Frequency Domain Features Research Articles

Smartphone-sensor-based human activities classification for forensics: a machine learning approach

The accurate classification of human activities in crime scenes during forensics (criminalistics) is of utmost importance in classifying suspicious and unlawful activities, easing their acceptability and interpretability by judges during legal procedures in courts or by other non-experts in the field of forensics. This paper implements machine learning (ML) algorithms: support vector machine (SVM) and decision tree (DT), to demonstrate with a high accuracy, how data emanating from smartphones’ sensors reveal and isolate relevant information about static and dynamic human activities in criminalistics. Smartphones’ data from five different sensors (accelerometer, gravity, orientation, Gyroscope and light), related to ten recurrent crime scenes activities, grouped into three classes of events (normal, felony and none-felony events) are classified by the proposed algorithms, with novelty being the classification decisions based on the entire period of the events and not instantaneous decision makings. Three independent data-subsets were made, with permutations done between them and at each time, two sets used for training and the third set used for testing. Time- and frequency-domain features were initially used separately and then combined for the model training and testing. The best average training accuracies of 100% and 97.8% were obtained for the DT and SVM, respectively, and the testing accuracies of 89.1% were obtained for both algorithms. We therefore believe that these results will serve as a solid persuasive and convincing argument to judges and non-experts of the field of forensics to accept and easily interpret computer-aided classification of suspicious activities emanating from criminalistic studies.

Fast audio signal denoising with low-rank approximation using windowed singular value decomposition of frequency division

The method of constructing Hankel matrices and using low-rank approximation has been demonstrated to be an effective approach to audio denoising. However, the significant computational complexity and the trade-off between the denoising quality and the loss of effective signal remain open issues. This paper proposes a denoising method based on frequency-divided Windowed Singular Value Decomposition (WSVD) and exploits the low-rank characteristics and frequency features commonly found in audio signals including speech and music recordings. The method incorporates an improved Lanczos Bidiagonalization algorithm to accelerate the singular value decomposition with low error and high tolerance. Furthermore, techniques are added at the window junctions to maintain the continuity and smoothness of the final audio, thus achieving denoising efficiently and effectively. This paper also assesses the influence of window segmentation length, main frequency domain characteristics, rank selection of Hankel matrix and characteristics of different noises on the final denoising effect. Finally, the denoising algorithm's robustness and effectiveness are validated through simulations and experiments.

Wave propagation analysis of the overhead conductor rail system based on numerical simulation and full-scale experiment

The overhead conductor rail system (OCR) is an important current-transmitting structure for electric trains in tunnels. As the train speed increases, the wave propagation behaviour in the OCR plays an ever-increasingly important role in affecting the current collection quality. This paper is the first endeavour to numerically and experimentally explore wave behaviours in the OCR. With the help of a finite element model, the spatial propagation and frequency-domain characteristics of the wave propagation are investigated. Based on the time-space distribution of waves, the wave speed of the OCR is identified. Subsequently, a full-scale experimental test is conducted to identify a real-life OCR's wave speed for the first time. The relative error between the simulated and experimental speed is only 5.50 %, highlighting the effectiveness of the presented model. Then, the influence of wave propagation on the interaction performance of pantograph-OCR is analysed. A significant reduction of the interaction performance is observed when the train speed approaches the wave speed. Through sensitivity analysis, the bending stiffness, the linear density, and the span length are identified as sensitive parameters affecting the wave speed.

Wavelet-Based Characterization of Spatiospectrotemporal Structures in F404 Engine Jet Noise

Spatiospectral lobes are significant contributors to noise radiated from full-scale tactical aircraft. Prior studies have explored lobe frequency-domain characteristics, but a joint time–frequency domain analysis has the potential to further describe these phenomena and connect them to source-related events in the time waveform. This paper uses acoustical data collected from a 120-microphone array near a T-7A-installed F404 engine to characterize the spatiospectral lobes in combinations of the time, frequency, and spatial domains. An event-based beamforming method is used in conjunction with a wavelet transform to determine propagation angles and event source locations corresponding to each of the lobes. Temporospectral events in the wavelet transform are then analyzed using Markov chains. Finally, spatiospectral maps created from the measured data are decomposed into individual lobes using events in the wavelet transform as a guide. The spatiospectrotemporal combination of these three analyses shows that the lobes originate from multiple, overlapping regions along the jet lipline and that each lobe has its own peak radiation angle. Additionally, events corresponding to the spatiospectral lobes occur intermittently and at different times from each other, leading to bursts of acoustic energy with rapidly changing directivities.

Integration of attention mechanism and CNN-BiGRU for TDOA/FDOA collaborative mobile underwater multi-scene localization algorithm

The aim of this study is to address the issue of TDOA/FDOA measurement accuracy in complex underwater environments, which is affected by multipath effects and variations in water sound velocity induced by the challenging nature of the underwater environment. To this end, a novel cooperative localisation algorithm has been developed, integrating the attention mechanism and convolutional neural network-bidirectional gated recurrent unit (CNN-BiGRU) with TDOA/FDOA and two-step weighted least squares (ImTSWLS). This algorithm is designed to enhance the accuracy of TDOA/FDOA measurements in complex underwater environments. The algorithm initially makes use of the considerable capacity of a convolutional neural network (CNN) to extract profound spatial and frequency domain characteristics from multimodal data. These features are of paramount importance for the characterisation of underwater signal propagation, particularly in complex environments. Subsequently, through the use of a bidirectional gated recurrent unit (BiGRU), the algorithm is able to effectively capture long-term dependencies in time series data. This enables a more comprehensive analysis and understanding of the changing pattern of signals over time. Furthermore, the incorporation of an attention mechanism within the algorithm enables the model to focus more on the signal features that have a significant impact on localisation, while simultaneously suppressing the interference of extraneous information. This further enhances the efficiency of identifying and utilising the key signal features. ImTSWLS is employed to resolve the position and velocity data following the acquisition of the predicted TDOA/FDOA, thereby enabling the accurate estimation of the position and velocity of the mobile radiation source. The algorithm was subjected to a series of tests in a variety of simulated underwater environments, including different sea states, target motion speeds and base station configurations. The experimental results demonstrate that the algorithm exhibits a deviation of only 2.88 m/s in velocity estimation and 2.58 m in position estimation when the noise level is 20 dB. The algorithm presented in this paper demonstrates superior performance in both position and velocity estimation compared to other algorithms.

Defect monitoring method for Al-CFRTP UFSW based on BWO–VMD–HHT and ResNet

Underwater friction stir welding (UFSW) achieves reliable joining between dissimilar materials and meets the welding demand for function and properties in lightweight structures of modern engineering. A defect monitoring method based on Variational Mode Decomposition optimized by Beluga Whale Optimization and Hilbert–Huang Transform (BWO–VMD–HHT) is proposed to solve the unclear feature of AE signal in UFSW due to the aqueous medium. UFSW experiments on Al alloy and carbon fiber reinforced thermoplastic (CFRTP) are carried out with AE signals measured. The time–frequency domain features of AE signals are extracted by BWO–VMD–HHT. The experimental results show that the main frequency of the AE signal is 22.5 kHz, and surface crack defects, shallow hole defects, and deep hole defects are accompanied by the transfer phenomena of different frequency components. Then, the feature vectors are built by frequency components in the BWO–VMD–HHT spectrum and reduced by principal component analysis, including 22.5 kHz, 24 kHz, 20.6 kHz, 18.4 kHz, 17.3 kHz, and 15.6 kHz. The feature vectors are divided into the train and test sets, and the welding defect prediction model (ResNet18-attention) is built by ResNet18 and trained by feature vectors. In the test set, the ResNet18-attention is compared with the BP, SVM, and RBF. Test results show that the precision of models has improved by at least 10%, which are trained by BWO–VMD–HHT features vector. Also, ResNet18-attention has achieved an average precision of 0.906 and recognizes the category of weld defect accurately, and this method can be applied to the defect monitoring of UFSW.

WiSigPro: Transformer for elevating CSI-based human activity recognition through attention mechanisms

The utilization of Channel State Information (CSI) in Wi-Fi-based passive sensing has become popular due to its cost-effectiveness and broad applicability. This technology is highly valued for its ability to gather data without requiring active user interaction, making it versatile in various contexts. However, existing methods face significant challenges, including low sensing accuracy, high processing requirements, and system instability. To address these issues, we introduce the WiSigPro Transformer, an advanced CSI-based Wi-Fi passive sensing model specifically designed for Human Activity Recognition. This model employs multi-head attention mechanisms and positional encoding to effectively capture complex spatiotemporal patterns, thereby enhancing both robustness and accuracy. Our approach integrates advanced signal processing techniques to improve signal quality and feature extraction. These techniques include wavelet denoising to reduce noise, median filtering to smooth the signal, and Power Spectral Density analysis using Welch’s method to capture frequency domain features. Additionally, we use normalization to standardize amplitude and phase data, and feature engineering methods to extract comprehensive signal characteristics, such as skewness and kurtosis. To address data imbalance, we apply the Synthetic Minority Over-sampling Technique and data augmentation strategies, ensuring balanced representation and improved model generalization. Through comprehensive simulations, the WiSigPro Transformer demonstrates superior performance across key metrics, including recognition accuracy, precision, recall, and F1-score. Achieving an impressive 98% accuracy, it outperforms conventional neural networks such as CNN, RNN, BiLSTM, LSTM, and ABLSTM. These results underscore the transformative potential of the WiSigPro Transformer in Wi-Fi-based passive sensing and activity recognition applications, making it a powerful tool for accurately capturing and analyzing spatiotemporal data.

PaFESD: Patterns augmented by Features Epileptic Seizure Detection.

The detection of epileptic seizures can have a significant impact on the patients' quality of life and on their caregivers. In this paper we propose a method for detecting such seizures from electroencephalogram (EEG) data named Patterns augmented by Features Epileptic Seizure Detection (PaFESD). The main novelty of our proposal consists in a detection model that combines EEG signal features with pattern matching. After cleaning the signal and removing artifacts (as eye blinking or muscle movement noise), time-domain and frequency-domain features are extracted to filter out non-seizure regions of the EEG. Jointly, pattern matching based on Dynamic Time Warping (DTW) distance is also leveraged to identify the most discriminative patterns of the seizures, even under scarce training data. The proposed model is evaluated on all patients in the CHB-MIT database, and the results show that it is able to detect seizures with an average F1 score of 98.9%. Furthermore, our approach achieves a F1 score of 100% (no false alarms or missed true seizures) for 20 of the patients (out of 24). Additionally, we automatically detect the most seizure/non-seizure discriminative EEG channel so that a wearable with only two electrodes would suffice to warn patients of seizures.

A Similarity Clustering Deformation Prediction Model Based on GNSS/Accelerometer Time-Frequency Analysis

Structural monitoring is crucial for assessing structural health, and high-precision deformation prediction can provide early warnings for safety monitoring. To address the issue of low prediction accuracy caused by the non-stationary and nonlinear characteristics of deformation sequences, this paper proposes a similarity clustering (SC) deformation prediction model based on GNSS/accelerometer time-frequency analysis. First, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm is used to decompose the original monitoring data, and the time-frequency characteristic correlations of the deformation data are established. Then, similarity clustering is conducted for the monitoring sub-sequences based on their frequency domain characteristics, and clustered sequences are combined subsequently. Finally, the Long Short-Term Memory (LSTM) model is used to separately predict GNSS displacement and acceleration with clustered time series, and the overall deformation displacement is reconstructed based on the predicted GNSS displacement and acceleration-derived displacement. A shake table simulation experiment was conducted to validate the feasibility and performance of the proposed CEEMDAN-SC-LSTM model. A duration of 5 s displacement prediction is analyzed after 153 s of monitoring data training. The results demonstrate that the root mean square error (RMSE) of predicted displacement is 0.011 m with the proposed model, which achieves an improvement of 64.45% and 61.51% in comparison to the CEEMDAN-LSTM and LSTM models, respectively. The acceleration predictions also show an improvement of 96.49% and 95.58%, respectively, the RMSE of the predicted acceleration-reconstructed displacement is less than 1 mm, with a reconstruction similarity of over 99%. The overall displacement reconstruction similarity can reach over 95%.

A hybrid physics-corrected neural network for RUL prognosis under random missing data

In order to accurately predict the remaining useful life (RUL) of mechanical equipment under conditions of missing data, this paper proposes a novel integrated framework for data repair and RUL prediction, named DRTCR. DRTCR possesses the dual functionality of missing data repair and RUL prediction. Initially, considering the underlying trends and periodic fluctuations in the signals, polynomial and trigonometric functions are incorporated into the implicit feature matrix (IFM) generated by Gaussian random functions. This approach involves constructing a data repair deep learning framework primarily based on LSTM and CNN. This framework facilitates the repair of missing data. Furthermore, this paper introduces the integration of trend, correlation, and robustness within the LSTM units. A predictive unit named TCRcell is devised, which enhances the feature extraction capability of the prediction model. Additionally, a corrective unit within TCRcell is constructed, predominantly centered around discrete Fourier transform (DFT) and discrete wavelet transform (DWT) as frequency domain feature extraction techniques. This incorporation introduces the physical mechanism information into DRTCR and refines the predictive outcomes of TCRcell. The global frequency perspective of DFT aids in capturing the overall trend in signal variations, while DWT precisely captures localized temporal details in the time series, resulting in a dynamically corrected TCRcell prediction outcome that combines both global trends and local intricacies. Finally, experimental validation was conducted to assess the predictive performance and robustness of DRTCR.

ZCHSound: Open-Source ZJU Paediatric Heart Sound Database With Congenital Heart Disease.

From 2020 to 2022, we collaborated with experienced cardiac surgeons from three general children's hospitals to collect heart sound signals from 1259 participants using electronic stethoscopes. To ensure the accuracy of the labels, the labels for all data were confirmed by two cardiac experts. To establish the baseline of ZCHsound, we extracted 84 features and used machine learning models to evaluate the performance of the classification task. The ZCHSound database was divided into two datasets: one is a high-quality, filtered clean heart sound dataset, and the other is a low-quality, noisy heart sound dataset. In the evaluation of the high-quality dataset, our random forest ensemble model achieved an F1 score of 90.3% in the classification task of normal and pathological heart sounds. This study has successfully established a large-scale, high-quality, rigorously standardized pediatric CHD sound database with precise disease diagnosis. This database not only provides important learning resources for clinical doctors in auscultation knowledge but also offers valuable data support for algorithm engineers in developing intelligent auscultation algorithms.

Machine anomalous sound detection based on audio synthesis generative adversarial network

Abstract In the pursuit of implementing safety monitoring within Industry 4.0 smart production, deep learning methodologies are employed to harness the audio signals emanating from the operation of machinery and equipment, facilitating anomaly detection. Aiming to address the challenge of the few-shot samples for anomalous sound detection in an unsupervised setting, this paper introduces a machine anomalous sound detection method using an Audio Synthesis Adversarial Generative Network (ASGAN). The augmentation of classifiers within the network’s discriminator is proposed to execute a multi-classification task, thereby transforming the unsupervised training milieu into a semi-supervised one and enhancing the discriminator’s accuracy. To address the oversight of audio frequency domain features by conventional generative adversarial networks, the squeeze-and-excitation network is applied to concentrate on crucial frequency bands within the frequency domain. Experimental validation is conducted by using the DCASE Challenge Task2 dataset, revealing that the performance of the anomaly detection method leveraging audio synthesis generative adversarial networks surpasses that of the baseline system.

A Low voltage AC fault arc detection method based on multi-feature fusion

Abstract The complex electrical environment makes it difficult for most arc detectors on the market to accurately detect faulty arcs. A universal fault arc detection method based on machine learning (ML) algorithms is proposed in this paper. To address the potential hazards of fault arcs in the power system, firstly, the causes, time-domain, and frequency-domain characteristics of fault arcs were analyzed. Then, an arc experiment platform was built according to national standards, and current data was collected under various load conditions. Finally, the arc detection model was trained based on ML. The main contribution of this study is to explore a feature combination that is not affected by load type interference and has strong generalization ability for identifying fault arcs, clarify the key factors and feature extraction methods for identifying fault arcs, and develop a set of high-precision arc detection methods, providing strong guarantees for the stable operation of the power system.

Enhancing structural integrity of refractories during manufacturing through integration of UPV and acoustic nonlinearity measurements

ABSTRACT This paper addresses the critical need for robust quality assurance in commercial refractories, emphasizing the role of Ultrasonic Pulse Velocity (UPV) testing in assessing material integrity. Traditionally, UPV testing has become a standard practice for evaluating refractory, ceramic, and concrete materials after production. However, this study introduces an innovative approach by advocating the integration of UPV tests at an intermediate stage prior to temperature curing. The primary objective is to predict the performance of refractory samples under compressive loading, examine intrinsic damages, and analyse ultrasonic characteristics in both time and frequency domains. Experimental investigations introduce damages, including artificial voids simulating various defect types, both before and during heat treatment. Analysis of UPV, Root Mean Squared (RMS) values of frequency spectra, and the acoustic nonlinearity parameter (ANP) reveals substantial differences between healthy and damaged regions. The mean UPV and RMS values consistently decrease in damaged regions, indicating sensitivity to defect severity. The ANP is sensitive to damage size, especially with higher frequency transducers detecting subtle changes more effectively. These findings emphasise the potential for proactive testing at an intermediate stage in the manufacturing process, enhancing the structural integrity and overall quality of refractory materials.

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.

High-resolution seismic inversion method based on joint data-driven in the time-frequency domain

Seismic inversion can be divided into time-domain inversion and frequency-domain inversion based on different transform domains. Time-domain inversion has stronger stability and noise resistance compared to frequency-domain inversion. Frequency domain inversion has stronger ability to identify small-scale bodies and higher inversion resolution. Therefore, the research on the joint inversion method in the time-frequency domain is of great significance for improving the inversion resolution, stability, and noise resistance. The introduction of prior information constraints can effectively reduce ambiguity in the inversion process. However, the existing model-driven time-frequency joint inversion assumes a specific prior distribution of the reservoir. These methods do not consider the original features of the data and are difficult to describe the relationship between time-domain features and frequency-domain features. Therefore, this paper proposes a high-resolution seismic inversion method based on joint data-driven in the time-frequency domain. The method is based on the impedance and reflectivity samples from logging, using joint dictionary learning to obtain adaptive feature information of the reservoir, and using sparse coefficients to capture the intrinsic relationship between impedance and reflectivity. The optimization result of the inversion is achieved through the regularization term of the joint dictionary sparse representation. We have finally achieved an inversion method that combines constraints on time-domain features and frequency features. By testing the model data and field data, the method has higher resolution in the inversion results and good noise resistance.

Spectral Features Analysis for Print Quality Prediction in Additive Manufacturing: An Acoustics-Based Approach.

Quality prediction in additive manufacturing (AM) processes is crucial, particularly in high-risk manufacturing sectors like aerospace, biomedicals, and automotive. Acoustic sensors have emerged as valuable tools for detecting variations in print patterns by analyzing signatures and extracting distinctive features. This study focuses on the collection, preprocessing, and analysis of acoustic data streams from a Fused Deposition Modeling (FDM) 3D-printed sample cube (10 mm × 10 mm × 5 mm). Time and frequency-domain features were extracted at 10-s intervals at varying layer thicknesses. The audio samples were preprocessed using the Harmonic-Percussive Source Separation (HPSS) method, and the analysis of time and frequency features was performed using the Librosa module. Feature importance analysis was conducted, and machine learning (ML) prediction was implemented using eight different classifier algorithms (K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Decision Trees (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LightGBM)) for the classification of print quality based on the labeled datasets. Three-dimensional-printed samples with varying layer thicknesses, representing two print quality levels, were used to generate audio samples. The extracted spectral features from these audio samples served as input variables for the supervised ML algorithms to predict print quality. The investigation revealed that the mean of the spectral flatness, spectral centroid, power spectral density, and RMS energy were the most critical acoustic features. Prediction metrics, including accuracy scores, F-1 scores, recall, precision, and ROC/AUC, were utilized to evaluate the models. The extreme gradient boosting algorithm stood out as the top model, attaining a prediction accuracy of 91.3%, precision of 88.8%, recall of 92.9%, F-1 score of 90.8%, and AUC of 96.3%. This research lays the foundation for acoustic based quality prediction and control of 3D printed parts using Fused Deposition Modeling and can be extended to other additive manufacturing techniques.

Radio Signal Modulation Recognition Method Based on Hybrid Feature and Ensemble Learning: For Radar and Jamming Signals.

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning.

Study on the classification of sleep stages in EEG signals based on DoubleLinkSleepCLNet.

The classification of sleep stages based on Electroencephalogram (EEG) changes has significant implications for evaluating sleep quality and sleep status. Most polysomnography (PSG) systems have a limited number of channels and do not achieve optimal classification performance due to a paucity of raw data. To leverage the data characteristics and enhance the classification accuracy, we propose and evaluate a novel dual-link deep neural network model, 'DoubleLinkSleepCLNet'. The DoubleLinkSleepCLNet model performs feature extraction and efficient classification on both the raw EEG and the EEG processed with the Hilbert transform. It leverages the frequency domain and time domain feature modules, resulting in superior performance compared to other models. The DoubleLinkSleepCLNet model, using the 2 Raw/2 Hilbert data modes, achieved the highest classification performance with an accuracy of 88.47%. The average accuracy of the EEG was improved by approximately 4.08% after the application of the Hilbert transform. Additionally, Convolutional Neural Network (CNN) demonstrated superior performance in processing phase information, whereas Long Short-Term Memory (LSTM) excelled in handling time series data. The application of the Hilbert transform to EEG data, followed by processing it with a convolutional neural network, enhances the accuracy of the model. These findings introduce novel concepts for accelerating sleep stage prediction research, suggesting potential applications of these methods to other EEG analyses.

An adaptive few-shot fault diagnosis method based on virtual samples generated by fault characteristics of rotating machines

The existing intelligent diagnostic methods based on the machine learning achieve good diagnostic results under the condition of large amount of the failure data available. However, in most cases, the diagnosis model is difficult to be constructed under the few-shot problem, which only normal data of the equipment is available. Therefore, a novel Adaptive Diagnosis with Fault Characteristics (ADFC) method, which builds the diagnosis model by generating personalized virtual fault samples, is proposed in the paper. The fault common characteristics are obtained based on the failure mechanism and the law of transmission paths, and the personalized fault virtual samples are generated by combining health state data contain the individual characteristics of the equipment. Then, the frequency domain features reflecting the operating status of the equipment are extracted as training samples. Finally, the fault diagnosis model based on the Convolutional Neural Network (CNN) is constructed for the equipment. The ADFC method is validated by the rotating machinery data, including the public data, the laboratory data and the field application data. The results indicate that the ADFC method achieved an average diagnostic accuracy of 92.16%, and the accuracy has been improved by at least 0.78% compared to the comparison method.