8 September 2022 in IEEE Transactions on Instrumentation and Measurement
Transmission lines’ status detection and fault diagnosis are based on the high-accuracy detection of typical fittings in aerial inspection photographs. Detecting tiny-size fittings in complicated sceneries is still an unresolved issue, nevertheless, because of the constraints of the small number of feature pixels. Considering the characteristics of fitting connection structures, we proposed a novel method named context-based graph reasoning model (CGRM), which is based on multiscale context, self-attention map, and graph learning. This proposed model includes one graph-based global context (GGC) subnetwork and one multiscale local context (MLC) subnetwork. The GGC effectively extracted the pixel-level global map based on multihead attention mechanism to capture global context and the graph convolutional neural network (GCN) was further used for reasoning. The MLC exploited the internal and external contextual information of multiscale for each unique proposal to capture its local context. The final detection result is then reached by fusing the global and local circumstances. Experimental results well demonstrate the superiority of the proposed model for fitting detection. In addition, compared with the original Faster R-CNN, the detection accuracy of CGRM is increased by 16.3%. It also provides a new idea for general object detection of tiny-size targets.
23 October 2025 in Engineering Applications of Artificial Intelligence
1 January 2026 in IET Renewable Power Generation
To overcome the challenges in traditional virtual power plant (VPP) scheduling—difficulties in coordinating economic and ecological benefits and limited intra‐day adaptability due to resource temporal coupling, like energy storage—this paper proposes a two‐stage multi‐objective optimal scheduling strategy. In the day‐ahead stage, a multi‐objective optimization model is established and an improved bi‐directional multi‐objective optimal scheduling strategy. In the day‐ahead stage, a multi‐objective optimization model is establishedhe optimal compromise solution. Additionally, a spectral decomposition method based on a value sensitivity matrix is introduced to identify key regulation intervals for energy storage. In the intra‐day stage, this high‐value period information guides the adaptive adjustment of the rolling optimization window. Simulation results show that the proposed strategy effectively balances renewable energy consumption, carbon emission reduction and operational economics. Compared to traditional fixed‐window methods, the proposed approach optimizes the balance between intra‐day operational revenue and computational burden, leading to superior energy storage regulation during critical demand response periods and thereby alleviating the conflict between global and local scheduling.