Synthetic aperture radar (SAR) ship detection is a heated and challenging problem. Traditional methods are based on hand-crafted feature extraction or limited shallow-learning features representation. Recently, with the excellent ability of feature representation, deep neural networks such as faster region based convolution neural network (FRCN) have shown great performance in object detection tasks. However, several challenges limit the applications of FRCN in SAR ship detection: (1) FRCN with a fixed receptive field cannot match the scale variability of multiscale SAR ship objects, and the performance degrade when the objects are small; (2) as a two-stage detector, FRCN performs an intensive computation and leads to low-speed detection; (3) when the background is complex, the imbalance of easy and hard examples will lead to a high false detection. To tackle the above issues, we design a multilayer fusion light-head detector (MFLHD) for SAR ship detection. Instead of using a single feature map, shallow high-resolution and deep semantic feature are combined to produce region proposal. In detection subnetwork, we propose a light-head detector with large-kernel separable convolution and position sensitive pooling to improve the detection speed. In addition, we adapt focal loss to loss function and training more hard examples to reduce the false alarm. Extensive experiments on SAR ship detection dataset (SSDD) show that the proposed method achieves superior performance in SAR ship detection both in accuracy and speed.

No abstract

No abstract

No abstract

The structure of an improved wind turbine gearbox is presented for meeting the operation of the optimized wind turbine power‐wind speed curve (P‐v curve). When the wind speed is lower than the cut‐in wind speed, the operation mode of the wind turbine is changed by the extra power, which is supplied by the motor excited source to keep the wind turbine running. Moreover, the transmission principle of the improved wind turbine gearbox is discussed. Various motor power impacts on the transmission characteristic for the improved transmission structure are investigated and results are compared with the professional software. Results indicate that as the motor power increases, the transverse vibration of sun gears and meshing forces of the low‐speed and medium‐speed planetary stages decreases. The transverse vibration for the pinion gear of the high‐speed stage enhances with the increase of the motor power. Load‐sharing coefficients of the planetary gear stages are augmented with the enlargement of the motor power. It is found that meshing forces of the torque‐implement parallel stage are increased with augmentation of the motor power.