Residual Convolution Research Articles

A Signal Generation Fault Diagnosis Method for Planetary Reducer of High‐Pressure Grinding Roll

ABSTRACTThis paper proposes a signal generation fault diagnosis method for the challenge of insufficient training samples in the planetary reducer of high‐pressure grinding roll (HPGR). The expression of the vibration response signal is derived, and a fault vibration signal model is established for the planetary reducer of HPGR. To generate the expanded samples, an adaptive fox optimization (AFO) algorithm is employed for optimizing the parameters of the fault vibration signal model, so that the simulated signal matches the measured signal. Before that, the measured vibration signal of the planetary reducer of HPGR is preprocessed by a tunable Q‐factor wavelet transform (TQWT). Finally, the residual convolution neural and long short‐term memory network with attention mechanism (ResCNN‐LSTM‐ATT) is utilized for feature extraction from collected signals, and the hierarchical fault classifier is developed for the fault classification. The experimental results show that the AFO algorithm has better performance, and the signals generated by the optimized fault vibration signal model are in good agreement with the measured signals. The classification accuracy of normal signals reaches 99.70%, which shows good diagnosis accuracy in both known fault classification and unknown fault identification. Compared to other methods, the proposed method has better diagnostic accuracy.

Semantic Web-Based Image Super-Resolution for Enhanced Steel Surface Defect Detection

This study addresses the challenges of steel surface defect detection by introducing the ATG-SRGAN model, which integrates Semantic Web technologies with an Adaptive Transformer and Generation module. By leveraging self-attention mechanisms and residual convolution within the SRGAN framework, the model enhances image resolution, reduces noise, and uncovers finer details, achieving superior PSNR (37.17) and SSIM (0.9590) metrics. Integrated with an improved YOLOv8-ghost-p2 framework, the model also attains a mean Average Precision (mAP) of 81.2 and a recall rate of 76 in defect detection. These results demonstrate the model's potential to significantly improve automated quality control in industrial settings, highlighting the importance of Semantic Web technologies in advancing defect detection methods.

A lightweight hybrid model-based condition monitoring method for grinding wheels using acoustic emission signals

Abstract Various data-driven methods based on acoustic emission (AE) signals have been proposed to monitor and accurately identify the wear stages of the grinding wheel. However, extracting effectively generalized and discriminative features from AE signals remains a challenging task. This paper proposes a new lightweight hybrid deep learning model that combines enhanced convolution with enhanced vision transformer to effectively address the above challenges. Specifically, the key contributions of this paper are three-fold: (1) A two-stage signal preprocessing mechanism based on variational mode decomposition and continuous wavelet transform is proposed to improve the signal-to-noise ratio and feature representation of the AE signals. (2) To prevent model overfitting, a new regularization strategy based on stabilizing sparse convolutional weights and a weight penalty mechanism is designed. This approach improves the hybrid mode’s capacity to extract generalized features. (3) To concentrate on capturing multi-scale discriminative features between different wear conditions, a parameter-efficient residual convolution module based on the dropout depthwise convolution is designed, which is utilized to reconstruct the encoder of the vision transformer. In particular, to improve the training efficiency of the model, a lightweight mechanism using a stage-stride decreasing strategy is used to compress the spatial dimensions of the feature maps in the attention mechanism. The ablation experiment demonstrates the rationality of the proposed model structure. Comparative experiments show that the proposed method achieves a diagnostic accuracy of 99.6% on the test set and outperforms other state-of-the-art deep learning methods.

RlaNet: A Residual Convolution Nested Long-Short-Term Memory Model with an Attention Mechanism for Wind Turbine Fault Diagnosis

This paper proposes a new fault diagnosis model for wind power systems called residual convolution nested long short-term memory network with an attention mechanism (rlaNet). The method first preprocesses the SCADA data through feature engineering, uses the Hermite interpolation method to handle missing data, and uses the mutual information-based dimensionality reduction technique to improve data quality and eliminate redundant information. rlaNet combines residual networks and nested long short-term memory networks to replace traditional convolutional neural networks and standard long short-term memory architectures, thereby improving feature extraction and ensuring the abstractness and depth of the extracted features. In addition, the model emphasizes the weighted learning of spatiotemporal features in the input data, enhances the focus on key features, and improves training efficiency. Experimental results show that rlaNet achieves an accuracy of more than 90% in wind turbine fault diagnosis, showing good robustness. Furthermore, noise simulation experiments verify the model’s resistance to interference, providing a reliable solution for wind turbine fault diagnosis under complex operating conditions.

Remaining Useful Life Prediction of Bearings Using Reverse Attention Graph Convolution Network With Residual Convolution Transformer

Remaining Useful Life Prediction of Bearings Using Reverse Attention Graph Convolution Network With Residual Convolution Transformer

EGCNet: a hierarchical graph convolutional neural network for improved classification of electrocardiograms

The automatic classification of electrocardiograms (ECGs) plays a crucial role in the early diagnosis of cardiovascular diseases. In recent research, deep neural network (DNN)-based methods have garnered significant attention due to their exceptional feature extraction capabilities. However, these methods face challenges in dealing with the complex inter- and intra-class dependencies inherent in different arrhythmias. We propose a classification model for electrocardiograms based on the Graph Convolutional Neural Network (EGCNet) to address this. In our EGCNet framework, we first employ the row and column 1-dimensional residual convolution to learn intra-class dependency. Then, we construct a hierarchical graph structure to model the inter-class dependency. In such a graph, each node represents one type of disease, and the edges describe the relationship between diseases. To reduce the complexity of inter-class dependency, we build a hierarchical graph structure by treating similar nodes as the same type. Thus, we can learn the discriminant dependency in the higher-level graph space and feed this high-level knowledge back to the lower-level graph space. Finally, we evaluated our method using publicly available datasets from the PhysioNet/Computing Challenge 2020 ECG data. For instance, our model achieved robust performance in the 24-label experiment with a precision of 0.753 and an F1 score of 0.722.

A method for recognizing abnormal behaviors of personnel at petroleum stations based on GTB-ResNet

PurposeThe abnormal behaviors of staff at petroleum stations pose significant safety hazards. Addressing the challenges of high parameter counts, lengthy training periods and low recognition rates in existing 3D ResNet behavior recognition models, this paper proposes GTB-ResNet, a network designed to detect abnormal behaviors in petroleum station staff.Design/methodology/approachFirstly, to mitigate the issues of excessive parameters and computational complexity in 3D ResNet, a lightweight residual convolution module called the Ghost residual module (GhostNet) is introduced in the feature extraction network. Ghost convolution replaces standard convolution, reducing model parameters while preserving multi-scale feature extraction capabilities. Secondly, to enhance the model's focus on salient features amidst wide surveillance ranges and small target objects, the triplet attention mechanism module is integrated to facilitate spatial and channel information interaction. Lastly, to address the challenge of short time-series features leading to misjudgments in similar actions, a bidirectional gated recurrent network is added to the feature extraction backbone network. This ensures the extraction of key long time-series features, thereby improving feature extraction accuracy.FindingsThe experimental setup encompasses four behavior types: illegal phone answering, smoking, falling (abnormal) and touching the face (normal), comprising a total of 892 videos. Experimental results showcase GTB-ResNet achieving a recognition accuracy of 96.7% with a model parameter count of 4.46 M and a computational complexity of 3.898 G. This represents a 4.4% improvement over 3D ResNet, with reductions of 90.4% in parameters and 61.5% in computational complexity.Originality/valueSpecifically designed for edge devices in oil stations, the 3D ResNet network is tailored for real-time action prediction. To address the challenges posed by the large number of parameters in 3D ResNet networks and the difficulties in deployment on edge devices, a lightweight residual module based on ghost convolution is developed. Additionally, to tackle the issue of low detection accuracy of behaviors amidst the noisy environment of petroleum stations, a triple attention mechanism is introduced during feature extraction to enhance focus on salient features. Moreover, to overcome the potential for misjudgments arising from the similarity of actions, a Bi-GRU model is introduced to enhance the extraction of key long-term features.

Judicial decision prediction using an integrated attention based bidirectional long-short term memory and dilated skip residual convolution neural network

Judicial decision prediction using an integrated attention based bidirectional long-short term memory and dilated skip residual convolution neural network

CosGCTFormer: An end-to-end driver state recognition framework

Driver state is critical for safety in mixed traffic environments with automated and human-driven vehicles. Recognizing and monitoring the driver’s state is essential to provide early warnings of abnormal driving performance. This paper proposes a driver state recognition framework called cosGCTFormer for end-to-end recognition of the driver’s emotional state and mental load. First, we employ an inverted residual convolution module to extract local features from physiological signal data. Second, the cosGCT module is introduced to extract global features. This module uses cos attention to address the high computational complexity of the Transformer in calculating attention weights. Additionally, it employs Gated Channel Transformation (GCT) to establish relationships between different channel dimensions, something the Transformer alone cannot do effectively. Finally, a simulated driving experiment was designed to collect data for training and testing the proposed method. Results demonstrate that our framework achieves higher accuracy and a more lightweight design compared to prevalent Convolution neural network-based (CNN-based) and Transformer-based methods. Additionally, the effectiveness of both modules was verified.

Global and local feature extraction based on convolutional neural network residual learning for MR image denoising.

Given the different noise distribution information of global and local magnetic resonance (MR) images, this study aims to extend the current work on convolutional neural networks that preserve global structure and local details in MR image denoising tasks. This study proposed a parallel and serial network for denoising 3D MR images, called 3D-PSNet. We use the residual depthwise separable convolution block to learn the local information of the feature map, reduce the network parameters, and thus improve the training speed and parameter efficiency. In addition, we consider the feature extraction of the global image and utilize residual dilated convolution to process the feature map to expand the receptive field of the network and avoid the loss of global information. Finally, we combine both of them to form a parallel network. What's more, we integrate reinforced residual convolution blocks with dense connections to form serial network branches, which can remove redundant information and refine features to further obtain accurate noise information. The peak signal-to-noise ratio, structural similarity index measure, and root mean square error metrics of 3D-PSNet are as high as 47.79%, 99.81%, and 0.40%, respectively, achieving competitive denoising effect on three public datasets. The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets. The proposed 3D-PSNet takes advantage of multi-scale receptive fields, local feature extraction and residual dense connections to more effectively restore the global structure and local fine features in MR images, and is expected to help doctors quickly and accurately diagnose patients' conditions.

A lightweight parallel attention residual network for tile defect recognition

In modern industrial production, permanent magnet motors are an indispensable part of industrial manufacturing. The quality of the magnetic tiles directly affects the working performance of the permanent magnet motors, making the detection of defects on the surface of magnetic tiles critically important. However, due to the small size of defects on the tile image and the reflectivity of the defective surface, the details of image characteristics are not prominently acquired.These problems bring a lot of difficulties for the recognition of magnetic tile defects. In this paper, a magnetic tile defect detection method is proposed for the probAlems of unclear image features and small defects. First, the image is processed using linear variation to enhance the image detail features. Then, by introducing the inverted bottleneck block structure in MobileNetV2, the Attention Parallel Residual Convolution Block (APR) is proposed, and the Lightweight Parallel Attention Residual Network (LPAR-Net) is built. In APR Block, 7 × 7 convolution is introduced so that the model can extract spatial features from a larger range, and weighted fusion of input images by residual structure. In addition, in this paper, CBAM is improved, split into two parts and inserted into APR Block. Finally, the mainstream image classification models and the LPAR-Net proposed in this paper are used for comparison, respectively. The experimental results show that the method achieves 93.63% accuracy on the adopted dataset, which is better than the existing mainstream image classification network models DenseNet, MobileNet, ConvNext and so on. In addition, this paper introduces a strip steel surface defect dataset and compares it with the above image classification model, which verifies that the detection method proposed in this paper still has strong recognition capability.

Dental Caries Segmentation using Deformable Dense Residual Half U-Net for Teledentistry System

Clinical practitioners’ workload and challenges are significantly reduced by classifying, predicting, and localizing lesions or dental caries. In recent research, a high-reliability diagnostic system within deep learning models has been implemented in a clinical teledentistry system. In order to construct an efficient, precise, and lightweight deep learning architecture, it is dynamically structured. In this paper, we present an efficient, accurate, and lightweight deep learning architecture for augmenting spatial locations and improving the transformation modeling abilities of fixed-structure CNNs. Deformable Dense Residual (DDR) enhances the efficacy of the residual convolution block by optimizing its structure, thereby mitigating model redundancy and ameliorating the challenge of vanishing gradients encountered during the training stages. DDR Half U-Net presents notable advancements to the simplified U-Net framework across three pivotal domains: the encoder, decoder, and loss function. Specifically, the encoder integrates deformable convolutions, thereby enhancing the model's capacity to discern features of diverse scales and configurations. In the decoder, a sophisticated arrangement of dense residual connections facilitates the fusion of low-level and high-level features, contributing to comprehensive feature extraction. Moreover, the utilization of a weight-adaptive loss function ensures equitable consideration of both caries and non-caries samples, thereby promoting balanced optimization during training.

A Novel Network for Low-Dose CT Denoising Based on Dual-Branch Structure and Multi-Scale Residual Attention.

Deep learning-based denoising of low-dose medical CT images has received great attention both from academic researchers and physicians in recent years, and has shown important application value in clinical practice. In this work, a novel two-branch and multi-scale residual attention-based network for low-dose CT image denoising is proposed. It adopts a two-branch framework structure, to extract and fuse image features at shallow and deep levels respectively, to recover image texture and structure information as much as possible. We propose the adaptive dynamic convolution block (ADCB) in the local information extraction layer. It can effectively extract the detailed information of low-dose CT denoising and enables the network to better capture the local details and texture features of the image, thereby improving the denoising effect and image quality. Multi-scale edge enhancement attention block (MEAB) is proposed in the global information extraction layer, to perform feature fusion through dilated convolution and a multi-dimensional attention mechanism. A multi-scale residual convolution block (MRCB) is proposed to integrate feature information and improve the robustness and generalization of the network. To demonstrate the effectiveness of our method, extensive comparison experiments are conducted and the performances evaluated on two publicly available datasets. Our model achieves 29.3004 PSNR, 0.8659 SSIM, and 14.0284 RMSE on the AAPM-Mayo dataset. It is evaluated by adding four different noise levels σ = 15, 30, 45, and 60 on the Qin_LUNG_CT dataset and achieves the best results. Ablation studies show that the proposed ADCB, MEAB, and MRCB modules improve the denoising performances significantly. The source code is available at https://github.com/Ye111-cmd/LDMANet .

Combining optical flow and Swin Transformer for Space-Time video super-resolution

Space–time video super-resolution is a task that aims to interpolate low frame rate, low resolution videos to high frame rate, high resolution ones. While existing Transformer-based methods have achieved results comparable to convolutional neural networks-based methods, the computational cost of Transformer limits its performance with constrained computational resources. Moreover, Swin Transformer may fail to fully exploit the spatio-temporal information of video frames due to the limitation of window size, impeding its effectiveness in handling large motions. To address these limitations, we propose an end-to-end space–time video super-resolution architecture based on optical flow alignment and Swin Transformer. The alignment module is introduced to extract spatio-temporal information from adjacent frames without significantly increasing the computational burden. Additionally, we design a residual convolution layer to enhance the translational invariance of the features extracted by Swin Transformer and introduces additional nonlinear transformations. Experimental results demonstrate that our proposed method achieves superior performance on various benchmark datasets compared to state-of-the-art methods. In terms of Peak Signal-to-Noise Ratio, our method outperforms the state-of-the-art methods by at least 0.15 dB on Vimeo-Medium dataset.

Brain Emotion Perception Inspired EEG Emotion Recognition With Deep Reinforcement Learning.

Inspired by the well-known Papez circuit theory and neuroscience knowledge of reinforcement learning, a double dueling deep Q network (DQN) is built incorporating the electroencephalogram (EEG) signals of the frontal lobe as prior information, which is named frontal lobe double dueling DQN (FLD3QN). The framework of FLD3QN is constructed in accord with the brain emotion mechanism which takes the frontal lobe and the thalamus as the core, in which the part of the Papez circuit is simulated by the bifrontal lobe residual convolution neural network (BiFRCNN). Moreover, a step penalty factor is designed to constrain the number of mistakes of the agent. The ablation studies results on the public EEG emotion dataset DEAP verified the important roles of the frontal lobe and the Papez circuit in modeling the procedure of learning rewards during the perception of emotions, with a great increase in the average accuracies by 25.24% and 23.31% in valence and arousal dimensions.

MRCNN: Multi-input residual convolution neural network for three-dimensional reconstruction of bubble flows from light field images

Accurate measurement of bubbles in air-water two-phase flows holds immense significance in the realm of thermal hydraulics assessments within nuclear reactors. Nevertheless, conventional bubble measurement techniques grapple with challenges encompassing system intricacy, limited real-time capabilities, and inaccuracies stemming from their inherent two-dimensional (2-D) nature. In response, we pioneered an innovative three-dimensional (3-D) analysis approach that leverages light field (LF) imaging diagnosis and deep learning algorithms. Unlike traditional 2-D reconstruction methods, our approach enables direct computation of bubble depth from LF images using digital refocusing technology. Following calibration, a seamless transformation is established between the camera coordinate system and the real-world coordinate system using a sharpness evaluation algorithm. This calibration process ensures precise alignment of refocused images with real-world positions. Subsequently, fully automated and highly accurate computations of bubble depth are realized from input images via the incorporation of a multi-input residual convolution neural network (MRCNN). The limitations of traditional two-dimensional imaging techniques are effectively addressed by this methodology, resulting in a reduction in measurement errors. The study confirms the feasibility of employing LF imaging diagnosis and deep learning algorithms for bubble measurements in an air-water two-phase flow, offering a significant improvement over traditional methods.

FCT-Net: A dual-encoding-path network fusing atrous spatial pyramid pooling and transformer for pavement crack detection

Cracks are a typical form of road damage, and accurate detection of cracks is of great significance for road maintenance work and ensuring traffic safety. Recently, computer vision has gradually been applied in the field of crack segmentation. However, there are still some extremely challenging problems in crack segmentation, such as complex backgrounds, information loss caused by pooling and convolution operations, and insufficient fusion of global and local semantic information. In response to the above problems, this paper proposes a dual-encoding-path network with U-Net architecture called FCT-Net, by fusing channel atrous spatial pyramid pooling (CASPP) and transformer. Specifically, CASPP obtains multi-scale receptive fields by incorporating spatial and channel attention, while refining and extracting local features. Meanwhile, we introduce long-short distance attention to construct a novel transformer with the prominent characteristic of interaction between local and global attention features. In addition, a residual convolution module is designed to enhance the local features of the transformer. Furthermore, we devise a multi-scale attention weight cross fusion module to aggregate the features of the dual encoding branch, for reducing information loss during downsampling and suppress background information. Eventually, we evaluate the performance of FCT-Net by experiments on three public datasets. Extensive experimental results show that FCT-Net achieves higher F1-score and mean intersection over union (mIoU) than state-of-the-art segmentation networks on the DeepCrack537 and CrackLS315 datasets. Meanwhile, it has excellent segmentation performance for cracks in complex scenes, with the highest recall, F1-score, and mIoU respectively as 85.64%, 81.67%, and 84.05% on the CrackTree260 dataset.

Intelligent mechanical fault diagnosis using multiscale residual network and multisensor fusion

Abstract Mechanical faults in manufacturing systems need to be diagnosed accurately to ensure safety and cost savings. With the development of sensor technologies, data from multiple sensors is frequently utilized to assess the health of intricate industrial systems. In such cases, it is necessary to study the multisensor data based intelligent mechanical fault diagnosis method. First, the multisensor data is converted into grey images and then fused into a three-channel red-green-blue (RGB) image. Then, a multiscale with residual convolution module is proposed, which can extract multiscale deep features of the complex raw signal. Additionally, an attention module for channel and spatial attention is introduced to adaptively adjust the feature response values of each scale. Two datasets and a specific engineering application are used to validate the superiority of the network. The results show that the multisensor multiscale residual network outperforms other fault diagnosis networks in terms of fault identification accuracy, diagnostic efficiency, and applicability.

Video frame interpolation based on depthwise over-parameterized recurrent residual convolution

Video frame interpolation based on depthwise over-parameterized recurrent residual convolution

A multi-scale attention mechanism for detecting defects in leather fabrics

Defect detection is critical to industrial quality control in leather production engineering. The various sizes and locations of defects in leather, as well as significant differences within the same class and indistinctive variations between different classes of defects, contribute to the complexity of the problem. To address this challenge, we propose a Multi-Layer Residual Convolutional Attention (MLRCA) approach. MLRCA enhances its ability to capture both intra-class and inter-class differences by enhancing the semantic feature representation in the backbone network. To improve multiscale fusion effects, we also incorporate the MLRCA module into the feature pyramid network (FPN) and propose a new multi-layer residual convolution attention feature pyramid network (ML-FPN). This approach enables more accurate identification of leather defects at a more detailed level by selectively capturing contextual information from different domains. We then implement the Side-Aware Boundary Localization (SABL) detection head, which accurately locates defects and helps the network distinguish between similar defect categories for more precise positioning. To validate the effectiveness of our approach, we conducted ablation experiments on the created leather dataset. Comparative experiments demonstrate the excellent capability of our model to detect minor defects. The model achieved 83.4, 89.7, and 85.6 for the AP, AP50, and AP75 evaluation metrics. In addition, the model achieves 71.3, 89.9, and 88.9 for APS, APM, and APL. Our approach has been confirmed feasible through experimentation and provides new insights for automated leather defect detection methods.