The fault characteristics of the rolling bearings of wind turbine gearboxes are unstable under actual operating conditions. Problems such as inadequate fault sample data, imbalanced data types, and noise labels (error labels) in historical data occur. Consequently, the accuracy of wind turbine gearbox bearing fault diagnosis under actual operating conditions is insufficient. Hence, a new method for the fault diagnosis of wind turbine gearbox bearings under actual operating conditions is proposed. It uses an improved label-noise robust auxiliary classifier generative adversarial network (rAC-GAN) driven by the limited data. The improved rAC-GAN realizes a batch comparison between the generated and real data to ensure the quality of the generated data and improve the generalization capability of the model in scenarios of actual operating conditions. It can be used to generate a large number of multitype fault data that satisfy the characteristics of the probability distribution of real samples and display higher robustness to label noises. Experiments indicate that, compared with other methods, the new method exhibits a higher accuracy in the multistate classification of rolling bearings under actual operating conditions when driven by the limited data with noise labels.

Fault Diagnosis of Bearing in Wind Turbine Gearbox Under Actual Operating Conditions Driven by Limited Data With Noise Labels

Most of existing compression artifacts reduction methods focused on the application for low-quality images and usually assumed a known compression quality factor. However, images compressed with high quality should also be manipulated because even small artifacts become noticeable when we enhance the compressed image. Also, the use of quality factor from the decoder is not practical because there are too many recompressed or transcoded images whose quality factor are not reliable and spatially varying. To address these issues, we propose a quality-adaptive artifacts removal network based on the gating scheme, with a quality estimator that works for a wide range of quality factor. Specifically, the estimator gives a pixel-wise quality factor, and our gating scheme generates gate-weights from the quality factor. Then, the gate-weights control the magnitudes of feature maps in our artifacts removal network. Thus, our gating scheme guarantees the proposed network to perform adaptively without changing the parameters according to the change of quality factor. Moreover, we exploit the Discrete Cosine Transform (DCT) scheme with 3D convolution for capturing both spatial and frequency dependencies of images. Experiments show that the proposed network provides better performance than the state-of-the-art methods over a wide range of quality factor. Also, the proposed method provides robust results in real-world scenarios such as the manipulation of transcoded images and videos.

/pdf/agarnet-adaptively-gated-jpeg-compression-artifacts-removal-1hoyzyulhb.pdf

AGARNet: Adaptively Gated JPEG Compression Artifacts Removal Network for a Wide Range Quality Factor

Although image denoising as a basic task of image restoration has been widely studied in the past decades, there are not many studies on mixed noise denoising. In this paper, we propose two structured dictionary learning models to recover images corrupted by mixed Gaussian and impulse noise. These two models can be merged as $\ell _{p}$ -norm fidelity plus $\ell _{q}$ -norm regularization. The fidelity term is used to fit image patches and the regularization term is employed for sparse coding. Particularly, we utilize proximal (and proximal linearized) alternating minimization methods as the main solvers to deal with these two models. We remove the Gaussian noise under the assumption that the uncorrupted image can be approximated with a linear representation under an appropriate orthogonal basis. We use different ways to remove impulse noise for these two models. The experimental results are reported to compare the existing methods and demonstrate the performance of the proposed denoising model is better than the other existing methods in terms of some quality assessment metrics.

Structured Dictionary Learning for Image Denoising Under Mixed Gaussian and Impulse Noise

Noise reduction is one of the most important and still active research topics in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we observed a substantially increased interest in the application of deep learning algorithms. Many computer vision systems use them, due to their impressive capability of feature extraction and classification. While these methods have also been successfully applied in image denoising, significantly improving its performance, most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering technique intended for impulsive noise removal using deep learning. In the proposed method, the distorted pixels are detected using a deep neural network architecture and restored with the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in color digital images.

Deep Learning Based Switching Filter for Impulsive Noise Removal in Color Images.

A two-stage denoising algorithm based on local similarity is proposed to process lowly and moderate corrupted images with random-valued impulse noise in this paper. In the noise detection stage, the pixel to be detected is centered and the local similarity between the pixel and each pixel in its neighborhood is calculated, which can be used as the probability that the pixel is noise. By obtaining the local similarity of each pixel in the image and setting an appropriate threshold, the noise pixels and clean pixels in the damaged image can be detected. In the image restoration stage, an improved bilateral filter based on local similarity and geometric distance is designed. The pixel detected as noise in the first stage is filtered and the new intensity value is the weighted average of all pixel intensities in its neighborhood. A large number of experiments have been conducted on different test images and the results show that compared with the mainstream denoising algorithms, the proposed method can detect and filter out the random-value impulse noise in the image more effectively and faster, while better retaining the edges and other details of the image.

/pdf/a-two-stage-algorithm-for-the-detection-and-removal-of-4cliv14bxw.pdf

A Two-Stage Algorithm for the Detection and Removal of Random-Valued Impulse Noise Based on Local Similarity

Denoising convolutional neural networks (DnCNNs), initially developed for Gaussian noise removal, are powerful nonlinear mapping models in image processing. After changes in training data, they can be used for suppression of random-valued impulse noise (RVIN) with excellent results. To achieve favorable denoising performance, however, it is necessary to have an accurate perception of the noise ratio so that the most suitable DnCNN can be chosen for denoising. Thus, this model is severely limited in flexibility. To address this problem, we propose a blind CNN model for RVIN denoising with a flexible noise ratio predictor (NRP) as an indicator. Some patches are randomly selected from the RVIN-corrupted test image, and feature vectors that indicate whether the center pixel is contaminated or not are extracted by the predictor. These feature vectors are composed of multiple statistics, namely, the multiple rank-ordered absolute differences (ROADs), the clean pixel median deviation (CPMD), and the edge pixel difference (EPD). They are rapidly mapped to noise/clean (1 for noise, 0 for clean) labels by the pre-trained noise detector (the key component of our NRP). According to the ratio of the obtained noisy labels to the total number of selected patches, the predictor provides the noise ratio of the whole image. From the output of the NRP, i.e., the predicted noise ratio, the most appropriate DnCNN specifically trained for this noise ratio is exploited for denoising. Under the guidance of the NRP, the proposed method has the ability to handle unknown noise ratios. Simulation results indicate that our blind denoising CNN model achieves state-of-the-art performance in terms of both execution efficiency and restoration results.

/pdf/a-blind-cnn-denoising-model-for-random-valued-impulse-noise-35ba0ik445.pdf

Guizhen Zhang

Papers

A Blind CNN Denoising Model for Random-Valued Impulse Noise