Time-frequency Characteristics Research Articles

Damage identification for railway tracks using ultrasound guided wave and hybrid probabilistic deep learning

Rails are often damaged by train extrusion and other external forces, which seriously affects track safety. Although deep learning is widely used in rail damage recognition, its usual inability to understand own uncertainty that is critical in engineering application. Hence, this paper proposes a hybrid probabilistic deep learning for rail damage identification. It combines the hierarchical representation capabilities of deep learning with probability distributions. The posterior distribution provides support for the uncertainty quantification in identification results. Firstly, ultrasonic guided waves were used to sense the rail damage and time-frequency feature map dataset was obtained by analysing its time-domain signal using wavelet transform. Then, two different weight perturbation methods are used for comparative study. The reparameterization method performs more consistently and efficiently in this task, with a recognition accuracy of 0.9400. Subsequently, the effect of the number of probabilistic and non-probabilistic layers in the hybrid network on recognition results was analysed. Experimental results showed that hybrid probabilistic deep learning achieved the highest testing accuracy of 0.9900. The uncertainty quantification metrics of recognition results from hybrid probabilistic deep learning are mostly less than 0.2, demonstrating favourable reliability.

A novel fault diagnosis method for second-order bandpass filter circuit based on TQWT-CNN.

To accurately locate faulty components in analog circuits, an analog circuit fault diagnosis method based on Tunable Q-factor Wavelet Transform(TQWT) and Convolutional Neural Network (CNN) is proposed in this paper. Firstly, the Grey Wolf algorithm (GWO) is used to improve the TQWT. The improved TQWT can adaptively determine the parameters Q-factor and decomposition level. Secondly, The signal is decomposed, and single-branch reconstruction is conducted with TQWT to facilitate adequate feature extraction. Thirdly, to capture the time-frequency features in the signal, a CNN-LSTM network is built by combining CNN and LSTM for feature extraction. Finally, CNN, which introduces Fully Convolutional Network (FCN) layers and a Batch Normalization layer, is used to fault diagnosis. The method was comprehensively evaluated with a second-order bandpass filter circuit. The experimental results illustrate that the proposed fault diagnosis method can achieve excellent fault diagnosis accuracy, and the average accuracy is 98.96%.

EEG-based emotion recognition using MobileNet Recurrent Neural Network with time-frequency features

Despite the developments in deep learning, extracting different features from brain signals remains a crucial challenge in EEG-based emotion recognition. This study introduces a novel methodology to overcome the challenge of capturing temporal and channel-related features. The basic idea of the proposed method is to use scalograms to capture subtle emotional patterns in EEG signals, followed by MobileNet Recurrent Neural Network (MRNN). Unlike conventional methods, MRNN utilizes recurrent connections to learn sequential patterns and recognize complex temporal dependencies in the data, enhancing EEG-based emotion recognition. The model is trained and tested on two publicly available datasets, DEAP and DREAMER, and achieved better results at 85.95 % for 15 classes and 96.29 % for 9 classes accuracy on average. Our approach extends beyond binary or limited multi-class emotion classification and significantly improves accuracy compared to the state-of-the-art methods. This research can have potential applications in developing emotion recognition systems for real-world scenarios, such as mental health monitoring or human-computer interaction.

Relevance of phase information for object classification in automotive ultrasonic sensing using convolutional neural networks

Automotive ultrasonic sensors come into play for close-range surround sensing in parking and maneuvering situations. In addition to ultrasonic ranging, classifying obstacles based on ultrasonic echoes to improve environmental perception for advanced driver-assistance systems is an ongoing research topic. Related studies consider only magnitude-based features for classification. However, the phase of an echo signal contains relevant information for target discrimination. This study discusses and evaluates the relevance of the target phase in echo signals for object classification in automotive ultrasonic sensing based on lab and field measurements. Several phase-aware features in the time domain and time-frequency features based on the continuous wavelet transform are proposed and processed using a convolutional neural network. Indeed, phase features are found to contain relevant information, producing only 4% less classification accuracy than magnitude features when the phase is appropriately processed. The investigation reveals high redundancy when magnitude and phase features are jointly fed into the neural network, especially when dealing with time-frequency features. However, incorporating the target phase information facilitates the identification quality in high clutter environments, increasing the model's robustness against signals with low signal-to-noise ratios. Ultimately, the presented work takes one further step toward enhanced object discrimination in advanced driver-assistance systems.

DC Series Arc Fault Diagnosis Scheme Based on Hybrid Time and Frequency Features Using Artificial Learning Models

DC series arc faults pose a significant threat to the reliability of DC systems, particularly in DC generation units where aging components and high voltage levels contribute to their occurrence. Recognizing the severity of this issue, this study aimed to enhance DC arc fault detection by proposing an advanced recognition procedure. The methodology involves a sophisticated combination of current filtering using the Three-Sigma Rule in the time domain and the removal of switching noise in the frequency domain. To further enhance the diagnostic capabilities, the proposed method utilizes time and frequency signals generated from power supply-side signals as a reference input. The time–frequency features extracted from the filtered signals are then combined with artificial learning models. This fusion of advanced signal processing and machine learning techniques aims to capitalize on the strengths of both domains, providing a more comprehensive and effective means of detecting arc faults. The results of this detection process validate the effectiveness and consistency of the proposed DC arc failure identification schematic. This research contributes to the advancement of fault detection methodologies in DC systems, particularly by addressing the challenges associated with distinguishing arc-related distortions, ultimately enhancing the safety and dependability of DC electrical systems.

Effects of inflow Mach numbers on shock train dynamics and turbulence features in a backpressured supersonic channel flow

Investigations on shock train dynamics and relevant turbulence features in a backpressured supersonic channel flow are carried out using direct numerical simulation for three inflow Mach numbers of Ma0= 1.61, 2.0, and 2.45. As Ma0 increases, the shock train undergoes a structural change characterized by the leading shock which changes from the symmetric “λ” (Ma0=1.61) to the symmetric “X” (Ma0=2.00) and then to the asymmetric “X” pattern (Ma0=2.45). The symmetry breaking of shock structures induces asymmetric separation, which significantly alters the distribution characteristics of wall variables such as wall pressure and friction. To examine the unsteady behaviors of the shock train, a mode decomposition technique, namely, reduced-order variational mode decomposition [Liao et al., J. Fluid Mech. 966, A7 (2023)], is adopted taking its merit of adaptively extracting time-frequency features of dynamic systems. The modal analysis reveals that the shock train system exhibits significant centralization of low-frequency energy. Specifically, two basic types of low-frequency oscillation modes dominate the unsteady motion of the shock train: one depicts overall translating oscillation while another represents accordion-like oscillation. The analysis of turbulent kinetic energy shows that turbulence amplification is mainly dominated by the interaction of the decelerating mean flow with streamwise velocity fluctuations in the vicinity of the leading shock for all three cases, which is unaffected by the symmetry breaking of shock structures.

An Intelligent Classification Framework for Complex PQDs Using Optimized KS-Transform and Multiple Fusion CNN

Intelligent classification of multiple power quality disturbances (PQDs) is a top priority in pollution control of the power grid. However, the large-scale application of renewable energy introduces lots of nonlinear and impact loads, which makes the PQDs more complex and challenges the effectiveness of conventional detection frameworks. In this paper, a novel framework based on optimized Kaiser window-based S-transform (OKST) and multiple fusion convolutional neural network (MFCNN) is proposed to identify multiple complex PQDs. First, the OKST is used for the time-frequency positioning of PQDs, where an improved control function is proposed to meet different detection requirements of time-frequency. Additionally, the parameters of the control function are adjusted automatically using maximum energy concentration. Then, the MFCNN based on residual networks (ResNets) is further proposed to extract and classify these time-frequency features automatically. In MFCNN, feature information is fused using different convolution kernels at a 2-dimensional level, which can effectively reduce information loss and improve classification performance. The network model is set up using the Pytorch platform, and the dataset containing 28 types of PQDs and 2 types of nonlinearly mixed PQDs is built to test our framework. The result shows that the proposed OKST-MFCNN obtains an average accuracy of 99.38% under the 20 dB noise level, which is more accurate and robust than some advanced PQDs detection frameworks. Moreover, the accuracy of 97.94% is achieved with satisfactory real-time performance in hardware platform experiments, proving its superior identification performance for complex PQDs.

Research on 3D ground penetrating radar deep underground cavity identification algorithm in urban roads using multi-dimensional time-frequency features

The 3D ground penetrating radar (GPR) is the main method for detecting underground cavities in urban roads. Due to the weak reflected signal energy of deep road cavities with depths exceeding 2.5 m, there is a significant shortage of available training samples. Existing identification algorithms primarily focus on the detection of shallow road cavities. As a result, the accuracy of deep cavity identification using 3D GPR is low, and there is a lack of effective intelligent algorithms for deep cavity identification. To address these challenges, this study integrates the smooth texture features and the abundant amplitude and phase spectrum features inherent in deep cavity GPR signals. Utilizing the time-frequency features of radar signals, this study has proposed an intelligent identification algorithm for the deep road cavity based on a Multi-Channel and Dimensional Time-Frequency Convolution Neural Network (MCD-TF CNN). Firstly, using MCD-FT CNN as the cavity value discriminator, inverse reinforcement learning is performed on the cavity region to obtain the value evaluation method of the 3D GPR cavity region. Subsequently, the discriminator is applied to deep radar data for cavity detection and interacts with the value discriminator through 3D target region range adjustment actions. The interaction through region adjustments aims to maximize the value of cavity areas within the discriminator relative to the target detection area. It can ensure the inclusion of cavity regions in the detection results, thereby achieving the goal of intelligent deep cavity recognition. This algorithm employs the thought of global relative optimality from reinforcement learning, addressing the limitations of existing algorithms that rely on extracting absolute features and thereby enhancing the accuracy of deep cavity identification.

Channel Semantic Enhancement-Based Emotional Recognition Method Using SCLE-2D-CNN

The existing EEG emotion classification methods have some problems, such as insufficient emotion representation and lack of targeted channel enhancement module due to feature redundancy. To this end, a novel EEG emotion recognition method (SCLE-2D-CNN) combining scaled convolutional layer (SCLs), enhanced channel module and two-dimensional convolutional neural network (2D-CNN) is proposed. Firstly, the time-frequency features of multi-channel EEG emotional signals were extracted by stacking scl layer by layer. Secondly, channel enhancement module is used to reassign different importance to all EEG physical channels. Finally, 2D-CNN was used to obtain deep local spatiotemporal features and complete emotion classification. The experimental results show that the accuracy of SEED data set and F1 are 98.09% and 97.00%, respectively, and the binary classification accuracy of DEAP data set is 98.06% and 96.83%, respectively, which are superior to other comparison methods. The proposed method has a certain application prospect in the recognition of human mental state.

Detection of Alzheimer’s Dementia by Using Deep Time–Frequency Feature Extraction

Detection of Alzheimer’s Dementia by Using Deep Time–Frequency Feature Extraction

Rapid Seismic Damage Assessment of RC Bridges Considering Time–Frequency Characteristics of Ground Motions

Rapid Seismic Damage Assessment of RC Bridges Considering Time–Frequency Characteristics of Ground Motions

Logistic regression-time–frequency algorithm for α/β discrimination in silicon photomultiplier–based Phoswich detectors

Phoswich (phosphor sandwich) systems composed of ZnS(Ag) and plastic dual scintillators have the ability to distinguish α and β particles via digital pulse-shape discrimination. In this work, a novel logistic regression algorithm based on time–frequency features (LR-TF) is presented and evaluated for its ability to digitally discriminate α and β particles in a mixed field. The LR-TF algorithm employs the charge comparison method (CCM) and Fourier gradient analysis (FGA) to extract time–frequency features from pulse shapes, thereby constructing a logistic regression model. Training of the model is shown to enable the discrimination α and β particles. The CCM, FGA, and LR-TF were applied to thousands of pulses obtained with a data acquisition system based on a Phoswich coupled with a silicon photomultiplier. The experimental results show that the LR-TF algorithm provided the best overall performance with misidentification ratios of 1.9 % and 0.63 % for α particles and β particles, respectively, achieving a figure of merit of 4.30, and an area under the receiver operating characteristic of 0.996.

Machine Fault Diagnosis through Vibration Analysis: Continuous Wavelet Transform with Complex Morlet Wavelet and Time–Frequency RGB Image Recognition via Convolutional Neural Network

In pursuit of advancing fault diagnosis in electromechanical systems, this research focusses on vibration analysis through innovative techniques. The study unfolds in a structured manner, beginning with an introduction that situates the research question in a broader context, emphasising the critical role of fault diagnosis. Subsequently, the methods section offers a concise summary of the primary techniques employed, highlighting the utilisation of short-time Fourier transform (STFT) and continuous wavelet transform (CWT) for extracting time–frequency components from the signal. The results section succinctly summarises the main findings of the article, showcasing the results of features extraction by CWT and subsequently utilising a convolutional neural network (CNN) for fault diagnosis. The proposed method, named CWTx6-CNN, was compared with the STFTx6-CNN method of the previous stage of the investigation. Visual insights into the time–frequency characteristics of the inertial measurement unit (IMU) data are presented for various operational classes, offering a clear representation of fault-related features. Finally, the conclusion section underscores the advantages of the suggested method, particularly the concentration of single-frequency components for enhanced fault representation. The research demonstrates commendable classification performance, highlighting the efficiency of the suggested approach in real-time scenarios of fault analysis in less than 50 ms. Calculation by CWT with a complex Morlet wavelet of six time–frequency images and combining them into a single colour image took less than 35 ms. In this study, interpretability techniques have been employed to address the imperative need for transparency in intricate neural network models, particularly in the context of the case presented. Notably, techniques such as Grad-CAM (gradient-weighted class activation mapping), occlusion, and LIME (locally interpretable model-agnostic explanation) have proven instrumental in elucidating the inner workings of the model. Through a comparative analysis of the proposed CWTx6-CNN method and the reference STFTx6-CNN method, the application of interpretability techniques, including Grad-CAM, occlusion, and LIME, has played a pivotal role in revealing the distinctive spectral representations of these methodologies.

Nonstationary time-frequency characteristics of vehicle suspension systems based on evolutionary power spectral density

Improving the ride comfort for vehicles that travel at varying speeds is a nonstationary problem and has been an increasingly important topic for suspension system research. Accurate identification of frequencies associated with the resonant responses is needed for effective design of active suspension control strategies. However, traditional time-frequency (TF) methods have resolution limitations in either the time domain or the frequency domain. This paper proposes a new methodology to employ the evolutionary power spectral density (EPSD) to describe the responses of vehicles in the time-frequency domain. The key to calculate the responses in nonstationary cases is to derive the nonuniform modulation function which is obtained by the pseudo excitation method. To illustrate the applicability of the proposed method, an example of a seven-degree-of-freedom vehicle model is investigated in which the nonstationary excitations acting on the wheels are computed by the nonuniform modulation function and a precise integration method. Results show that resolutions obtained by the EPSD are more precise than the traditional TF methods with less than 0.2 Hz of bandwidth in both the lower frequency range at the first natural frequency of 1 Hz and in the higher frequency around 10 Hz. Moreover, the changing of the resonant frequency with varying speeds provides the insights, from the perspective of human body’s sensitivity to frequencies of vibration, to improve the ride comfort for vehicles under nonstationary driving conditions.

Research on the short-term wind power prediction with dual branch multi-source fusion strategy

The smooth operation of the power system imposes high requirements on wind power forecasting. Given the forecasting challenges brought by the coexistence of strong and weak disturbances in wind power data, this paper proposes a hierarchical anti-disturbance mechanism to raise the accuracy of single-point wind power prediction. In the first-level disturbance processing, we prioritize the treatment of strong disturbances in wind power data through a dual-branch multi-source fusion prediction structure. The wind power subsequences with distinct time–frequency characteristics are divided into two sets, processed by the stationary set prediction branch and the drastic set prediction branch, respectively. For the drastic set, we incorporate microenvironmental multi-source data surrounding the wind turbine as input and propose a parallel-structured attention fusion module CA (Convolution attention fusion block) to provide effective data support for the prediction module, then extract rich fusion features through deep temporal LSTM algorithm and ultimately achieve fine-grained forecasting. For weak disturbances that have not been adequately addressed in the previous step, we conduct a secondary treatment through error correction strategy. By employing the hierarchical processing approach, this paper accomplishes a comprehensive handling of disturbances with different intensities. Experimental results on four data sets show that the proposed model DEWFM (Dual-branch and error correction wind power forecast) demonstrates remarkable performance advantages in comparing with the baseline model and other advanced models, the average values of MAE reaching 1.679, revealing the effectiveness of the proposed method in enhancing the precision of short-term wind power prediction.

Short-term PV power prediction based on VMD-CNN-IPSO-LSSVM hybrid model

Abstract This article discusses the significance and obstacles of short-term power prediction in photovoltaic systems and introduces a hybrid model for photovoltaic short-term power prediction technology based on variational mode decomposition (VMD), convolutional neural network (CNN), improved particle swarm optimization (IPSO) and least squares support vector machine (LSSVM). In the initial stage, the photovoltaic generation signal is decomposed into multiple Intrinsic mode functions (IMFs) using VMD to enhance the extraction of signal time–frequency characteristics. Subsequently, CNN is utilized for feature learning and extraction of each IMF, modeling the nonlinear and non-stationary features. Following this, the IPSO-LSSVM optimization algorithm is employed to establish and optimize multiple LSSVM models, predicting power fluctuations at different time scales. Finally, the predictions from each model are synthesized to obtain the final photovoltaic short-term power forecast. Through validation with actual photovoltaic generation data, this hybrid model demonstrates high accuracy and reliability in short-term power prediction, showing an average relative error and root mean square error reduction of 15.23 and 53.60%, respectively, compared to a certain comparative model. This proposed method based on VMD-CNN-IPSO-LSSVM hybrid model for photovoltaic power prediction holds promising prospects and practical value in the operation and scheduling of photovoltaic generation systems.

Intelligent triboelectric V-belts with condition monitoring capability

In this study, the V-belt transmission structure and triboelectric nanogenerator (TENG) are combined, and an intelligent transmission system, the triboelectric V-belt (TVB), is proposed. Furthermore, its condition-monitoring capability is investigated to improve the intelligence level of the traditional mechanical transmission system. The designed TVB can be integrated with a belt pulley without additional structural space; moreover, it exhibits good reliability by avoiding contact with the working surface of the V-belt transmission. For the output characteristics of the TVB, the variation curves of the output voltage and current with load resistance were tested and the influence of several design variables was elucidated. Through monitoring the amplitude and time–frequency features of the TVB output current, the slipping failure of the V-belt drive can be detected in time, and typical faults of a bevel gearbox (including defective driving/driven gears and supporting bearings) were classified with an average accuracy exceeding 90%. The classification accuracy based on TVB was only slightly lower than that based on the vibration sensor. The designed TVB exhibits promising application prospects for monitoring industrial transmission systems.

Classification of bruxism based on time-frequency and nonlinear features of single channel EEG

BackgroundIn the classification of bruxism patients based on electroencephalogram (EEG), feature extraction is essential. The method of using multi-channel EEG fusing electrocardiogram (ECG) and Electromyography (EMG) signal features has been proved to have good performance in bruxism classification, but the classification performance based on single channel EEG signal is still understudied. We investigate the efficacy of single EEG channel in bruxism classification.MethodsWe have extracted time-domain, frequency-domain, and nonlinear features from single EEG channel to classify bruxism. Five common bipolar EEG recordings from 2 bruxism patients and 4 healthy controls during REM sleep were analyzed. The time domain (mean, standard deviation, root mean squared value), frequency domain (absolute, relative and ratios power spectral density (PSD)), and non-linear features (sample entropy) of different EEG frequency bands were analyzed from five EEG channels of each participant. Fine tree algorithm was trained and tested for classifying sleep bruxism with healthy controls using five-fold cross-validation.ResultsOur results demonstrate that the C4P4 EEG channel was most effective for classification of sleep bruxism that yielded 95.59% sensitivity, 98.44% specificity, 97.84% accuracy, and 94.20% positive predictive value (PPV).ConclusionsOur results illustrate the feasibility of sleep bruxism classification using single EEG channel and provides an experimental foundation for the development of a future portable automatic sleep bruxism detection system.

A bearing fault diagnosis method with improved symplectic geometry mode decomposition and feature selection

A rolling bearing fault diagnosis method based on improved symplectic geometry mode decomposition (SGMD) and feature selection was proposed to solve the problem of low fault identification due to the influence of noise on early bearing fault features. First, the SGMD SGMD is improved to enhance its robustness in decomposing signals with noise, then the time domain, frequency domain, and time-frequency features of each symplectic geometric component are extracted as feature vectors. Second, a comprehensive feature selection strategy is proposed to select the optimal subset of features that are conducive to fault classification. Finally, considering the problem of low classification accuracy of a single machine learning model, the AdaBoost-WSO-SVM model is constructed for fault classification using the AdaBoost algorithm of integrated learning. Experimental decomposition of complex signals with noise indicates that the improved SGMD is more effective compared to traditional SGMD. Subsequently, multiple experiments were conducted using the bearing datasets from Case Western Reserve University (CWRU) and Jiangnan University (JNU). The experimental results reveal that, after comprehensive feature selection and ensemble learning pattern recognition experiments on the CWRU dataset, the average accuracy of fault diagnosis can reach 99.67%. On the JNU dataset, the proposed fault diagnosis method achieves an average accuracy of 95.03%. This suggests that, compared to other feature selection methods and classification models, the proposed approach in this paper exhibits higher accuracy and generalization capabilities.

Intelligent intrusion detection for optical fiber perimeter security system based on an improved high efficiency feature extraction technique

The automated analysis of optical fiber vibration sensing data has been highly demanded in engineering applications. Therefore, intrusion analysis, which aims at detecting, recognizing, and classifying intrusions, holds great importance for optical fiber vibration sensing. In this work, an intelligent intrusion detection scheme employing an improved high-efficiency feature extraction technique and utilizing a dual Mach–Zehnder interferometer (DMZI)-based optical fiber perimeter security system is proposed. So, the DMZI-based perimeter security system in practical settings can be successfully established. Specifically, time-frequency feature vectors with nine features are firstly constructed using a maximal overlap discrete wavelet transformation approach and a zero crossing rate method. Then, the feature vectors are classified into corresponding categories using a radial basis function neural network. The effectiveness of the proposed scheme has been validated using six types of human intrusions, such as knocking, climbing, waggling, cutting, crashing and kicking the fence. The results show that the given intrusions can be accurately and rapidly recognized by the proposed scheme. The average recognition rate of 95.0% is achieved, and the average processing time for each sample data is only 0.033 s, which is significantly lower than the sampling interval (0.3 s) in our experiment. It is believed that the proposed scheme holds promising potential in the field of optical fiber perimeter security systems.