The object detection in UAV application is a challenging task due to the diversity of target scales, variation of views and complex backgrounds. To solve several challenges, including dense objects, objects with arbitrary orientation and diversity of aspect ratios, this paper proposes an end-to-end object detection method based on the convolutional neural network. In this paper, the feature extraction performance is enhanced by utilizing a deep residual neural network. Multi-scale feature maps are obtained through fusion with different convolutional layers, thus combining the high-level semantic information and low-level detail information. Rotation Region Proposal Network is adopted to generate rotated regions, which makes the bounding box sensitive to dense objects in aerial images. Meanwhile, the RoIAlign is used and a convolution layer is appended in the classification stage. And Focal loss is used in the classification stage. The proposed method focuses on arbitrary-oriented and dense objects in UAV images. After a comprehensive evaluation with several state-of-the-art object detection algorithms, the proposed method is proved to be effective to detect multi-class artificial objects in aerial images. Extensive experiments are conducted on the DOTA, VEDAI and the VisDrone UAV image datasets, which demonstrate that the proposed method can obtain discriminative features through the improved multi-scale feature extraction and the rotating region network. The results on the above datasets show that our method obtains gains in mAP compared with several state-of-the-art methods.

With the rise in the use of DC distributed energy resources and the growth of DC electricity load, the difficulty in improving DC power quality has become an important research direction. The research on DC power quality has an important impact on the development of DC power distribution theory and technology. In this paper, an evaluation method that combines empirical mode decomposition (EMD) with a one-dimensional convolutional neural network (1D-CNN) of DC power quality is proposed. As a method of data preprocessing, EMD decomposes the original electrical signal into several intrinsic mode functions (IMFs). Then, the 1-D CNN with a residual module is used to train the data obtained from EMD and conducts a comprehensive evaluation with different levels. In addition, the proposed network was compared with other state-of-the-art deep neural networks, and the experiment proved its effectiveness. Finally, an example analysis is carried out with the data provided by the Gree Photovoltaic Direct-driven Inverter Multi VRF (variable refrigerant flow) System to show the validity of the proposed method for evaluating DC power quality in a real case.

Accurate detection of ripple components of the direct-current (DC) signals is essential for evaluating DC power quality. In this study, the combination algorithm based on variational mode decomposition (VMD) and Hilbert transform (HT) is applied to detect and analyze the characteristics of the ripple components of the DC disturbance signals. Firstly, the optimal modal number of VMD algorithms is comprehensively determined by observing the center frequencies of the mode components and the Index of Orthogonality (IO) of mode components. Through utilizing the VMD algorithm, the DC disturbance signal is accurately decomposed into a series of amplitude modulation-frequency modulation (AM-FM) functions. Then, the HT algorithm is applied to each AM-FM function to obtain the corresponding instantaneous amplitude and frequency, and the characteristics of DC disturbance signal are determined. Some case studies are implemented to analyze the ripple components of the DC disturbance signal with the VMD-HT and empirical mode decomposition (EMD) algorithm. Finally, the experiment results of Gree Photovoltaic Cabin have verified the feasibility and effectiveness of the proposed combination VMD-HT algorithm by comparison with EMD and the window interpolation fast Fourier transform (WIFFT) algorithms.