This article proposes an end-to-end method based on an improved convolutional neural network model for inverter fault diagnosis. First, transient time-domain sequence data under different faults are ...analyzed, and raw signals are taken as fault representations without manually selecting feature extraction methods. Second, the model can automatically learn and extract features in the input domain using stacked convolution layers with the wide first-layer convolution kernel and a global max pooling layer; thus, it eliminated the influence of expert experience. Finally, the fault diagnosis results of the three-phase voltage-source inverter are automatically obtained in the softmax layer. The proposed fault diagnosis method has superior recognition performance with mixed noise data and variable load data. Contrastive experiments show that the improved fault diagnosis model is effective than traditional machine learning and other deep learning methods.
Domain adaptation studies learning algorithms that generalize across source domains and target domains that exhibit different distributions. Recent studies reveal that deep neural networks can learn ...transferable features that generalize well to similar novel tasks. However, as deep features eventually transition from general to specific along the network, feature transferability drops significantly in higher task-specific layers with increasing domain discrepancy. To formally reduce the effects of this discrepancy and enhance feature transferability in task-specific layers, we develop a novel framework for deep adaptation networks that extends deep convolutional neural networks to domain adaptation problems. The framework embeds the deep features of all task-specific layers into reproducing kernel Hilbert spaces (RKHSs) and optimally matches different domain distributions. The deep features are made more transferable by exploiting low-density separation of target-unlabeled data in very deep architectures, while the domain discrepancy is further reduced via the use of multiple kernel learning that enhances the statistical power of kernel embedding matching. The overall framework is cast in a minimax game setting. Extensive empirical evidence shows that the proposed networks yield state-of-the-art results on standard visual domain-adaptation benchmarks.
Aiming at fault visualization and automatic feature extraction, this article presents a new and intelligent bearing fault diagnostic method by combining symmetrized dot pattern (SDP) representation ...with squeeze-and-excitation-enabled convolutional neural network (SE-CNN) model. Graphical representations of bearing states are shown intuitively by using the SDP method. Meanwhile, optimal parameters during SDP images' generation are selected to enhance the image resolution for distinctly distinguishing different bearing states and create the corresponding bearing fault sample sets. To automatically and effectively extract SDP image features, the channel attention mechanism using the SE network is integrated with the CNN network. The proposed SE-CNN-based diagnostic framework has the ability to assign certain weight to each feature extraction channel and further enforce the bearing diagnosis model focusing on the major features, meanwhile reducing the redundant information. The final diagnosis task is realized by the Softmax classifier located behind the SE-CNN model. Experimental results prove that the proposed method not only achieves the classification rate over 99% but also has better generalization ability and stability.
Rapidly random-exploring tree (RRT) and its variants are very popular due to their ability to quickly and efficiently explore the state space. However, they suffer sensitivity to the initial solution ...and slow convergence to the optimal solution, which means that they consume a lot of memory and time to find the optimal path. It is critical to quickly find a short path in many applications such as the autonomous vehicle with limited power/fuel. To overcome these limitations, we propose a novel optimal path planning algorithm based on the convolutional neural network (CNN), namely the neural RRT* (NRRT*). The NRRT* utilizes a nonuniform sampling distribution generated from a CNN model. The model is trained using quantities of successful path planning cases. In this article, we use the A* algorithm to generate the training data set consisting of the map information and the optimal path. For a given task, the proposed CNN model can predict the probability distribution of the optimal path on the map, which is used to guide the sampling process. The time cost and memory usage of the planned path are selected as the metric to demonstrate the effectiveness and efficiency of the NRRT*. The simulation results reveal that the NRRT* can achieve convincing performance compared with the state-of-the-art path planning algorithms. Note to Practitioners -The motivation of this article stems from the need to develop a fast and efficient path planning algorithm for practical applications such as autonomous driving, warehouse robot, and countless others. Sampling-based algorithms are widely used in these areas due to their good scalability and high efficiency. However, the quality of the initial path is not guaranteed and it takes much time to converge to the optimal path. To quickly obtain a high-quality initial path and accelerate the convergence speed, we propose the NRRT*. It utilizes a nonuniform sampling distribution and achieves better performance. The NRRT* can be also applied to other sampling-based algorithms for improved results in different applications.
As an important task in the field of remote sensing image processing, remote sensing image change detection (CD) has made significant advances through the use of convolutional neural networks (CNN). ...The Transformer has recently been introduced into the field of CD due to its excellent global perception capabilities. Some works have attempted to combine CNN and Transformer to jointly harvest local-global features. However, these works have not paid much attention to the interaction between the features extracted by both. Also, the use of the Transformer has resulted in significant resource consumption. In this paper, we propose the Asymmetric Cross-attention Hierarchical Network (ACAHNet) by combining CNN and Transformer in a series-parallel manners. The proposed Asymmetric Multi-headed Cross Attention (AMCA) module reduces the quadratic computational complexity of the Transformer to linear, and the module enhances the interaction between features extracted from the CNN and the Transformer. Different from the early and late fusion strategies employed in previous work, the effectiveness of the mid-term fusion strategy employed by ACAHNet shows a new choice of timing for feature fusion in the CD task. Our experiments on the proposed method on three public datasets show that our network has better performance in terms of effectiveness and computational resource consumption compared to other comparative methods.
Deep convolutional neural networks (CNNs) have achieved remarkable results in image processing tasks. However, their high expression ability risks overfitting. Consequently, data augmentation ...techniques have been proposed to prevent overfitting while enriching datasets. Recent CNN architectures with more parameters are rendering traditional data augmentation techniques insufficient. In this study, we propose a new data augmentation technique called random image cropping and patching ( RICAP ) which randomly crops four images and patches them to create a new training image. Moreover, RICAP mixes the class labels of the four images, resulting in an advantage of the soft labels. We evaluated RICAP with current state-of-the-art CNNs (e.g., the shake-shake regularization model) by comparison with competitive data augmentation techniques such as cutout and mixup. RICAP achieves a new state-of-the-art test error of 2.19% on CIFAR-10. We also confirmed that deep CNNs with RICAP achieve better results on classification tasks using CIFAR-100 and ImageNet, an image-caption retrieval task using Microsoft COCO, and other computer vision tasks.
Increasing availability of data related to air quality from ground monitoring stations has provided the chance for data mining researchers to propose sophisticated models for predicting the ...concentrations of different air pollutants. In this paper, we proposed a hybrid model based on deep learning methods that integrates Graph Convolutional networks and Long Short-Term Memory networks (GC-LSTM) to model and forecast the spatiotemporal variation of PM
concentrations. Specifically, historical observations on different stations are constructed as spatiotemporal graph series, and historical air quality variables, meteorological factors, spatial terms and temporal attributes are defined as graph signals. To evaluate the performance of the GC-LSTM, we compared our results with several state-of-the-art methods in different time intervals. Based on the results, our GC-LSTM model achieved the best performance for predictions. Moreover, evaluations of recall rate (68.45%), false alarm rate (4.65%) (both of threshold: 115 μg/m
) and correlation coefficient R
(0.72) for 72-hour predictions also verify the feasibility of our proposed model. This methodology can be used for concentration forecasting of different air pollutants in future.
The trade-off between feature representation power and spatial localization accuracy is crucial for the dense classification/semantic segmentation of remote sensing images (RSIs). High-level features ...extracted from the late layers of a neural network are rich in semantic information, yet have blurred spatial details; low-level features extracted from the early layers of a network contain more pixel-level information but are isolated and noisy. It is therefore difficult to bridge the gap between high- and low-level features due to their difference in terms of physical information content and spatial distribution. In this article, we contribute to solve this problem by enhancing the feature representation in two ways. On the one hand, a patch attention module (PAM) is proposed to enhance the embedding of context information based on a patchwise calculation of local attention. On the other hand, an attention embedding module (AEM) is proposed to enrich the semantic information of low-level features by embedding local focus from high-level features. Both proposed modules are lightweight and can be applied to process the extracted features of convolutional neural networks (CNNs). Experiments show that, by integrating the proposed modules into a baseline fully convolutional network (FCN), the resulting local attention network (LANet) greatly improves the performance over the baseline and outperforms other attention-based methods on two RSI data sets.
Due to the complexity of the actual operating conditions of lithium-ion batteries, accurately estimating their state-of-health (SOH) often requires a significant amount of battery data, but most of ...the current SOH estimation methods lack generalizability. To address this issue, this article proposes a meta-learning SOH estimation method, which combines the meta-learning model with the convolutional neural network with a long short-term memory model to improve the generalization of lithium-ion battery SOH estimation. It not only possesses better generalization ability but also has higher estimation accuracy. In addition, regardless of the four different types of CALCE datasets or lithium-ion battery datasets in the laboratory, the maximum root-mean-square error and mean absolute error of the proposed method is 2.31% and 2.03%, which indicates the good performance of the proposed method for SOH estimation. Compared with two prevalent deep learning methods, this method enhances the estimation accuracy by an average of 25% across different battery data.
Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN), such as Graph Attention Networks (GAT), are two classic neural network models, which are applied to the processing of grid data ...and graph data respectively. They have achieved outstanding performance in hyperspectral images (HSIs) classification field, which have attracted great interest. However, CNN has been facing the problem of small samples and GNN has to pay a huge computational cost, which restrict the performance of the two models. In this paper, we propose Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network (WFCG) for HSI classification, by using the characteristics of superpixel-based GAT and pixel-based CNN, which proved to be complementary. We first establish GAT with the help of superpixel-based encoder and decoder modules. Then we combined the attention mechanism to construct CNN. Finally, the features are weighted fusion with the characteristics of two neural network models. Rigorous experiments on three real-world HSI data sets show WFCG can fully explore the high-dimensional feature of HSI, and obtain competitive results compared to other state-of-the art methods.