Research on lung cancer automatic detection using deep learning algorithms has achieved good results but, due to the complexity of tumor edge features and possible changes in tumor positions, it is still a great challenge to diagnose patients with lung tumors based on computed tomography (CT) images. In order to solve the problem of scales and meet the requirements of real-time detection, an efficient one-stage model for automatic lung tumor detection in CT Images, called ELCT-YOLO, is presented in this paper. Instead of deepening the backbone or relying on a complex feature fusion network, ELCT-YOLO uses a specially designed neck structure, which is suitable to enhance the multi-scale representation ability of the entire feature layer. At the same time, in order to solve the problem of lacking a receptive field after decoupling, the proposed model uses a novel Cascaded Refinement Scheme (CRS), composed of two different types of receptive field enhancement modules (RFEMs), which enables expanding the effective receptive field and aggregate multi-scale context information, thus improving the tumor detection performance of the model. The experimental results show that the proposed ELCT-YOLO model has strong ability in expressing multi-scale information and good robustness in detecting lung tumors of various sizes.

Due to the unmatched feeder impedance, the conventional voltage and frequency droop control method is unable to accurately allocate the output reactive power of DG units in proportion to their power ratings. To solve this issue, this paper has proposed a feeder impedance identification based droop control method. Firstly, the relationship among the reactive power sharing, reactive power droop slope and feeder impedance in islanded microgrids is illustrated. An online feeder impedance identification method is subsequently adopted to modify the reactive power droop slope of DG unit. In this way, the effect of unmatched feeder impedance on reactive power sharing is eliminated without communication among DG units. Experimental results implemented on an islanded microgrid apparatus have validated the feasibility of the proposed droop control method.

Microgrids have two operational states: grid-connected and islanded. Ensuring seamless transition between these different operational states is a critical measure for enhancing the stability of microgrids. Under the above background, this paper proposes a hybrid AC-DC microgrid system and a smooth switching control strategy based on improved voltage loop. First, the typical topology, operation mode and traditional control method of the proposed microgrid are introduced. Secondly, an improved voltage loop based on current compensation is proposed to reduce the current reference shock. Finally, the control of voltage amplitude and phase Angle pre-synchronization is added to the AC/DC converter of microgrid to realize smooth grid connection. Through simulation analysis, it is verified that the proposed microgrid system and the improved voltage loop control mode can coordinate the switching of each control mode, reduce the influence of current, and improve the operating stability of the microgrid.