Defect detection of lithium batteries is a crucial step in lithium battery production. However, traditional detection methods mainly rely on the human eyes to observe the bottom defects of lithium battery products, which have low detection accuracy and slow detection speed. To solve this practical problem, an improved YOLOv5s model is proposed in this paper. Firstly, a new layer of the network output layer is added to improve the detection effect of small defects. Secondly, to extract important information in the feature maps, the convolutional block attention module attention mechanism is added to the YOLOv5s model. Finally, a new position loss function is used to improve the accuracy of the position prediction of the model. The experimental results indicate that the improved YOLOv5s model can accurately and quickly detect three types of defects on the bottom surface of lithium batteries. Specifically, the loss and mean average precision (mAP) of the improved YOLOv5s model are 0.033 94 and 67.5% respectively. Compared with the traditional YOLOv5s model, the loss of the improved YOLOv5s model is reduced by 31%. As well as, the mAP of the improved YOLOv5s model is increased by 4.3% on the lithium battery defect dataset. Compared with the YOLOv3, YOLOv3-spp, retinanet and YOLOv4, the mAP of the improved YOLOv5s model increased by 5.4%, 0.7%, 11.9% and 3.7% respectively. Compared with other improved YOLOv5 algorithms used in various fields, the mAP of the proposed model on the lithium battery dataset is the highest. The detection speed of the improved YOLOv5s model reaches 111 frames per second, which can meet the real-time detection requirements. The improved YOLOv5s model has board application prospects in the industrial production of lithium batteries.

A dual stage tuning fork transducer (DSTFT) is designed as a stator for a resonant-type inertial linear motor. The first- and second-layer resonant frequencies of DSTFT are automatically adjusted with a ratio of 1:2 by using an ANSYS optimization design algorithm, and a resonant-type sawtooth-shaped mechanical waveform is generated by composing the two resonant vibrations of DSTFT. An inertial linear motor prototype is fabricated and tested. Experimental results confirmed the effectiveness of the designed transducer. The no-load maximum speed is 21.5 mm/s with a driving voltage of 67.2 V_p-p at a base frequency of 2831 Hz. The linear speed is 10.5 mm/s, and the drag load is 0.02 N at a preload force of 1 N and a driving voltage of 114 V_p-p for the base frequency. The movement direction could be reversed by changing the driving voltage phase.

The controlling of plasma shape and position are essential to the success of Tokamak discharge. A real-time image acquisition system was designed to obtain plasma radiation image during the discharge processes in the Experimental Advanced Superconducting Tokamak (EAST) device. The hardware structure and software design of this visible camera system are introduced in detail. According to the general structure of EAST and the layout of the observation window, spatial location of the discharging plasma in the image was measured. An improved Sobel edge detection algorithm using iterative threshold was proposed to detect plasma boundary. EAST discharge results show that the proposed method acquired plasma position and boundary with high accuracy, which is of great significance for better plasma control.

Resonant-type piezoelectric impact motors can improve the output capability effectively. A new construction of asymmetric inertial masses is proposed to synthesize approximate saw-tooth wave resonant vibration with matched anti-phase and in-phase modes. A prototype is designed, manufactured, and tested. With 40 V_p–p, 400 Hz exciting voltage for the anti-phase mode and 16 V_p–p, 800 Hz exciting voltage for the in-phase mode, the prototype provides a maximum no-load velocity of 17.2 mm/s and a maximum output power of 0.72 mW with 100 mN load. The velocity and output power of the prototype in the proposed resonant state are near three orders of magnitude higher than those in the traditional quasi-static state.