|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | NEW TECHNOLOGY FOR FAULT DIAGNOSIS BASED ON WAVELET DENOISING AND MODIFIED EXPONENTIAL TIME-FREQUENCY DISTRIBUTION显示文摘Fast wavelet multi-resolution analysis (wavelet MRA) provides a effective tool for analyzing and canceling disturbing components in original signal. Because of its exponential frequency axis, this method isn’t suitable for extracting harmonic components. The modified exponential time-frequency distribution ( MED) overcomes the problems of Wigner distribution( WD) ,can suppress cross-terms and cancel noise further more. MED provides high resolution in both time and frequency domains, so it can make out weak period impulse components fmm signal with mighty harmonic components. According to the 'time' behavior, together with 'frequency' behavior in one figure,the essential structure of a signal is revealed clearly. According to the analysis of algorithm and fault diagnosis example, the joint of wavelet MRA and MED is a powerful tool for fault diagnosis. | Wang Xinqing,Wang Yaohua,Qian Shuhua,Chen Liuhai (Engineering College of PLA University of Science and Technology) Xu Yanshen,Zhao Xiangsong (Tianjin University) | 2001 | Chinese Journal of Mechanical Engineering2001，14，3： | 13 |
| 2 | Gearbox fault diagnosis of rolling mills using multiwavelet sliding window neighboring coefficient denoising and optimal blind deconvolution显示文摘Fault diagnosis of rolling mills, especially the main drive gearbox, is of great importance to the high quality products and long-term safe operation. However, the useful fault information is usually submerged in heavy background noise under the severe condition. Thereby, a novel method based on multiwavelet sliding window neighboring coefficient denoising and optimal blind deconvolution is proposed for gearbox fault diagnosis in rolling mills. The emerging multiwavelets can seize the important signal processing properties simultaneously. Owing to the multiple scaling and wavelet basis functions, they have the supreme possibility of matching various features. Due to the periodicity of gearbox signals, sliding window is recommended to conduct local threshold denoising, so as to avoid the 'overkill' of conventional universal thresholding techniques. Meanwhile, neighboring coefficient denoising, considering the correlation of the coefficients, is introduced to effectively process the noisy signals in every sliding window. Thus, multiwavelet sliding window neighboring coefficient denoising not only can perform excellent fault extraction, but also accords with the essence of gearbox fault features. On the other hand, optimal blind deconvolution is carried out to highlight the denoised features for operators' easy identification. The filter length is vital for the effective and meaningful results. Hence, the foremost filter length selection based on the kurtosis is discussed in order to full benefits of this technique. The new method is applied to two gearbox fault diagnostic cases of hot strip finishing mills, compared with multiwavelet and scalar wavelet methods with/without optimal blind deconvolution. The results show that it could enhance the ability of fault detection for the main drive gearboxes. | YUAN Jing HE ZhengJia ZI YanYang LIU Han | 2009 | Science China(Technological Sciences)2009，52，10： | 7 |
| 3 | Deep residual learning for denoising Monte Carlo renderings显示文摘Learning-based techniques have recently been shown to be effective for denoising Monte Carlo rendering methods. However, there remains a quality gap to state-of-the-art handcrafted denoisers. In this paper, we propose a deep residual learning based method that outperforms both state-of-the-art handcrafted denoisers and learning-based denoisers.Unlike the indirect nature of existing learning-based methods(which e.g., estimate the parameters and kernel weights of an explicit feature based filter), we directly map the noisy input pixels to the smoothed output. Using this direct mapping formulation, we demonstrate that even a simple-and-standard ResNet and three common auxiliary features(depth, normal,and albedo) are sufficient to achieve high-quality denoising. This minimal requirement on auxiliary data simplifies both training and integration of our method into most production rendering pipelines. We have evaluated our method on unseen images created by a different renderer. Consistently superior quality denoising is obtained in all cases. | Kin-Ming Wong Tien-Tsin Wong | 2019 | Computational Visual Media2019，5，3： | 6 |
| 4 | The improved ICA algorithm and its application in the seismic data denoising显示文摘The field seismic data is disturbed by the interferential information, which has low signal to noise ratio (SNR). That is disadvantage for seismic data interpretation. So it is important to remove the noise of seismic data. Independent component analysis (ICA) can remove most of the noise interference. However, ICA has some defects in noise reduction, because it needs some conditions that seismic data is independent reciprocally for denoising. To solve these defects, this paper proposes an improved ICA algorithm to noise reduction. Through simulation experiments, it can be obtained that the best decomposition levels of the new algorithm is 3. At last, the proposed improved ICA is applied to deal with the actual seismic data. The results show that it can effectively eliminate most of seismic noise such as random noise, linear interference, surface waves, and so on. The improved ICA is not only easy to denoising, but also has excellent mathematical theoretical properties. | 秦飞龙 刘剑 YAN Wen-yong | 2018 | Journal of Chongqing University2018，17，4： | 6 |
| 5 | Aircraft engine fault detection based on grouped convolutional denoising autoencoders显示文摘Many existing aircraft engine fault detection methods are highly dependent on performance deviation data that are provided by the original equipment manufacturer. To improve the independent engine fault detection ability, Aircraft Communications Addressing and Reporting System(ACARS) data can be used. However, owing to the characteristics of high dimension, complex correlations between parameters, and large noise content, it is difficult for existing methods to detect faults effectively by using ACARS data. To solve this problem, a novel engine fault detection method based on original ACARS data is proposed. First, inspired by computer vision methods, all variables were divided into separated groups according to their correlations. Then, an improved convolutional denoising autoencoder was used to extract the features of each group. Finally, all of the extracted features were fused to form feature vectors. Thereby, fault samples could be identified based on these feature vectors. Experiments were conducted to validate the effectiveness and efficiency of our method and other competing methods by considering real ACARS data as the data source. The results reveal the good performance of our method with regard to comprehensive fault detection and robustness. Additionally, the computational and time costs of our method are shown to be relatively low. | Xuyun FU Hui LUO Shisheng ZHONG Lin LIN | 2019 | Chinese Journal of Aeronautics2019，32，2： | 6 |
| 6 | Convolutional adaptive denoising autoencoders for hierarchical feature extraction显示文摘Convolutional neural networks (CNNs)are typical structures for deep learning and are widely used in image recognition and classification.However,the random initialization strategy tends to become stuck at local plateaus or even diverge,which results in rather unstable and ineffective solutions in real applications.To address this limitation, we propose a hybrid deep learning CNN-AdapDAE model, which applies the features learned by the AdapDAE algorithm to initialize CNN filters and then train the improved CNN for classification tasks.In this model,AdapDAE is proposed as a CNN pre-training procedure,which adaptively obtains the noise level based on the principle of annealing,by starting with a high level of noise and lowering it as the training progresses.Thus,the features learned by AdapDAE include a combination of features at different levels of granu- larity.Extensive experimental results on STL-10,CIFAR-10, and MNIST datasets demonstrate that the proposed algorithm performs favorably compared to CNN (random filters),CNNAE (pre-training filters by autoencoder),and a few other unsupervised feature learning methods. | Qianjun ZHANG Lei ZHANG | 2018 | Frontiers of Computer Science2018，12，6： | 5 |
| 7 | Physics-constrained bayesian neural network for fluid flow reconstruction with sparse and noisy data显示文摘In many applications,flow measurements are usually sparse and possibly noisy.The reconstruction of a high-resolution flow field from limited and imperfect flow information is significant yet challenging.In this work,we propose an innovative physics-constrained Bayesian deep learning approach to reconstruct flow fields from sparse,noisy velocity data,where equationbased constraints are imposed through the likelihood function and uncertainty of the reconstructed flow can be estimated.Specifically,a Bayesian deep neural network is trained on sparse measurement data to capture the flow field.In the meantime,the violation of physical laws will be penalized on a large number of spatiotemporal points where measurements are not available.A non-parametric variational inference approach is applied to enable efficient physicsconstrained Bayesian learning.Several test cases on idealized vascular flows with synthetic measurement data are studied to demonstrate the merit of the proposed method. | Luning Sun Jian-Xun Wang | 2020 | Theoretical & Applied Mechanics Letters2020，10，3： | 5 |
| 8 | Advances in deep learning for computed tomography denoising显示文摘Computed tomography(CT)has seen a rapid increase in use in recent years.Radiation from CT accounts for a significant proportion of total medical radiation.However,given the known harmful impact of radiation exposure to the human body,the excessive use of CT in medical environments raises concerns.Concerns over increasing CT use and its associated radiation burden have prompted efforts to reduce radiation dose during the procedure.Therefore,low-dose CT has attracted major attention in the radiology,since CT-associated x-ray radiation carries health risks for patients.The reduction of the CT radiation dose,however,compromises the signal-to-noise ratio,which affects image quality and diagnostic performance.Therefore,several denoising methods have been developed and applied to image processing technologies with the goal of reducing image noise.Recently,deep learning applications that improve image quality by reducing the noise and artifacts have become commercially available for diagnostic imaging.Deep learning image reconstruction shows great potential as an advanced reconstruction method to improve the quality of clinical CT images.These improvements can provide significant benefit to patients regardless of their disease,and further advances are expected in the near future. | Sung Bin Park | 2021 | World Journal of Clinical Cases2021，9，26： | 4 |
| 9 | Memristor bridge-based low pass filter for image processing显示文摘This paper highlights the memristor bridge-based lowpass filter (LPF) and improved image processing algorithms along with a novel adaptive Gaussian filter for denoising image and a new Gaussian pyramid for scale invariant feature transform (SIFT). First, a novel kind of LPF based on the memristor bridge is designed, whose cut-off frequency and other traits are demonstrated to change with different time and memristance. In light of the changeable parameter of the memristor bridge-based LPF, a new adaptive Gaussian filter and an improved SIFT algorithm are presented. Finally, experiment results show that the peak signalto- noise ratio (PSNR) of our denoising is bettered more than 2.77 dB compared to the corresponding of the traditional Gaussian filter, and our improved SIFT performances including the number of matched feature points and the percent of correct matches are higher than the traditional SIFT, which verifies feasibility and effectiveness of our algorithm. | YU Yongbin YANG Nijing YANG Chenyu NYIMA Tashi | 2019 | Journal of Systems Engineering and Electronics2019，30，3： | 4 |
| 10 | Simultaneous Denoising and Interpolation of Seismic Data via the Deep Learning Method显示文摘Utilizing data from controlled seismic sources to image the subsurface structures and invert the physical properties of the subsurface media is a major effort in exploration geophysics. Dense seismic records with high signal-to-noise ratio(SNR) and high fidelity helps in producing high quality imaging results. Therefore, seismic data denoising and missing traces reconstruction are significant for seismic data processing. Traditional denoising and interpolation methods rarely occasioned rely on noise level estimations, thus requiring heavy manual work to deal with records and the selection of optimal parameters. We propose a simultaneous denoising and interpolation method based on deep learning. For noisy records with missing traces, we adopt an iterative alternating optimization strategy and separate the objective function of the data restoring problem into two sub-problems. The seismic records can be reconstructed by solving a least-square problem and applying a set of pre-trained denoising models alternatively and iteratively.We demonstrate this method with synthetic and field data. | GAO Han ZHANG Jie | 2019 | Earthquake Research in China2019，33，1： | 4 |
| 11 | Low-illumination image denoising method for wide-area search of nighttime sea surface显示文摘In order to suppress complex mixing noise in low-illumination images for wide-area search of nighttime sea surface,a model based on total variation(TV)and split Bregman is proposed in this paper.A fidelity term based on L1 norm and a fidelity term based on L2 norm are designed considering the difference between various noise types,and the regularization mixed first-order TV and second-order TV are designed to balance the influence of details information such as texture and edge for sea surface image.The final detection result is obtained by using the high-frequency component solved from L1 norm and the low-frequency component solved from L2 norm through wavelet transform.The experimental results show that the proposed denoising model has perfect denoising performance for artificially degraded and low-illumination images,and the result of image quality assessment index for the denoising image is superior to that of the contrastive models. | 宋明珠 曲宏松 张贵祥 陶淑苹 金光 | 2018 | Optoelectronics Letters2018，14，3： | 3 |
| 12 | Study on Denoising Based on the Wavelet Transform显示文摘The wavelet transform has remarkable advantages and wide applications in denoising because of its characteristic of good time-frequency. Based on the analysis of traditional wavelet denoising methods, which are based on Fourier transform, an improved method is proposed. It overcomes the shortcomings of the traditional Fourier denoising method. In this paper, the denoising procedures are introduced respectively based on the wavelet transform and the method of connecting the wavelet threshold with the wavelet basis is adopted. Through Matlab simulation and concrete data, it arrives at the conclusion that the method of signal denoising based on the wavelet transform is obviously more effective and better than the traditional method based on Fourier transform. | MA Liang HUANG Weizhi XIAO Zhitao | 2010 | Semiconductor Photonics and Technology2010，16，1： | 3 |
| 13 | Denoising for satellite laser altimetry full-waveform data based on EMD-Hurst analysis显示文摘Full-waveform decomposition is crucial for obtaining accurate satelliteground distance,the accuracy of which is severely affected by noises.However,the traditional filters all depend on filtering parameters.This paper presents a new and adaptive method for denoising based on empirical mode decomposition(EMD)and Hurst analysis(EMD-Hurst).The noisy full-waveforms are first decomposed into their intrinsic mode functions(IMFs),and the Hurst exponent of each IMF is established by the detrended fluctuation analysis.The IMF is regarded as the highfrequency noise and is deleted if its Hurst exponent is≤0.5.Both simulated and real full-waveforms were conducted to validate and evaluate the method by comparing with six other IMF selection methods via metrics like waveform decomposition consistency ratio(CR),average error of decomposition parameters,and ICESat/GLAS waveformparameter product GLAH05.The comparisons show that:(1)under different SNR conditions,EMD-Hurst performs robustly and obtains a higher CR than other EMD based methods;(2)obtains the highest average CR and a relatively lower average error for the echo parameters;and(3)peak numbers and fitting accuracy for GLAH01 are more reasonable and precise than those of GLAH05,which could offer a good reference for the processing on future space-borne full-waveform data. | Zhijie Zhang Huan Xie Xiaohua Tong Hanwei Zhang Yang Liu Binbin Li | 2020 | International Journal of Digital Earth2020，13，11： | 3 |
| 14 | Improved Weight Function for Nonlocal Means Image Denoising显示文摘The nonlocal means( NLM) has been widely used in image processing. In this paper,we introduce a modified weight function for NLM denoising, which will compute the nonlocal similarities among the pre-processing pixel patches instead of the commonly used similarity measure based on noisy observations. By the law of large number,the norm for the pre-processing pixel patches is closer to the norm of the original clean pixel patches,so the proposed weight functions are more optimized and the selected similar patches are more accurate. Experimental results indicate the proposed algorithm achieves better restored results compared to the classical NLM's method. | 许建楼 郝岩 | 2018 | Journal of Donghua University(English Edition)2018，35，5： | 2 |
| 15 | Improved Denoising Autoencoder for Maritime Image Denoising and Semantic Segmentation of USV显示文摘Unmanned surface vehicle(USV)is currently a hot research topic in maritime communication network(MCN),where denoising and semantic segmentation of maritime images taken by USV have been rarely studied.The former has recently researched on autoencoder model used for image denoising,but the existed models are too complicated to be suitable for real-time detection of USV.In this paper,we proposed a lightweight autoencoder combined with inception module for maritime image denoising in different noisy environments and explore the effect of different inception modules on the denoising performance.Furthermore,we completed the semantic segmentation task for maritime images taken by USV utilizing the pretrained U-Net model with tuning,and compared them with original U-Net model based on different backbone.Subsequently,we compared the semantic segmentation of noised and denoised maritime images respectively to explore the effect of image noise on semantic segmentation performance.Case studies are provided to prove the feasibility of our proposed denoising and segmentation method.Finally,a simple integrated communication system combining image denoising and segmentation for USV is shown. | Yuhang Qiu Yongcheng Yang Zhijian Lin Pingping Chen Yang Luo Wenqi Huang | 2020 | China Communications2020，17，3： | 2 |
| 16 | An Ensemble Detection Method for Shilling Attacks Based on Features of Automatic Extraction显示文摘Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks. | Yaojun Hao Fuzhi Zhang Jinbo Chao | 2019 | China Communications2019，16，8： | 2 |
| 17 | Risk Index Prediction of Civil Aviation Based on Deep Neural Network显示文摘Safety is the foundation of sustainable development in civil aviation.Although catastrophic accidents are rare,indicators of potential incidents and unsafe events frequently materialize.Therefore,a history of unsafe data are considered in predicting safety risks.A deep learning method is adopted for extracting reactions in safety risks.The deep neural network(DNN)model for safety risk prediction is shown to extract complex data characteristics better than a shallow network model.Using extended unsafe data and monthly risk indices,hidden layers and iterations are determined.The effectiveness of DNN is also revealed in comparison with the traditional neural network.Through early risk detection using the method in the paper,airlines and the government can mitigate potential risk and take proactive measures to improve civil aviation safety. | NI Xiaomei WANG Huawei CHE Changchang | 2019 | Transactions of Nanjing University of Aeronautics and Astronautics2019，36，2： | 2 |
| 18 | Fast Non-Local Means Algorithm Based on Krawtchouk Moments显示文摘Non-local means(NLM)method is a state-of-the-art denoising algorithm, which replaces each pixel with a weighted average of all the pixels in the image. However, the huge computational complexity makes it impractical for real applications. Thus, a fast non-local means algorithm based on Krawtchouk moments is proposed to improve the denoising performance and reduce the computing time. Krawtchouk moments of each image patch are calculated and used in the subsequent similarity measure in order to perform a weighted averaging. Instead of computing the Euclidean distance of two image patches, the similarity measure is obtained by low-order Krawtchouk moments, which can reduce a lot of computational complexity. Since Krawtchouk moments can extract local features and have a good antinoise ability, they can classify the useful information out of noise and provide an accurate similarity measure. Detailed experiments demonstrate that the proposed method outperforms the original NLM method and other moment-based methods according to a comprehensive consideration on subjective visual quality, method noise, peak signal to noise ratio(PSNR), structural similarity(SSIM) index and computing time. Most importantly, the proposed method is around 35 times faster than the original NLM method. | 吴一全 戴一冕 殷骏 吴健生 | 2015 | Transactions of Tianjin University2015，21，2： | 2 |
| 19 | Research on Anti-noise Processing Method of Production Signal Based on Ensemble Empirical Mode Decomposition(EEMD)显示文摘The grain production prediction is one of the most important links in precision agriculture. In the process of grain production prediction, mechanical noise caused by the factors of difference in field topography and mechanical vibration will be mixed in the original signal, which undoubtedly will affect the prediction accuracy. Therefore, in order to reduce the influence of vibration noise on the prediction accuracy, an adaptive Ensemble Empirical Mode Decomposition(EEMD) threshold filtering algorithm was applied to the original signal in this paper: the output signal was decomposed into a finite number of Intrinsic Mode Functions(IMF) from high frequency to low frequency by using the Empirical Mode Decomposition(EMD) algorithm which could effectively restrain the mode mixing phenomenon; then the demarcation point of high and low frequency IMF components were determined by Continuous Mean Square Error criterion(CMSE), the high frequency IMF components were denoised by wavelet threshold algorithm, and finally the signal was reconstructed. The algorithm was an improved algorithm based on the commonly used wavelet threshold. The two algorithms were used to denoise the original production signal respectively, the adaptive EEMD threshold filtering algorithm had significant advantages in three denoising performance indexes of signal denoising ratio, root mean square error and smoothness. The five field verification tests showed that the average error of field experiment was 1.994% and the maximum relative error was less than 3%. According to the test results, the relative error of the predicted yield per hectare was 2.97%, which was relative to the actual yield. The test results showed that the algorithm could effectively resist noise and improve the accuracy of prediction. | Fang Jun-long Yu Xiao-juan Wang Rui-fa Wang Run-tao Li Peng-fei Shao Chang-hui | 2017 | Journal of Northeast Agricultural University(English Edition)2017，24，4： | 2 |
| 20 | Denoising Fault-Aware Wavelet Network:A Signal Processing Informed Neural Network for Fault Diagnosis显示文摘Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et. | Zuogang Shang Zhibin Zhao Ruqiang Yan | 2023 | Chinese Journal of Mechanical Engineering2023，36，1： | 2 |
您所在的机构暂未开通此部分的功能，请联系管理员