Detecting small split pins on transmission lines poses significant challenges, including low accuracy in complex backgrounds and slow inference speeds. To address these limitations, this study proposes a novel two-stage collaborative detection framework. The first stage utilizes a Yolo11x-based model to localize and crop components containing split pins from high-resolution images. This procedure transforms the difficult small-object detection problem into a more manageable, conventional detection task on a simplified background. For the second stage, a new high-performance detector, Mamba-YOLO-SPDC, is introduced. This model enhances the Yolo11 backbone by incorporating a Vision State Space (VSS) block, which leverages Mamba—a State Space Model (SSM) with linear computational complexity—to efficiently capture global context. Furthermore, a Space-to-Depth Convolution (SPD-Conv) module is integrated into the neck to mitigate the loss of fine-grained feature information during downsampling. Experimental results confirm the efficacy of the two-stage strategy. On the cropped dataset, the Mamba-YOLO-SPDC model achieves a mean Average Precision (mAP) of 61.9%, a 238% improvement over the 18.3% mAP obtained by the baseline Yolo11s on the original images. Compared to the conventional SAHI framework, the proposed method provides superior accuracy with a substantial increase in inference speed. This work demonstrates that the ‘localize first, then detect’ strategy, powered by the Mamba-YOLO-SPDC model, offers an effective balance between accuracy and efficiency for small object detection.
As the demand for power supply stability and reliability in the active distribution network (ADN) increases, the primary and secondary integrated intelligent switch (PSIIS) has become the primary choice for smart grid transformation in many weak infrastructure areas. However, the number of PSIISs that can be configured is often limited. It is necessary to comprehensively utilize the measurement data and sectional capabilities of PSIISs through the optimal configuration method to find the optimal configuration scheme. Therefore, fault observability-related indexes (FORIs) are proposed based on the functional characteristics of PSIISs. These indexes include fault type observability, fault location observability, fault current distribution characteristics observability, transition resistance observability, and weak infrastructure area observability. An optimization configuration model of PSIISs considering the comprehensive fault observability (CFO) is constructed. The adaptive genetic algorithm (AGA) is selected as the model-solving method. Subsequently, an optimal configuration method of PSIISs considering CFO is proposed. Finally, an example analysis is conducted in MATLAB to verify the effectiveness and feasibility of the proposed method. This optimal configuration method aims to maximize the use of a limited number of PSIISs by considering CFO, and the AGA proves to be an effective tool in solving the optimal configuration scheme.
The widespread integration of inverter-based distributed generators (IIDGs) severely limits the adaptability of conventional three-step overcurrent protection in distribution networks (DNs). To address weak rural infrastructure and incomplete post-fault data, this paper proposes a dynamic adaptive current protection strategy for active distribution networks (ADNs) against two-phase short-circuit faults (TPSCFs), using local sequence components. First, we derive analytical expressions for positive/negative-sequence current/voltage at feeder outlet protection devices during TPSCFs, analyzing how the IIDG fault output affects these components. Based on this, an adaptive scheme is developed using only local measurements, with feeder head voltage/current sequence components as criteria. Leveraging line impedance and topology, the scheme ensures selective, accurate fault section identification under incomplete measurements, requiring only feeder head sequence data. A high-IIDG-penetration DN model is built in PSCAD/EMTDC, and TPSCFs under various conditions are simulated. Results show the scheme provides rapid, reliable full-line protection for TPSCFs in IIDG-penetrated ADNs, enhancing protection effectiveness.