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.

In response to the constant power negative impedance characteristics on the load side of a ship DC microgrid, leading to voltage oscillation issues in the DC bus, this paper proposes a control optimization method based on impedance reshaping using bus voltage feedback. First, a simplified small-signal diagram of a lithium battery energy storage system converter is analyzed. Combining active damping control technology, an impedance regulator is introduced, and its parameters are optimized to effectively reduce the output impedance magnitude on the power source side. Subsequently, a ship DC microgrid simulation model is constructed using MATLAB R2022a/Simulink for validation, and comparative analysis is conducted on the anti-interference ability of the DC bus voltage before and after impedance reshaping. Finally, a model is built on a semi-physical simulation platform to experimentally verify the proposed method. The research results indicate that the proposed control optimization method can effectively increase the system’s stability margin, suppress DC bus oscillations, and enhance the anti-interference ability of the ship DC microgrid’s bus voltage when facing significant power load variations.

For the frequent occurrence of pulse power load operation and load switching disturbances in AC/DC shipboard microgrids, a large-signal stability analysis method based on hybrid potential theory is proposed. The proposed method utilizes a mixed potential function to analyze the impact of interconnected converters on system stability. First, the entire system is equivalently modeled as a DC system in a d-q rotating reference frame. Then, a mixed potential function model of the AC/DC system is established for stability analysis, leading to the development of a large-signal stability criterion for the system. Using this criterion, the boundary values of bidirectional power transfer for the interconnected converters are derived. Finally, a simulation model of the AC/DC hybrid microgrid system was built in Simulink for verification, and further validation was carried out on the RT-lab hardware-in-the-loop (HIL) simulation platform. Simulation and experimental results show that the proposed criterion can effectively ensure the stability of the AC/DC hybrid microgrid system under large disturbances.

A suspension flux internal model control method is proposed to address the problem of the strong coupling of a single-winding bearingless flux-switching permanent magnet motor leading to a significant ripple of the rotor radial displacement. Firstly, based on air-gap magnetic field modulation theory, the stator flux equation considering rotor dynamic eccentricity is established to reveal the relationship between the eccentric rotor and the magnetic field. Secondly, according to the dynamic characteristics of the motor and the variation law of the air-gap magnetic field, the suspension-plane flux is substituted into the rotor dynamic model, and the suspension flux-dynamics internal model and corresponding output are constructed, respectively. Finally, a complete control strategy is established, and the rotor is stably suspended by PWM control. The simulation and experimental results show that the proposed method has better steady-state and dynamic performance than traditional PID control, and the maximum radial displacement ripples of the rotor are reduced by 53% and 50% in steady-state and dynamic operation.

Shipboard DC microgrids face critical stability challenges including low-inertia-induced voltage fluctuations and impedance mismatch caused by constant power loads (CPLs), which severely threaten system stability. Existing virtual DC machine (VDCM) control methods typically treat inertia support and impedance optimization as separate design objectives, lacking a unified frequency-domain design framework. To address this issue, this paper first establishes an accurate virtual impedance model for the standard VDCM controller, quantitatively revealing how its control parameters (J and D) shape the frequency-domain impedance characteristics and identifying potential stability conflicts. Building upon this model, a feedforward-compensated VDCM (FFC-VDCM) strategy is proposed, introducing a differential feedforward loop to actively reshape the converter output impedance in the critical mid-frequency range without interfering with the inertia support function. The impedance reshaping effect is quantified via impedance-based stability analysis; the proposed method improves the gain margin from $4.1$ dB (with conventional VDCM) to $8.6$ dB, along with a significant enhancement in the phase margin, confirming improved system robustness. Hardware-in-the-loop (HIL) experiments conducted under realistic shipboard conditions further confirm the theoretical analysis, demonstrating superior transient voltage regulation and validating the practical effectiveness of the proposed strategy. The FFC-VDCM provides a synergistic solution for concurrently improving inertia and stability in low-inertia DC microgrids.