Search

In printed circuit board (PCB) defect detection, it is difficult to collect defect samples, and the detection effect is poor due to the lack of data. On the basis of the few-shot learning method, a few-shot PCB defect detection model is proposed. This model introduces feature enhancement module and multi-scale fusion module. The feature enhancement module based on the improved convolution block attention module (CBAM) can highlight the key areas of the received feature maps and suppress the interference of useless information. Aiming at the small size of PCB defects, a multi-scale feature fusion strategy is proposed. It can extract multi-scale feature maps of PCB and fuse them into a high-quality feature map containing different scale information, which can improve the detection precision of the model for small object defects. A large number of experiments on PCB dataset show that our few-shot PCB defect detection model outperforms state-of-the-art methods under different shot settings ( $\text{k}=1$ ,2,3,5,10,30). Notably, the proposed model can take into account both detection efficiency and precision, which means it has high practical application value.

The continuum manipulators, which have gradually become a research hotspot of minimally invasive surgery have the characteristics of small size, lightweight, and better environmental adaptability. In this paper, a two degrees of freedom continuum manipulator with notches is proposed. The kinematic and mechanical models of the notch continuum manipulator are coupled. The output driving force of the motor is needed to control the manipulator. Due to the drift of the current of the motor, the accuracy of the control is low. In order to solve the above problem, the constant curvature assumption is realized by changing the structural parameters of the notches. The continuum manipulator mechanics model is established through the analysis of the continuum manipulator structure. The calculation of the deformation angle of a single notch of the manipulator is carried out. The overall deformation of the manipulator is derived through iterative algorithms. The stiffness of the continuum manipulator, which can affect the deformation of the continuum manipulator is modified by changing the structural parameters. In this way, the problem of the non-constant curvature deformation under the uniform notch of the continuum manipulator is improved. And the effectiveness of the variable stiffness model is verified by simulation experiments.