traditional fuzzy strategy, and 4.2% lower than the fuzzy strategy of the two-dimensional feature recognition model. In general, the proposed EMS can effectively improve the fuel consumption of extended-range electric vehicles.

Local spectral attention for full-band speech enhancement.

Attention mechanism has been widely used in speech enhancement (SE) because, theoretically, it can effectively model the inherent connection of signal in time domain and spectrum domain. In this Letter, it is found that the attention over the entire frequency range hampers the inference for full-band SE and possibly leads to excessive residual noise and degradation of speech. To alleviate this problem, the local spectral attention is introduced into full-band SE model by limiting the span of attention. The ablation tests on three full-band SE models reveal that the local frequency attention can effectively improve overall performance.

Terahertz wave imaging using time domain iterative shrink threshold method

We propose a new linear imaging method that combines the iterative shrinkage thresholding algorithm (ISTA) with the synthetic aperture (SA) method to achieve high resolution. Unlike other ISTA methods that use a single frequency component of signals, we use time domain signals directly as measurement, which allows for simultaneous wide bandwidth calculation and potentially better imaging results. Additionally, we simplify the backward estimation process by using impulse back-projection based on the SA method, which reduces the computing cost compared to the ISTA method. Numerical simulation and experimental measurement results show that the image resolution is similar to that of our previous non-linear imaging method, and two reflectors with different reflectivity are imaged linearly. These comparison results demonstrate the effectiveness of our proposed method in achieving high-resolution and maintaining the linearity of target reflectivity.

A GPU-accelerated real-time human voice separation framework for mobile phones

Mobile speech communication can experience significant degradation in quality when users are in a noisy acoustic environment. With the rapid development of artificial intelligence in recent years, deep learning based monaural speech separation methods have shown remarkable progress in boosting the performance of the separation accuracy. However, the latency and computational cost of these methods remain far insufficient for mobile devices. Performance and power constraints make it still challenging to deploy such methods on mobile devices due to their high computational complexity. In this paper, we present VoiceBit, an efficient and light-weight human voice separation framework for real-time speech separation on mobile devices. Specifically, we propose a light-weight speech separation network to segregate human voice and interfering noises directly from time-domain signals. We binarize the convolution blocks in down-sampling blocks to reduce computation complexity and memory footprint, and leverage scaler layers as well as learnable bias layers to enhance the representation ability of binary filters. In addition, we present a set of parallel optimizations to accelerate the operations in VoiceBit. Specifically, we adopt KKC-minor format for weight matrices of convolution layers to coalesce memory access from global memory. Then, we explore different methods to implement the transposed convolution operation under PhoneBit framework. Experimental results on the MUSDB18-HQ dataset and VCTK dataset show that VoiceBit achieves significant speedup and energy efficiency compared with state-of-the-art frameworks, while maintaining minimal compromise in accuracy.

Single-Photon Level Dispersive Fourier Transform: Ultrasensitive Characterization of Noise-Driven Nonlinear Dynamics.

Dispersive Fourier transform is a characterization technique that allows directly extracting an optical spectrum from a time domain signal, thus providing access to real-time characterization of the signal spectrum. However, these techniques suffer from sensitivity and dynamic range limitations, hampering their use for special applications in, e.g., high-contrast characterizations and sensing. Here, we report on a novel approach to dispersive Fourier transform-based characterization using single-photon detectors. In particular, we experimentally develop this approach by leveraging mutual information analysis for signal processing and hold a performance comparison with standard dispersive Fourier transform detection and statistical tools. We apply the comparison to the analysis of noise-driven nonlinear dynamics arising from well-known modulation instability processes. We demonstrate that with this dispersive Fourier transform approach, mutual information metrics allow for successfully gaining insight into the fluctuations associated with modulation instability-induced spectral broadening, providing qualitatively similar signatures compared to ultrafast photodetector-based dispersive Fourier transform but with improved signal quality and spectral resolution (down to 53 pm). The technique presents an intrinsically unlimited dynamic range and is extremely sensitive, with a sensitivity reaching below the femtowatt (typically 4 orders of magnitude better than ultrafast dispersive Fourier transform detection). We show that this method can not only be implemented to gain insight into noise-driven (spontaneous) frequency conversion processes but also be leveraged to characterize incoherent dynamics seeded by weak coherent optical fields.

Reconstruction of Water-Filled Pipe Ultrasonic Guided Wave Signals in the Distance Domain by Orthogonal Matching Pursuit Based on Dispersion and Multi-Mode.

Ultrasonic guided waves (UGWs) in water-filled pipes are subject to more severe dispersion and attenuation than vacant pipes, posing significant challenges for defect identification and localization. To this end, a novel sparse signal decomposition method called orthogonal matching pursuit based on dispersion and multi-mode (DMOMP) was proposed, which utilizes the second-order asymptotic solution of dispersion curves and the conversion characteristics of asymmetric UGWs in the defect contact stage to reconstruct the dispersive signals and converts the time-domain dispersive signals to distance-domain non-dispersive signals by dispersion compensated time-distance mapping. The synthesized simulation results indicate that DMOMP not only exhibits higher reconstruction accuracy compared to OMP, but also reveals more accurate and stable mode recognition and localization compared to DOMP, which only considers the dispersion under perturbation and noise. In addition, the UGW testing experimental results of water-filled pipes verify the effectiveness of DMOMP, the localization accuracies of three feature signals (defct 1, defct 2 and end echo) with DMOMP are 99.10%, 98.72% and 98.36%, respectively, and the average localization accuracy of DMOMP is as high as 98.73%.

A Wasserstein generative adversarial network with gradient penalty for active sonar signal reverberation suppression

Reverberation is the primary background interference of active sonar systems in shallow water environments, affecting target position detection accuracy. Reverberation suppression is a signal processing technique used to improve the clarity and accuracy of received signals by eliminating the echoes, reverberations, and noise that occur during underwater propagation. Existing reverberation suppression methods include algorithms based on Time-Frequency domain processing, noise reduction, adaptive filtering, and spectral subtraction, but their performance in high-reverberation environments (echo of small targets) still does not meet the requirements of target detection. To address the impact of high reverberation environments, we propose a structural suppression method based on the Wasserstein gradient penalty generative adversarial network (RSWGAN-GP). The reverberation suppression generation network uses a one-dimensional convolutional network structure to process normalized time-domain signals and achieves the reconstruction of the reverberation signal through Encoder-Decoder. The proposed method is verified through accurate and effective data collection during sea trials. Comparative results show that RSWGAN-GP effectively suppresses reverberation in observation signals with multiple bright spots, improving the signal-to-reverberation ratio by approximately 10 dB compared to other excellent algorithms and enhancing the information analysis and feature extraction capabilities of active sonar signals.

Research on online monitoring technology for transmission tower bolt looseness

Minor damages such as tower bolt looseness are difficult to detect through manual inspections. Operational modal analysis plays an important role in the online monitoring of transmission tower structure safety. However, the traditional analysis methods select feature parameters manually, and the deviation generated will directly affect the estimation accuracy of structural modal parameters. This article proposes a method for diagnosing tower bolt looseness without human intervention. This method can reduce the influence of background noise greatly through data cleaning and data fusion. Besides, the intelligent feature recognition of vibration acceleration time-domain signals based on an improved 1DCNN algorithm can improve the monitoring accuracy and speed significantly. The effectiveness of the method has been validated by conducting dynamic response tests on a 110KV transmission tower under different bolt loosening conditions. In the end, an online monitoring technology for transmission towers bolt looseness has been developed and successfully applied to the Guangdong power grid. The results show that this method has high identification accuracy and provides a new approach for online monitoring of tower bolt looseness.

Optical adaptive power control based on atmospheric channel reciprocity for mitigating turbulence disturbances in free-space optics communication.

A continuous time-domain adaptive power model of transmitter optical and control algorithm based on atmospheric turbulence channel reciprocity are explored for mitigating the free-space optical communication (FSOC) receiver optical intensity scintillation and bit error rate (BER) deterioration. First, a transmitter optical adaptive power control (OAPC) system architecture using four wavelength optical signals based on atmospheric turbulence channel reciprocity is proposed, and electronically variable optical attenuator (EVOA) and erbium-doped fiber amplifier (EDFA) are employed as the main OAPC units for power adaptation. Moreover, a reciprocity evaluation model for gamma-gamma (G-G) continuous-time signals is generated using the autoregressive moving average (ARMA) stochastic process, which takes into account the delay time and system noise, and a reciprocity-based OPAC algorithm is proposed. Numerical simulations were also performed to analyze the signal reciprocity characteristics under different turbulence, noise, and sampling time mismatch at both ends, as well as the scintillation index (SI) performance under OAPC system operation. Simultaneously, the time-domain signals of continuous quadrature amplitude modulation -16 (QAM-16) and QAM-32 real states are fused with the gamma-gamma (G-G) reciprocal turbulence continuous signals to analyze the probability density function (PDF) and bit error ratio (BER) performance after OAPC correction. Finally, a 64 Gpbs QAM-16 OPAC communication experiment was successfully executed based on an atmospheric turbulence simulator. It is shown that the OAPC correction is carried out using reciprocity at millisecond sampling delay, the light intensity scintillation of the communication signal can be well suppressed, the signal-to-noise ratio (SNR) is greatly improved, the suppression is more obvious under strong turbulence, the overall BER reduction is greater than 2.8 orders of magnitude with the OAPC system, and this trend becomes more pronounced as the received power increases, even reach 6 orders of magnitude in some places. This work provides real time-domain continuous signal samples for real signal generation of communication signals in real turbulence environments, adaptive coding modulation using reciprocity, channel estimation, and optical wavefront adaptive suppression, which are the basis of advanced adaptive signal processing algorithms.

Compound fault separation and diagnosis method for online rolling bearings based on RSEUnet and 1DCNN

Compound fault signals interfere with one another, resulting in an inconspicuous feature extraction that requires sophisticated signal processing techniques and expert experience. However, good online diagnostic methods are not available to carry out this process. This paper proposes a method based on Residual Connection and Squeeze-and-Excitation Unet (RSEUnet) and one-dimensional convolutional neural network (1DCNN). The process includes fault separation and diagnosis. First, the feature extraction module of the RSEUnet network introduces an attention mechanism and a residual connection that adaptively assigns various weights to different channels. This model is used to train the maps of the fault signal after time-frequency transformation. Ideal binary masks with excellent performance are the training targets to complete the intelligent separation of compound faults. Second, the 1DCNN is used as a feature learning model to efficiently learn the features of single faults from time-domain signals. An embedded system consisting of a Jetson Nano and a signal acquisition circuit is then built to perform online diagnosis. The test is carried out on the fault experimental platform. Results show that the method has an accuracy of 99.71%, making it highly suitable for the diagnosis of bearing compound faults.

Multi-Order Mode Excitation and Separation of Ultrasonic Guided Waves in Rod Structures Using 2D-FFT.

The ultrasonic guided wave technique is extensively used for nondestructive structural testing, and one of the key steps is to extract a single mode with certain purity from multi-order mixed modes. In this paper, the propagation of ultrasonic guided waves in the cylindrical rod is simulated first; the appropriate broadband excitation signal is selected to excite the multi-order modes in a specific frequency range; and the time-space signal containing multi-order modes is converted to the frequency-wavenumber domain signal by two-dimensional Fourier transform. In the frequency-wavenumber domain, the frequency-wavenumber ridge is extracted from the multi-mode frequency-wavenumber domain based on the dynamic programming method, and then the time-domain signal corresponding to a single mode can be reconstructed. By comparing the excited multi-order mode and the separated single mode with the theoretical results, it is observed that the two results are consistent. Thus, the employed mode-excitation method can accurately excite the multi-order modes in rod structures. Furthermore, the proposed method enables the separation of a single-mode wave with high purity, providing a foundation for future utilization of isolated modes.

Self-Attention-Based Deep Convolution LSTM Framework for Sensor-Based Badminton Activity Recognition.

Sensor-based human activity recognition aims to classify human activities or behaviors according to the data from wearable or embedded sensors, leading to a new direction in the field of Artificial Intelligence. When the activities become high-level and sophisticated, such as in the multiple technical skills of playing badminton, it is usually a challenging task due to the difficulty of feature extraction from the sensor data. As a kind of end-to-end approach, deep neural networks have the capacity of automatic feature learning and extracting. However, most current studies on sensor-based badminton activity recognition adopt CNN-based architectures, which lack the ability of capturing temporal information and global signal comprehension. To overcome these shortcomings, we propose a deep learning framework which combines the convolutional layers, LSTM structure, and self-attention mechanism together. Specifically, this framework can automatically extract the local features of the sensor signals in time domain, take the LSTM structure for processing the badminton activity data, and focus attention on the information that is essential to the badminton activity recognition task. It is demonstrated by the experimental results on an actual badminton single sensor dataset that our proposed framework has obtained a badminton activity recognition (37 classes) accuracy of 97.83%, which outperforms the existing methods, and also has the advantages of lower training time and faster convergence.