Signal Processing Technology Research Articles

Multidisciplinary Framework for Vibration-Based Gear Fault Diagnosis Using Experiments, Modeling, and Machine Learning

Vibration-based gear diagnosis is crucial for ensuring the reliability of rotating machinery, making the monitoring of gear health essential for preventing costly downtime and optimizing performance. This study proposes a multidisciplinary framework to enhance gear diagnosis, that aligns with the new era of digital twins by integrating experiments, dynamic modeling, physical preprocessing, and machine learning. Within this framework, we focus on three core procedures: domain adaptation to reduce discrepancies between measured data and synthetic data generated by dynamic models; physical preprocessing, grounded in in-depth investigations dictating signal processing and feature engineering techniques; and learning algorithms, encompassing the process of training AI-based models. We demonstrate this framework through a comprehensive case study of localized tooth fault diagnosis, using controlled-degradation tests and realistic simulations. First, we detect faults using unsupervised learning algorithms; then, we use zero-shot-learning for classifying between localized and distributed faults; finally, we adopt a one-shot-learning strategy for severity estimation. Above all, this hybrid framework bridges the gaps between physical-based and AI-based approaches by combining physical knowledge and advanced algorithmics with machine learning. This contributes to the PHM field by offering valuable insights into integrating different aspects of research, thereby enhancing performance in gear diagnosis tasks.

Improvement of multiscale decomposition for space-based gravitational wave signal processing technology.

During the process of detecting gravitational waves in space, addressing noise issues caused by terrestrial vibrations, natural environmental changes, and the factors intrinsic to the detectors, this paper proposes a multiscale variational mode adaptive denoising algorithm based on momentum gradient descent. This algorithm integrates momentum factors and multiscale concepts into the variational mode algorithm to resolve the issue of multiple local optima encountered during operation, reduce oscillations in regions with large or unstable gradient changes, and improve convergence speed. Additionally, the algorithm combines the least mean squares algorithm to automatically adjust weights, thereby mitigating the impact of noise, addressing the issue of noise from multiple and random sources, effectively suppressing noise in the gravitational wave signal, and enhancing the quality and reliability of the gravitational wave signal. Experimental results demonstrate that this algorithm performs better than other algorithms in noise suppression, effectively reducing noise in gravitational wave signals and meeting the noise suppression requirements for space-based gravitational wave detection.

Analysis of methods for reducing the signal PAPR under the influence of the Doppler effect in hybrid communication networks

Background. For further development of communication networks, it is planned to use hybrid satellite networks for traffic transmission. However, satellite communication channels have features such as distortion caused by the Doppler effect and increased energy efficiency requirements. Aim of this study is to analyze variants of orthogonal frequency multiplexing methods and modulation methods in order to choose the most stable technology, taking into account destabilizing factors. Method. Comparing different signal processing technologies and studying their resistance to bit errors is the imitation modeling of the communication channel in the Matlab environment. This approach allows creating a model of the communication network, taking into account the main parameters of communication channels, such as the Doppler effect, energy deficiency and destabilizing factors. Results. The distribution of the bit error coefficient for various signal processing technologies, depending on the signal-to-noise ratio, is compared. The method of frequency multiplexing is defined, providing the minimum peak factor and the most resistant to bit error. It is also noted that the effectiveness of all the studied technologies depends on the spacing and modulation constellations, and that it is necessary to adjust the characteristics of the system for each case. Conclusion. The results of this study can be used to improve the quality of communication in difficult interference conditions of hybrid mobile networks of 5 and 6 generations using the satellite segment.

Preface

The 2024 International Conference on Computational Intelligence and Communication System (CCICS2024), held in Wuhan, China from June 26-28, 2024, is a testament to the ever-evolving nature of fields of computational intelligence and communication technology, has attracted a diverse and brilliant array of researchers, engineers, and scholars from around the globe. CCICS2024 attracted more than 80 participants from around the world, which is a vibrant and engaging event, with a diverse program that included an opening ceremony, keynote speeches, oral presentations, poster sessions, Q&A discussions, and an ending ceremony. The keynote speakers, renowned experts worldwide in their respective fields, provided insightful overviews of the latest developments and trends in domains related to computational intelligence and communication technology. The oral presentations and poster sessions were equally enriching. Researchers and practitioners shared their latest findings, discussed challenges and opportunities, and explored potential collaborations. The lively discussions and interactions among the participants created a vibrant intellectual atmosphere that fostered innovation and knowledge sharing. The submissions received for this conference are vivid evidence of the creativity and innovation that flourishes in related areas. The manuscripts cover a wide range of topics, including computing for emerging technology, signal processing, sensor and detection technology, futuristic communication and network technologies, etc. The diversity and depth of these contributions reflect the vibrant and interdisciplinary nature of relevant industries. All papers submitted to the conference have been reviewed using a double-blind peer-review process. Each paper was tested for similarity with already published content using the Turnitin platform. All sources of similarities were checked and only original content was accepted. This volume of proceedings is beneficial for readers from academia and industry to understand and tackle the challenges efficiently and adopt appropriate solutions in the above-mentioned topics. Building on the success of this event, we hope CCICS 2024 will be one of the most spectacular events in those areas. We would like to thank the reviewers and the members of the international scientific committees. We also extend our sincere thanks to Prof. Joarder Kamruzzaman, Prof. Yangjun Chen, Prof. Oscar Eduardo Ruiz Salguero, Prof. Jie Yang, Prof. JingTao Yao and Dr. Iacovos Ioannou for their wonderful keynote talks. We are grateful to everyone who has contributed to the realization of CCICS 2024. We also look forward to the next conferences in this series, which will continue to build upon the foundation laid by this one. Organizing Committee of CCICS 2024 Prof. Yuriy S. Shmaliy (Conference Chair) IEEE Fellow, AAIA Fellow, University of Guanajuato, Mexico List of Conference Committee is available in this Pdf.

Improved PHY-layer authentication utilizing multi-modal features for mmWave MIMO UAV-enabled systems

This paper exploits multi-modal Physical (PHY)-layer features in terms of artificial fingerprint, In-phase/Quadrature (IQ) imbalance and Angle of Arrival (AoA) to propose a novel PHY-layer authentication framework for a Millimeter Wave (mmWave) Multiple-Input Multiple-Output (MIMO) Unmanned Aerial Vehicle (UAV)-enabled communication system. First, we resort to the AoA-based spatial fingerprint to effectively address the challenge of channel fingerprint instability induced by high-speed UAV mobility. To further enhance the low discriminability of hardware fingerprints caused by refined manufacturing techniques, artificial Gaussian noise is injected into the transmission signals to assist the receiver in better distinguishing between legitimate and illegitimate UAVs. Then, we jointly combine with inherent IQ imbalance and AoA features to design a hybrid authentication scheme and thus construct a multi-dimensional fingerprint space for a comprehensive characterization of UAV identities. To theoretically evaluate the effectiveness of the proposed authentication framework, the analytical closed-form expressions of performance metrics like false alarm and detection probabilities are also exactly derived based on the statistical signal processing technology and composite hypothesis testing. Finally, we provide large simulation results to validate the correctness and feasibility of the proposed theoretical models, and also discuss the relation between system security and communication service quality under different artificial fingerprint level.

Fault Line Selection of Small Current Grounding System Research Based on Zero Sequence Circuit Current Phase

Abstract This paper investigates fault line selection in small current grounding systems, focusing on the zero sequence current phase characteristics. Small current grounding systems, prevalent in medium voltage distribution networks, face challenges in fault detection due to minimal fault currents during single status phase grounding faults. Traditional methods relying on manual line switching and zero sequence voltage monitoring are inefficient and can induce overvoltage. This study categorizes fault line selection techniques into three approaches: steady-state fault information, transient information, and modern signal processing technology. The analysis of zero sequence currents in non-grounded systems reveals that fault line zero sequence currents equal the sum of system capacitive currents, flowing opposite to those in non-fault lines. Additionally, transient signal analysis shows that these signals provide more robust information for fault detection. MATLAB simulations validate the theoretical models, demonstrating that zero sequence current direction and amplitude effectively identify fault lines. The results confirm the efficacy of combining steady-state and transient signal analyses for accurate fault line selection, contributing to enhanced safety and reliability in power distribution networks. This research offers practical insights and tools for engineers, improving fault management and reducing potential economic losses in small current grounding systems.

Utilizing multi-point temperature sensing to evaluate the low frequency noise of phasemeter for intersatellite laser interferometer.

High-precision phasemeters are a key technology in intersatellite laser interferometers used for detecting gravitational waves (GWs) in space. As the core of the readout system, the phasemeter must operate in the bandwidth of 5-25MHz, and its resolution needs to reach the order of μrad/Hz at mHz. It presents significant challenges to electronic signal processing technology. To investigate the primary noise source in the low-frequency band, a mathematical model of thermal drift to phase noise was established, and a multi-point temperature sensing scheme for critical electronic components was proposed. In particular, we evaluated a phasemeter based on a commercial platform and assessed the thermal drift noise according to the proposed model. This study identifies and explains the effects of temperature linear drift and overcorrection in components, demonstrating that thermal drift noise is the main noise source for the phasemeter at frequencies from 0.1 to 1 mHz. In addition, the proposed scheme is universal in its applicability and may be implemented in any circuit for the evaluation of temperature effects on the components of interest.

Analysis and Calculation of Marginal Electricity Price of Nodes with Network Loss from the Perspective of Intelligent Robot Considering Digital Signal Processing Technology

Analysis and Calculation of Marginal Electricity Price of Nodes with Network Loss from the Perspective of Intelligent Robot Considering Digital Signal Processing Technology

END-TO-END AUTOMATIC MUSIC TRANSCRIPTION OF POLYPHONIC QANUN AND OUD MUSIC USING DEEP NEURAL NETWORK

This paper introduces an automatic music transcription model using Deep Neural Networks (DNNs), focusing on simulating the "trained ear" in music. It advances the field of signal processing and music technology, particularly in multi-instrument transcription involving traditional Turkish instruments, Qanun and Oud. Those instruments have unique timbral characteristics with early decay periods. The study involves generating basic combinations of multi-pitch datasets, training the DNN model on this data, and demonstrating its effectiveness in transcribing two-part compositions with high accuracy and F1 measures. The model's training involves understanding the fundamental characteristics of individual instruments, enabling it to identify and isolate complex patterns in mixed compositions. The primary goal is to empower the model to distinguish and analyze individual musical components, thereby enhancing applications in music production, audio engineering, and education

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.

An application and discussion of wide-band signal processing technology in the primary calibration for hydrophones

Abstract Wide-band signals are potentially available in the measurement of transducers, which can obtain wide-band responses of electroacoustic parameters of them directly. The hydrophone of B&K 8103 is calibrated in a Φ 1.2 m×1.8 m small water vessel by wide-band signal processing technology in the frequency range of 3.15 kHz to 100 kHz. A thin pellicle co-vibrates with acoustic particle in the free-field, and its oscillation can be detected by a laser Doppler vibrometer, which can estimate the acoustic pressure distribution. The transfer function model is established in a small water vessel, and the wide-band frequency responses of the transfer impedance of transducer and hydrophone as well as the transfer impedance of transducer and pellicle in the small water vessel are calculated respectively. The wide-band signal processing technology of frequency domain filter process are used, which can isolate the reflecting acoustic wave from the boundaries and the surface of the water vessel. To verify the accuracy of the wide-band calibration measurements, the calibration results are compared with that using tone-burst signals in the water vessel and using free-field reciprocity method in the large water tank. The comparisons show that their calibration results are in a good agreement with each other, and the maximum deviation is 0.7 dB. All these demonstrate that the wide-band signal processing technology described is accurate and stable.

On the convergence of Fourier representations and Schwartz distributions

While Fourier theory remains a cornerstone for analyzing and interpreting the spectral content of diverse signals, its limitations often surface in practical applications. Notably, popular signals like sinusoids, Dirac deltas, signums, and unit steps lack convergent Fourier representations within the conventional framework. This discrepancy necessitates distribution theory to build and interpret suitable representations for such signals. However, existing literature in signal processing and communication engineering often glosses over these intricacies, leaving researchers grappling with obscure concepts regarding the very existence of Fourier representations for non-conforming signals. This work bridges this critical gap by offering a comprehensive exploration of the conditions guaranteeing the existence of Fourier representations. We introduce a novel linear space – the Gauss–Schwartz (GS) function space – and its corresponding class of tempered superexponential (TSE) distributions. We demonstrate that the Fourier transform (FT) acts as an isomorphism on the GS space of test functions and, by duality, on TSE distributions. Crucially, the GS space proves to be minimal in the sense that its dual, encompassing TSE distributions, represents the largest possible linear space over which the FT can be defined through duality. This theoretical advancement signifies a twofold contribution. Firstly, it clarifies the existence and interpretation of Fourier representations for prevalent signals that evade conventional analysis. Secondly, the introduction of the GS-TSE framework expands the reach of the FT to encompass a broader spectrum of functions, enabling novel applications in diverse fields. Ultimately, this work paves the way for a more robust and accessible understanding of Fourier analysis, empowering researchers and practitioners to leverage its full potential in exploring and processing a wider range of signals.

A novel energy-focused slow-time MIMO radar and signal processing scheme

In this paper, we propose a novel energy-focused slow-time MIMO radar and signal processing scheme, aimed at addressing key challenges in slow-time coding and signal processing technology. Conventional slow-time MIMO radar faces issues such as energy waste due to the omnidirectional transmit beampattern of orthogonal coding and the velocity ambiguity problem. To overcome these limitations, the proposed radar system utilizes a method based on Doppler frequency offset diversity (DFOD) for slow-time coding design. This method enables the adjustment of Doppler offset parameters to achieve a rectangular transmit beampattern with any mainlobe width within a single coherent processing interval (CPI), offering the advantage of low computational complexity. Through an analysis of the ambiguity function for DFOD-based coding, we evaluate both Doppler and angular resolution. To further improve Doppler frequency resolution, a slow-time coding design is introduced based on Pulse Random Permutation (PRP). Subsequently, a signal processing scheme based on matched filtering is presented. To tackle the high Doppler sidelobe issue associated with PRP-based coding, we propose a mismatch filter (MMF) design method utilizing convex optimization. Ultimately, the performance enhancement of the proposed slow-time MIMO radar is verified through simulation analysis in comparison to existing technologies.

Heart Diseases Recognition Model Based on HRV Feature Extraction over 12-Lead ECG Signals.

Heart Rate Variability (HRV) refers to the capability of the heart rhythm to vary at different times, typically reflecting the regulation of the heart by the autonomic nervous system. In recent years, with advancements in Electrocardiogram (ECG) signal processing technology, HRV features reflect various aspects of cardiac activity, such as variability in heart rate, cardiac health status, and responses. We extracted key features of HRV and used them to develop and evaluate an automatic recognition model for cardiac diseases. Consequently, we proposed the HRV Heart Disease Recognition (HHDR) method, employing the Spectral Magnitude Quantification (SMQ) technique for feature extraction. Firstly, the HRV signals are extracted through electrocardiogram signal processing. Then, by analyzing parts of the HRV signal within various frequency ranges, the SMQ method extracts rich features of partial information. Finally, the Random Forest (RF) classification computational method is employed to classify the extracted information, achieving efficient and accurate cardiac disease recognition. Experimental results indicate that this method surpasses current technologies in recognizing cardiac diseases, with an average accuracy rate of 95.1% for normal/diseased classification, and an average accuracy of 84.8% in classifying five different disease categories. Thus, the proposed HHDR method effectively utilizes the local information of HRV signals for efficient and accurate cardiac disease recognition, providing strong support for cardiac disease research in the medical field.

Study on the optimization process and application of FIR digital filter

As one of the components of digital signal processing technology, the FIR digital filter has been widely used in real life and played an increasingly important role due to its advantages of system stability and ease of linear phase. This paper will summarize and analyze the research results of some past scientific research teams on FIR digital filters, and show the optimization process of this technology and the application examples in real life. This paper focuses on the optimization process of noise reduction performance, delay and size, and energy consumption optimization of FIR digital filters. This study summarizes three examples of its applications in medical, audio processing, and radar. In the medical field, the processing of electrocardiogram (ECG) signals, the audio processing fields are the frequency shaping, noise removal, and signal enhancement of audio signals, and the precise filtering and processing of received signals in the radar field. At the end of this paper, the FIR digital filter has an irreplaceable role in all fields in the world and gradually develops in the direction of miniaturization and low power consumption in the future.

Spiral Ouroboros: Metasimulacrum in Rock and Metal Electric Guitar Processing and Modeling Technologies

The article reviews Jean Baudrillard’s concept of simulacrum and puts it in dialogue with the evolution of signal processing technologies for electric guitar, introducing the concept of metasimulacrum—a simulacrum of a simulacrum—to describe the historical trajectory from early electric guitar amplification to recent advances in digital signal processing, taking a critical stance on technological determinism

Portable Hadamard-Transform Raman Spectrometer: A Powerful Analytical Tool for Point-of-Care Testing.

A portable Hadamard-transform Raman spectrometer with excellent performance was fabricated consisting of a 785 nm laser, an optical filter, an optical system, a control system, and a signal processing system. As the core of the spectrometer, the optical system was composed of a slit, collimator, optical grating, reflector, digital micromirror devices (DMD), lens system, and InGaAs photodetector. Compared with a conventional dispersive Raman spectrometer, the proposed Raman spectrometer adopted the DMD and corresponding controlling device (DLPC350 control chip) to collect the Raman spectrum. Thus, in our design, the gratings are fixed, while the full Raman spectrum was collected by the deflection of the micromirror. This design can greatly improve the vibration resistance ability of the spectrometer since the gratings are not rotating during the spectrum collecting. More importantly, Hadamard-transform was used as signal processing technology, which has the ability of faster calculation, the merits of high energy input, single detector multichannel simultaneous detection (imaging) ability, and high signal-to-noise ratio (SNR). Hence, the Hadamard-transform portable Raman spectrometer has the potential to be applied in the field of point-of-care testing (POCT).

Intrusion Detection System with Ensemble Machine Learning Approaches using VotingClassifier

Internets have become a part of our everyday life due to the advancement in the electronics and signal processing technologies during past decades. The tremendous growth of internet leads towards the network threats. Many times firewalls and anti-viruses fails to manage the network because of this Intrusion Detection System (IDS) comes to assists us. In this paper we use IDS with Ensemble methodologies utilized in machine learning involve the fusion of multiple classifiers to improve predictive performance, while voting classifiers combine predictions from individual models to reach conclusive decisions. The paper employs a voting ensemble method combing decision tree, logistic regression and support vector machine classifier models. We test our proposedmodel to classify the NSL-KDD dataset. Our ensemble methodologies of proposed algorithmproduce a good result.

Application of deep learning-based speech signal processing technology in electronic communication

In recent years, the artificial intelligence boom triggered by deep learning is influencing and changing peoples lifestyles. People are no longer satisfied with human-computer interaction through simple text commands; instead, they look forward to more convenient and faster communication methods like voice interaction. Against the backdrop of innovative development, the application of speech signal processing systems is becoming increasingly widespread. Therefore, it is necessary to study the application of deep learning-based speech signal processing technology in electronic communication. This can provide more valuable references and assistance for future development, promoting the better development of deep learning-based speech signal processing technology in electronic communication. In this paper, we first review the application of deep learning in speech signal enhancement, speech recognition, and speech synthesis from a theoretical analysis perspective. Then, we discuss the application of deep learning-based speech signal processing in electronic communication, including the application of models such as Transformer, LAS (Listen, Attend and Spell), and GFT-conformer in speech signal processing. We also discuss some application scenarios of deep learning-based speech signal processing in electronic communication. Finally, we identify the need for deeper application of deep learning technology in speech signal processing and electronic communication, with continuous optimization and adjustment.

Ingredient-guided multi-modal interaction and refinement network for RGB-D food nutrition assessment

RGB-D food nutrition assessment entails the direct prediction of nutritional content in pairs of RGB and depth food images using signal processing technology. However, existing methods present numerous challenges related to accuracy and computational complexity. In this paper, we introduce the Ingredient-guided Multi-modal Interaction and Refinement Network (IMIR-Net), a novel framework for RGB-D food nutrition assessment. We first utilize a visual grounding model to accurately identify the dish region containing food in the input image with complex semantics. The identified RGB-D dish regions are processed through a multi-modal interaction and refinement module to compute the fused embedding. Concurrently, we introduce an ingredient guidance module to effectively capture ingredient textual information, thereby facilitating the acquisition of the enhanced fused embedding. Finally, we design a decoupled nutrition predictor to predict nutrition from the fused RGB-D embedding. The IMIR-Net can capture the rich multi-modal semantics for RGB-D food nutrition assessment and achieves state-of-the-art performances on the Nutrition5k dataset. Specifically, the percentage of mean absolute error (PMAE) of Calories, Mass, Fat, Carb and Protein reached 14.5%, 10.4%, 21.8%, 20.4% and 20.0%, respectively. Compared with the existing best method, our IMIR-Net demonstrated superior prediction accuracy, with a mean PMAE value of 17.4%, an improvement of 1.1%. In terms of computational complexity, the floating-point operations (FLOPs) and parameters reached 63.87 and 105.11 via our method, which is improved by 5.2% and 7.4%, respectively. The codes, data, and model of our method are publicly available at https://github.com/nianfd/IMIR-Net-DSP.