Signals In Frequency Domain Research Articles

A Lightweight and Efficient Multimodal Feature Fusion Network for Bearing Fault Diagnosis in Industrial Applications.

To address the issues of single-structured feature input channels, insufficient feature learning capabilities in noisy environments, and large model parameter sizes in intelligent diagnostic models for mechanical equipment, a lightweight and efficient multimodal feature fusion convolutional neural network (LEMFN) method is proposed. Compared with existing models, LEMFN captures rich fault features at multiple scales by combining time-domain and frequency-domain signals, thereby enhancing the model's robustness to noise and improving data adaptability under varying operating conditions. Additionally, the convolutional block attention module (CBAM) and random overlapping sampling technology (ROST) are introduced, and through a feature fusion strategy, the accurate diagnosis of mechanical equipment faults is achieved. Experimental results demonstrate that the proposed method not only possesses high diagnostic accuracy and rapid convergence but also exhibits strong robustness in noisy environments. Finally, a graphical user interface (GUI)-based mechanical equipment fault detection system was developed to promote the practical application of intelligent fault diagnosis in mechanical equipment.

Research on coal rock parameter calibration based on discrete element method

To ensure that the discrete element model of the coal wall accurately reflects the actual cutting process of coal and rock during virtual prototype simulation of mining equipment, this study aims to expedite the development of intelligent mining machinery. Using coal samples from the 4602 working face of Yangcun Coal Mine, operated by Yanzhou Coal Mining Group, we conducted coal rock packing experiments and uniaxial compression tests to obtain the packing angle and compressive strength of the coal samples. Based on the experimental results, we designed Plackett–Burman experiments (PB experiments), steepest ascent experiments, and Box-Behnken experiments to study the influence of particle contact mechanics parameters and bonding mechanics parameters on the packing angle and compressive strength, using the packing angle and compressive strength as response variables. Our objective is to minimize the relative error between the simulated packing angle and the measured packing angle. We solved and optimized the parameter calibration model and conducted simulation calibration experiments based on the optimization results. A comparative analysis with the actual test results revealed that the maximum relative errors between the simulated and measured values for the packing angle and compressive strength were only 2.9% and 5.0%, respectively. Additionally, a discrete element model of a typical working face coal wall was established based on the parameters obtained from this calibration method. A bidirectional coupling model of the cutting process between the coal and rock was created using EDEM-RecurDyn to simulate the rigid-flexible coupling of the coal cutter. An experimental coal wall model was constructed based on similarity theory, and both simulation and physical experiments were conducted. The evaluation metrics for comparison were the time-domain and frequency-domain characteristics of the drum’s vibration signals. The maximum relative error for the time-domain signal characteristics between the two experimental setups was only 4.19%, while the maximum relative error for the frequency-domain signal characteristics was 3.75%. This validates the feasibility of the proposed calibration method for the discrete element coal wall model and the accuracy of the calibration results. Furthermore, it demonstrates that the constructed discrete element coal wall accurately represents the actual coal and rock properties. The virtual simulation based on this model effectively replicates the interaction process between mining machinery and coal, providing a safe, efficient, and low-cost technological approach for performance analysis of mining equipment and intelligent control of supporting devices.

915 nm pumping kilowatt fiber oscillator with high optical-to-optical efficiency

We demonstrate an all-fiber oscillator with high optical-to-optical efficiency using laser diodes working at 915nm as the pump sources to reduce the demand for thermal management. When the output power of the bidirectional pumped oscillator is 1.16kW, the optical-to-optical efficiency is as high as 75.4%. In this working state, the output characteristics of the oscillator are observed. The Raman suppression ratio is 41.23dB and the beam quality factor Mx2 = 1.14, My2 = 1.29. Analyzing the time trajectory of the highest power output, there are no significant characteristic peaks in the time domain signal and the frequency domain signal, which indicates that the oscillator has good stability.Improving the output characteristics of the 915nm pumping lasers has a positive significance for the application of non-strict ambient temperature control.

Speaker Recognition System Using Hybrid of MFCC and RCNN with HCO Algorithm Optimization

Though there are advancements in speaker recognition technology, available systems often fail to correctly recognize speakers especially in noisy environments. The use of Mel-frequency cepstral coefficients (MFCC) has been improved using Convolutional Neural Networks (CNN) yet difficulties in achieving high accuracies still exists. Hybrid algorithms combining MFCC and Region-based Convolutional Neural Networks (RCNN) have been found to be promising. In this research features from speech signals were extracted for speaker recognition, to denoise the signals, design and develop a DFT-based denoising system using spectrum subtraction and to develop a speaker recognition method for the Verbatim Transcription using MFCC. The DFT was used to transform the sampled audio signal waveform into a frequency-domain signal. RCNN was used to model the characteristics of speakers based on their voice samples, and to classify them into different categories or identities. The novelty of the research was that it used MFCC integrated with RCNN and optimized with Host-Cuckoo Optimization (HCO) algorithm. HCO algorithm is capable of further weight optimization through the process of generating fit cuckoos for best weights. It also captured the temporal dependencies and long-term information. The system was tested and validated on audio recordings from different personalities from the National Assembly of Kenya. The results were compared with the actual identity of the speakers to confirm accuracy. The performance of the proposed approach was compared with two other existing speaker recognition the traditional approaches being MFCC-CNN and Linear Predictive Coefficients (LPC)-CNN. The comparison was based the Equal Error Rate (EER), False Rejection Rate (FRR), False Match Rate (FMR), and True Match Rate (TMR). Results show that the proposed algorithm outperformed the others in maintaining a lowest EER, FMR, FRR and highest TMR.

Fault location method for new distribution networks based on waveform matching of time–frequency travelling waves

AbstractSome existing fault location methods for distribution networks rely too much on the local wave head information of the time or frequency domain signals, making it difficult to adapt to the increasingly complex structure and operating conditions of the distribution network after the new energy access. For improvement, the travelling wave (TW) time and frequency ranges that can effectively avoid waveform distortion caused by new energy access are analysed. The one‐to‐one matching relationship between the TW waveforms in these ranges and the fault positions is revealed. A fault TW time–frequency matrix with specific time and frequency windows is constructed, and a new distribution network fault location method is proposed based on the matching technique of waveform features, which realises the accurate fault location by exploring the proportionality between the cumulative trend of the matrix energy amplitude deviation and the fault point position. Simulation test results show that the proposed method is not affected by the complex structure of distribution networks such as new energy access and overhead‐cable line mixing on fault location and flexibly transforms the fault location problem into a time–frequency TW waveform matching problem, which improves the accuracy and robustness of the fault location for new distribution networks to a degree.

A Fault Diagnosis Method for Pumped Storage Unit Stator Based on Improved STFT-SVDD Hybrid Algorithm

Stator faults are one of the common issues in pumped storage generators, significantly impacting their performance and safety. To ensure the safe and stable operation of pumped storage generators, a stator fault diagnosis method based on an improved short-time Fourier transform (STFT)-support vector data description (SVDD) hybrid algorithm is proposed. This method establishes a fault model for inter-turn short circuits in the stator windings of pumped storage generators and analyzes the electrical and magnetic states associated with such faults. Based on the three-phase current signals observed during an inter-turn short circuit fault in the stator windings, the three-phase currents are first converted into two-phase currents using the principle of equal magnetic potential. Then, the STFT is applied to transform the time-domain signals of the stator’s two-phase currents into frequency-domain signals, and the resulting fault current spectrum is input into the improved SVDD network for processing. This ultimately outputs the diagnosis result for inter-turn short circuit faults in the stator windings of the pumped storage generator. Experimental results demonstrate that this method can effectively distinguish between normal and faulty states in pumped storage generators, enabling the diagnosis of inter-turn short circuit faults in stator windings with low cross-entropy loss. Through analysis, under small data sample conditions, the accuracy of the proposed method in this paper can be improved by up to 7.2%. In the presence of strong noise interference, the fault diagnosis accuracy of the proposed method remains above 90%, and compared to conventional methods, the fault diagnosis accuracy can be improved by up to 6.9%. This demonstrates that the proposed method possesses excellent noise robustness and small sample learning ability, making it effective in complex, dynamic, and noisy environments.

A tail probability density distribution model of stress amplitude under band-limited stochastic vibration loadings

Resonance of engineering structures under stochastic vibration loadings is a primary cause of fatigue failure. Considering that cyclic loadings below the fatigue limit of the material contribute little to fatigue damage, the portion of the stress amplitude distribution that exceeds the fatigue limit is in focus in this paper, and a tail probability density distribution model of stress amplitude under band-limited stochastic vibration loadings is proposed. First, the response stress power spectral density functions under band-limited loadings are simulated by using the normal distribution and the Weibull distribution, respectively, and then the frequency domain signals are converted into time domain signals by adopting the inverse fast Fourier transform method. A two-parameter Weibull model of tail probability density distribution of stress amplitude is proposed, and the relationship between model parameters and power spectral moment parameters is given. Finally, the comparative analysis of the model accuracy and the vibration fatigue test of aluminum alloy notch specimen are carried out. It is demonstrated that the fatigue life predicted by the presented model is highly coincident with the results of tests and the time domain method.

Dynamic Peripheral Hemoperfusion Distribution Monitoring Based on Janus Flexible Sensor System.

Peripheral vascular disease is a worldwide leading health concern. Real-time peripheral hemoperfusion monitoring during treatment is essential to plan treatment strategies to improve circulatory enhancement effects. The present work establishes a Janus flexible perfusion (JFP) sensor system for dynamic peripheral hemoperfusion monitoring. We develop a Janus structure with different Young's modulus to improve the mechanical properties for motion artifacts suppression. Besides, we propose a peripheral perfusion index (PPI) based on an optical perfusion model that is experimentally verified using an in-vitro model. The effectiveness of the system is assessed in three experimental scenarios, including motion artifact-robust test, induced vascular occlusion, and peripheral hemoperfusion monitoring with the intermittent pneumatic compression treatment. The noise level of the traditional rigid sensor is five times that of the JFP sensor within the effective signal frequency domain when there is movement. The PPI can effectively discriminate between different peripheral hemoperfusion states and has a correlation coefficient of 0.92 with the Laser Doppler flowmetry (LDF) mean values. The kappa statistic between the JFP sensor and LDF is 0.78, indicating substantial agreement to estimate the peripheral hemoperfusion improvements. The sensor system we proposed can monitor peripheral hemoperfusion variation in real-time and is insensitive to motion artifacts. The proposed sensing system provides a functional module for real-time estimation of peripheral hemoperfusion during clinical interventions.

Classification of Three Anesthesia Stages Based on Near-Infrared Spectroscopy Signals.

Proper monitoring of anesthesia stages can guarantee the safe performance of clinical surgeries. In this study, different anesthesia stages were classified using near-infrared spectroscopy (NIRS) signals with machine learning. The cerebral hemodynamic variables of right proximal oxyhemoglobin (HbO2) in maintenance (MNT), emergence (EM) and the consciousness (CON) stage were collected and then the differences between the three stages were compared by phase-amplitude coupling (PAC). Then combined with time-domain including linear (mean, standard deviation, max, min and range), nonlinear (sample entropy) and power in frequency-domain signal features, feature selection was performed and finally classification was performed by support vector machine (SVM) classifier. The results show that the PAC of the NIRS signal was gradually enhanced with the deepening of anesthesia level. A good three-classification accuracy of 69.27% was obtained, which exceeded the result of classification of any single category feature. These results indicate the feasibility of NIRS signals in performing three or even more anesthesia stage classifications, providing insight into the development of new anesthesia monitoring modalities.

Potential multi-parametric OFDR system based on the wavelength-division cross-correlation method

In this study, an optical frequency domain reflectometer (OFDR) system for simultaneous measurement of temperature, strain, and relative humidity (RH) based on the wavelength-division cross-correlation method is proposed and experimentally demonstrated. The Rayleigh scattered spectrum shifts introduced by environmental changes can be demodulated by the cross-correlation operation, and the magnitude of the shifts exhibits variability in distinct wavelength subregions. Leveraging the distinct sensitivity characteristics of different parameters across different wavelength subregions, simultaneous multi-parameter decoupling can be achieved. In the signal processing flow, the frequency domain signals in different wavelength subregions are intercepted, and then the cross-correlation operation is performed separately to obtain the spectrum shift information in different wavelength subregions. The decoupling matrix is constructed to realize the decoupling of the three parameters based on the sensitivity differences of temperature, strain, and RH in different wavelength subregions. This novel and simple multi-parameter sensing system, to the best of our knowledge, has potential applications in engineering monitoring, chemical applications, and environmental measurements.

Investigating Intra-Pulse Doppler Frequency Coupled in the Radar Echo Signal of a Plasma Sheath-Enveloped Target

In detecting hypersonic vehicles, the radar echo signal is coupled with an intra-pulse Doppler frequency (I-D frequency) component caused by relative motion of a plasma sheath (PSh) and the vehicle, which can induce the phenomenon of a ghost target in a one-dimensional range profile. In order to investigate the I-D frequency generated by the relative motion of a PSh, this study transforms a linear frequency modulated (LFM) signal into a single carrier frequency signal based on echo signal equivalent time delay-dechirp processing and realizes high resolution and fast extraction of the I-D frequency coupled with the frequency-domain echo signal. Furthermore, by relying on the computation of the surface flow field of the RAMC-II Blunt Cone Reentry Vehicle, the coupled I-D frequency in the radar echo signal of a PSh-enveloped target under circumstances of typical altitudes and carrier frequencies is extracted and further investigated, revealing the variation law of I-D frequency. The key findings of this study provide a novel approach for suppressing anomalies in radar detection of PSh-enveloped targets as well as effective detecting and as robust target tracking.

An interpretable TFAFI-1DCNN-LSTM framework for UGW-based pre-stress identification of steel strands

Steel strands serve as the key load-bearing components of pre-stressed bridges, yet the identification of effective pre-stress for steel strands is a challenging task. In this study, a time and frequency adaptive fusion input-one dimensional convolutional neural network-long short-term memory (TFAFI-1DCNN-LSTM) framework was proposed for ultrasonic guided wave (UGW)-based effective pre-stress identification of steel strands. In this framework, the time and frequency domain signals of UGW were input into the network as two parallel branches, CNN and LSTM were utilized to extract spatial and serial-related features, and a trainable weight coefficient was introduced for adaptive fusion of time and frequency domain features. Firstly, ablation studies were conducted to investigate the influence of each key component in the proposed framework on the prediction results. Secondly, deep learning (DL) models of Res Net, Dense Net and Inception Net were introduced as comparisons, and the prediction results based on TFAFI-1DCNN-LSTM were compared with those based on the above DL models. Thirdly, the noise-robustness and performance under a few trainable samples of TFAFI-1DCNN-LSTM were also investigated. Finally, the outputs of various key layers of the proposed framework were subjected to dimensionality reduction and visualization to provide an intuitive demonstration of the feature extraction process, and the inherent mechanisms of the proposed framework were interpreted using local interpretable model-agnostic explanations (LIME). Results show that the architecture of TFAFI-1DCNN-LSTM is reasonably designed and all key components are necessary. The weights of features in time and frequency domain branches are rationally assigned due to the addition of an adaptive weight coefficient. Compared with other DL models, the proposed TFAFI-1DCNN-LSTM exhibits higher pre-stress identification accuracy, excellent noise-robustness, and superior performance under only a few trainable samples. The correlation between features extracted by the network and the pre-stress labels significantly increases with the deepening of the network, and the correlation between input UGW signals and predicted pre-stress values is effectively interpreted utilizing LIME, proving that the architecture of the proposed framework is reasonable and effective, the predicted results are reliable and credible.

Investigation on effects of water-shale interaction on acoustic characteristics of organic-rich shale in Ordos Basin, China

The water-shale interaction affect the shale structure, leading to wellbore instability and increasing drilling costs. The extent of structural changes within the shale can be determined non-destructively by analyzing its acoustic characteristics. Experiments were conducted to investigate the acoustic properties of shale from the Yanchang Formation in the Ordos Basin before and after exposure to brines of varying types, soaking times, and salinities. The study investigated the effects of brine type, soaking time, and salinity on shale’s acoustic properties, including changes in acoustic wave propagation speed, P/S wave velocity ratio, and both time-domain and frequency-domain amplitudes. The results indicate that although the type of brine has a limited impact on the water-shale interaction, KCl exhibits a significant inhibitory effect. However, the soaking time and the brine salinity have a significant impact on the acoustic properties of shale. As the soaking time increases, the decrease in wave velocity increases, the P/S wave velocity ratio increases, and the decrease in time-domain amplitude increases. The amplitude of the main frequency in the frequency domain signal also decreases with the increase of reaction time, which is consistent with the analysis results of the time domain signal. As the salinity of brine increases, the decrease in wave velocity decreases, the P/S wave velocity ratio decreases, and the decrease in time-domain amplitude decreases. The amplitude of the main frequency in the frequency domain signal also decreases with the increase of brine salinity, which is consistent with the analysis results of the time domain signal. This work establishes the relationship between water-shale interaction and acoustic characteristics, which can quantitatively evaluate the degree of interaction between water and shale without damaging shale. Furthermore, this research provides new insights and guidance for predicting drilling collapse cycles and optimizing drilling fluid compositions.

A novel damage localization technique for type III composite pressure vessels based on guided wave mode-matching method

Damage monitoring during the service life of Type III composite overwrapped pressure vessels (COPVs) is crucial for ensuring their safe operation. This paper focuses on the damage localization in COPVs using ultrasonic guided waves structural health monitoring (SHM) techniques. Firstly, dispersion curves were plotted to establish a foundation for experiments and simulations based on the propagation theory of guided waves in multilayered anisotropic structures. Subsequently, a 3D finite element model of COPV was constructed to capture the propagation characteristics of guided waves within the COPV and their interaction with damage. The effects of different fiber angles and fiber layer numbers on guided waves propagation were analyzed, and their interrelationships were established. Furthermore, the “Wave Velocity Directionality” effect of the A0 mode was identified during its propagation in COPV. The monitoring signals obtained from experiments were analyzed to assess the impact of damage on the time-domain and frequency-domain signals of guided waves. Finally, a damage localization algorithm based on mode-matching was proposed, and its localization accuracy was verified in COPVs with different damage locations and fiber layer numbers. The results demonstrate the significant potential of the proposed damage localization algorithm in the damage monitoring of COPV structures.

V-DAFT: visual technique for texture image defect recognition with denoising autoencoder and fourier transform

Texture is the surface qualities and visual attributes of an object, determined by the arrangement, size, shape, density, and proportion of its fundamental components. In the manufacturing industry, products typically have uniform textures, allowing for automated visual inspections of the product surface to recognize defects. During this process, texture defect recognition techniques can be employed. In this paper, we propose a method that combines a convolutional autoencoder architecture with Fourier transform analysis. We employ a normal reconstructed template as defined in this study. Despite its simple structure and rapid training and inference capabilities, it offers recognition performance comparable to state-of-the-art methods. Fourier transform is a powerful tool for analyzing the frequency domain of images and signals, which is essential for effective defect recognition as texture defects often exhibit characteristic changes in specific frequency ranges. The experiment evaluates the recognition performance using the AUC metric, with the proposed method showing a score of 93.7%. To compare with existing approaches, we present experimental results from previous research, an ablation study of the proposed method, and results based on the high-pass filter used in the Fourier mask.

Evaluation of grouting effectiveness for Semi-Rigid pavement base layer cracks based on Time-Frequency domain signal characteristics of 3D GPR

This study aims to address the deficiency of rapid, comprehensive, and non-destructive methods for evaluating the effectiveness of grouting treatment on semi-rigid pavement base layer cracks. By integrating radar simulation with empirical measurements, we establish a comprehensive evaluation method for the grouting treatment effectiveness of pavement base layer cracks. Initially, we propose a GprMax simulation of crack models with varying grout-filled volumes, analyzing the time–frequency domain signal characteristics before and after grouting. Based on data sensitivity, thirteen time–frequency domain signal characteristics are selected as grading evaluation indicators. Subsequently, relying on an engineering case study, we conduct a graded evaluation of the grouting effect on base layer cracks, analyzing the correlation and weight of evaluation indicators to derive a comprehensive evaluation method. Field coring results confirm the accuracy of the comprehensive graded evaluation method.

Damage identification of honeycomb sandwich structures based on Lamb waves and 1D-CNN

A specific method combining Lamb waves and 1D-CNN is proposed in this paper for damage assessment of honeycomb sandwich structures, which can identify the location and degree of damage simultaneously. The applicability of the Lamb waves method is verified by simulating the interaction between the Lamb waves and different degrees of damage on the honeycomb panel. In the experiment, four identical piezoelectric wafers were placed on a honeycomb plate in a square shape, and a mass block was placed inside to simulate damage. One of the sensors was used as an actuator to generate the Lamb waves signal, and the remaining three sensors received the response signals after interacting with the damage. The collected signals were denoised by Kalman filter, and the time domain signals were transformed into the frequency domain signals by Fourier transform, so as to extract the feature more effectively. The amplitude frequency characteristics of Lamb wave signals were used as inputs to the 1D-CNN model, and the damage categories were used as outputs. 365 samples were used for model testing, 364 were correctly identified with a correct recognition rate of 99.7 %. The result shows that the proposed method is feasible for damage identification of honeycomb sandwich structures.

Wavelet Transform-Based Inertial Neural Network for Spatial Positioning Using Inertial Measurement Units

As the demand for spatial positioning continues to grow, positioning methods based on inertial measurement units (IMUs) are emerging as a promising research topic due to their low cost and robustness against environmental interference. These methods are particularly well suited for global navigation satellite system (GNSS)-denied environments and challenging visual scenarios. While existing algorithms for position estimation using IMUs have demonstrated some effectiveness, there is still significant room for improvement in terms of estimation accuracy. Current approaches primarily treat IMU data as simple time series, neglecting the frequency-domain characteristics of IMU signals. This paper emphasizes the importance of frequency-domain information in IMU signals and proposes a novel neural network, WINNet (Wavelet Inertial Neural Network), which integrates time- and frequency-domain signals using a wavelet transform for spatial positioning with inertial sensors. Additionally, we collected ground-truth data using a LiDAR setup and combined it with the TLIO dataset to form a new IMU spatial positioning dataset. The experimental results demonstrate that our proposed method outperforms the current state-of-the-art inertial neural network algorithms in terms of the ATE, RTE, and drift error metrics overall.

Application of Distributed Acoustic Sensing Technology in Pipeline Leakage Monitoring

Pipeline leak monitoring is an important industrial safety measure designed to ensure the safety of liquids or gases during transportation. Distributed acoustic sensing (DAS) technology is based on the reverse Rayleigh scattering inside the fiber to reflect the change of the measured physical quantity, and has great advantages in monitoring range, environmental adaptability, transmission loss control and system stability. In this paper, the pipeline leakage monitoring technology based on distributed acoustic sensing fiber is used to study the leakage signal of small leak aperture. In order to improve the sensitivity of leakage monitoring, the optical fiber is spiral wound on the pipe section. The identification method of pipeline leakage signal based on fast Fourier transform is proposed. By analyzing the vibration of the optical fiber in the time domain and the frequency domain, the leakage signal can be accurately monitored. Pipeline leakage tests with different leak apertures were carried out, and the leakage locations were studied by energy attenuation and cross-correlation techniques. The experimental results show that the time-domain signal fluctuates obviously and the full-band energy of the frequency-domain signal increases after pipeline leakage. The increase of leakage diameter will gradually increase the signal energy, and the leakage energy will gradually move from high frequency to low frequency. The energy attenuation positioning technique can locate the leakage within the range of a single sensing unit, and determine the leakage location through cross-correlation analysis with an error of less than 3 m.

Automatic Recognition of Auditory Brainstem Response Waveforms Using a Deep Learning-Based Framework.

Recognition of auditory brainstem response (ABR) waveforms may be challenging, particularly for older individuals or those with hearing loss. This study aimed to investigate deep learning frameworks to improve the automatic recognition of ABR waveforms in participants with varying ages and hearing levels. The research used a descriptive study design to collect and analyze pure tone audiometry and ABR data from 100 participants. The research was conducted at a tertiary academic medical center, specifically at the Clinical Audiology Center of Tsinghua Chang Gung Hospital (Beijing, China). Data from 100 participants were collected and categorized into four groups based on age and hearing level. Features from both time-domain and frequency-domain ABR signals were extracted and combined with demographic factors, such as age, sex, pure-tone thresholds, stimulus intensity, and original signal sequences to generate feature vectors. An enhanced Wide&Deep model was utilized, incorporating the Light-multi-layer perceptron (MLP) model to train the recognition of ABR waveforms. The recognition accuracy (ACC) of each model was calculated for the overall data set and each group. The ACC rates of the Light-MLP model were 97.8%, 97.2%, 93.8%, and 92.0% for Groups 1 to 4, respectively, with a weighted average ACC rate of 95.4%. For the Wide&Deep model, the ACC rates were 93.4%, 90.8%, 92.0%, and 88.3% for Groups 1 to 4, respectively, with a weighted average ACC rate of 91.0%. Both the Light-MLP model and the Wide&Deep model demonstrated excellent ACC in automatic recognition of ABR waveforms across participants with diverse ages and hearing levels. While the Wide&Deep model's performance was slightly poorer than that of the Light-MLP model, particularly due to the limited sample size, it is anticipated that with an expanded data set, the performance of Wide&Deep model may be further improved.