With the increasing penetration level of wind turbine generators (WTGs) integrated into the power system, the WTGs are enforced to aid network and fulfill the low voltage ride through (LVRT) requirements during faults. To enhance LVRT capability of permanent magnet synchronous generator (PMSG)-based WTG connected to the grid, this paper presents a novel coordinated control scheme named overspeed-while-storing control for PMSG-based WTG. The proposed control scheme purely regulates the rotor speed to reduce the input power of the machine-side converter (MSC) during slight voltage sags. Contrarily, when the severe voltage sag occurs, the coordinated control scheme sets the rotor speed at the upper-limit to decrease the input power of the MSC at the greatest extent, while the surplus power is absorbed by the supercapacitor energy storage (SCES) so as to reduce its maximum capacity. Moreover, the specific capacity configuration scheme of SCES is detailed in this paper. The effectiveness of the overspeed-while-storing control in enhancing the LVRT capability is validated under different levels of voltage sags and different fault types in MATLAB/Simulink.

Despite the continuous advancement of intelligent power substations, the terminal block components within equipment cabinet inspection work still often require loads of personnel. The repetitive documentary works not only lack efficiency but are also susceptible to inaccuracies introduced by substation personnel. To resolve the problem of lengthy, time-consuming inspections, a terminal block component detection and identification method is presented in this paper. The identification method is a multi-stage system that incorporates a streamlined version of You Only Look Once version 7 (YOLOv7), a fusion of YOLOv7 and differential binarization (DB), and the utilization of PaddleOCR. Firstly, the YOLOv7 Area-Oriented (YOLOv7-AO) model is developed to precisely locate the complete region of terminal blocks within substation scene images. The compact area extraction model rapidly cuts out the valid proportion of the input image. Furthermore, the DB segmentation head is integrated into the YOLOv7 model to effectively handle the densely arranged, irregularly shaped block components. To detect all the components within a target electrical cabinet of substation equipment, the YOLOv7 model with a differential binarization attention head (YOLOv7-DBAH) is proposed, integrating spatial and channel attention mechanisms. Finally, a general OCR algorithm is applied to the cropped-out instances after image distortion to match and record the component’s identity information. The experimental results show that the YOLOv7-AO model reaches high detection accuracy with good portability, gaining 4.45 times faster running speed. Moreover, the terminal block component detection results show that the YOLOv7-DBAH model achieves the highest evaluation metrics, increasing the F1-score from 0.83 to 0.89 and boosting the precision to over 0.91. The proposed method achieves the goal of terminal block component identification and can be applied in practical situations.

The matching of schematic diagrams and physical information of terminal blocks in substation secondary screen cabinets plays a crucial role in the operation and maintenance of substations. To enhance the automation level of this task and reduce labor costs, a method for identifying and matching information of terminal blocks in substation secondary screen cabinets based on artificial intelligence is investigated in this paper. Initially, multi-layer object detection networks, tailored to the characteristics of both the schematic diagrams and the physical entities in substation secondary screen cabinets, are designed for the precise extraction of information. Subsequently, network topologies for both the schematic and physical systems are established using the Neo4j database, which allows for the digital storage of information in the substation secondary screen cabinet systems. Finally, the branch-and-bound method, improved by the application of a multi-modular graph convolutional network (MGCN) and deep Q-network (DQN), is employed to solve the maximum common subgraph (MCS) problem, resulting in the rapid and efficient matching of schematic and physical data.

High-resistance faults on the DC lines of multi-terminal VSC-HVDC grids lead to insufficient protection reliability, and the introduction of current-limiting strategies alters the system’s intrinsic fault characteristics, degrading protection performance. To address these issues, we propose a DC-line protection scheme that is immune to converter control strategies and highly tolerant to fault resistance. First, based on the grid topology, post-fault current paths are analyzed, and the fault characteristics produced solely by the fault-induced voltage source are identified. A sequential overlapping derivative transformation is then employed to magnify the discrepancy between internal and external faults, forming the core of the fault-identification criterion; the zero-mode component is used for pole selection. Finally, a four-terminal VSC-HVDC model is built in PSCAD/EMTDC version 4.6.2 for validation. Simulation results show that, after applying the current-limiting strategy, the characteristic quantity changes only marginally, and the proposed protection can reliably withstand fault resistances of up to 700 Ω.