Anti-noise Performance Research Articles

Detection and Classification of Multiple Power Quality Disturbances Using Stockwell Transform and Deep Learning

With the widespread access of nonlinear loads, enterprises and consumers are faced with the problem of power quality disturbance (PQD) in the grid. The detection and classification of multiple power quality disturbances is considered to be a challenging task. In this paper, a novel hybrid method based on Stockwell Transform (ST) and Deep Learning is proposed to detect and classify multiple power quality disturbances (MPQDs). Compared with previous cases where only single or dual PQDs are considered, this paper fully considers the existence of MPQDs compounds in real situations and designs a more general and automated approach based on Deep Learning for automated feature selection and classification. Firstly, the S-transform is used to extract the features of the one-dimensional signal and take the modulus of the result to obtain the ST-matrix of the signal. In order to improve the anti-noise performance of the system, the parameters for generating the time-frequency domain contour are optimized, so that contour images with less noise can be drawn. Secondly, the above images are fed into the designed Convolutional Neural Network (CNN) for training. A total of 37 PQDs detection and classification tasks including single and multiple disturbances were completed. It is compared with other existing methods to demonstrate its robustness under noisy environments. Finally, an experimental platform for MPQDs was built to verify the proposed method, and the results demonstrated that the method can effectively detect and classify MPQDS.

Analysis and Compensation of Phase Error Caused by Noise and Nonlinear Response of 3-D Measurement System

For static objects where the fringes are not saturated, the phase accuracy is mainly affected by the unavoidable factors of the introduction of fringe noise and the nonlinear response of the measurement system. The existing noise-induced phase error model is based on a Gaussian noise model, but in fact the noise of the fringe pattern is random. In this work, we establish a new evaluation method that directly converts the noise variance into phase variance, and we compare the anti-noise performance of the three-step and four-step phase-shift methods according to the phase error coefficient. Theoretical and experimental results confirm that the anti-noise performance of the four-step phase-shifting method is 25% higher than that of the three-step phase-shifting method. Subsequently, we also established a phase error model for the nonlinear response of the three-dimensional (3D) measurement system. Since the low measurement efficiency of the existing double <i>N</i>-step phase-shifting (DNPS) method, an improved double <i>N</i>-step phase-shifting (IDNPS) method is proposed. The RMSE of the compensated phase with IDNPS is approximately equal to that with DNPS, but the number of additional fringes with IDNPS is reduced to half that with DNPS. The total time cost of using IDNPS is reduced to 68.5% of using DNPS. Simulations and experiments are conducted to verify the validity of the theoretical analysis results.

Deep Learning-Based High Accuracy Bottom Tracking on 1-D Side-Scan Sonar Data

The bottom tracking is to confirm the first bottom return signal in each ping to divide the data into the seabed area and the water column area, which is an essential part of side-scan sonar (SSS) data processing. More than that, SSS is usually affected by water flow or suspended solids, resulting in serious noises, which make the bottom tracking more difficult and complex. Some existing methods follow ideas such as abnormal point detection or filtering, resulting in unsatisfactory bottom tracking effects. Inspired by the semantic segmentation mission in deep learning, we innovatively transform the bottom tracking into a binary-class semantic segmentation mission on 1-D SSS data. Following this idea, we propose a semantic segmentation-based bottom tracking method and modify two image semantic segmentation models, SegNet and U-Net, so that they can achieve bottom tracking on 1-D SSS data. Benefiting from the large receptive field brought by convolution and down-sampling, our method has made significant progress in accuracy and antinoise performance compared with the existing method. According to the experimental result, our method has obvious improvement compared with the existing method on the testing set; not only that, our method also performs better on the unused data.

Reconfigurable and Storable Chaotic Logic Operations in Drive-Response VCSELs With Optical Feedback

Based on the system of drive-response vertical cavity surface emitting lasers (VCSELs) with optical feedback and the new electro-optic (EO) modulation theory, we propose a novel reconfigurable and storable logic operations scheme to perform the behaviors of flexible switching and delayed storage among different logic operations. Here, the optical feedback intensity is modulated into logic input, the applied electric field in drive system and response system are modulated into logical control signals, the logic output is decoded by threshold mechanism. When the logical control signal in drive system and response system remain equal and both of them satisfy different logic operation relationships with the logic inputs, the system can perform the mutual conversion and delayed storage among the logic operations such as AND, NAND, OR, NOR, XOR and XNOR. Furthermore, the half adder logic operations are also being realized. Finally, the influence of bit duration time and noise intensity on the reliability of the logic operations is analyzed, and the results indicate that the logic operations have good anti-noise performance.

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder.

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

Sliding Dispersion Entropy-Based Fault State Detection for Diaphragm Pump Parts

Aiming at the disadvantages of low trend, poor characterization performance, and poor anti-noise performance of traditional degradation features such as dispersion entropy (DE), a fault detection method based on sliding dispersion entropy (SDE) is proposed. Firstly, a sliding window is added to the signal before extracting the DE feature, and the root mean square of the signal inside the sliding window is used to replace the signal in the window to realize down sampling, which enhances the trend of DE. Secondly, the hyperbolic tangent sigmoid function (TANSIG) is introduced to map the signals to different categories when extracting the DE feature, which is more in line with the signal distribution of mechanical parts and the monotonicity of the degradation feature is improved. For noisy signal, the introduction of locally weighted scatterplot smoothing (LOWESS) can remove the burrs and fluctuations of the SDE curve, and the anti-noise performance of SDE is improved. Finally, the SDE state warning line is constructed based on the 2σ criterion, which can determine the fault warning point in time and effectively. The state detection results of bearing and check valve show that the proposed SDE improves the trend, monotonicity, and robustness of the state tracking curve, and provides a new method for fault state detection of mechanical parts.

An unsupervised bearing fault diagnosis based on deep subdomain adaptation under noise and variable load condition

Deep learning-based approaches for diagnosing bearing faults have attracted considerable attention in the last years. However, in real-world applications, these methods face challenges. For proper training of these models, a considerable amount of labeled data are necessary, and due to limitations in industry, obtaining this amount of data may not be possible. Because of load variations, the distribution of training and test data may vary, which reduces the accuracy of the trained model for various working conditions. Furthermore, noise has a significant impact on bearing fault diagnosis performance in real-world industrial applications. This study introduced the deep subdomain adaptation convolutional neural network (DSACNN) method to overcome these challenges in real scenarios. The local maximum mean discrepancy (LMMD) method reduces the difference between each class distribution in the source and target domains. We validated our proposed method by CWRU bearing dataset under various loads and noise with different SNRs. The results show that DSACNN outperforms other comparative methods in anti-noise performance and reduction of domain distribution discrepancies.

Spinal Codes Over Fading Channel: Error Probability Analysis and Encoding Structure Improvement

In order to facilitate the reliability of data transmission of Spinal codes over the fading channel, performance analysis of Spinal codes is conducted, and an improved encoding structure is proposed. First, we derive an approximate frame error rate (FER) upper bound for Spinal codes over the Rayleigh fading channel in the finite block length (FBL) regime. Then, inspired by the FER analysis process, we propose an improved encoding structure, named self-concatenation structure, to reduce the FER of Spinal codes. In addition, a parallel structure is proposed for Spinal codes to improve the decoding throughput. For the self-concatenation structure, simulation results show that it exhibits a significant gain in anti-noise performance compared with the original Spinal codes over the Rayleigh fading channel. For the parallel structure, we find that by combining the parallel structure with the self-concatenation structure, not only is the encoding and decoding throughput of Spinal codes significantly improved but also the FER of Spinal codes is reduced.

Automatic modal parameters identification and uncertainty quantification based on block-bootstrap and multi-stage clustering under ambient excitation

This study proposes an algorithm for autonomous modal estimation to automatically eliminate false modes and quantify the uncertainty caused by the clustering algorithm and ambient factors. This algorithm belongs to the stochastic subspace identification (SSI) techniques and is based on the Block-Bootstrap and multi-stage clustering analysis. First, the Block-Bootstrap is introduced to decompose the response signal of the structure into M blocks of data. The covariance-driven stochastic subspace identification (SSI-Cov) method is used to process a random sample of data and obtain the corresponding M stabilization diagrams. In addition, the hierarchical clustering method is adopted to carry out the secondary clustering of the picked stable axis according to the defined distance threshold. Then, false modes are eliminated according to the proposed true and false modal discrimination index ( MDI). Finally, the above steps are repeated B times, and MDI is used to modify the initial modal parameters of group B. The mean value of elements in the cluster is taken as the recognition result of modal parameters, and the standard deviation is used to measure the accuracy of the recognition result. The numerical simulation results and the modal parameter identification of the Jing-yuan Yellow River Bridge show that, for identifying true and false modals, the proposed modal discrimination index is more effective than the threshold value of the traditional index. Also, it was found that the proposed method can eliminate the uncertainty introduced in the clustering process. In addition, this method can remove the influence of ambient noises, and it can improve the identification accuracy. It will be shown that this method has better anti-noise performance.

Few-Shot Abnormal Network Traffic Detection Based on Multi-scale Deep-CapsNet and Adversarial Reconstruction

Detecting various attacks and abnormal traffic in the network is extremely important to network security. Existing detection models used massive amounts of data to complete abnormal traffic detection. However, few-shot attack samples can only be intercepted in certain special scenarios. In addition, the discrimination of traffic attributes will also be affected by the change of feature attitude. But the traditional neural network model cannot detect this kind of attitude change. Therefore, the accuracy and efficiency of few-shot sample abnormal traffic detection are very low. In this paper, we proposed a few-shot abnormal network traffic detection method. It was composed of the multi-scale Deep-CapsNet and adversarial reconstruction. First, we designed an improved EM vector clustering of the Deep-CapsNet. The attitude transformation matrix was used to complete the prediction from low-level to high-level features. Second, a multi-scale convolutional capsule was designed to optimize the Deep-CapsNet. Third, an adversarial reconstruction classification network (ARCN) was proposed. The supervised source data classification and the unsupervised target data reconstruction were achieved. Moreover, we proposed an adversarial training strategy, which alleviated the noise interference during reconstruction. Fourth, the few-shot sample classification were obtained by combining multi-scale Deep-CapsNet and adversarial reconstruction. The ICSX2012 and CICIDS2017 datasets were used to verify the performance. The experimental results show that our method has better training performance. Moreover, it has the highest accuracy in two-classification and multi-classification. Especially it has good anti-noise performance and short running time, which can be used for real-time few-shot abnormal network traffic detection.

A Novel Composite Coding Method for Incoherent Scatter Radar

Many modern ionospheric studies rely on incoherent scatter radars (ISR) since this kind of radar is able to detect various ionospheric parameters over very long ranges. The performance of ISR significantly depends on its coding system. In recent decades, a new type of coding system, which is the so-called composite coding, was presented. It used to be constructed by using a certain code to modulate alternating code to achieve better detection resolution and anti-noise performance for ISRs. In the present study, a new composite coding system was presented, which is constructed based on complementary codes and alternating codes. In this paper, the performance of the new composite code will be compared with that of several traditional codes to show that the new composite code can help to improve the detection performance of the ISR. According to the analysis based on the ambiguity function, the present composite coding system helps to improve the range resolution and detection range for ISR detections. In addition, numerical tests on anti-noise performance show that the complementary composite coding system has a good anti-noise performance and helps to reduce the necessary times of incoherent integration. As a result, the composite coding system can improve the time resolution.

An Entropy-Based Anti-Noise Method for Reducing Ranging Error in Photon Counting Lidar.

Photon counting lidar for long-range detection faces the problem of declining ranging performance caused by background noise. Current anti-noise methods are not robust enough in the case of weak signal and strong background noise, resulting in poor ranging error. In this work, based on the characteristics of the uncertainty of echo signal and noise in photon counting lidar, an entropy-based anti-noise method is proposed to reduce the ranging error under high background noise. Firstly, the photon counting entropy, which is considered as the feature to distinguish signal from noise, is defined to quantify the uncertainty of fluctuation among photon events responding to the Geiger mode avalanche photodiode. Then, the photon counting entropy is combined with a windowing operation to enhance the difference between signal and noise, so as to mitigate the effect of background noise and estimate the time of flight of the laser pulses. Simulation and experimental analysis show that the proposed method improves the anti-noise performance well, and experimental results demonstrate that the proposed method effectively mitigates the effect of background noise to reduce ranging error despite high background noise.

Associating brain imaging phenotypes and genetic in Alzheimer's disease via JSCCA approach with autocorrelation constraints.

Imaging genetics research can explore the potential correlation between imaging and genomics. Most association analysis methods cannot effectively use the prior knowledge of the original data. In this respect, we add the prior knowledge of each original data to mine more effective biomarkers. The study of imaging genetics based on the sparse canonical correlation analysis (SCCA) is helpful to mine the potential biomarkers of neurological diseases. To improve the performance and interpretability of SCCA, we proposed a penalty method based on the autocorrelation matrix for discovering the possible biological mechanism between single nucleotide polymorphisms (SNP) variations and brain regions changes of Alzheimer's disease (AD). The addition of the penalty allows the proposed algorithm to analyze the correlation between different modal features. The proposed algorithm obtains more biologically interpretable ROIs and SNPs that are significantly related to AD, which has better anti-noise performance. Compared with other SCCA-based algorithms (JCB-SCCA, JSNMNMF), the proposed algorithm can still maintain a stronger correlation with ground truth even when the noise is larger. Then, we put the regions of interest (ROI) selected by the three algorithms into the SVM classifier. The proposed algorithm has higher classification accuracy. Also, we use ridge regression with SNPs selected by three algorithms and four AD risk ROIs. The proposed algorithm has a smaller root mean square error (RMSE). It shows that proposed algorithm has a good ability in association recognition and feature selection. Furthermore, it selects important features more stably, improving the clinical diagnosis of new potential biomarkers.

Simulation research on magneto-acoustic concentration tomography of magnetic nanoparticles based on truncated singular value decomposition (TSVD).

The existing magneto-acoustic concentration tomography with magnetic induction (MACT-MI) inverse problem algorithm has some problems such as the singularity of reconstructed boundary and poor anti-noise performance, which make it difficult to be applied to recognition of early breast cancer tumor. Therefore, a system matrix linking the concentration distribution information of magnetic nanoparticles (MNPs) to the ultrasonic signal was built in this paper, and a truncated singular value decomposition (TSVD) based MNPS concentration reconstruction algorithm was proposed. Firstly, a simulation model was established. Secondly, the magnetic field and acoustic field simulation data were substituted into the inverse problem algorithm based on TSVD for concentration reconstruction. Finally, the effects of the number of singular values, SNR and radius of MNPs on the reconstruction results were studied. The simulation results show that, the inverse problem algorithm based on TSVD proposed in this paper can maximize the use of ultrasonic signals, and has a good reconstruction effect on 1mm small-radius MNPs, high resolution reconstructed images can also be obtained under the condition of low SNR, which can effectively promote the clinical application of this imaging method.

Multi-Scale Capsule Attention Network and Joint Distributed Optimal Transport for Bearing Fault Diagnosis under Different Working Loads.

In recent years, intelligent fault diagnosis methods based on deep learning have developed rapidly. However, most of the existing work performs well under the assumption that training and testing samples are collected from the same distribution, and the performance drops sharply when the data distribution changes. For rolling bearings, the data distribution will change when the load and speed change. In this article, to improve fault diagnosis accuracy and anti-noise ability under different working loads, a transfer learning method based on multi-scale capsule attention network and joint distributed optimal transport (MSCAN-JDOT) is proposed for bearing fault diagnosis under different loads. Because multi-scale capsule attention networks can improve feature expression ability and anti-noise performance, the fault data can be better expressed. Using the domain adaptation ability of joint distribution optimal transport, the feature distribution of fault data under different loads is aligned, and domain-invariant features are learned. Through experiments that investigate bearings fault diagnosis under different loads, the effectiveness of MSCAN-JDOT is verified; the fault diagnosis accuracy is higher than that of other methods. In addition, fault diagnosis experiment is carried out in different noise environments to demonstrate MSCAN-JDOT, which achieves a better anti-noise ability than other transfer learning methods.

Improving Compressed Sensing Image Reconstruction Based on Atmospheric Modulation Using the Distributed Cumulative Synthesis Method

The problem of long-distance imaging through time-varying scattering media, such as the atmosphere, is encountered in many science fields. Recent studies have demonstrated that random atmospheric variability can be considered a spatial light modulator in compressed sensing imaging. However, the quality of the reconstructed image needs to be further improved. In this paper, we propose a distributed cumulative synthesis method to improve the compressed sensing image reconstruction based on atmospheric modulation. For multiple original images of various types, the compressed sensing imaging simulation experiment with different sampling rates was conducted using the distributed cumulative synthesis method. The simulation results show that, compared with the imaging method using a single light source, the distributed cumulative synthesis method can effectively improve the quality of the reconstructed image, whether it is full sampling or undersampling. In addition, a sparsity impact factor is defined to quantify the reconstruction ability of the measurement matrix obtained by the distributed cumulative synthesis method. This value can be used as an evaluation index for the optimized design of the measurement matrix by the distributed cumulative synthesis method. Noise analysis shows that the proposed method has better anti-noise performance than the single light source imaging method.

An anti-noise one-dimension convolutional neural network learning model applying on bearing fault diagnosis

Since the continuous shrinking of the spatial distance between components from large-scale mechanized equipment which causes the physical characteristic signals transmitted by them to be buried in a large amount of interference noise. Aiming at the poor anti-noise performance and high computation complexity of conventional fault diagnosis methods toward rotatory machinery. This study proposes a one-dimension convolutional neural network (1DCNN) for fault diagnosis that directly worked on time-domain signals. A compact 1DCNN network structure is deeply optimized under the Pytorch software environment; features are automatically extracted from the background noise. Moreover, fully connected neural networks, softmax activation function, Adam optimization algorithm, and cross-entropy loss function are utilized for achieving the accuracy of over 99% to multi-classification tasks. Subsequently, when dealing with the noise-rich scenario, simulation results demonstrate that the accuracy rate can reach 98.31% when the signal-to-noise ratio is −8dB. What's more, the proposed model can still keep the valuable accuracy rate at 87.27% under −10 dB, which made a breakthrough contribution to the model's anti-noise performance by more than 7%. The result of this work verifies the effectiveness of the anti-noise robustness performance, thereby becoming a cornerstone inside the preventive fault diagnosis system for rotatory machinery.

Unsupervised deep learning for 3D reconstruction with dual-frequency fringe projection profilometry.

The fringe projection profilometry (FPP) technique has been widely applied in three-dimensional (3D) reconstruction in industry for its high speed and high accuracy. Recently, deep learning has been successfully applied in FPP to achieve high-accuracy and robust 3D reconstructions in an efficient way. However, the network training needs to generate and label numerous ground truth 3D data, which can be time-consuming and labor-intensive. In this paper, we propose to design an unsupervised convolutional neural network (CNN) model based on dual-frequency fringe images to fix the problem. The fringe reprojection model is created to transform the output height map to the corresponding fringe image to realize the unsupervised training of the CNN. Our network takes two fringe images with different frequencies and outputs the corresponding height map. Unlike most of the previous works, our proposed network avoids numerous data annotations and can be trained without ground truth 3D data for unsupervised learning. Experimental results verify that our proposed unsupervised model (1) can get competitive-accuracy reconstruction results compared with previous supervised methods, (2) has excellent anti-noise and generalization performance and (3) saves time for dataset generation and labeling (3.2 hours, one-sixth of the supervised method) and computer space for dataset storage (1.27 GB, one-tenth of the supervised method).

An adaptive anti-noise network with recursive attention mechanism for gear fault diagnosis in real-industrial noise environment condition

Acoustic-based diagnosis (ABD) is a promising method for machinery fault detection due to its ability of non-contact measurement by air-couple. However, most of the ABD methods are constrained by strong and highly non-stationary background noise interference in practical industrial application. To address the shortcoming, a novel anti-noise ABD method based on recursive attention mechanism (RAM) is proposed in this paper. In proposed method, a multi-stage attention module (MSAM) is firstly designed as fundament of RAM to automatically estimate the noise interference probability within time–frequency (T-F) unit of each signal sample. Simultaneously, a recursive learning strategy is introduced to construct RAM by reusing the MSAM for multiple blocks to gradually refine the estimated probability and adaptively simulated noise interference in diagnosis model for enhancing anti-noise diagnosis ability. Then, based on RAM, a domain adaption method is established to endow the model with good cross-domain ability for further improving the anti-noise performance of the diagnosis model. The experiment result in both real-industrial noise condition and stimulated noise conditions with different SNRs indicate that the proposed method has stronger robustness and better generalization ability than other popular methods in dealing with gear fault diagnosis task under noise condition.

Particle size distribution inversion in dynamic light scattering by adaptive step-size non-negative least squares

The non-negative least squares algorithm is widely used in dynamic light scattering, however, it suffers the shortcomings of sparse solutions and poor anti-noise performance. It is found that the construction of the kernel matrix of the algorithm is of great significance to the accuracy of the final results. In this paper, we propose an adaptive strategy to find the optimal step-size to construct the kernel matrix. By calculating the L2-norm between the measured and reconstructed light intensity autocorrelation function, the optimal step-size is determined corresponding to the minimum difference error. Then the kernel matrix constructed by this optimal step-size is used in the inversion. The final result is obtained by fitting the solution to a predefined model, such as a Gaussian model. This strategy improves the sparsity of NNLS solution, and thus the accuracy and stability of NNLS inversion results. The simulation and experiments demonstrate that the adaptive step-size strategy improves the stability and accuracy of the non-negative least squares inversion algorithm for dynamic light scattering.