To address the current issues of complex structures and low accuracies in citrus pest identification models, a lightweight pest identification model was proposed. First, a parameterized linear rectification function was introduced to avoid neuronal death. Second, the model’s attention to pest characteristics was improved by incorporating an improved mixed attention mechanism. Subsequently, the network structure of the original model was adjusted to reduce architectural complexity. Finally, by employing transfer learning, an SCHNet model was developed. The experimental results indicated that the proposed model achieved an accuracy rate of 94.48% with a compact size of 3.84 MB. Compared to the original ShuffleNet V2 network, the SCHNet model showed a 3.12% accuracy improvement while reducing the model size by 22.7%. The SCHNet model exhibited an excellent classification performance for citrus pest identification, enabling the accurate identification of citrus pests.

Silicon carbide (SiC) MOSFETs exhibit superior performance compared to traditional silicon (Si) MOSFETs, characterized by faster switching speeds, lower on-resistance, higher breakdown voltage, and greater operational temperature tolerance. These attributes make SiC MOSFETs highly suitable for applications in electric vehicles, charging stations, and mobile devices. However, their rapid switching speed can intensify current and voltage overshoot and oscillations during device switching, leading to increased device losses or potential damage. To address this issue, this paper proposes a current-type active gate drive (AGD) circuit. The circuit first detects the rate of change in the drain current and drain-source voltage. Subsequently, it employs an analog amplifier circuit and adjustable drive resistors to decelerate the rate of change in the drain-source voltage and drain current. As a result, overshoot and oscillation in the drain-source voltage and drain current are mitigated. Experimental results demonstrate that the proposed AGD circuit can reduce drain current overshoot by 60%, drain-source voltage overshoot by 15.38%, and waveform oscillations. Additionally, the AGD circuit decreases conduction and turn-off losses by 24% and effectively mitigates electromagnetic interference (EMI) issues within the frequency range of 0.1 to 3 MHz.

The application of GaN power devices has significantly increased the power density of flyback power supplies but has also caused severe electromagnetic interference (EMI) issues. To address the challenge of conducted interference in flyback power supplies, a comprehensive analysis of the transmission mechanism of conducted common-mode noise is undertaken. This analysis involves simplifying the equivalent model of conducted interference and leveraging the circuit characteristics of conducted noise to propose a solution for attenuating common-mode noise. Considering the constraints of external compensation capacitors, a balanced winding is further introduced to mitigate the impact of noise. To enhance the efficacy of conducted interference suppression, it is suggested to change the winding structure of the transformer and incorporate a shielding winding. This configuration aims to minimize the generation and propagation of common-mode noise within the transformer. Finally, experimental verification is carried out using a 150 W GaN flyback power supply prototype. The experimental results demonstrate that the proposed method effectively suppresses common-mode noise in the circuit.